diff --git "a/raw_rss_feeds/https___arxiv_org_rss_cs.xml" "b/raw_rss_feeds/https___arxiv_org_rss_cs.xml" --- "a/raw_rss_feeds/https___arxiv_org_rss_cs.xml" +++ "b/raw_rss_feeds/https___arxiv_org_rss_cs.xml" @@ -7,19803 +7,10768 @@ http://www.rssboard.org/rss-specification en-us - Tue, 09 Dec 2025 05:00:22 +0000 + Wed, 10 Dec 2025 05:00:08 +0000 rss-help@arxiv.org - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 - Sunday Saturday + Sunday - Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices - https://arxiv.org/abs/2512.05969 - arXiv:2512.05969v1 Announce Type: new -Abstract: We show that video generation models could reason now. Testing on tasks such as chess, maze, Sudoku, mental rotation, and Raven's Matrices, leading models such as Sora-2 achieve sixty percent success rates. We establish a robust experimental paradigm centered on the "Task Pair" design. We build a code framework, with 39 models available already, that supports this paradigm and allows for easy scaling - users can add models and tasks efficiently. We show our automated evaluation strongly correlates with human judgment, and therefore this paradigm is highly scalable. We see an opportunity, given the availability of our paradigm, to do reinforcement learning for improving reasoning in video models. You could checkout all of our raw $\href{https://grow-ai-like-a-child.com/video-reason/}{results}$ and our $\href{https://github.com/hokindeng/VMEvalKit}{VMEvalKit}$ codebase. - oai:arXiv.org:2512.05969v1 + Detection of Cyberbullying in GIF using AI + https://arxiv.org/abs/2512.07838 + arXiv:2512.07838v1 Announce Type: new +Abstract: Cyberbullying is a well-known social issue, and it is escalating day by day. Due to the vigorous development of the internet, social media provide many different ways for the user to express their opinions and exchange information. Cyberbullying occurs on social media using text messages, comments, sharing images and GIFs or stickers, and audio and video. Much research has been done to detect cyberbullying on textual data; some are available for images. Very few studies are available to detect cyberbullying on GIFs/stickers. We collect a GIF dataset from Twitter and Applied a deep learning model to detect cyberbullying from the dataset. Firstly, we extracted hashtags related to cyberbullying using Twitter. We used these hashtags to download GIF file using publicly available API GIPHY. We collected over 4100 GIFs including cyberbullying and non cyberbullying. we applied deep learning pre-trained model VGG16 for the detection of the cyberbullying. The deep learning model achieved the accuracy of 97%. Our work provides the GIF dataset for researchers working in this area. + oai:arXiv.org:2512.07838v1 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + cs.MM + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Hokin Deng + Pal Dave, Xiaohong Yuan, Madhuri Siddula, Kaushik Roy - A Multi-objective Optimization Approach for Feature Selection in Gentelligent Systems - https://arxiv.org/abs/2512.05971 - arXiv:2512.05971v1 Announce Type: new -Abstract: The integration of advanced technologies, such as Artificial Intelligence (AI), into manufacturing processes is attracting significant attention, paving the way for the development of intelligent systems that enhance efficiency and automation. This paper uses the term "Gentelligent system" to refer to systems that incorporate inherent component information (akin to genes in bioinformatics-where manufacturing operations are likened to chromosomes in this study) and automated mechanisms. By implementing reliable fault detection methods, manufacturers can achieve several benefits, including improved product quality, increased yield, and reduced production costs. To support these objectives, we propose a hybrid framework with a dominance-based multi-objective evolutionary algorithm. This mechanism enables simultaneous optimization of feature selection and classification performance by exploring Pareto-optimal solutions in a single run. This solution helps monitor various manufacturing operations, addressing a range of conflicting objectives that need to be minimized together. Manufacturers can leverage such predictive methods and better adapt to emerging trends. To strengthen the validation of our model, we incorporate two real-world datasets from different industrial domains. The results on both datasets demonstrate the generalizability and effectiveness of our approach. - oai:arXiv.org:2512.05971v1 - cs.NE + Impact of Data-Oriented and Object-Oriented Design on Performance and Cache Utilization with Artificial Intelligence Algorithms in Multi-Threaded CPUs + https://arxiv.org/abs/2512.07841 + arXiv:2512.07841v1 Announce Type: new +Abstract: The growing performance gap between multi-core CPUs and main memory necessitates hardware-aware software design paradigms. This study provides a comprehensive performance analysis of Data Oriented Design (DOD) versus the traditional Object-Oriented Design (OOD), focusing on cache utilization and efficiency in multi-threaded environments. We developed and compared four distinct versions of the A* search algorithm: single-threaded OOD (ST-OOD), single-threaded DOD (ST-DOD), multi-threaded OOD (MT-OOD), and multi-threaded DOD (MT-DOD). The evaluation was based on metrics including execution time, memory usage, and CPU cache misses. In multi-threaded tests, the DOD implementation demonstrated considerable performance gains, with faster execution times and a lower number of raw system calls and cache misses. While OOD occasionally showed marginal advantages in memory usage or percentage-based cache miss rates, DOD's efficiency in data-intensive operations was more evident. Furthermore, our findings reveal that for a fine-grained task like the A* algorithm, the overhead associated with thread management led to single-threaded versions significantly outperforming their multi-threaded counterparts in both paradigms. We conclude that even when performance differences appear subtle in simple algorithms, the consistent advantages of DOD in critical metrics highlight its foundational architectural superiority, suggesting it is a more effective approach for maximizing hardware efficiency in complex, large-scale AI and parallel computing tasks. + oai:arXiv.org:2512.07841v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - 10.1109/JIOT.2025.3629076 - Mohammadhossein Ghahramani, Yan Qiao, NaiQi Wu, Mengchu Zhou - - - SEB-ChOA: An Improved Chimp Optimization Algorithm Using Spiral Exploitation Behavior - https://arxiv.org/abs/2512.05981 - arXiv:2512.05981v1 Announce Type: new -Abstract: The chimp optimization algorithm (ChOA) is a nature-inspired algorithm that imitates chimpanzees' individual intelligence and hunting behaviors. In this algorithm, the hunting process consists of four steps: driving, blocking, chasing, and attacking. Because of the novelty of ChOA, the steps of the hunting process have been modeled in a simple way, leading to slow and premature convergence similar to other iterative algorithms. This paper proposes six spiral functions and introduces two novel hybrid spiral functions (SEB-ChOA) to address these deficiencies. The performance of SEB-ChOA is evaluated on 23 standard benchmarks, 20 benchmarks of the IEEE CEC-2005 test suite, 10 cases from the IEEE CEC06-2019 test suite, and 12 constrained real-world engineering problems from IEEE CEC-2020. The SEB-ChOA variants are compared with three groups of optimization algorithms, including Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) as well-known optimizers; Slime Mould Algorithm (SMA), Marine Predators Algorithm (MPA), Ant Lion Optimization (ALO), and Henry Gas Solubility Optimization (HGSO) as recently developed optimizers; and jDE100 and DISHchain1e+12, the winners of the IEEE CEC06-2019 competition. Additional comparisons are made with EBOwithCMAR and CIPDE as strong secondary baselines. The SEB-ChOA methods achieve top-ranked results on nearly all benchmarks and show competitive performance compared to jDE100 and DISHchain1e+12. Statistical results indicate that SEB-ChOA outperforms PSO, GA, SMA, MPA, ALO, and HGSO while producing results comparable to those of jDE100 and DISHchain1e+12. - oai:arXiv.org:2512.05981v1 - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 + cs.PF + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1007/s00521-023-09236-y - Neural Computing and Applications (2024) - Leren Qian, Mohammad Khishe, Yiqian Huang, Seyedali Mirjalili + Gabriel M. Arantes, Richard F. Pinto, Bruno L. Dalmazo, Eduardo N. Borges, Giancarlo Lucca, Viviane L. D. de Mattos, Fabian C. Cardoso, Rafael A. Berri - AI-Generated Compromises for Coalition Formation: Modeling, Simulation, and a Textual Case Study - https://arxiv.org/abs/2512.05983 - arXiv:2512.05983v1 Announce Type: new -Abstract: The challenge of finding compromises between agent proposals is fundamental to AI sub-fields such as argumentation, mediation, and negotiation. Building on this tradition, Elkind et al. (2021) introduced a process for coalition formation that seeks majority-supported proposals preferable to the status quo, using a metric space where each agent has an ideal point. The crucial step in this iterative process involves identifying compromise proposals around which agent coalitions can unite. How to effectively find such compromise proposals, however, remains an open question. We address this gap by formalizing a holistic model that encompasses agent bounded rationality and uncertainty and developing AI models to generate such compromise proposals. We focus on the domain of collaboratively writing text documents -- e.g., to enable the democratic creation of a community constitution. We apply NLP (Natural Language Processing) techniques and utilize LLMs (Large Language Models) to create a semantic metric space for text and develop algorithms to suggest suitable compromise points. To evaluate the effectiveness of our algorithms, we simulate various coalition formation processes and demonstrate the potential of AI to facilitate large-scale democratic text editing, such as collaboratively drafting a constitution, an area where traditional tools are limited. - oai:arXiv.org:2512.05983v1 - cs.MA + ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models + https://arxiv.org/abs/2512.07843 + arXiv:2512.07843v1 Announce Type: new +Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but inherently sequential decoding leads to substantial latency, especially on complex tasks. Recent work on adaptive parallel reasoning aims to improve inference efficiency by decomposing the problem-solving process into concurrent reasoning threads when beneficial. However, existing methods on realistic tasks are either limited to supervised behavior cloning or exhibit significant accuracy drops compared to widely-used sequential long chain-of-thought (CoT) baselines. Moreover, many require customized inference engines, complicating deployment. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that achieves accuracy on par with popular sequential reasoning models of comparable size while significantly reducing inference latency. ThreadWeaver's performance stems from three key innovations: 1) a two-stage parallel trajectory generator that produces large-scale, high-quality CoT data with parallel annotations for supervised fine-tuning; 2) a trie-based training-inference co-design that enables parallel reasoning on any off-the-shelf autoregressive inference engine without modifying position embeddings or KV caches; and 3) a parallelization-aware reinforcement learning framework that teaches the model to balance accuracy with effective parallelization. Across six challenging mathematical reasoning benchmarks, ThreadWeaver trained atop Qwen3-8B achieves accuracy comparable to cutting-edge sequential reasoning models (71.9% on average and 79.9% on AIME24) while delivering up to 1.53x average speedup in token latency, establishing a new Pareto frontier between accuracy and efficiency. + oai:arXiv.org:2512.07843v1 + cs.LG + cs.AI cs.CL - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.4204/EPTCS.437.32 - EPTCS 437, 2025, pp. 417-432 - Eyal Briman (Ben Gurion University of the Negev), Ehud Shapiro (Weizmann Institute of Science), Nimrod Talmon (Ben Gurion University of the Negev) + Long Lian, Sida Wang, Felix Juefei-Xu, Tsu-Jui Fu, Xiuyu Li, Adam Yala, Trevor Darrell, Alane Suhr, Yuandong Tian, Xi Victoria Lin - Adaptive Dataset Quantization: A New Direction for Dataset Pruning - https://arxiv.org/abs/2512.05987 - arXiv:2512.05987v1 Announce Type: new -Abstract: This paper addresses the challenges of storage and communication costs for large-scale datasets in resource-constrained edge devices by proposing a novel dataset quantization approach to reduce intra-sample redundancy. Unlike traditional dataset pruning and distillation methods that focus on inter-sample redundancy, the proposed method compresses each image by reducing redundant or less informative content within samples while preserving essential features. It first applies linear symmetric quantization to obtain an initial quantization range and scale for each sample. Then, an adaptive quantization allocation algorithm is introduced to distribute different quantization ratios for samples with varying precision requirements, maintaining a constant total compression ratio. The main contributions include: (1) being the first to use limited bits to represent datasets for storage reduction; (2) introducing a dataset-level quantization algorithm with adaptive ratio allocation; and (3) validating the method's effectiveness through extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K. Results show that the method maintains model training performance while achieving significant dataset compression, outperforming traditional quantization and dataset pruning baselines under the same compression ratios. - oai:arXiv.org:2512.05987v1 - cs.CV + Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning + https://arxiv.org/abs/2512.07844 + arXiv:2512.07844v1 Announce Type: new +Abstract: Recent studies on Neural Collapse (NC) reveal that, under class-balanced conditions, the class feature means and classifier weights spontaneously align into a simplex equiangular tight frame (ETF). In long-tailed regimes, however, severe sample imbalance tends to prevent the emergence of the NC phenomenon, resulting in poor generalization performance. Current efforts predominantly seek to recover the ETF geometry by imposing constraints on features or classifier weights, yet overlook a critical problem: There is a pronounced misalignment between the feature and the classifier weight spaces. In this paper, we theoretically quantify the harm of such misalignment through an optimal error exponent analysis. Built on this insight, we propose three explicit alignment strategies that plug-and-play into existing long-tail methods without architectural change. Extensive experiments on the CIFAR-10-LT, CIFAR-100-LT, and ImageNet-LT datasets consistently boost examined baselines and achieve the state-of-the-art performances. + oai:arXiv.org:2512.07844v1 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chenyue Yu, Jianyu Yu + http://creativecommons.org/licenses/by/4.0/ + Jinping Wang, Zhiqiang Gao, Zhiwu Xie - VG3T: Visual Geometry Grounded Gaussian Transformer - https://arxiv.org/abs/2512.05988 - arXiv:2512.05988v1 Announce Type: new -Abstract: Generating a coherent 3D scene representation from multi-view images is a fundamental yet challenging task. Existing methods often struggle with multi-view fusion, leading to fragmented 3D representations and sub-optimal performance. To address this, we introduce VG3T, a novel multi-view feed-forward network that predicts a 3D semantic occupancy via a 3D Gaussian representation. Unlike prior methods that infer Gaussians from single-view images, our model directly predicts a set of semantically attributed Gaussians in a joint, multi-view fashion. This novel approach overcomes the fragmentation and inconsistency inherent in view-by-view processing, offering a unified paradigm to represent both geometry and semantics. We also introduce two key components, Grid-Based Sampling and Positional Refinement, to mitigate the distance-dependent density bias common in pixel-aligned Gaussian initialization methods. Our VG3T shows a notable 1.7%p improvement in mIoU while using 46% fewer primitives than the previous state-of-the-art on the nuScenes benchmark, highlighting its superior efficiency and performance. - oai:arXiv.org:2512.05988v1 - cs.CV + AudioScene: Integrating Object-Event Audio into 3D Scenes + https://arxiv.org/abs/2512.07845 + arXiv:2512.07845v1 Announce Type: new +Abstract: The rapid advances in audio analysis underscore its vast potential for humancomputer interaction, environmental monitoring, and public safety; yet, existing audioonly datasets often lack spatial context. To address this gap, we present two novel audiospatial scene datasets, AudioScanNet and AudioRoboTHOR, designed to explore audioconditioned tasks within 3D environments. By integrating audio clips with spatially aligned 3D scenes, our datasets enable research on how audio signals interact with spatial context. To associate audio events with corresponding spatial information, we leverage the common sense reasoning ability of large language models and supplement them with rigorous human verification, This approach offers greater scalability compared to purely manual annotation while maintaining high standards of accuracy, completeness, and diversity, quantified through inter annotator agreement and performance on two benchmark tasks audio based 3D visual grounding and audio based robotic zeroshot navigation. The results highlight the limitations of current audiocentric methods and underscore the practical challenges and significance of our datasets in advancing audio guided spatial learning. + oai:arXiv.org:2512.07845v1 + cs.SD cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + eess.AS + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junho Kim, Seongwon Lee + http://creativecommons.org/licenses/by/4.0/ + Shuaihang Yuan, Congcong Wen, Muhammad Shafique, Anthony Tzes, Yi Fang - A self-driving lab for solution-processed electrochromic thin films - https://arxiv.org/abs/2512.05989 - arXiv:2512.05989v1 Announce Type: new -Abstract: Solution-processed electrochromic materials offer high potential for energy-efficient smart windows and displays. Their performance varies with material choice and processing conditions. Electrochromic thin film electrodes require a smooth, defect-free coating for optimal contrast between bleached and colored states. The complexity of optimizing the spin-coated electrochromic thin layer poses challenges for rapid development. This study demonstrates the use of self-driving laboratories to accelerate the development of electrochromic coatings by coupling automation with machine learning. Our system combines automated data acquisition, image processing, spectral analysis, and Bayesian optimization to explore processing parameters efficiently. This approach not only increases throughput but also enables a pointed search for optimal processing parameters. The approach can be applied to various solution-processed materials, highlighting the potential of self-driving labs in enhancing materials discovery and process optimization. - oai:arXiv.org:2512.05989v1 + MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction + https://arxiv.org/abs/2512.07846 + arXiv:2512.07846v1 Announce Type: new +Abstract: Large language models (LLMs) excel at capturing semantic nuances and therefore show impressive relevance ranking performance in modern recommendation and search systems. However, they suffer from high computational overhead under industrial latency and throughput requirements. In particular, cross-encoder ranking systems often create long context prefill-heavy workloads, as the model has to be presented with the user, query and item information. To this end, we propose MixLM, a novel LLM-based ranking framework, which significantly improves the system throughput via reducing the input context length, while preserving the semantic strength of cross-encoder rankers. In contrast to a standard ranking system where the context is presented to the model as pure text, we propose to use mix-interaction, a mixture of text and embedding tokens to represent the input. Specifically, MixLM encodes all items in the catalog into a few embedding tokens and stores in a nearline cache. The encoded item descriptions are used during online inference, effectively reducing the item length from a few thousand text tokens to a few embedding tokens. We share insights from deploying our MixLM framework to a real-world search application at LinkedIn, including a detailed discussion of our training pipelines, as well as a thorough analysis of our online serving infrastructure optimization. Comparing with strong baselines, MixLM increased throughput by 10.0x under the same latency budget, while maintaining relevance metrics. The efficiency gains delivered by MixLM enabled full-traffic deployment of LLM-powered search, which resulted in a significant 0.47% increase in Daily Active Users (DAU) in online A/B tests. + oai:arXiv.org:2512.07846v1 + cs.IR + cs.AI + cs.CL cs.LG - cond-mat.mtrl-sci - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Selma Dahms, Luca Torresi, Shahbaz Tareq Bandesha, Jan Hansmann, Holger R\"ohm, Alexander Colsmann, Marco Schott, Pascal Friederich + Guoyao Li, Ran He, Shusen Jing, Kayhan Behdin, Yubo Wang, Sundara Raman Ramachandran, Chanh Nguyen, Jian Sheng, Xiaojing Ma, Chuanrui Zhu, Sriram Vasudevan, Muchen Wu, Sayan Ghosh, Lin Su, Qingquan Song, Xiaoqing Wang, Zhipeng Wang, Qing Lan, Yanning Chen, Jingwei Wu, Luke Simon, Wenjing Zhang, Qi Guo, Fedor Borisyuk - Memory-Amortized Inference: A Topological Unification of Search, Closure, and Structure - https://arxiv.org/abs/2512.05990 - arXiv:2512.05990v1 Announce Type: new -Abstract: Contemporary ML separates the static structure of parameters from the dynamic flow of inference, yielding systems that lack the sample efficiency and thermodynamic frugality of biological cognition. In this theoretical work, we propose \textbf{Memory-Amortized Inference (MAI)}, a formal framework rooted in algebraic topology that unifies learning and memory as phase transitions of a single geometric substrate. Central to our theory is the \textbf{Homological Parity Principle}, which posits a fundamental dichotomy: even-dimensional homology ($H_{even}$) physically instantiates stable \textbf{Content} (stable scaffolds or ``what''), while odd-dimensional homology ($H_{odd}$) instantiates dynamic \textbf{Context} (dynamic flows or ``where''). We derive the logical flow of MAI as a topological trinity transformation: \textbf{Search $\to$ Closure $\to$ Structure}. Specifically, we demonstrate that cognition operates by converting high-complexity recursive search (modeled by \textit{Savitch's Theorem} in NPSPACE) into low-complexity lookup (modeled by \textit{Dynamic Programming} in P) via the mechanism of \textbf{Topological Cycle Closure}. We further show that this consolidation process is governed by a topological generalization of the Wake-Sleep algorithm, functioning as a coordinate descent that alternates between optimizing the $H_{odd}$ flow (inference/wake) and condensing persistent cycles into the $H_{even}$ scaffold (learning/sleep). This framework offers a rigorous explanation for the emergence of fast-thinking (intuition) from slow-thinking (reasoning) and provides a blueprint for post-Turing architectures that compute via topological resonance. - oai:arXiv.org:2512.05990v1 + CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics + https://arxiv.org/abs/2512.07847 + arXiv:2512.07847v1 Announce Type: new +Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving algorithmic innovation through standardized datasets and reproducible evaluation protocols. The growing availability of large-scale Computational Fluid Dynamics (CFD) datasets has opened new opportunities for applying machine learning to aerodynamic and engineering design. Yet, despite this progress, there exists no standardized benchmark for large-scale numerical simulations in engineering design. In this work, we introduce CarBench, the first comprehensive benchmark dedicated to large-scale 3D car aerodynamics, performing a large-scale evaluation of state-of-the-art models on DrivAerNet++, the largest public dataset for automotive aerodynamics, containing over 8,000 high-fidelity car simulations. We assess eleven architectures spanning neural operator methods (e.g., Fourier Neural Operator), geometric deep learning (PointNet, RegDGCNN, PointMAE, PointTransformer), transformer-based neural solvers (Transolver, Transolver++, AB-UPT), and implicit field networks (TripNet). Beyond standard interpolation tasks, we perform cross-category experiments in which transformer-based solvers trained on a single car archetype are evaluated on unseen categories. Our analysis covers predictive accuracy, physical consistency, computational efficiency, and statistical uncertainty. To accelerate progress in data-driven engineering, we open-source the benchmark framework, including training pipelines, uncertainty estimation routines based on bootstrap resampling, and pretrained model weights, establishing the first reproducible foundation for large-scale learning from high-fidelity CFD simulations, available at https://github.com/Mohamedelrefaie/CarBench. + oai:arXiv.org:2512.07847v1 cs.LG - q-bio.NC - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/publicdomain/zero/1.0/ - Xin Li + http://creativecommons.org/licenses/by/4.0/ + Mohamed Elrefaie, Dule Shu, Matt Klenk, Faez Ahmed - EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head - https://arxiv.org/abs/2512.05991 - arXiv:2512.05991v1 Announce Type: new -Abstract: Recent photo-realistic 3D talking head via 3D Gaussian Splatting still has significant shortcoming in emotional expression manipulation, especially for fine-grained and expansive dynamics emotional editing using multi-modal control. This paper introduces a new editable 3D Gaussian talking head, i.e. EmoDiffTalk. Our key idea is a novel Emotion-aware Gaussian Diffusion, which includes an action unit (AU) prompt Gaussian diffusion process for fine-grained facial animator, and moreover an accurate text-to-AU emotion controller to provide accurate and expansive dynamic emotional editing using text input. Experiments on public EmoTalk3D and RenderMe-360 datasets demonstrate superior emotional subtlety, lip-sync fidelity, and controllability of our EmoDiffTalk over previous works, establishing a principled pathway toward high-quality, diffusion-driven, multimodal editable 3D talking-head synthesis. To our best knowledge, our EmoDiffTalk is one of the first few 3D Gaussian Splatting talking-head generation framework, especially supporting continuous, multimodal emotional editing within the AU-based expression space. - oai:arXiv.org:2512.05991v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction + https://arxiv.org/abs/2512.07848 + arXiv:2512.07848v1 Announce Type: new +Abstract: New York City reports over one hundred thousand motor vehicle collisions each year, creating substantial injury and public health burden. We present RaX-Crash, a resource efficient and explainable small model pipeline for structured injury severity prediction on the official NYC Motor Vehicle Collisions dataset. RaX-Crash integrates three linked tables with tens of millions of records, builds a unified feature schema in partitioned storage, and trains compact tree based ensembles (Random Forest and XGBoost) on engineered tabular features, which are compared against locally deployed small language models (SLMs) prompted with textual summaries. On a temporally held out test set, XGBoost and Random Forest achieve accuracies of 0.7828 and 0.7794, clearly outperforming SLMs (0.594 and 0.496); class imbalance analysis shows that simple class weighting improves fatal recall with modest accuracy trade offs, and SHAP attribution highlights human vulnerability factors, timing, and location as dominant drivers of predicted severity. Overall, RaX-Crash indicates that interpretable small model ensembles remain strong baselines for city scale injury analytics, while hybrid pipelines that pair tabular predictors with SLM generated narratives improve communication without sacrificing scalability. + oai:arXiv.org:2512.07848v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chang Liu, Tianjiao Jing, Chengcheng Ma, Xuanqi Zhou, Zhengxuan Lian, Qin Jin, Hongliang Yuan, Shi-Sheng Huang + http://creativecommons.org/licenses/by/4.0/ + Di Zhu, Chen Xie, Ziwei Wang, Haoyun Zhang - Domain-Specific Foundation Model Improves AI-Based Analysis of Neuropathology - https://arxiv.org/abs/2512.05993 - arXiv:2512.05993v1 Announce Type: new -Abstract: Foundation models have transformed computational pathology by providing generalizable representations from large-scale histology datasets. However, existing models are predominantly trained on surgical pathology data, which is enriched for non-nervous tissue and overrepresents neoplastic, inflammatory, metabolic, and other non-neurological diseases. Neuropathology represents a markedly different domain of histopathology, characterized by unique cell types (neurons, glia, etc.), distinct cytoarchitecture, and disease-specific pathological features including neurofibrillary tangles, amyloid plaques, Lewy bodies, and pattern-specific neurodegeneration. This domain mismatch may limit the ability of general-purpose foundation models to capture the morphological patterns critical for interpreting neurodegenerative diseases such as Alzheimer's disease, Parkinson's disease, and cerebellar ataxias. To address this gap, we developed NeuroFM, a foundation model trained specifically on whole-slide images of brain tissue spanning diverse neurodegenerative pathologies. NeuroFM demonstrates superior performance compared to general-purpose models across multiple neuropathology-specific downstream tasks, including mixed dementia disease classification, hippocampal region segmentation, and neurodegenerative ataxia identification encompassing cerebellar essential tremor and spinocerebellar ataxia subtypes. This work establishes that domain-specialized foundation models trained on brain tissue can better capture neuropathology-specific features than models trained on general surgical pathology datasets. By tailoring foundation models to the unique morphological landscape of neurodegenerative diseases, NeuroFM enables more accurate and reliable AI-based analysis for brain disease diagnosis and research, setting a precedent for domain-specific model development in specialized areas of digital pathology. - oai:arXiv.org:2512.05993v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Ruchika Verma, Shrishtee Kandoi, Robina Afzal, Shengjia Chen, Jannes Jegminat, Michael W. Karlovich, Melissa Umphlett, Timothy E. Richardson, Kevin Clare, Quazi Hossain, Jorge Samanamud, Phyllis L. Faust, Elan D. Louis, Ann C. McKee, Thor D. Stein, Jonathan D. Cherry, Jesse Mez, Anya C. McGoldrick, Dalilah D. Quintana Mora, Melissa J. Nirenberg, Ruth H. Walker, Yolfrankcis Mendez, Susan Morgello, Dennis W. Dickson, Melissa E. Murray, Carlos Cordon-Cardo, Nadejda M. Tsankova, Jamie M. Walker, Diana K. Dangoor, Stephanie McQuillan, Emma L. Thorn, Claudia De Sanctis, Shuying Li, Thomas J. Fuchs, Kurt Farrell, John F. Crary, Gabriele Campanella - - - The Tragedy of Productivity: A Unified Framework for Diagnosing Coordination Failures in Labor Markets and AI Governance - https://arxiv.org/abs/2512.05995 - arXiv:2512.05995v1 Announce Type: new -Abstract: Despite productivity increasing eightfold since Keynes's 1930 - prediction of 15-hour workweeks, workers globally still work roughly - double these hours. Separately, AI development accelerates despite - existential risk warnings from leading researchers. We demonstrate - these failures share identical game-theoretic structure. - We synthesize five necessary and sufficient conditions - characterizing structural tragedies: N-player structure, - binary choices with negative externalities, dominance where - defection yields higher payoffs, Pareto-inefficiency where - cooperation dominates mutual defection, and enforcement difficulty - from structural barriers. We validate this framework across canonical - cases and extend it through condition intensities, introducing a - Tragedy Index revealing AI governance faces orders-of-magnitude - greater coordination difficulty than climate change or nuclear - weapons. - Applied to productivity competition, we prove firms face - coordination failure preventing productivity gains from translating - to worker welfare. European evidence shows that even under favorable - conditions, productivity-welfare decoupling persists. Applied to AI - governance, we demonstrate development faces the same structure but - with amplified intensity across eight dimensions compared to - successful arms control. The Russia-Ukraine drone war validates this: - both sides escalated from zero to thousands of drones monthly within - two years despite prior governance dialogue. - The analysis is diagnostic rather than prescriptive, identifying - structural barriers to coordination rather than proposing solutions. - oai:arXiv.org:2512.05995v1 + Accelerating Urban Science Research with AI Urban Scientist + https://arxiv.org/abs/2512.07849 + arXiv:2512.07849v1 Announce Type: new +Abstract: Cities are complex, adaptive systems whose underlying principles remain difficult to disentangle despite unprecedented data abundance. Urban science therefore faces a fundamental challenge: converting vast, fragmented and interdisciplinary information into coherent explanations of how cities function and evolve. The emergence of AI scientists, i.e., agents capable of autonomous reasoning, hypothesis formation and data-driven experimentation, offers a new pathway toward accelerating this transformation, yet general-purpose systems fall short of the domain knowledge and methodological depth required for urban science research. Here we introduce a knowledge-driven AI Urban Scientist, built from hypotheses, peer-review signals, datasets and analytical patterns distilled from thousands of high-quality studies, and implemented as a coordinated multi-agent framework for end-to-end inquiry. The system generates structured hypotheses, retrieves and harmonizes heterogeneous datasets, conducts automated empirical analysis and simulation, and synthesizes insights in forms compatible with urban scientific reasoning. By providing reusable analytical tools and supporting community-driven extensions, the AI Urban Scientist lowers barriers to advanced urban analytics and acts not merely as an assistant but as an active collaborator in revealing the mechanisms that shape urban systems and in guiding the design of more resilient and equitable cities. + oai:arXiv.org:2512.07849v1 cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CL + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ali Dasdan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Tong Xia, Jiankun Zhang, Ruiwen You, Ao Xu, Linghao Zhang, Tengyao Tu, Jingzhi Wang, Jinghua Piao, Yunke Zhang, Fengli Xu, Yong Li - FishDetector-R1: Unified MLLM-Based Framework with Reinforcement Fine-Tuning for Weakly Supervised Fish Detection, Segmentation, and Counting - https://arxiv.org/abs/2512.05996 - arXiv:2512.05996v1 Announce Type: new -Abstract: Analyzing underwater fish imagery is critical for ecological monitoring but remains difficult due to visual degradation and costly annotations. We introduce FishDetector-R1, a unified MLLM-based framework for fish detection, segmentation, and counting under weak supervision. On the DeepFish dataset, our framework achieves substantial gains over baselines, improving AP by 20% and mIoU by 10%, while reducing MAE by 30% and GAME by 35%. These improvements stem from two key components: a novel detect-to-count prompt that enforces spatially consistent detections and counts, and Reinforcement Learning from Verifiable Reward (RLVR) with a complementary scalable paradigm leveraging sparse point labels. Ablation studies further validate the effectiveness of this reward design. Moreover, the improvement generalizes well to other underwater datasets, confirming strong cross-domain robustness. Overall, FishDetector-R1 provides a reliable and scalable solution for accurate marine visual understanding via weak supervision. The project page for FishDetector-R1 is https://umfieldrobotics.github.io/FishDetector-R1. - oai:arXiv.org:2512.05996v1 - cs.CV - cs.CY - cs.RO - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 + SABER: Small Actions, Big Errors - Safeguarding Mutating Steps in LLM Agents + https://arxiv.org/abs/2512.07850 + arXiv:2512.07850v1 Announce Type: new +Abstract: Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: \emph{do all actions contribute equally to failure?} Analyzing execution traces on $\tau$-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into \emph{mutating} (environment-changing) vs.\ non-mutating steps and formalize \emph{decisive deviations}, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto $92\%$ on Airline and upto $96\%$ on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce \cm{}, a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects \emph{Targeted Reflection} before mutating steps, and (iii) performs block-based context cleaning. \cm{} delivers consistent gains, e.g., Qwen3-Thinking: +28\% \emph{relative} on Airline, +11\% on Retail, and +7\% on SWE-Bench Verified; Claude: +9\%/+7\%. We further identify ceiling effects in $\tau$-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release $\tau$-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents. + oai:arXiv.org:2512.07850v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Yi Liu, Jingyu Song, Vedanth Kallakuri, Katherine A. Skinner + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Alejandro Cuadron, Pengfei Yu, Yang Liu, Arpit Gupta - Going All-In on LLM Accuracy: Fake Prediction Markets, Real Confidence Signals - https://arxiv.org/abs/2512.05998 - arXiv:2512.05998v1 Announce Type: new -Abstract: Large language models are increasingly used to evaluate other models, yet these judgments typically lack any representation of confidence. This pilot study tests whether framing an evaluation task as a betting game (a fictional prediction market with its own LLM currency) improves forecasting accuracy and surfaces calibrated confidence signals. We generated 100 math and logic questions with verifiable answers. Six Baseline models (three current-generation, three prior-generation) answered all items. Three Predictor models then forecasted, for each question-baseline pair, if the baseline would answer correctly. Each predictor completed matched runs in two conditions: Control (simple correct/incorrect predictions) and Incentive (predictions plus wagers of 1-100,000 LLMCoin under even odds, starting from a 1,000,000 LLMCoin bankroll). Across 5,400 predictions per condition, Incentive runs showed modestly higher accuracy (81.5% vs. 79.1%, p = .089, d = 0.86) and significantly faster learning across rounds (12.0 vs. 2.9 percentage-point improvement from Round 1 to Round 4, p = .011). Most notably, stake size tracked confidence. "Whale" bets of 40,000+ coins were correct ~99% of the time, while small bets (<1,000 coins) showed only ~74% accuracy. The key finding is not that fictional money makes models smarter; accuracy gains were modest and did not reach statistical significance (p = .089) in this pilot. Rather, the betting mechanic created a legible confidence signal absent from binary yes/no outputs. This suggests that simple financial framing may help transform LLMs into risk-aware forecasters, making their internal beliefs visible and usable. The protocol offers a foundation for future work for meta-evaluation systems and what may become LLM-to-LLM prediction markets. - oai:arXiv.org:2512.05998v1 - cs.AI - cs.GT + GPU Memory Prediction for Multimodal Model Training + https://arxiv.org/abs/2512.07853 + arXiv:2512.07853v1 Announce Type: new +Abstract: As deep learning models in agentic AI systems grow in scale and complexity, GPU memory requirements increase and often exceed the available GPU memory capacity, so that out-of-memory (OoM) errors occur. It is well known that OoM interrupts the whole training itself and wastes substantial computational resources. Therefore, to prevent OoM, accurate prediction of GPU memory usage is essential. However, previous studies focus only on unimodal architectures and fail to generalize to multimodal models, even though the multimodal models are a common choice in agentic AI systems. To address this limitation, we propose a framework that predicts the peak GPU memory usage by analyzing the model architecture and training behavior of multimodal models. Specifically, the framework decomposes the multimodal model into its constituent layers and applies factorization to estimate the memory usage of each layer. Our evaluation shows that our framework achieves high prediction accuracy of ~8.7% average MAPE. + oai:arXiv.org:2512.07853v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.17605/OSF.IO/DC24T - Michael Todasco (Visiting Fellow at the James Silberrad Center for Artificial Intelligence, San Diego State University) + Jinwoo Jeong, Minchul Kang, Younghun Go, Changyong Shin, Hyunho Lee, Junho Yoon, Gyeongsik Yang, Chuck Yoo - POrTAL: Plan-Orchestrated Tree Assembly for Lookahead - https://arxiv.org/abs/2512.06002 - arXiv:2512.06002v1 Announce Type: new -Abstract: Assigning tasks to robots often involves supplying the robot with an overarching goal, such as through natural language, and then relying on the robot to uncover and execute a plan to achieve that goal. In many settings common to human-robot interaction, however, the world is only partially observable to the robot, requiring that it create plans under uncertainty. Although many probabilistic planning algorithms exist for this purpose, these algorithms can be inefficient if executed with the robot's limited computational resources, or may require more steps than expected to achieve the goal. We thereby created a new, lightweight, probabilistic planning algorithm, Plan-Orchestrated Tree Assembly for Lookahead (POrTAL), that combines the strengths of two baseline planning algorithms, FF-Replan and POMCP. In a series of case studies, we demonstrate POrTAL's ability to quickly arrive at solutions that outperform these baselines in terms of number of steps. We additionally demonstrate how POrTAL performs under varying temporal constraints. - oai:arXiv.org:2512.06002v1 - cs.RO - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + HSTMixer: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting + https://arxiv.org/abs/2512.07854 + arXiv:2512.07854v1 Announce Type: new +Abstract: Traffic forecasting task is significant to modern urban management. Recently, there is growing attention on large-scale forecasting, as it better reflects the complexity of real-world traffic networks. However, existing models often exhibit quadratic computational complexity, making them impractical for large-scale real-world scenarios. In this paper, we propose a novel framework, Hierarchical Spatio-Temporal Mixer (HSTMixer), which leverages an all-MLP architecture for efficient and effective large-scale traffic forecasting. HSTMixer employs a hierarchical spatiotemporal mixing block to extract multi-resolution features through bottom-up aggregation and top-down propagation. Furthermore, an adaptive region mixer generates transformation matrices based on regional semantics, enabling our model to dynamically capture evolving spatiotemporal patterns for different regions. Extensive experiments conducted on four large-scale real-world datasets demonstrate that the proposed method not only achieves state-of-the-art performance but also exhibits competitive computational efficiency. + oai:arXiv.org:2512.07854v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Evan Conway, David Porfirio, David Chan, Mark Roberts, Laura M. Hiatt + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yongyao Wang, Jingyuan Wang, Xie Yu, Jiahao Ji, Chao Li - PrunedCaps: A Case For Primary Capsules Discrimination - https://arxiv.org/abs/2512.06003 - arXiv:2512.06003v1 Announce Type: new -Abstract: Capsule Networks (CapsNets) are a generation of image classifiers with proven advantages over Convolutional Neural Networks (CNNs). Better robustness to affine transformation and overlapping image detection are some of the benefits associated with CapsNets. However, CapsNets cannot be classified as resource-efficient deep learning architecture due to the high number of Primary Capsules (PCs). In addition, CapsNets' training and testing are slow and resource hungry. This paper investigates the possibility of Primary Capsules pruning in CapsNets on MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and SVHN datasets. We show that a pruned version of CapsNet performs up to 9.90 times faster than the conventional architecture by removing 95 percent of Capsules without a loss of accuracy. Also, our pruned architecture saves on more than 95.36 percent of floating-point operations in the dynamic routing stage of the architecture. Moreover, we provide insight into why some datasets benefit significantly from pruning while others fall behind. - oai:arXiv.org:2512.06003v1 + LAPA: Log-Domain Prediction-Driven Dynamic Sparsity Accelerator for Transformer Model + https://arxiv.org/abs/2512.07855 + arXiv:2512.07855v1 Announce Type: new +Abstract: Attention-based Transformers have revolutionized natural language processing (NLP) and shown strong performance in computer vision (CV) tasks. However, as the input sequence varies, the computational bottlenecks in Transformer models exhibit dynamic behavior across stages, which calls for a cross-stage sparse acceleration strategy. Unfortunately, most existing sparse Transformer approaches are single-stage based, and their sparsity prediction mechanisms lead to significant power overhead when applied across multiple stages. To this end, this paper proposes a log-domain attention prediction algorithm-architecture co-design, named LAPA. First, an asymmetric leading one computing (ALOC) scheme is designed to eliminate expensive multiplications. Next, a mixed-precision multi-round shifting accumulation (MRSA) mechanism is further proposed to mitigate the accumulation overhead. A data-feature dependent filter (DDF) strategy is designed to work in concert with the MRSA process. Finally, an elaborate accelerator is designed to translate the theoretical enhancement into practical hardware improvement. Experimental results show that LAPA achieves 3.52x, 3.24x and 2.79x higher energy efficiency than the state-of-the-art (SOTA) works Spatten, Sanger and FACT, respectively. + oai:arXiv.org:2512.07855v1 + cs.LG cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1109/ICMLA52953.2021.00231 - Ramin Sharifi, Pouya Shiri, Amirali Baniasadi + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Huizheng Wang, Hongbin Wang, Shaojun Wei, Yang Hu, Shouyi Yin - Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization - https://arxiv.org/abs/2512.06006 - arXiv:2512.06006v1 Announce Type: new -Abstract: Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code adaptation costs scientists weeks to months of effort. We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design for this targeted task. We introduce a systematic evaluation framework for agentic code optimization and use it to study three production-level biomedical imaging pipelines. We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions. Our analysis reveals that common, complex agent architectures are not universally beneficial, leading to a practical roadmap for agent design. We open source our framework and validate our approach by deploying agent-generated functions into a production pipeline, demonstrating a clear pathway for real-world impact. - oai:arXiv.org:2512.06006v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Medical Test-free Disease Detection Based on Big Data + https://arxiv.org/abs/2512.07856 + arXiv:2512.07856v1 Announce Type: new +Abstract: Accurate disease detection is of paramount importance for effective medical treatment and patient care. However, the process of disease detection is often associated with extensive medical testing and considerable costs, making it impractical to perform all possible medical tests on a patient to diagnose or predict hundreds or thousands of diseases. In this work, we propose Collaborative Learning for Disease Detection (CLDD), a novel graph-based deep learning model that formulates disease detection as a collaborative learning task by exploiting associations among diseases and similarities among patients adaptively. CLDD integrates patient-disease interactions and demographic features from electronic health records to detect hundreds or thousands of diseases for every patient, with little to no reliance on the corresponding medical tests. Extensive experiments on a processed version of the MIMIC-IV dataset comprising 61,191 patients and 2,000 diseases demonstrate that CLDD consistently outperforms representative baselines across multiple metrics, achieving a 6.33\% improvement in recall and 7.63\% improvement in precision. Furthermore, case studies on individual patients illustrate that CLDD can successfully recover masked diseases within its top-ranked predictions, demonstrating both interpretability and reliability in disease prediction. By reducing diagnostic costs and improving accessibility, CLDD holds promise for large-scale disease screening and social health security. + oai:arXiv.org:2512.07856v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Xuefei (Julie), Wang, Kai A. Horstmann, Ethan Lin, Jonathan Chen, Alexander R. Farhang, Sophia Stiles, Atharva Sehgal, Jonathan Light, David Van Valen, Yisong Yue, Jennifer J. Sun + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Haokun Zhao, Yingzhe Bai, Qingyang Xu, Lixin Zhou, Jianxin Chen, Jicong Fan - Fast and Flexible Robustness Certificates for Semantic Segmentation - https://arxiv.org/abs/2512.06010 - arXiv:2512.06010v1 Announce Type: new -Abstract: Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust Deep Learning attempts to either enhance the robustness of neural networks (e.g, via adversarial training) or to certify their decisions up to a given robustness level (e.g, by using randomized smoothing, formal methods or Lipschitz bounds). These studies mostly focus on classification tasks and few efficient certification procedures currently exist for semantic segmentation. In this work, we introduce a new class of certifiably robust Semantic Segmentation networks with built-in Lipschitz constraints that are efficiently trainable and achieve competitive pixel accuracy on challenging datasets such as Cityscapes. Additionally, we provide a novel framework that generalizes robustness certificates for semantic segmentation tasks, where we showcase the flexibility and computational efficiency of using Lipschitz networks. Our approach unlocks real-time compatible certifiably robust semantic segmentation for the first time. Moreover, it allows the computation of worst-case performance under $\ell_2$ attacks of radius $\epsilon$ across a wide range of performance measures. Crucially, we benchmark the runtime of our certification process and find our approach to be around 600 times faster than randomized smoothing methods at inference with comparable certificates on an NVIDIA A100 GPU. Finally, we evaluate the tightness of our worstcase certificates against state-of-the-art adversarial attacks to further validate the performance of our method. - oai:arXiv.org:2512.06010v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + SA^2GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation + https://arxiv.org/abs/2512.07857 + arXiv:2512.07857v1 Announce Type: new +Abstract: We present Graph Foundation Models (GFMs) which have made significant progress in various tasks, but their robustness against domain noise, structural perturbations, and adversarial attacks remains underexplored. A key limitation is the insufficient modeling of hierarchical structural semantics, which are crucial for generalization. In this paper, we propose SA^2GFM, a robust GFM framework that improves domain-adaptive representations through Structure-Aware Semantic Augmentation. First, we encode hierarchical structural priors by transforming entropy-based encoding trees into structure-aware textual prompts for feature augmentation. The enhanced inputs are processed by a self-supervised Information Bottleneck mechanism that distills robust, transferable representations via structure-guided compression. To address negative transfer in cross-domain adaptation, we introduce an expert adaptive routing mechanism, combining a mixture-of-experts architecture with a null expert design. For efficient downstream adaptation, we propose a fine-tuning module that optimizes hierarchical structures through joint intra- and inter-community structure learning. Extensive experiments demonstrate that SA^2GFM outperforms 9 state-of-the-art baselines in terms of effectiveness and robustness against random noise and adversarial perturbations for node and graph classification. + oai:arXiv.org:2512.07857v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Thomas Massena (IRIT-MISFIT, DTIPG - SNCF, UT3), Corentin Friedrich (IRIT-MISFIT), Franck Mamalet (IRIT-MISFIT), Mathieu Serrurier (IRIT-MISFIT) + Junhua Shi, Qingyun Sun, Haonan Yuan, Xingcheng Fu - High-Throughput Unsupervised Profiling of the Morphology of 316L Powder Particles for Use in Additive Manufacturing - https://arxiv.org/abs/2512.06012 - arXiv:2512.06012v1 Announce Type: new -Abstract: Selective Laser Melting (SLM) is a powder-bed additive manufacturing technique whose part quality depends critically on feedstock morphology. However, conventional powder characterization methods are low-throughput and qualitative, failing to capture the heterogeneity of industrial-scale batches. We present an automated, machine learning framework that couples high-throughput imaging with shape extraction and clustering to profile metallic powder morphology at scale. We develop and evaluate three clustering pipelines: an autoencoder pipeline, a shape-descriptor pipeline, and a functional-data pipeline. Across a dataset of approximately 126,000 powder images (0.5-102 micrometer diameter), internal validity metrics identify the Fourier-descriptor + k-means pipeline as the most effective, achieving the lowest Davies-Bouldin index and highest Calinski-Harabasz score while maintaining sub-millisecond runtime per particle on a standard desktop workstation. Although the present work focuses on establishing the morphological-clustering framework, the resulting shape groups form a basis for future studies examining their relationship to flowability, packing density, and SLM part quality. Overall, this unsupervised learning framework enables rapid, automated assessment of powder morphology and supports tracking of shape evolution across reuse cycles, offering a path toward real-time feedstock monitoring in SLM workflows. - oai:arXiv.org:2512.06012v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + FAIM: Frequency-Aware Interactive Mamba for Time Series Classification + https://arxiv.org/abs/2512.07858 + arXiv:2512.07858v1 Announce Type: new +Abstract: Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition. TSC tasks require models to effectively capture discriminative information for accurate class identification. Although deep learning architectures excel at capturing temporal dependencies, they often suffer from high computational cost, sensitivity to noise perturbations, and susceptibility to overfitting on small-scale datasets. To address these challenges, we propose FAIM, a lightweight Frequency-Aware Interactive Mamba model. Specifically, we introduce an Adaptive Filtering Block (AFB) that leverages Fourier Transform to extract frequency-domain features from time series data. The AFB incorporates learnable adaptive thresholds to dynamically suppress noise and employs element-wise coupling of global and local semantic adaptive filtering, enabling in-depth modeling of the synergy among different frequency components. Furthermore, we design an Interactive Mamba Block (IMB) to facilitate efficient multi-granularity information interaction, balancing the extraction of fine-grained discriminative features and comprehensive global contextual information, thereby endowing FAIM with powerful and expressive representations for TSC tasks. Additionally, we incorporate a self-supervised pre-training mechanism to enhance FAIM's understanding of complex temporal patterns and improve its robustness across various domains and high-noise scenarios. Extensive experiments on multiple benchmarks demonstrate that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency and exhibits outstanding performance. + oai:arXiv.org:2512.07858v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Emmanuel Akeweje, Conall Kirk, Chi-Wai Chan, Denis Dowling, Mimi Zhang + Da Zhang, Bingyu Li, Zhiyuan Zhao, Yanhan Zhang, Junyu Gao, Feiping Nie, Xuelong Li - VAT: Vision Action Transformer by Unlocking Full Representation of ViT - https://arxiv.org/abs/2512.06013 - arXiv:2512.06013v1 Announce Type: new -Abstract: In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the Vision Action Transformer (VAT), a novel architecture that is extended from ViT and unlocks the full feature hierarchy of ViT. VAT processes specialized action tokens with visual features across all transformer layers, enabling a deep and progressive fusion of perception and action generation. On a suite of simulated manipulation tasks, VAT achieves a 98.15\% average success rate across four LIBERO benchmarks, establishing a new state-of-the-art by outperforming prior methods like OpenVLA-OFT. Our work presents not only a powerful model for imitation learning but also demonstrates the critical importance of leveraging the complete ''representation trajectory'' of vision models to advance robotic policy. The GitHub URL for the project code is https://github.com/sellerbubble/VAT. - oai:arXiv.org:2512.06013v1 - cs.CV - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + SetAD: Semi-Supervised Anomaly Learning in Contextual Sets + https://arxiv.org/abs/2512.07863 + arXiv:2512.07863v1 Announce Type: new +Abstract: Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or pair-centric} view not only overlooks the contextual nature of anomalies, which are defined by their deviation from a collective group, but also fails to exploit the rich supervisory signals that can be generated from the combinatorial composition of sets. Consequently, such models struggle to exploit the high-order interactions within the data, which are critical for learning discriminative representations. To address these limitations, we propose SetAD, a novel framework that reframes semi-supervised AD as a Set-level Anomaly Detection task. SetAD employs an attention-based set encoder trained via a graded learning objective, where the model learns to quantify the degree of anomalousness within an entire set. This approach directly models the complex group-level interactions that define anomalies. Furthermore, to enhance robustness and score calibration, we propose a context-calibrated anomaly scoring mechanism, which assesses a point's anomaly score by aggregating its normalized deviations from peer behavior across multiple, diverse contextual sets. Extensive experiments on 10 real-world datasets demonstrate that SetAD significantly outperforms state-of-the-art models. Notably, we show that our model's performance consistently improves with increasing set size, providing strong empirical support for the set-based formulation of anomaly detection. + oai:arXiv.org:2512.07863v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wenhao Li, Chengwei Ma, Weixin Mao + http://creativecommons.org/licenses/by/4.0/ + Jianling Gao, Chongyang Tao, Xuelian Lin, Junfeng Liu, Shuai Ma - Benchmarking CXR Foundation Models With Publicly Available MIMIC-CXR and NIH-CXR14 Datasets - https://arxiv.org/abs/2512.06014 - arXiv:2512.06014v1 Announce Type: new -Abstract: Recent foundation models have demonstrated strong performance in medical image representation learning, yet their comparative behaviour across datasets remains underexplored. This work benchmarks two large-scale chest X-ray (CXR) embedding models (CXR-Foundation (ELIXR v2.0) and MedImagelnsight) on public MIMIC-CR and NIH ChestX-ray14 datasets. Each model was evaluated using a unified preprocessing pipeline and fixed downstream classifiers to ensure reproducible comparison. We extracted embeddings directly from pre-trained encoders, trained lightweight LightGBM classifiers on multiple disease labels, and reported mean AUROC, and F1-score with 95% confidence intervals. MedImageInsight achieved slightly higher performance across most tasks, while CXR-Foundation exhibited strong cross-dataset stability. Unsupervised clustering of MedImageIn-sight embeddings further revealed a coherent disease-specific structure consistent with quantitative results. The results highlight the need for standardised evaluation of medical foundation models and establish reproducible baselines for future multimodal and clinical integration studies. - oai:arXiv.org:2512.06014v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Pattern Recognition of Ozone-Depleting Substance Exports in Global Trade Data + https://arxiv.org/abs/2512.07864 + arXiv:2512.07864v1 Announce Type: new +Abstract: New methods are needed to monitor environmental treaties, like the Montreal Protocol, by reviewing large, complex customs datasets. This paper introduces a framework using unsupervised machine learning to systematically detect suspicious trade patterns and highlight activities for review. Our methodology, applied to 100,000 trade records, combines several ML techniques. Unsupervised Clustering (K-Means) discovers natural trade archetypes based on shipment value and weight. Anomaly Detection (Isolation Forest and IQR) identifies rare "mega-trades" and shipments with commercially unusual price-per-kilogram values. This is supplemented by Heuristic Flagging to find tactics like vague shipment descriptions. These layers are combined into a priority score, which successfully identified 1,351 price outliers and 1,288 high-priority shipments for customs review. A key finding is that high-priority commodities show a different and more valuable value-to-weight ratio than general goods. This was validated using Explainable AI (SHAP), which confirmed vague descriptions and high value as the most significant risk predictors. The model's sensitivity was validated by its detection of a massive spike in "mega-trades" in early 2021, correlating directly with the real-world regulatory impact of the US AIM Act. This work presents a repeatable unsupervised learning pipeline to turn raw trade data into prioritized, usable intelligence for regulatory groups. + oai:arXiv.org:2512.07864v1 + cs.LG + econ.EM + econ.GN + q-fin.EC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Jiho Shin, Dominic Marshall, Matthieu Komorowski + Muhammad Sukri Bin Ramli - Training-Free Robot Pose Estimation using Off-the-Shelf Foundational Models - https://arxiv.org/abs/2512.06017 - arXiv:2512.06017v1 Announce Type: new -Abstract: Pose estimation of a robot arm from visual inputs is a challenging task. However, with the increasing adoption of robot arms for both industrial and residential use cases, reliable joint angle estimation can offer improved safety and performance guarantees, and also be used as a verifier to further train robot policies. This paper introduces using frontier vision-language models (VLMs) as an ``off-the-shelf" tool to estimate a robot arm's joint angles from a single target image. By evaluating frontier VLMs on both synthetic and real-world image-data pairs, this paper establishes a performance baseline attained by current FLMs. In addition, this paper presents empirical results suggesting that test time scaling or parameter scaling alone does not lead to improved joint angle predictions. - oai:arXiv.org:2512.06017v1 - cs.RO - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 + Using Text-Based Life Trajectories from Swedish Register Data to Predict Residential Mobility with Pretrained Transformers + https://arxiv.org/abs/2512.07865 + arXiv:2512.07865v1 Announce Type: new +Abstract: We transform large-scale Swedish register data into textual life trajectories to address two long-standing challenges in data analysis: high cardinality of categorical variables and inconsistencies in coding schemes over time. Leveraging this uniquely comprehensive population register, we convert register data from 6.9 million individuals (2001-2013) into semantically rich texts and predict individuals' residential mobility in later years (2013-2017). These life trajectories combine demographic information with annual changes in residence, work, education, income, and family circumstances, allowing us to assess how effectively such sequences support longitudinal prediction. We compare multiple NLP architectures (including LSTM, DistilBERT, BERT, and Qwen) and find that sequential and transformer-based models capture temporal and semantic structure more effectively than baseline models. The results show that textualized register data preserves meaningful information about individual pathways and supports complex, scalable modeling. Because few countries maintain longitudinal microdata with comparable coverage and precision, this dataset enables analyses and methodological tests that would be difficult or impossible elsewhere, offering a rigorous testbed for developing and evaluating new sequence-modeling approaches. Overall, our findings demonstrate that combining semantically rich register data with modern language models can substantially advance longitudinal analysis in social sciences. + oai:arXiv.org:2512.07865v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Laurence Liang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Philipp Stark, Alexandros Sopasakis, Ola Hall, Markus Grillitsch - Uncovering Students' Inquiry Patterns in GenAI-Supported Clinical Practice: An Integration of Epistemic Network Analysis and Sequential Pattern Mining - https://arxiv.org/abs/2512.06018 - arXiv:2512.06018v1 Announce Type: new -Abstract: Assessment of medication history-taking has traditionally relied on human observation, limiting scalability and detailed performance data. While Generative AI (GenAI) platforms enable extensive data collection and learning analytics provide powerful methods for analyzing educational traces, these approaches remain largely underexplored in pharmacy clinical training. This study addresses this gap by applying learning analytics to understand how students develop clinical communication competencies with GenAI-powered virtual patients -- a crucial endeavor given the diversity of student cohorts, varying language backgrounds, and the limited opportunities for individualized feedback in traditional training settings. We analyzed 323 students' interaction logs across Australian and Malaysian institutions, comprising 50,871 coded utterances from 1,487 student-GenAI dialogues. Combining Epistemic Network Analysis to model inquiry co-occurrences with Sequential Pattern Mining to capture temporal sequences, we found that high performers demonstrated strategic deployment of information recognition behaviors. Specifically, high performers centered inquiry on recognizing clinically relevant information, integrating rapport-building and structural organization, while low performers remained in routine question-verification loops. Demographic factors including first-language background, prior pharmacy work experience, and institutional context, also shaped distinct inquiry patterns. These findings reveal inquiry patterns that may indicate clinical reasoning development in GenAI-assisted contexts, providing methodological insights for health professions education assessment and informing adaptive GenAI system design that supports diverse learning pathways. - oai:arXiv.org:2512.06018v1 - cs.CY + Command & Control (C2) Traffic Detection Via Algorithm Generated Domain (Dga) Classification Using Deep Learning And Natural Language Processing + https://arxiv.org/abs/2512.07866 + arXiv:2512.07866v1 Announce Type: new +Abstract: The sophistication of modern malware, specifically regarding communication with Command and Control (C2) servers, has rendered static blacklist-based defenses obsolete. The use of Domain Generation Algorithms (DGA) allows attackers to generate thousands of dynamic addresses daily, hindering blocking by traditional firewalls. This paper aims to propose and evaluate a method for detecting DGA domains using Deep Learning and Natural Language Processing (NLP) techniques. The methodology consisted of collecting a hybrid database containing 50,000 legitimate and 50,000 malicious domains, followed by the extraction of lexical features and the training of a Recurrent Neural Network (LSTM). Results demonstrated that while statistical entropy analysis is effective for simple DGAs, the Neural Network approach presents superiority in detecting complex patterns, reaching 97.2% accuracy and reducing the false positive rate in ambiguous lawful traffic scenarios. + oai:arXiv.org:2512.07866v1 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiameng Wei, Dinh Dang, Kaixun Yang, Emily Stokes, Amna Mazeh, Angelina Lim, David Wei Dai, Joel Moore, Yizhou Fan, Danijela Gasevic, Dragan Gasevic, Guanliang Chen + Maria Milena Araujo Felix - PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation - https://arxiv.org/abs/2512.06020 - arXiv:2512.06020v1 Announce Type: new -Abstract: Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either fail to capture nuanced user preferences or lack effective mechanisms to encode personalized visual signals. In this work, we propose a multimodal framework that leverages multimodal large language models (MLLMs) to extract rich user representations and inject them into diffusion-based image generation. We train the MLLM with a preference-oriented visual question answering task to capture fine-grained semantic cues. To isolate preference-relevant features, we introduce two complementary probing tasks: inter-user discrimination to distinguish between different users, and intra-user discrimination to separate liked from disliked content. To ensure compatibility with diffusion text encoders, we design a maximum mean discrepancy-based alignment loss that bridges the modality gap while preserving multimodal structure. The resulting embeddings are used to condition the generator, enabling faithful adherence to both prompts and user preferences. Extensive experiments demonstrate that our method substantially outperforms strong baselines in both image quality and preference alignment, highlighting the effectiveness of representation extraction and alignment for personalized generation. - oai:arXiv.org:2512.06020v1 - cs.CV + Bayesian Optimization for Function-Valued Responses under Min-Max Criteria + https://arxiv.org/abs/2512.07868 + arXiv:2512.07868v1 Announce Type: new +Abstract: Bayesian optimization is widely used for optimizing expensive black box functions, but most existing approaches focus on scalar responses. In many scientific and engineering settings the response is functional, varying smoothly over an index such as time or wavelength, which makes classical formulations inadequate. Existing methods often minimize integrated error, which captures average performance but neglects worst case deviations. To address this limitation we propose min-max Functional Bayesian Optimization (MM-FBO), a framework that directly minimizes the maximum error across the functional domain. Functional responses are represented using functional principal component analysis, and Gaussian process surrogates are constructed for the principal component scores. Building on this representation, MM-FBO introduces an integrated uncertainty acquisition function that balances exploitation of worst case expected error with exploration across the functional domain. We provide two theoretical guarantees: a discretization bound for the worst case objective, and a consistency result showing that as the surrogate becomes accurate and uncertainty vanishes, the acquisition converges to the true min-max objective. We validate the method through experiments on synthetic benchmarks and physics inspired case studies involving electromagnetic scattering by metaphotonic devices and vapor phase infiltration. Results show that MM-FBO consistently outperforms existing baselines and highlights the importance of explicitly modeling functional uncertainty in Bayesian optimization. + oai:arXiv.org:2512.07868v1 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wenyi Mo, Tianyu Zhang, Yalong Bai, Ligong Han, Ying Ba, Dimitris N. Metaxas + http://creativecommons.org/licenses/by/4.0/ + Pouya Ahadi, Reza Marzban, Ali Adibi, Kamran Paynabar - DreamFoley: Scalable VLMs for High-Fidelity Video-to-Audio Generation - https://arxiv.org/abs/2512.06022 - arXiv:2512.06022v1 Announce Type: new -Abstract: Recent advances in video generation have achieved remarkable improvements in visual content fidelity. However, the absence of synchronized audio severely undermines immersive experience and restricts practical applications of these technologies. To address this challenge, several pioneering works have explored diffusion transformer architectures for generating plausible video-synchronized audio, including Kling-foley, HunyuanVideo-foley and Thinksound. Distinct from existing works, we introduce an autoregressive audio generation architecture (DreamFoley) that harnesses the capabilities of large vision-language models (VLMs) to jointly model sequential interactions among video, audio, and text modalities. Our approach features a dual-visual encoder module that effectively captures both audio-aligned and text-aligned visual features. Additionally, we employ a Residual Vector Quantization audio tokenizer with a delay-pattern generation scheme to balance the trade-off between training efficiency and audio quality. Moreover, we introduce the classifier-free guidance strategy into VLMs to bootstrap generated audio quality. Furthermore, we establish an efficient data production pipeline to scale audio-video-text triple collection. Finally, extensive experiments are conducted to validate the effectiveness of our model, achieving promising performance across popular benchmarks. We hope that the findings in this study provide a strong foundation for future video-to-audio generation research. We also release the previously missing audio-visual textual descriptions from the public benchmark, aiming to facilitate subsequent researchers in conducting more convenient and effective evaluations and comparisons. - oai:arXiv.org:2512.06022v1 + LocaGen: Sub-Sample Time-Delay Learning for Beam Localization + https://arxiv.org/abs/2512.07872 + arXiv:2512.07872v1 Announce Type: new +Abstract: The goal of LocaGen is to improve the localization performance of audio signals in the 2-D beam localization problem. LocaGen reduces sampling quantization errors through machine learning models trained on realistic synthetic data generated by a simulation. The system increases the accuracy of both direction-of-arrival (DOA) and precise location estimation of an audio beam from an array of three microphones. We demonstrate LocaGen's efficacy on a low-powered embedded system with an increased localization accuracy with a minimal increase in real-time resource usage. LocaGen was demonstrated to reduce DOA error by approximately 67% even with a microphone array of only 10 kHz in audio processing. + oai:arXiv.org:2512.07872v1 cs.SD - cs.MM - Tue, 09 Dec 2025 00:00:00 -0500 + eess.AS + eess.SP + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fu Li, Weichao Zhao, You Li, Zhichao Zhou, Dongliang He + http://creativecommons.org/licenses/by/4.0/ + Ishaan Kunwar, Henry Cantor, Tyler Rizzo, Ayaan Qayyum - Neural reconstruction of 3D ocean wave hydrodynamics from camera sensing - https://arxiv.org/abs/2512.06024 - arXiv:2512.06024v1 Announce Type: new -Abstract: Precise three-dimensional (3D) reconstruction of wave free surfaces and associated velocity fields is essential for developing a comprehensive understanding of ocean physics. To address the high computational cost of dense visual reconstruction in long-term ocean wave observation tasks and the challenges introduced by persistent visual occlusions, we propose an wave free surface visual reconstruction neural network, which is designed as an attention-augmented pyramid architecture tailored to the multi-scale and temporally continuous characteristics of wave motions. Using physics-based constraints, we perform time-resolved reconstruction of nonlinear 3D velocity fields from the evolving free-surface boundary. Experiments under real-sea conditions demonstrate millimetre-level wave elevation prediction in the central region, dominant-frequency errors below 0.01 Hz, precise estimation of high-frequency spectral power laws, and high-fidelity 3D reconstruction of nonlinear velocity fields, while enabling dense reconstruction of two million points in only 1.35 s. Built on a stereo-vision dataset, the model outperforms conventional visual reconstruction approaches and maintains strong generalization in occluded conditions, owing to its global multi-scale attention and its learned encoding of wave propagation dynamics. - oai:arXiv.org:2512.06024v1 - cs.CV - physics.flu-dyn - Tue, 09 Dec 2025 00:00:00 -0500 + Advancing physiological time series reconstruction and imputation via mixture of receptive fields and experts fusion + https://arxiv.org/abs/2512.07873 + arXiv:2512.07873v1 Announce Type: new +Abstract: Recent studies show that using diffusion models for time series signal reconstruc- tion holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the physiological time series signals, such as multivariate, high temporal variability, highly noisy, and artifact-prone, make deep learning-based approaches still challenging for tasks such as imputation. Hence, we propose a novel Mixture of Experts (MoE)-based noise estimator within a score-based diffusion framework. Specifically, the Receptive Field Adaptive MoE (RFAMoE) module is designed to enable each channel to adap- tively select desired receptive fields throughout the diffusion process. Moreover, recent literature has found that when generating a physiological signal, performing multiple inferences and averaging the reconstructed signals can effectively reduce reconstruction errors, but at the cost of significant computational and latency over- head. We design a Fusion MoE module and innovatively leverage the nature of MoE module to generate K noise signals in parallel, fuse them using a routing mechanism, and complete signal reconstruction in a single inference step. This design not only improves performance over previous methods but also eliminates the substantial computational cost and latency associated with multiple inference processes. Extensive results demonstrate that our proposed framework consistently outperforms diffusion-based SOTA works on different tasks and datasets. + oai:arXiv.org:2512.07873v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiabin Liu, Zihao Zhou, Jialei Yan, Anxin Guo, Alvise Benetazzo, Hui Li + Ci Zhang, Huayu Li, Changdi Yang, Jiangnan Xia, Yanzhi Wang, Xiaolong Ma, Jin Lu, Geng Yuan - The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation - https://arxiv.org/abs/2512.06032 - arXiv:2512.06032v1 Announce Type: new -Abstract: This paper investigates the fundamental discontinuity between the latest two Segment Anything Models: SAM2 and SAM3. We explain why the expertise in prompt-based segmentation of SAM2 does not transfer to the multimodal concept-driven paradigm of SAM3. SAM2 operates through spatial prompts points, boxes, and masks yielding purely geometric and temporal segmentation. In contrast, SAM3 introduces a unified vision-language architecture capable of open-vocabulary reasoning, semantic grounding, contrastive alignment, and exemplar-based concept understanding. We structure this analysis through five core components: (1) a Conceptual Break Between Prompt-Based and Concept-Based Segmentation, contrasting spatial prompt semantics of SAM2 with multimodal fusion and text-conditioned mask generation of SAM3; (2) Architectural Divergence, detailing pure vision-temporal design of SAM2 versus integration of vision-language encoders, geometry and exemplar encoders, fusion modules, DETR-style decoders, object queries, and ambiguity-handling via Mixture-of-Experts in SAM3; (3) Dataset and Annotation Differences, contrasting SA-V video masks with multimodal concept-annotated corpora of SAM3; (4) Training and Hyperparameter Distinctions, showing why SAM2 optimization knowledge does not apply to SAM3; and (5) Evaluation, Metrics, and Failure Modes, outlining the transition from geometric IoU metrics to semantic, open-vocabulary evaluation. Together, these analyses establish SAM3 as a new class of segmentation foundation model and chart future directions for the emerging concept-driven segmentation era. - oai:arXiv.org:2512.06032v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Controllable risk scenario generation from human crash data for autonomous vehicle testing + https://arxiv.org/abs/2512.07874 + arXiv:2512.07874v1 Announce Type: new +Abstract: Ensuring the safety of autonomous vehicles (AV) requires rigorous testing under both everyday driving and rare, safety-critical conditions. A key challenge lies in simulating environment agents, including background vehicles (BVs) and vulnerable road users (VRUs), that behave realistically in nominal traffic while also exhibiting risk-prone behaviors consistent with real-world accidents. We introduce Controllable Risk Agent Generation (CRAG), a framework designed to unify the modeling of dominant nominal behaviors and rare safety-critical behaviors. CRAG constructs a structured latent space that disentangles normal and risk-related behaviors, enabling efficient use of limited crash data. By combining risk-aware latent representations with optimization-based mode-transition mechanisms, the framework allows agents to shift smoothly and plausibly from safe to risk states over extended horizons, while maintaining high fidelity in both regimes. Extensive experiments show that CRAG improves diversity compared to existing baselines, while also enabling controllable generation of risk scenarios for targeted and efficient evaluation of AV robustness. + oai:arXiv.org:2512.07874v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Qiujing Lu, Xuanhan Wang, Runze Yuan, Wei Lu, Xinyi Gong, Shuo Feng - Sell Data to AI Algorithms Without Revealing It: Secure Data Valuation and Sharing via Homomorphic Encryption - https://arxiv.org/abs/2512.06033 - arXiv:2512.06033v1 Announce Type: new -Abstract: The rapid expansion of Artificial Intelligence is hindered by a fundamental friction in data markets: the value-privacy dilemma, where buyers cannot verify a dataset's utility without inspection, yet inspection may expose the data (Arrow's Information Paradox). We resolve this challenge by introducing the Trustworthy Influence Protocol (TIP), a privacy-preserving framework that enables prospective buyers to quantify the utility of external data without ever decrypting the raw assets. By integrating Homomorphic Encryption with gradient-based influence functions, our approach allows for the precise, blinded scoring of data points against a buyer's specific AI model. To ensure scalability for Large Language Models (LLMs), we employ low-rank gradient projections that reduce computational overhead while maintaining near-perfect fidelity to plaintext baselines, as demonstrated across BERT and GPT-2 architectures. Empirical simulations in healthcare and generative AI domains validate the framework's economic potential: we show that encrypted valuation signals achieve a high correlation with realized clinical utility and reveal a heavy-tailed distribution of data value in pre-training corpora where a minority of texts drive capability while the majority degrades it. These findings challenge prevailing flat-rate compensation models and offer a scalable technical foundation for a meritocratic, secure data economy. - oai:arXiv.org:2512.06033v1 - cs.CR - econ.GN - q-fin.EC - Tue, 09 Dec 2025 00:00:00 -0500 + Softly Symbolifying Kolmogorov-Arnold Networks + https://arxiv.org/abs/2512.07875 + arXiv:2512.07875v1 Announce Type: new +Abstract: Kolmogorov-Arnold Networks (KANs) offer a promising path toward interpretable machine learning: their learnable activations can be studied individually, while collectively fitting complex data accurately. In practice, however, trained activations often lack symbolic fidelity, learning pathological decompositions with no meaningful correspondence to interpretable forms. We propose Softly Symbolified Kolmogorov-Arnold Networks (S2KAN), which integrate symbolic primitives directly into training. Each activation draws from a dictionary of symbolic and dense terms, with learnable gates that sparsify the representation. Crucially, this sparsification is differentiable, enabling end-to-end optimization, and is guided by a principled Minimum Description Length objective. When symbolic terms suffice, S2KAN discovers interpretable forms; when they do not, it gracefully degrades to dense splines. We demonstrate competitive or superior accuracy with substantially smaller models across symbolic benchmarks, dynamical systems forecasting, and real-world prediction tasks, and observe evidence of emergent self-sparsification even without regularization pressure. + oai:arXiv.org:2512.07875v1 + cs.LG + cs.NE + physics.data-an + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Michael Yang (Eric), Ruijiang Gao (Eric), Zhiqiang (Eric), Zheng + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + James Bagrow, Josh Bongard - Closed-Loop Robotic Manipulation of Transparent Substrates for Self-Driving Laboratories using Deep Learning Micro-Error Correction - https://arxiv.org/abs/2512.06038 - arXiv:2512.06038v1 Announce Type: new -Abstract: Self-driving laboratories (SDLs) have accelerated the throughput and automation capabilities for discovering and improving chemistries and materials. Although these SDLs have automated many of the steps required to conduct chemical and materials experiments, a commonly overlooked step in the automation pipeline is the handling and reloading of substrates used to transfer or deposit materials onto for downstream characterization. Here, we develop a closed-loop method of Automated Substrate Handling and Exchange (ASHE) using robotics, dual-actuated dispensers, and deep learning-driven computer vision to detect and correct errors in the manipulation of fragile and transparent substrates for SDLs. Using ASHE, we demonstrate a 98.5% first-time placement accuracy across 130 independent trials of reloading transparent glass substrates into an SDL, where only two substrate misplacements occurred and were successfully detected as errors and automatically corrected. Through the development of more accurate and reliable methods for handling various types of substrates, we move toward an improvement in the automation capabilities of self-driving laboratories, furthering the acceleration of novel chemical and materials discoveries. - oai:arXiv.org:2512.06038v1 - cs.RO + Fourier-Enhanced Recurrent Neural Networks for Electrical Load Time Series Downscaling + https://arxiv.org/abs/2512.07876 + arXiv:2512.07876v1 Announce Type: new +Abstract: We present a Fourier-enhanced recurrent neural network (RNN) for downscaling electrical loads. The model combines (i) a recurrent backbone driven by low-resolution inputs, (ii) explicit Fourier seasonal embeddings fused in latent space, and (iii) a self-attention layer that captures dependencies among high-resolution components within each period. Across four PJM territories, the approach yields RMSE lower and flatter horizon-wise than classical Prophet baselines (with and without seasonality/LAA) and than RNN ablations without attention or Fourier features. + oai:arXiv.org:2512.07876v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Kelsey Fontenot, Anjali Gorti, Iva Goel, Tonio Buonassisi, Alexander E. Siemenn + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Qi Chen, Mihai Anitescu - The Reproducible Research Platform establishes a unified open science environment bridging data and software lifecycles across disciplines, from proposal to publication - https://arxiv.org/abs/2512.06039 - arXiv:2512.06039v1 Announce Type: new -Abstract: Many research groups aspire to make data and code FAIR and reproducible, yet struggle because the data and code life cycles are disconnected, executable environments are often missing from published work, and technical skill requirements hinder adoption. Existing approaches rarely enable researchers to keep using their preferred tools or support seamless execution across domains. To close this gap, we developed the open-source Reproducible Research Platform (RRP), which unifies research data management with version-controlled, containerized computational environments in modular, shareable projects. RRP enables anyone to execute, reuse, and publish fully documented, FAIR research workflows without manual retrieval or platform-specific setup. We demonstrate RRP's impact by reproducing results from diverse published studies, including work over a decade old, showing sustained reproducibility and usability. With a minimal graphical interface focused on core tasks, modular tool installation, and compatibility with institutional servers or local computers, RRP makes reproducible science broadly accessible across scientific domains. - oai:arXiv.org:2512.06039v1 - cs.DL - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Artificial Intelligence-Driven Network-on-Chip Design Space Exploration: Neural Network Architectures for Design + https://arxiv.org/abs/2512.07877 + arXiv:2512.07877v1 Announce Type: new +Abstract: Network-on-Chip (NoC) design requires exploring a high-dimensional configuration space to satisfy stringent throughput requirements and latency constraints.Traditional design space exploration techniques are often slow and struggle to handle complex, non-linear parameter interactions.This work presents a machine learning-driven framework that automates NoC design space exploration using BookSim simulations and reverse neural network models.Specifically, we compare three architectures - a Multi-Layer Perceptron (MLP),a Conditional Diffusion Model, and a Conditional Variational Autoencoder (CVAE) to predict optimal NoC parameters given target performance metrics.Our pipeline generates over 150,000 simulation data points across varied mesh topologies.The Conditional Diffusion Model achieved the highest predictive accuracy, attaining a mean squared error (MSE) of 0.463 on unseen data.Furthermore, the proposed framework reduces design exploration time by several orders of magnitude, making it a practical solution for rapid and scalable NoC co-design. + oai:arXiv.org:2512.07877v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Andreas P. Cuny, Henry L\"utcke, Andrei-Valentin Plamad\u{a}, Antti Luomi, John Hennig, Matthew Baker, Fabian Rudolf, Bernd Rinn + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Amogh Anshu N, Harish BP - Physics-Guided Deepfake Detection for Voice Authentication Systems - https://arxiv.org/abs/2512.06040 - arXiv:2512.06040v1 Announce Type: new -Abstract: Voice authentication systems deployed at the network edge face dual threats: a) sophisticated deepfake synthesis attacks and b) control-plane poisoning in distributed federated learning protocols. We present a framework coupling physics-guided deepfake detection with uncertainty-aware in edge learning. The framework fuses interpretable physics features modeling vocal tract dynamics with representations coming from a self-supervised learning module. The representations are then processed via a Multi-Modal Ensemble Architecture, followed by a Bayesian ensemble providing uncertainty estimates. Incorporating physics-based characteristics evaluations and uncertainty estimates of audio samples allows our proposed framework to remain robust to both advanced deepfake attacks and sophisticated control-plane poisoning, addressing the complete threat model for networked voice authentication. - oai:arXiv.org:2512.06040v1 - cs.SD - cs.AI - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 + Graph Contrastive Learning via Spectral Graph Alignment + https://arxiv.org/abs/2512.07878 + arXiv:2512.07878v1 Announce Type: new +Abstract: Given augmented views of each input graph, contrastive learning methods (e.g., InfoNCE) optimize pairwise alignment of graph embeddings across views while providing no mechanism to control the global structure of the view specific graph-of-graphs built from these embeddings. We introduce SpecMatch-CL, a novel loss function that aligns the view specific graph-of-graphs by minimizing the difference between their normalized Laplacians. Theoretically, we show that under certain assumptions, the difference between normalized Laplacians provides an upper bound not only for the difference between the ideal Perfect Alignment contrastive loss and the current loss, but also for the Uniformly loss. Empirically, SpecMatch-CL establishes new state of the art on eight TU benchmarks under unsupervised learning and semi-supervised learning at low label rates, and yields consistent gains in transfer learning on PPI-306K and ZINC 2M datasets. + oai:arXiv.org:2512.07878v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Alireza Mohammadi, Keshav Sood, Dhananjay Thiruvady, Asef Nazari + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Manh Nguyen (Department of Statistics, University of Wisconsin-Madison), Joshua Cape (Department of Statistics, University of Wisconsin-Madison) - Technical Report of Nomi Team in the Environmental Sound Deepfake Detection Challenge 2026 - https://arxiv.org/abs/2512.06041 - arXiv:2512.06041v1 Announce Type: new -Abstract: This paper presents our work for the ICASSP 2026 Environmental Sound Deepfake Detection (ESDD) Challenge. The challenge is based on the large-scale EnvSDD dataset that consists of various synthetic environmental sounds. We focus on addressing the complexities of unseen generators and low-resource black-box scenarios by proposing an audio-text cross-attention model. Experiments with individual and combined text-audio models demonstrate competitive EER improvements over the challenge baseline (BEATs+AASIST model). - oai:arXiv.org:2512.06041v1 - cs.SD - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 + Nonnegative Matrix Factorization through Cone Collapse + https://arxiv.org/abs/2512.07879 + arXiv:2512.07879v1 Announce Type: new +Abstract: Nonnegative matrix factorization (NMF) is a widely used tool for learning parts-based, low-dimensional representations of nonnegative data, with applications in vision, text, and bioinformatics. In clustering applications, orthogonal NMF (ONMF) variants further impose (approximate) orthogonality on the representation matrix so that its rows behave like soft cluster indicators. Existing algorithms, however, are typically derived from optimization viewpoints and do not explicitly exploit the conic geometry induced by NMF: data points lie in a convex cone whose extreme rays encode fundamental directions or "topics". In this work we revisit NMF from this geometric perspective and propose Cone Collapse, an algorithm that starts from the full nonnegative orthant and iteratively shrinks it toward the minimal cone generated by the data. We prove that, under mild assumptions on the data, Cone Collapse terminates in finitely many steps and recovers the minimal generating cone of $\mathbf{X}^\top$ . Building on this basis, we then derive a cone-aware orthogonal NMF model (CC-NMF) by applying uni-orthogonal NMF to the recovered extreme rays. Across 16 benchmark gene-expression, text, and image datasets, CC-NMF consistently matches or outperforms strong NMF baselines-including multiplicative updates, ANLS, projective NMF, ONMF, and sparse NMF-in terms of clustering purity. These results demonstrate that explicitly recovering the data cone can yield both theoretically grounded and empirically strong NMF-based clustering methods. + oai:arXiv.org:2512.07879v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Candy Olivia Mawalim, Haotian Zhang, Shogo Okada + Manh Nguyen (Department of Statistics), Daniel Pimentel-Alarc\'on (Department of Biostatistics and Medical Informatics, Wisconsin Institute of Discovery, University of Wisconsin-Madison) - Auto-SPT: Automating Semantic Preserving Transformations for Code - https://arxiv.org/abs/2512.06042 - arXiv:2512.06042v1 Announce Type: new -Abstract: Machine learning (ML) models for code clone detection determine whether two pieces of code are semantically equivalent, which in turn is a key building block for software-engineering tasks like refactoring and security tasks like vulnerability and malware detection. While these models are predominantly trained on clean, structured code datasets, real-world code often undergoes a variety of semantic-preserving transformations, including refactoring, minification, automated formatting, and compiler optimizations. To address this critical gap between training and test data, we propose Auto-SPT, a novel framework to automatically construct synthetic-data generators for code. Auto-SPT is designed to produce Semantic Preserving Transformations (SPTs) that alter a program's syntactic structure while preserving its functionality and is instantiated on top of Large Language Models (LLMs). In particular, we use LLMs to craft a diverse set of SPTs, generate strong implementations for these SPTs, and compose them to result into strong transformations. Our formal analysis shows that the diversity of SPTs impacts the strength of their composition. We then empirically demonstrate that Auto-SPT generates more diverse SPTs than existing approaches and these SPTs significantly drop the performance of state-of-the-art code clone detectors. Further experiments show Auto-SPT can be used to enhance code datasets for training, to produce code-clone detection models that are robust to real-world, adversarial code transformations. - oai:arXiv.org:2512.06042v1 - cs.SE - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Semi-Supervised Contrastive Learning with Orthonormal Prototypes + https://arxiv.org/abs/2512.07880 + arXiv:2512.07880v1 Announce Type: new +Abstract: Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embeddings converge into a lower-dimensional space, poses a significant challenge, especially in semi-supervised and self-supervised setups. In this paper, we first identify a critical learning-rate threshold, beyond which standard contrastive losses converge to collapsed solutions. Building on these insights, we propose CLOP, a novel semi-supervised loss function designed to prevent dimensional collapse by promoting the formation of orthogonal linear subspaces among class embeddings. Through extensive experiments on real and synthetic datasets, we demonstrate that CLOP improves performance in image classification and object detection tasks while also exhibiting greater stability across different learning rates and batch sizes. + oai:arXiv.org:2512.07880v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ashish Hooda, Mihai Christodorescu, Chuangang Ren, Aaron Wilson, Kassem Fawaz, Somesh Jha + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Huanran Li (Department of Electrical Engineering), Manh Nguyen (Statistics), Daniel Pimentel-Alarc\'on (Biostatistics, Wisconsin Institute of Discovery, University of Wisconsin-Madison) - Beyond Prototyping: Autonomous, Enterprise-Grade Frontend Development from Pixel to Production via a Specialized Multi-Agent Framework - https://arxiv.org/abs/2512.06046 - arXiv:2512.06046v1 Announce Type: new -Abstract: We present AI4UI, a framework of autonomous front-end development agents purpose-built to meet the rigorous requirements of enterprise-grade application delivery. Unlike general-purpose code assistants designed for rapid prototyping, AI4UI focuses on production readiness delivering secure, scalable, compliant, and maintainable UI code integrated seamlessly into enterprise workflows. AI4UI operates with targeted human-in-the-loop involvement: at the design stage, developers embed a Gen-AI-friendly grammar into Figma prototypes to encode requirements for precise interpretation; and at the post processing stage, domain experts refine outputs for nuanced design adjustments, domain-specific optimizations, and compliance needs. Between these stages, AI4UI runs fully autonomously, converting designs into engineering-ready UI code. Technical contributions include a Figma grammar for autonomous interpretation, domain-aware knowledge graphs, a secure abstract/package code integration strategy, expertise driven architecture templates, and a change-oriented workflow coordinated by specialized agent roles. In large-scale benchmarks against industry baselines and leading competitor systems, AI4UI achieved 97.24% platform compatibility, 87.10% compilation success, 86.98% security compliance, 78.00% feature implementation success, 73.50% code-review quality, and 73.36% UI/UX consistency. In blind preference studies with 200 expert evaluators, AI4UI emerged as one of the leaders demonstrating strong competitive standing among leading solutions. Operating asynchronously, AI4UI generates thousands of validated UI screens in weeks rather than months, compressing delivery timeline - oai:arXiv.org:2512.06046v1 - cs.SE + GSPN-2: Efficient Parallel Sequence Modeling + https://arxiv.org/abs/2512.07884 + arXiv:2512.07884v1 Announce Type: new +Abstract: Efficient vision transformer remains a bottleneck for high-resolution images and long-video related real-world applications. Generalized Spatial Propagation Network (GSPN) addresses this by replacing quadratic self-attention with a line-scan propagation scheme, bringing the cost close to linear in the number of rows or columns, while retaining accuracy. Despite this advancement, the existing GSPN implementation still suffers from (i) heavy overhead due to repeatedly launching GPU kernels, (ii) excessive data transfers from global GPU memory, and (iii) redundant computations caused by maintaining separate propagation weights for each channel. We introduce GSPN-2, a joint algorithm-system redesign. In particular, we eliminate thousands of micro-launches from the previous implementation into one single 2D kernel, explicitly pin one warp to each channel slice, and stage the previous column's activations in shared memory. On the model side, we introduce a compact channel propagation strategy that replaces per-channel matrices, trimming parameters, and align naturally with the affinity map used in transformer attention. Experiments demonstrate GSPN-2's effectiveness across image classification and text-to-image synthesis tasks, matching transformer-level accuracy with significantly lower computational cost. GSPN-2 establishes a new efficiency frontier for modeling global spatial context in vision applications through its unique combination of structured matrix transformations and GPU-optimized implementation. Project page: https://whj363636.github.io/GSPN2/ + oai:arXiv.org:2512.07884v1 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Ramprasath Ganesaraja, Swathika N, Saravanan AP, Kamalkumar Rathinasamy, Chetana Amancharla, Rahul Das, Sahil Dilip Panse, Aditya Batwe, Dileep Vijayan, Veena Ashok, Thanushree A P, Kausthubh J Rao, Alden Olivero, Roshan, Rajeshwar Reddy Manthena, Asmitha Yuga Sre A, Harsh Tripathi, Suganya Selvaraj, Vito Chin, Kasthuri Rangan Bhaskar, Kasthuri Rangan Bhaskar, Venkatraman R, Sajit Vijayakumar + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Hongjun Wang, Yitong Jiang, Collin McCarthy, David Wehr, Hanrong Ye, Xinhao Li, Ka Chun Cheung, Wonmin Byeon, Jinwei Gu, Ke Chen, Kai Han, Hongxu Yin, Pavlo Molchanov, Jan Kautz, Sifei Liu - The Road of Adaptive AI for Precision in Cybersecurity - https://arxiv.org/abs/2512.06048 - arXiv:2512.06048v1 Announce Type: new -Abstract: Cybersecurity's evolving complexity presents unique challenges and opportunities for AI research and practice. This paper shares key lessons and insights from designing, building, and operating production-grade GenAI pipelines in cybersecurity, with a focus on the continual adaptation required to keep pace with ever-shifting knowledge bases, tooling, and threats. Our goal is to provide an actionable perspective for AI practitioners and industry stakeholders navigating the frontier of GenAI for cybersecurity, with particular attention to how different adaptation mechanisms complement each other in end-to-end systems. We present practical guidance derived from real-world deployments, propose best practices for leveraging retrieval- and model-level adaptation, and highlight open research directions for making GenAI more robust, precise, and auditable in cyber defense. - oai:arXiv.org:2512.06048v1 - cs.CR - cs.AI - cs.CL + ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking + https://arxiv.org/abs/2512.07885 + arXiv:2512.07885v1 Announce Type: new +Abstract: Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science. Traditional tracking schemes mainly rely on subjective thresholds, which may introduce biases in their skills on the geographical region of application. We present ByteStorm, an efficient data-driven framework for reconstructing TC tracks without threshold tuning. It leverages deep learning networks to detect TC centers (via classification and localization), using only relative vorticity (850 mb) and mean sea-level pressure. Then, detected centers are linked into TC tracks through the BYTE algorithm. ByteStorm is evaluated against state-of-the-art deterministic trackers in the East- and West-North Pacific basins (ENP and WNP). The proposed framework achieves superior performance in terms of Probability of Detection ($85.05\%$ ENP, $79.48\%$ WNP), False Alarm Rate ($23.26\%$ ENP, $16.14\%$ WNP), and high Inter-Annual Variability correlations ($0.75$ ENP and $0.69$ WNP). These results highlight the potential of integrating deep learning and computer vision for fast and accurate TC tracking, offering a robust alternative to traditional approaches. + oai:arXiv.org:2512.07885v1 cs.LG - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Sahil Garg + Davide Donno, Donatello Elia, Gabriele Accarino, Marco De Carlo, Enrico Scoccimarro, Silvio Gualdi - ORTHOCUB: integral and differential cubature rules by orthogonal moments - https://arxiv.org/abs/2512.06049 - arXiv:2512.06049v1 Announce Type: new -Abstract: We discuss a numerical package, named ORTHOCUB, for the computation of linear functionals of both integral and differential type on multivariate polynomial spaces. The weighted sums corresponding to such integral and differential cubatures are implemented via orthogonal polynomial moments and auxiliary near-minimal algebraic cubature in a bounding box, with no conditioning issue since no matrix inversion or factorization is needed. The whole computational process indeed reduces to moment computation and dense matrix-vector products of relatively small size. The Matlab and Python codes are freely available, to be used as building blocks for integral and differential problems. - oai:arXiv.org:2512.06049v1 - cs.MS - Tue, 09 Dec 2025 00:00:00 -0500 + CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models + https://arxiv.org/abs/2512.07890 + arXiv:2512.07890v1 Announce Type: new +Abstract: The emergence of large language models (LLMs) has sparked much interest in creating LLM-based digital populations that can be applied to many applications such as social simulation, crowdsourcing, marketing, and recommendation systems. A digital population can reduce the cost of recruiting human participants and alleviate many concerns related to human subject study. However, research has found that most of the existing works rely solely on LLMs and could not sufficiently capture the accuracy and diversity of a real human population. To address this limitation, we propose CrowdLLM that integrates pretrained LLMs and generative models to enhance the diversity and fidelity of the digital population. We conduct theoretical analysis of CrowdLLM regarding its great potential in creating cost-effective, sufficiently representative, scalable digital populations that can match the quality of a real crowd. Comprehensive experiments are also conducted across multiple domains (e.g., crowdsourcing, voting, user rating) and simulation studies which demonstrate that CrowdLLM achieves promising performance in both accuracy and distributional fidelity to human data. + oai:arXiv.org:2512.07890v1 + cs.MA + cs.LG + stat.ME + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Laura Rinaldi, Alvise Sommariva, Marco Vianello + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ryan Feng Lin, Keyu Tian, Hanming Zheng, Congjing Zhang, Li Zeng, Shuai Huang - Measuring the Potential of Scientific Literature: A Network-Based Approach to Identifying Paradigm-Shifting Research - https://arxiv.org/abs/2512.06054 - arXiv:2512.06054v1 Announce Type: new -Abstract: This study introduces the Disruption Index as a superior citation-based metric. This index quantitatively assesses the degree to which a publication redirects subsequent scholarly attention away from its preceding literature, thus measuring its novelty and disruptive impact. We tested the D metric's efficacy using a rigorous dataset comprising seminal publications by Nobel Prize winners across Physics, Chemistry, and Physiology or Medicine, benchmarked against control papers with comparable citation counts but non-transformative influence. Our analysis conclusively demonstrates that the D metric effectively distinguishes these prize-worthy, field-redefining works from highly cited but merely incremental research. Furthermore, we explore two contextual variables associated with high disruptive potential: (i) the scale of collaboration (author team size) and (ii) the linguistic structure of the article's title and summary text. The results reveal a strong positive correlation between larger collaborative teams and elevated average D scores, suggesting that extensive collaboration may be a facilitator for generating paradigm shifts. Additionally, publications with high D values tend to feature more expansive titles and greater density of specialized, technical jargon in their abstracts. These findings validate the D metric as a reliable and scalable instrument for both historical and predictive identification of transformative research. They also furnish empirical evidence concerning the team structures and communication patterns that optimize for the production of groundbreaking scientific knowledge. - oai:arXiv.org:2512.06054v1 + Investigating the originality of scientific papers across time and domain: A quantitative analysis + https://arxiv.org/abs/2512.07892 + arXiv:2512.07892v1 Announce Type: new +Abstract: The study of creativity in science has long sought quantitative metrics capable of capturing the originality of the scientific insights contained within articles and other scientific works. In recent years, the field has witnessed a substantial expansion of research activity, enabled by advances in natural language processing and network analysis, and has utilised both macro- and micro-scale approaches with success. However, they often do not examine the text itself for evidence of originality. In this paper, we apply a computational measure correlating with originality from creativity science, Divergent Semantic Integration (DSI), to a set of 51,200 scientific abstracts and titles sourced from the Web of Science. To adapt DSI for application to scientific texts, we advance the original BERT method by incorporating SciBERT (a model trained on scientific corpora) into the computation of DSI. In our study, we observe that DSI plays a more pronounced role in the accrual of early citations for papers with fewer authors, varies substantially across subjects and research fields, and exhibits a declining correlation with citation counts over time. Furthermore, by modelling SciBERT- and BERT-DSI as predictors of the logarithm of 5-year citation counts alongside field, publication year, and the logarithm of author count, we find statistically significant relationships, with adjusted R-squared of 0.103 and 0.101 for BERT-DSI and SciBERT-DSI. Because existing scientometric measures rarely assess the originality expressed in textual content, DSI provides a valuable means of directly quantifying the conceptual originality embedded in scientific writing. + oai:arXiv.org:2512.07892v1 cs.DL - physics.soc-ph - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Sarah James + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jack H. Culbert Yoed N. Kenett, Philipp Mayr - Representation Learning for Point Cloud Understanding - https://arxiv.org/abs/2512.06058 - arXiv:2512.06058v1 Announce Type: new -Abstract: With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as 3D scanners, LiDARs, and RGB-D cameras, provides rich geometric, shape, and scale information. When combined with 2D images, 3D data offers machines a comprehensive understanding of their environment, benefiting applications like autonomous driving, robotics, remote sensing, and medical treatment. This dissertation focuses on three main areas: supervised representation learning for point cloud primitive segmentation, self-supervised learning methods, and transfer learning from 2D to 3D. Our approach, which integrates pre-trained 2D models to support 3D network training, significantly improves 3D understanding without merely transforming 2D data. Extensive experiments validate the effectiveness of our methods, showcasing their potential to advance point cloud representation learning by effectively integrating 2D knowledge. - oai:arXiv.org:2512.06058v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement + https://arxiv.org/abs/2512.07898 + arXiv:2512.07898v1 Announce Type: new +Abstract: Large Language Model (LLM)-based agents demonstrate advanced reasoning capabilities, yet practical constraints frequently limit outputs to single responses, leaving significant performance potential unrealized. This paper introduces MARINE (Multi-Agent Recursive IN-context Enhancement), a theoretically grounded framework that reconceptualizes test-time reasoning as iterative refinement of a persistent reference trajectory, fundamentally departing from conventional one-shot or multi-sample paradigms. The MARINE refinement operator systematically converts a base model's pass@N capabilities into near-optimal pass@1 performance. Rigorous theoretical analysis establishes that minimal feasible batches maximize expected performance gains under fixed invocation budgets, while logarithmically growing batch schedules ensure continuous improvement without computational constraints. Comprehensive evaluation on the BrowserComp-ZH benchmark demonstrates state-of-the-art results, with a 685B-parameter implementation achieving 46.0% pass@1 accuracy. Meanwhile, MARINE establishes a new paradigm for parameter-efficient reasoning: an 80B-parameter model augmented with MARINE matches the performance of standalone 1000B-parameter agents, reducing parameter requirements by over an order of magnitude. Notably, within a fixed computational budget, the proposed MARINE delivers higher-quality samples to alignment and optimization processes than traditional sampling-and-ranking strategies. Consequently, it has great potential to boost post-training efficiency. + oai:arXiv.org:2512.07898v1 + cs.MA + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Siming Yan + Hongwei Zhang, Ji Lu, Yongsheng Du, Yanqin Gao, Lingjun Huang, Baoli Wang, Fang Tan, Peng Zou - Deep learning recognition and analysis of Volatile Organic Compounds based on experimental and synthetic infrared absorption spectra - https://arxiv.org/abs/2512.06059 - arXiv:2512.06059v1 Announce Type: new -Abstract: Volatile Organic Compounds (VOCs) are organic molecules that have low boiling points and therefore easily evaporate into the air. They pose significant risks to human health, making their accurate detection the crux of efforts to monitor and minimize exposure. Infrared (IR) spectroscopy enables the ultrasensitive detection at low-concentrations of VOCs in the atmosphere by measuring their IR absorption spectra. However, the complexity of the IR spectra limits the possibility to implement VOC recognition and quantification in real-time. While deep neural networks (NNs) are increasingly used for the recognition of complex data structures, they typically require massive datasets for the training phase. Here, we create an experimental VOC dataset for nine different classes of compounds at various concentrations, using their IR absorption spectra. To further increase the amount of spectra and their diversity in term of VOC concentration, we augment the experimental dataset with synthetic spectra created via conditional generative NNs. This allows us to train robust discriminative NNs, able to reliably identify the nine VOCs, as well as to precisely predict their concentrations. The trained NN is suitable to be incorporated into sensing devices for VOCs recognition and analysis. - oai:arXiv.org:2512.06059v1 - cs.LG - physics.app-ph - physics.chem-ph - Tue, 09 Dec 2025 00:00:00 -0500 + Finding core subgraphs of directed graphs via discrete Ricci curvature flow + https://arxiv.org/abs/2512.07899 + arXiv:2512.07899v1 Announce Type: new +Abstract: Ricci curvature and its associated flow offer powerful geometric methods for analyzing complex networks. While existing research heavily focuses on applications for undirected graphs such as community detection and core extraction, there have been relatively less attention on directed graphs. + In this paper, we introduce a definition of Ricci curvature and an accompanying curvature flow for directed graphs. Crucially, for strongly connected directed graphs, this flow admits a unique global solution. We then apply this flow to detect strongly connected subgraphs from weakly connected directed graphs. (A weakly connected graph is connected overall but not necessarily strongly connected). Unlike prior work requiring graphs to be strongly connected, our method loosens this requirement. We transform a weakly connected graph into a strongly connected one by adding edges with very large artificial weights. This modification does not compromise our core subgraph detection. Due to their extreme weight, these added edges are automatically discarded during the final iteration of the Ricci curvature flow. + For core evaluation, our approach consistently surpasses traditional methods, achieving better results on at least two out of three key metrics. The implementation code is publicly available at https://github.com/12tangze12/Finding-core-subgraphs-on-directed-graphs. + oai:arXiv.org:2512.07899v1 + cs.SI + math.CO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Andrea Della Valle, Annalisa D'Arco, Tiziana Mancini, Rosanna Mosetti, Maria Chiara Paolozzi, Stefano Lupi, Sebastiano Pilati, Andrea Perali + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Juan Zhao, Jicheng Ma, Yunyan Yang, Liang Zhao - Reinforcement Learning Integrated Agentic RAG for Software Test Cases Authoring - https://arxiv.org/abs/2512.06060 - arXiv:2512.06060v1 Announce Type: new -Abstract: This paper introduces a framework that integrates reinforcement learning (RL) with autonomous agents to enable continuous improvement in the automated process of software test cases authoring from business requirement documents within Quality Engineering (QE) workflows. Conventional systems employing Large Language Models (LLMs) generate test cases from static knowledge bases, which fundamentally limits their capacity to enhance performance over time. Our proposed Reinforcement Infused Agentic RAG (Retrieve, Augment, Generate) framework overcomes this limitation by employing AI agents that learn from QE feedback, assessments, and defect discovery outcomes to automatically improve their test case generation strategies. The system combines specialized agents with a hybrid vector-graph knowledge base that stores and retrieves software testing knowledge. Through advanced RL algorithms, specifically Proximal Policy Optimization (PPO) and Deep Q-Networks (DQN), these agents optimize their behavior based on QE-reported test effectiveness, defect detection rates, and workflow metrics. As QEs execute AI-generated test cases and provide feedback, the system learns from this expert guidance to improve future iterations. Experimental validation on enterprise Apple projects yielded substantive improvements: a 2.4% increase in test generation accuracy (from 94.8% to 97.2%), and a 10.8% improvement in defect detection rates. The framework establishes a continuous knowledge refinement loop driven by QE expertise, resulting in progressively superior test case quality that enhances, rather than replaces, human testing capabilities. - oai:arXiv.org:2512.06060v1 - cs.SE + The Theory of Strategic Evolution: Games with Endogenous Players and Strategic Replicators + https://arxiv.org/abs/2512.07901 + arXiv:2512.07901v1 Announce Type: new +Abstract: This paper develops the Theory of Strategic Evolution, a general model for systems in which the population of players, strategies, and institutional rules evolve together. The theory extends replicator dynamics to settings with endogenous players, multi level selection, innovation, constitutional change, and meta governance. The central mathematical object is a Poiesis stack: a hierarchy of strategic layers linked by cross level gain matrices. Under small gain conditions, the system admits a global Lyapunov function and satisfies selection, tracking, and stochastic stability results at every finite depth. We prove that the class is closed under block extension, innovation events, heterogeneous utilities, continuous strategy spaces, and constitutional evolution. The closure theorem shows that no new dynamics arise at higher levels and that unrestricted self modification cannot preserve Lyapunov structure. The theory unifies results from evolutionary game theory, institutional design, innovation dynamics, and constitutional political economy, providing a general mathematical model of long run strategic adaptation. + oai:arXiv.org:2512.07901v1 + cs.GT cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + econ.TH + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Mohanakrishnan Hariharan + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Kevin Vallier - When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models - https://arxiv.org/abs/2512.06062 - arXiv:2512.06062v1 Announce Type: new -Abstract: Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the underlying training samples through structural overlap in the data manifold. We propose a black-box membership inference attack that exploits this vulnerability without requiring access to model internals or real data. The attacker repeatedly queries the generative model to obtain large numbers of synthetic samples, performs unsupervised clustering to identify dense regions of the synthetic distribution, and then analyzes cluster medoids and neighborhoods that correspond to high-density regions in the original training data. These neighborhoods act as proxies for training samples, enabling the adversary to infer membership or reconstruct approximate records. Our experiments across healthcare, finance, and other sensitive domains show that cluster overlap between real and synthetic data leads to measurable membership leakage-even when the generator is trained with differential privacy or other noise mechanisms. The results highlight an under-explored attack surface in synthetic data generation pipelines and call for stronger privacy guarantees that account for distributional neighborhood inference rather than sample-level memorization alone, underscoring its role in privacy-preserving data publishing. Implementation and evaluation code are publicly available at:github.com/Cluster-Medoid-Leakage-Attack. - oai:arXiv.org:2512.06062v1 - cs.LG + Agentic Artificial Intelligence for Ethical Cybersecurity in Uganda: A Reinforcement Learning Framework for Threat Detection in Resource-Constrained Environments + https://arxiv.org/abs/2512.07909 + arXiv:2512.07909v1 Announce Type: new +Abstract: Uganda's rapid digital transformation, supported by national strategies such as Vision 2040 and the Digital Transformation Roadmap, has expanded reliance on networked services while simultaneously increasing exposure to sophisticated cyber threats. In resource-constrained settings, commonly deployed rule-based intrusion detection systems lack the adaptability and ethical safeguards needed to address evolving attack patterns, leading to undetected breaches and excessive blocking of legitimate traffic. This study proposes an Agentic Artificial Intelligence (AAI) framework that integrates reinforcement learning, an explicit ethical governance layer, and human oversight to deliver adaptive and trustworthy cybersecurity. A CPU-optimized simulation environment was developed using a five-node network topology that mirrors key elements of Uganda's critical digital infrastructure and generates both benign and malicious traffic, including phishing, ransomware, and distributed denial-of-service attacks. A Q-learning agent, operating within clearly defined ethical constraints and subject to human auditability, was trained and evaluated against a traditional rule-based baseline. The AAI framework achieved a 100 percent detection rate, zero false positives, and full ethical compliance, compared with 70 percent detection and 15 percent false positives for the baseline system. These results demonstrate that agentic, ethically governed reinforcement learning can substantially improve cybersecurity effectiveness and fairness in CPU-only, resource-constrained environments, offering a practical pathway for operationalizing responsible AI in Uganda's national cybersecurity strategy. + oai:arXiv.org:2512.07909v1 + cs.CR + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Ibrahim Adabara, Bashir Olaniyi Sadiq, Aliyu Nuhu Shuaibu, Yale Ibrahim Danjuma, Venkateswarlu Maninti, Mutebi Joe + + + CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automation + https://arxiv.org/abs/2512.07917 + arXiv:2512.07917v1 Announce Type: new +Abstract: Configuring computational fluid dynamics (CFD) simulations requires significant expertise in physics modeling and numerical methods, posing a barrier to non-specialists. Although automating scientific tasks with large language models (LLMs) has attracted attention, applying them to the complete, end-to-end CFD workflow remains a challenge due to its stringent domain-specific requirements. We introduce CFD-copilot, a domain-specialized LLM framework designed to facilitate natural language-driven CFD simulation from setup to post-processing. The framework employs a fine-tuned LLM to directly translate user descriptions into executable CFD setups. A multi-agent system integrates the LLM with simulation execution, automatic error correction, and result analysis. For post-processing, the framework utilizes the model context protocol (MCP), an open standard that decouples LLM reasoning from external tool execution. This modular design allows the LLM to interact with numerous specialized post-processing functions through a unified and scalable interface, improving the automation of data extraction and analysis. The framework was evaluated on benchmarks including the NACA~0012 airfoil and the three-element 30P-30N airfoil. The results indicate that domain-specific adaptation and the incorporation of the MCP jointly enhance the reliability and efficiency of LLM-driven engineering workflows. + oai:arXiv.org:2512.07917v1 + cs.SE cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + physics.flu-dyn + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - S. M. Mustaqim, Anantaa Kotal, Paul H. Yi + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Zhehao Dong, Shanghai Du, Zhen Lu, Yue Yang - EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing - https://arxiv.org/abs/2512.06065 - arXiv:2512.06065v1 Announce Type: new -Abstract: We study instruction-guided editing of egocentric videos for interactive AR applications. While recent AI video editors perform well on third-person footage, egocentric views present unique challenges - including rapid egomotion and frequent hand-object interactions - that create a significant domain gap. Moreover, existing offline editing pipelines suffer from high latency, limiting real-time interaction. To address these issues, we present a complete ecosystem for egocentric video editing. First, we construct EgoEditData, a carefully designed and manually curated dataset specifically designed for egocentric editing scenarios, featuring rich hand-object interactions, while explicitly preserving hands. Second, we develop EgoEdit, an instruction-following egocentric video editor that supports real-time streaming inference on a single GPU. Finally, we introduce EgoEditBench, an evaluation suite targeting instruction faithfulness, hand and interaction preservation, and temporal stability under egomotion. Across both egocentric and general editing tasks, EgoEdit produces temporally stable, instruction-faithful results with interactive latency. It achieves clear gains on egocentric editing benchmarks-where existing methods struggle-while maintaining performance comparable to the strongest baselines on general editing tasks. EgoEditData and EgoEditBench will be made public for the research community. See our website at https://snap-research.github.io/EgoEdit - oai:arXiv.org:2512.06065v1 - cs.CV + DeepCode: Open Agentic Coding + https://arxiv.org/abs/2512.07921 + arXiv:2512.07921v1 Announce Type: new +Abstract: Recent advances in large language models (LLMs) have given rise to powerful coding agents, making it possible for code assistants to evolve into code engineers. However, existing methods still face significant challenges in achieving high-fidelity document-to-codebase synthesis--such as scientific papers to code--primarily due to a fundamental conflict between information overload and the context bottlenecks of LLMs. In this work, we introduce DeepCode, a fully autonomous framework that fundamentally addresses this challenge through principled information-flow management. By treating repository synthesis as a channel optimization problem, DeepCode seamlessly orchestrates four information operations to maximize task-relevant signals under finite context budgets: source compression via blueprint distillation, structured indexing using stateful code memory, conditional knowledge injection via retrieval-augmented generation, and closed-loop error correction. Extensive evaluations on the PaperBench benchmark demonstrate that DeepCode achieves state-of-the-art performance, decisively outperforming leading commercial agents such as Cursor and Claude Code, and crucially, surpassing PhD-level human experts from top institutes on key reproduction metrics. By systematically transforming paper specifications into production-grade implementations comparable to human expert quality, this work establishes new foundations for autonomous scientific reproduction that can accelerate research evaluation and discovery. + oai:arXiv.org:2512.07921v1 + cs.SE cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Runjia Li, Moayed Haji-Ali, Ashkan Mirzaei, Chaoyang Wang, Arpit Sahni, Ivan Skorokhodov, Aliaksandr Siarohin, Tomas Jakab, Junlin Han, Sergey Tulyakov, Philip Torr, Willi Menapace + http://creativecommons.org/licenses/by/4.0/ + Zongwei Li, Zhonghang Li, Zirui Guo, Xubin Ren, Chao Huang - Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light - https://arxiv.org/abs/2512.06080 - arXiv:2512.06080v1 Announce Type: new -Abstract: 3D scene reconstruction from a single measurement is challenging, especially in the presence of occluded regions and specular materials, such as mirrors. We address these challenges by leveraging single-photon lidars. These lidars estimate depth from light that is emitted into the scene and reflected directly back to the sensor. However, they can also measure light that bounces multiple times in the scene before reaching the sensor. This multi-bounce light contains additional information that can be used to recover dense depth, occluded geometry, and material properties. Prior work with single-photon lidar, however, has only demonstrated these use cases when a laser sequentially illuminates one scene point at a time. We instead focus on the more practical - and challenging - scenario of illuminating multiple scene points simultaneously. The complexity of light transport due to the combined effects of multiplexed illumination, two-bounce light, shadows, and specular reflections is challenging to invert analytically. Instead, we propose a data-driven method to invert light transport in single-photon lidar. To enable this approach, we create the first large-scale simulated dataset of ~100k lidar transients for indoor scenes. We use this dataset to learn a prior on complex light transport, enabling measured two-bounce light to be decomposed into the constituent contributions from each laser spot. Finally, we experimentally demonstrate how this decomposed light can be used to infer 3D geometry in scenes with occlusions and mirrors from a single measurement. Our code and dataset are released at https://shoot-bounce-3d.github.io. - oai:arXiv.org:2512.06080v1 + Near-real time fires detection using satellite imagery in Sudan conflict + https://arxiv.org/abs/2512.07925 + arXiv:2512.07925v1 Announce Type: new +Abstract: The challenges of ongoing war in Sudan highlight the need for rapid moni- toring and analysis of such conflicts. Advances in deep learning and readily available satellite remote sensing imagery allow for near real-time monitor- ing. This paper uses 4-band imagery from Planet Labs with a deep learning model to show that fire damage in armed conflicts can be monitored with minimal delay. We demonstrate the effectiveness of our approach using five case studies in Sudan. We show that, compared to a baseline, the automated method captures the active fires and charred areas more accurately. Our re- sults indicate that using 8-band imagery or time series of such imagery only result in marginal gains. + oai:arXiv.org:2512.07925v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Tzofi Klinghoffer, Siddharth Somasundaram, Xiaoyu Xiang, Yuchen Fan, Christian Richardt, Akshat Dave, Ramesh Raskar, Rakesh Ranjan + Kuldip Singh Atwal, Dieter Pfoser, Daniel Rothbart - Compass: Mapping Space Exploration for Multi-Chiplet Accelerators Targeting LLM Inference Serving Workloads - https://arxiv.org/abs/2512.06093 - arXiv:2512.06093v1 Announce Type: new -Abstract: Large Language Models (LLMs) impose massive computational demands, driving the need for scalable multi-chiplet accelerators. However, existing mapping space exploration efforts for such accelerators primarily focus on traditional CNN/Transformer workloads and fail to adequately support the dynamic behaviors of mixed request types and variable sequence lengths in real-world LLM inference serving. To bridge this gap, we first propose a computation execution graph-based mapping encoding scheme that decouples micro-batches and layers, enabling fine-grained execution control on heterogeneous chiplets and flexibly representing various parallelism strategies. Second, building upon this scheme, we develop the Compass framework, which integrates an evaluation engine and a genetic algorithm-based mapping generation engine to achieve efficient mapping search. Compared to state-of-the-art works, our solution achieves an average EDP reduction of 63.12%. - oai:arXiv.org:2512.06093v1 - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 + Can AI autonomously build, operate, and use the entire data stack? + https://arxiv.org/abs/2512.07926 + arXiv:2512.07926v1 Announce Type: new +Abstract: Enterprise data management is a monumental task. It spans data architecture and systems, integration, quality, governance, and continuous improvement. While AI assistants can help specific persona, such as data engineers and stewards, to navigate and configure the data stack, they fall far short of full automation. However, as AI becomes increasingly capable of tackling tasks that have previously resisted automation due to inherent complexities, we believe there is an imminent opportunity to target fully autonomous data estates. Currently, AI is used in different parts of the data stack, but in this paper, we argue for a paradigm shift from the use of AI in independent data component operations towards a more holistic and autonomous handling of the entire data lifecycle. Towards that end, we explore how each stage of the modern data stack can be autonomously managed by intelligent agents to build self-sufficient systems that can be used not only by human end-users, but also by AI itself. We begin by describing the mounting forces and opportunities that demand this paradigm shift, examine how agents can streamline the data lifecycle, and highlight open questions and areas where additional research is needed. We hope this work will inspire lively debate, stimulate further research, motivate collaborative approaches, and facilitate a more autonomous future for data systems. + oai:arXiv.org:2512.07926v1 + cs.AI + cs.DB + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Boyu Li, Zongwei Zhu, Yi Xiong, Qianyue Cao, Jiawei Geng, Xiaonan Zhang, Xi Li + http://creativecommons.org/licenses/by/4.0/ + Arvind Agarwal, Lisa Amini, Sameep Mehta, Horst Samulowitz, Kavitha Srinivas - BeLLA: End-to-End Birds Eye View Large Language Assistant for Autonomous Driving - https://arxiv.org/abs/2512.06096 - arXiv:2512.06096v1 Announce Type: new -Abstract: The rapid development of Vision-Language models (VLMs) and Multimodal Language Models (MLLMs) in autonomous driving research has significantly reshaped the landscape by enabling richer scene understanding, context-aware reasoning, and more interpretable decision-making. However, a lot of existing work often relies on either single-view encoders that fail to exploit the spatial structure of multi-camera systems or operate on aggregated multi-view features, which lack a unified spatial representation, making it more challenging to reason about ego-centric directions, object relations, and the wider context. We thus present BeLLA, an end-to-end architecture that connects unified 360{\deg} BEV representations with a large language model for question answering in autonomous driving. We primarily evaluate our work using two benchmarks - NuScenes-QA and DriveLM, where BeLLA consistently outperforms existing approaches on questions that require greater spatial reasoning, such as those involving relative object positioning and behavioral understanding of nearby objects, achieving up to +9.3% absolute improvement in certain tasks. In other categories, BeLLA performs competitively, demonstrating the capability of handling a diverse range of questions. - oai:arXiv.org:2512.06096v1 + Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality + https://arxiv.org/abs/2512.07951 + arXiv:2512.07951v1 Announce Type: new +Abstract: Video face swapping is crucial in film and entertainment production, where achieving high fidelity and temporal consistency over long and complex video sequences remains a significant challenge. Inspired by recent advances in reference-guided image editing, we explore whether rich visual attributes from source videos can be similarly leveraged to enhance both fidelity and temporal coherence in video face swapping. Building on this insight, this work presents LivingSwap, the first video reference guided face swapping model. Our approach employs keyframes as conditioning signals to inject the target identity, enabling flexible and controllable editing. By combining keyframe conditioning with video reference guidance, the model performs temporal stitching to ensure stable identity preservation and high-fidelity reconstruction across long video sequences. To address the scarcity of data for reference-guided training, we construct a paired face-swapping dataset, Face2Face, and further reverse the data pairs to ensure reliable ground-truth supervision. Extensive experiments demonstrate that our method achieves state-of-the-art results, seamlessly integrating the target identity with the source video's expressions, lighting, and motion, while significantly reducing manual effort in production workflows. Project webpage: https://aim-uofa.github.io/LivingSwap + oai:arXiv.org:2512.07951v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Karthik Mohan, Sonam Singh, Amit Arvind Kale + Zekai Luo, Zongze Du, Zhouhang Zhu, Hao Zhong, Muzhi Zhu, Wen Wang, Yuling Xi, Chenchen Jing, Hao Chen, Chunhua Shen - Empathy by Design: Aligning Large Language Models for Healthcare Dialogue - https://arxiv.org/abs/2512.06097 - arXiv:2512.06097v1 Announce Type: new -Abstract: General-purpose large language models (LLMs) have demonstrated remarkable generative and reasoning capabilities but remain limited in healthcare and caregiving applications due to two key deficiencies: factual unreliability and a lack of empathetic communication. These shortcomings pose significant risks in sensitive contexts where users, particularly non-professionals and caregivers, seek medically relevant guidance or emotional reassurance. To address these challenges, we introduce a Direct Preference Optimization (DPO)-based alignment framework designed to improve factual correctness, semantic coherence, and human-centric qualities such as empathy, politeness, and simplicity in caregiver-patient dialogues. Our approach fine-tunes domain-adapted LLMs using pairwise preference data, where preferred responses reflect supportive and accessible communication styles while rejected ones represent prescriptive or overly technical tones. This direct optimization method aligns model outputs with human preferences more efficiently than traditional reinforcement-learning-based alignment. Empirical evaluations across multiple open and proprietary LLMs show that our DPO-tuned models achieve higher semantic alignment, improved factual accuracy, and stronger human-centric evaluation scores compared to baseline and commercial alternatives such as Google medical dialogue systems. These improvements demonstrate that preference-based alignment offers a scalable and transparent pathway toward developing trustworthy, empathetic, and clinically informed AI assistants for caregiver and healthcare communication. Our open-source code is available at: https://github.com/LeonG19/Empathy-by-Design - oai:arXiv.org:2512.06097v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Towards symbolic regression for interpretable clinical decision scores + https://arxiv.org/abs/2512.07961 + arXiv:2512.07961v1 Announce Type: new +Abstract: Medical decision-making makes frequent use of algorithms that combine risk equations with rules, providing clear and standardized treatment pathways. Symbolic regression (SR) traditionally limits its search space to continuous function forms and their parameters, making it difficult to model this decision-making. However, due to its ability to derive data-driven, interpretable models, SR holds promise for developing data-driven clinical risk scores. To that end we introduce Brush, an SR algorithm that combines decision-tree-like splitting algorithms with non-linear constant optimization, allowing for seamless integration of rule-based logic into symbolic regression and classification models. Brush achieves Pareto-optimal performance on SRBench, and was applied to recapitulate two widely used clinical scoring systems, achieving high accuracy and interpretable models. Compared to decision trees, random forests, and other SR methods, Brush achieves comparable or superior predictive performance while producing simpler models. + oai:arXiv.org:2512.07961v1 + cs.LG + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Emre Umucu, Guillermina Solis, Leon Garza, Emilia Rivas, Beatrice Lee, Anantaa Kotal, Aritran Piplai + Guilherme Seidyo Imai Aldeia, Joseph D. Romano, Fabricio Olivetti de Franca, Daniel S. Herman, William G. La Cava - JaxWildfire: A GPU-Accelerated Wildfire Simulator for Reinforcement Learning - https://arxiv.org/abs/2512.06102 - arXiv:2512.06102v1 Announce Type: new -Abstract: Artificial intelligence methods are increasingly being explored for managing wildfires and other natural hazards. In particular, reinforcement learning (RL) is a promising path towards improving outcomes in such uncertain decision-making scenarios and moving beyond reactive strategies. However, training RL agents requires many environment interactions, and the speed of existing wildfire simulators is a severely limiting factor. We introduce $\texttt{JaxWildfire}$, a simulator underpinned by a principled probabilistic fire spread model based on cellular automata. It is implemented in JAX and enables vectorized simulations using $\texttt{vmap}$, allowing high throughput of simulations on GPUs. We demonstrate that $\texttt{JaxWildfire}$ achieves 6-35x speedup over existing software and enables gradient-based optimization of simulator parameters. Furthermore, we show that $\texttt{JaxWildfire}$ can be used to train RL agents to learn wildfire suppression policies. Our work is an important step towards enabling the advancement of RL techniques for managing natural hazards. - oai:arXiv.org:2512.06102v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Sparse Variable Projection in Robotic Perception: Exploiting Separable Structure for Efficient Nonlinear Optimization + https://arxiv.org/abs/2512.07969 + arXiv:2512.07969v1 Announce Type: new +Abstract: Robotic perception often requires solving large nonlinear least-squares (NLS) problems. While sparsity has been well-exploited to scale solvers, a complementary and underexploited structure is \emph{separability} -- where some variables (e.g., visual landmarks) appear linearly in the residuals and, for any estimate of the remaining variables (e.g., poses), have a closed-form solution. Variable projection (VarPro) methods are a family of techniques that exploit this structure by analytically eliminating the linear variables and presenting a reduced problem in the remaining variables that has favorable properties. However, VarPro has seen limited use in robotic perception; a major challenge arises from gauge symmetries (e.g., cost invariance to global shifts and rotations), which are common in perception and induce specific computational challenges in standard VarPro approaches. We present a VarPro scheme designed for problems with gauge symmetries that jointly exploits separability and sparsity. Our method can be applied as a one-time preprocessing step to construct a \emph{matrix-free Schur complement operator}. This operator allows efficient evaluation of costs, gradients, and Hessian-vector products of the reduced problem and readily integrates with standard iterative NLS solvers. We provide precise conditions under which our method applies, and describe extensions when these conditions are only partially met. Across synthetic and real benchmarks in SLAM, SNL, and SfM, our approach achieves up to \textbf{2$\times$--35$\times$ faster runtimes} than state-of-the-art methods while maintaining accuracy. We release an open-source C++ implementation and all datasets from our experiments. + oai:arXiv.org:2512.07969v1 + cs.RO + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ufuk \c{C}ak{\i}r, Victor-Alexandru Darvariu, Bruno Lacerda, Nick Hawes + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Alan Papalia, Nikolas Sanderson, Haoyu Han, Heng Yang, Hanumant Singh, Michael Everett - SpectraIrisPAD: Leveraging Vision Foundation Models for Spectrally Conditioned Multispectral Iris Presentation Attack Detection - https://arxiv.org/abs/2512.06103 - arXiv:2512.06103v1 Announce Type: new -Abstract: Iris recognition is widely recognized as one of the most accurate biometric modalities. However, its growing deployment in real-world applications raises significant concerns regarding its vulnerability to Presentation Attacks (PAs). Effective Presentation Attack Detection (PAD) is therefore critical to ensure the integrity and security of iris-based biometric systems. While conventional iris recognition systems predominantly operate in the near-infrared (NIR) spectrum, multispectral imaging across multiple NIR bands provides complementary reflectance information that can enhance the generalizability of PAD methods. In this work, we propose \textbf{SpectraIrisPAD}, a novel deep learning-based framework for robust multispectral iris PAD. The SpectraIrisPAD leverages a DINOv2 Vision Transformer (ViT) backbone equipped with learnable spectral positional encoding, token fusion, and contrastive learning to extract discriminative, band-specific features that effectively distinguish bona fide samples from various spoofing artifacts. Furthermore, we introduce a new comprehensive dataset Multispectral Iris PAD (\textbf{MSIrPAD}) with diverse PAIs, captured using a custom-designed multispectral iris sensor operating at five distinct NIR wavelengths (800\,nm, 830\,nm, 850\,nm, 870\,nm, and 980\,nm). The dataset includes 18,848 iris images encompassing eight diverse PAI categories, including five textured contact lenses, print attacks, and display-based attacks. We conduct comprehensive experiments under unseen attack evaluation protocols to assess the generalization capability of the proposed method. SpectraIrisPAD consistently outperforms several state-of-the-art baselines across all performance metrics, demonstrating superior robustness and generalizability in detecting a wide range of presentation attacks. - oai:arXiv.org:2512.06103v1 + VLD: Visual Language Goal Distance for Reinforcement Learning Navigation + https://arxiv.org/abs/2512.07976 + arXiv:2512.07976v1 Announce Type: new +Abstract: Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from either the sim-to-real gap during policy transfer or a limited amount of training data with action labels. To address this problem, we introduce Vision-Language Distance (VLD) learning, a scalable framework for goal-conditioned navigation that decouples perception learning from policy learning. Instead of relying on raw sensory inputs during policy training, we first train a self-supervised distance-to-goal predictor on internet-scale video data. This predictor generalizes across both image- and text-based goals, providing a distance signal that can be minimized by a reinforcement learning (RL) policy. The RL policy can be trained entirely in simulation using privileged geometric distance signals, with injected noise to mimic the uncertainty of the trained distance predictor. At deployment, the policy consumes VLD predictions, inheriting semantic goal information-"where to go"-from large-scale visual training while retaining the robust low-level navigation behaviors learned in simulation. We propose using ordinal consistency to assess distance functions directly and demonstrate that VLD outperforms prior temporal distance approaches, such as ViNT and VIP. Experiments show that our decoupled design achieves competitive navigation performance in simulation while supporting flexible goal modalities, providing an alternative and, most importantly, scalable path toward reliable, multimodal navigation policies. + oai:arXiv.org:2512.07976v1 + cs.RO cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Raghavendra Ramachandra, Sushma Venkatesh + Lazar Milikic, Manthan Patel, Jonas Frey - ARC-AGI Without Pretraining - https://arxiv.org/abs/2512.06104 - arXiv:2512.06104v1 Announce Type: new -Abstract: Conventional wisdom in the age of LLMs dictates that solving IQ-test-like visual puzzles from the ARC-AGI-1 benchmark requires capabilities derived from massive pretraining. To counter this, we introduce CompressARC, a 76K parameter model without any pretraining that solves 20% of evaluation puzzles by minimizing the description length (MDL) of the target puzzle purely during inference time. The MDL endows CompressARC with extreme generalization abilities typically unheard of in deep learning. To our knowledge, CompressARC is the only deep learning method for ARC-AGI where training happens only on a single sample: the target inference puzzle itself, with the final solution information removed. Moreover, CompressARC does not train on the pre-provided ARC-AGI "training set". Under these extremely data-limited conditions, we do not ordinarily expect any puzzles to be solvable at all. Yet CompressARC still solves a diverse distribution of creative ARC-AGI puzzles, suggesting MDL to be an alternative feasible way to produce intelligence, besides conventional pretraining. - oai:arXiv.org:2512.06104v1 + CIP-Net: Continual Interpretable Prototype-based Network + https://arxiv.org/abs/2512.07981 + arXiv:2512.07981v1 Announce Type: new +Abstract: Continual learning constrains models to learn new tasks over time without forgetting what they have already learned. A key challenge in this setting is catastrophic forgetting, where learning new information causes the model to lose its performance on previous tasks. Recently, explainable AI has been proposed as a promising way to better understand and reduce forgetting. In particular, self-explainable models are useful because they generate explanations during prediction, which can help preserve knowledge. However, most existing explainable approaches use post-hoc explanations or require additional memory for each new task, resulting in limited scalability. In this work, we introduce CIP-Net, an exemplar-free self-explainable prototype-based model designed for continual learning. CIP-Net avoids storing past examples and maintains a simple architecture, while still providing useful explanations and strong performance. We demonstrate that CIPNet achieves state-of-the-art performances compared to previous exemplar-free and self-explainable methods in both task- and class-incremental settings, while bearing significantly lower memory-related overhead. This makes it a practical and interpretable solution for continual learning. + oai:arXiv.org:2512.07981v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Isaac Liao, Albert Gu + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Federico Di Valerio, Michela Proietti, Alessio Ragno, Roberto Capobianco - Explainable Melanoma Diagnosis with Contrastive Learning and LLM-based Report Generation - https://arxiv.org/abs/2512.06105 - arXiv:2512.06105v1 Announce Type: new -Abstract: Deep learning has demonstrated expert-level performance in melanoma classification, positioning it as a powerful tool in clinical dermatology. However, model opacity and the lack of interpretability remain critical barriers to clinical adoption, as clinicians often struggle to trust the decision-making processes of black-box models. To address this gap, we present a Cross-modal Explainable Framework for Melanoma (CEFM) that leverages contrastive learning as the core mechanism for achieving interpretability. Specifically, CEFM maps clinical criteria for melanoma diagnosis-namely Asymmetry, Border, and Color (ABC)-into the Vision Transformer embedding space using dual projection heads, thereby aligning clinical semantics with visual features. The aligned representations are subsequently translated into structured textual explanations via natural language generation, creating a transparent link between raw image data and clinical interpretation. Experiments on public datasets demonstrate 92.79% accuracy and an AUC of 0.961, along with significant improvements across multiple interpretability metrics. Qualitative analyses further show that the spatial arrangement of the learned embeddings aligns with clinicians' application of the ABC rule, effectively bridging the gap between high-performance classification and clinical trust. - oai:arXiv.org:2512.06105v1 - cs.CV + An Empirical Framework for Evaluating Semantic Preservation Using Hugging Face + https://arxiv.org/abs/2512.07983 + arXiv:2512.07983v1 Announce Type: new +Abstract: As machine learning (ML) becomes an integral part of high-autonomy systems, it is critical to ensure the trustworthiness of learning-enabled software systems (LESS). Yet, the nondeterministic and run-time-defined semantics of ML complicate traditional software refactoring. We define semantic preservation in LESS as the property that optimizations of intelligent components do not alter the system's overall functional behavior. This paper introduces an empirical framework to evaluate semantic preservation in LESS by mining model evolution data from HuggingFace. We extract commit histories, $\textit{Model Cards}$, and performance metrics from a large number of models. To establish baselines, we conducted case studies in three domains, tracing performance changes across versions. Our analysis demonstrates how $\textit{semantic drift}$ can be detected via evaluation metrics across commits and reveals common refactoring patterns based on commit message analysis. Although API constraints limited the possibility of estimating a full-scale threshold, our pipeline offers a foundation for defining community-accepted boundaries for semantic preservation. Our contributions include: (1) a large-scale dataset of ML model evolution, curated from 1.7 million Hugging Face entries via a reproducible pipeline using the native HF hub API, (2) a practical pipeline for the evaluation of semantic preservation for a subset of 536 models and 4000+ metrics and (3) empirical case studies illustrating semantic drift in practice. Together, these contributions advance the foundations for more maintainable and trustworthy ML systems. + oai:arXiv.org:2512.07983v1 + cs.SE cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junwen Zheng, Xinran Xu, Li Rong Wang, Chang Cai, Lucinda Siyun Tan, Dingyuan Wang, Hong Liang Tey, Xiuyi Fan + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Nan Jia, Anita Raja, Raffi Khatchadourian - Future You: Designing and Evaluating Multimodal AI-generated Digital Twins for Strengthening Future Self-Continuity - https://arxiv.org/abs/2512.06106 - arXiv:2512.06106v1 Announce Type: new -Abstract: What if users could meet their future selves today? AI-generated future selves simulate meaningful encounters with a digital twin decades in the future. As AI systems advance, combining cloned voices, age-progressed facial rendering, and autobiographical narratives, a central question emerges: Does the modality of these future selves alter their psychological and affective impact? How might a text-based chatbot, a voice-only system, or a photorealistic avatar shape present-day decisions and our feeling of connection to the future? We report a randomized controlled study (N=92) evaluating three modalities of AI-generated future selves (text, voice, avatar) against a neutral control condition. We also report a systematic model evaluation between Claude 4 and three other Large Language Models (LLMs), assessing Claude 4 across psychological and interaction dimensions and establishing conversational AI quality as a critical determinant of intervention effectiveness. All personalized modalities strengthened Future Self-Continuity (FSC), emotional well-being, and motivation compared to control, with avatar producing the largest vividness gains, yet with no significant differences between formats. Interaction quality metrics, particularly persuasiveness, realism, and user engagement, emerged as robust predictors of psychological and affective outcomes, indicating that how compelling the interaction feels matters more than the form it takes. Content analysis found thematic patterns: text emphasized career planning, while voice and avatar facilitated personal reflection. Claude 4 outperformed ChatGPT 3.5, Llama 4, and Qwen 3 in enhancing psychological, affective, and FSC outcomes. - oai:arXiv.org:2512.06106v1 - cs.HC + Restrictive Hierarchical Semantic Segmentation for Stratified Tooth Layer Detection + https://arxiv.org/abs/2512.07984 + arXiv:2512.07984v1 Announce Type: new +Abstract: Accurate understanding of anatomical structures is essential for reliably staging certain dental diseases. A way of introducing this within semantic segmentation models is by utilising hierarchy-aware methodologies. However, existing hierarchy-aware segmentation methods largely encode anatomical structure through the loss functions, providing weak and indirect supervision. We introduce a general framework that embeds an explicit anatomical hierarchy into semantic segmentation by coupling a recurrent, level-wise prediction scheme with restrictive output heads and top-down feature conditioning. At each depth of the class tree, the backbone is re-run on the original image concatenated with logits from the previous level. Child class features are conditioned using Feature-wise Linear Modulation of their parent class probabilities, to modulate child feature spaces for fine grained detection. A probabilistic composition rule enforces consistency between parent and descendant classes. Hierarchical loss combines per-level class weighted Dice and cross entropy loss and a consistency term loss, ensuring parent predictions are the sum of their children. We validate our approach on our proposed dataset, TL-pano, containing 194 panoramic radiographs with dense instance and semantic segmentation annotations, of tooth layers and alveolar bone. Utilising UNet and HRNet as donor models across a 5-fold cross validation scheme, the hierarchical variants consistently increase IoU, Dice, and recall, particularly for fine-grained anatomies, and produce more anatomically coherent masks. However, hierarchical variants also demonstrated increased recall over precision, implying increased false positives. The results demonstrate that explicit hierarchical structuring improves both performance and clinical plausibility, especially in low data dental imaging regimes. + oai:arXiv.org:2512.07984v1 + cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Constanze Albrecht, Chayapatr Archiwaranguprok, Rachel Poonsiriwong, Awu Chen, Peggy Yin, Monchai Lertsutthiwong, Kavin Winson, Hal Hershfield, Pattie Maes, Pat Pataranutaporn - - - Protocol Futuring: Speculating Second-Order Dynamics of Protocols in Sociotechnical Infrastructural Futures - https://arxiv.org/abs/2512.06108 - arXiv:2512.06108v1 Announce Type: new -Abstract: Drawing on infrastructure studies in HCI and CSCW, this paper introduces Protocol Futuring, a methodological framework that extends design futuring by foregrounding protocols-rules, standards, and coordination mechanisms-as the primary material of speculative inquiry. Rather than imagining discrete future artifacts, Protocol Futuring examines how protocol rules accumulate drift, jam, and other second-order effects over long temporal horizons. We demonstrate the method through a case study of Knowledge Futurama, a multi-team participatory workshop exploring millennial-scale knowledge preservation. Using a relay format in which teams inherited and reinterpreted partially formed designs, the workshop revealed how ambiguous handovers, adversarial reinterpretations, shifting cultural norms, and crisis dynamics transform protocols as they move across communities and epochs. The case shows how Protocol Futuring makes infrastructural politics and long-run consequences analytically visible. We discuss the method's strengths, limitations, and implications for researchers seeking to investigate emergent sociotechnical systems whose impacts unfold over extended timescales. - oai:arXiv.org:2512.06108v1 - cs.CY - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Botao 'Amber' Hu, Samuel Chua, Helena Rong + Ryan Banks, Camila Lindoni Azevedo, Hongying Tang, Yunpeng Li - A Prescriptive Framework for Determining Optimal Days for Short-Term Traffic Counts - https://arxiv.org/abs/2512.06111 - arXiv:2512.06111v1 Announce Type: new -Abstract: The Federal Highway Administration (FHWA) mandates that state Departments of Transportation (DOTs) collect reliable Annual Average Daily Traffic (AADT) data. However, many U.S. DOTs struggle to obtain accurate AADT, especially for unmonitored roads. While continuous count (CC) stations offer accurate traffic volume data, their implementation is expensive and difficult to deploy widely, compelling agencies to rely on short-duration traffic counts. This study proposes a machine learning framework, the first to our knowledge, to identify optimal representative days for conducting short count (SC) data collection to improve AADT prediction accuracy. Using 2022 and 2023 traffic volume data from the state of Texas, we compare two scenarios: an 'optimal day' approach that iteratively selects the most informative days for AADT estimation and a 'no optimal day' baseline reflecting current practice by most DOTs. To align with Texas DOT's traffic monitoring program, continuous count data were utilized to simulate the 24 hour short counts. The actual field short counts were used to enhance feature engineering through using a leave-one-out (LOO) technique to generate unbiased representative daily traffic features across similar road segments. Our proposed methodology outperforms the baseline across the top five days, with the best day (Day 186) achieving lower errors (RMSE: 7,871.15, MAE: 3,645.09, MAPE: 11.95%) and higher R^2 (0.9756) than the baseline (RMSE: 11,185.00, MAE: 5,118.57, MAPE: 14.42%, R^2: 0.9499). This research offers DOTs an alternative to conventional short-duration count practices, improving AADT estimation, supporting Highway Performance Monitoring System compliance, and reducing the operational costs of statewide traffic data collection. - oai:arXiv.org:2512.06111v1 + HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability + https://arxiv.org/abs/2512.07988 + arXiv:2512.07988v1 Announce Type: new +Abstract: Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of Latent Embeddings), a method for analyzing and interpreting deep neural networks through persistent homology. HOLE extracts topological features from neural activations and presents them using a suite of visualization techniques, including Sankey diagrams, heatmaps, dendrograms, and blob graphs. These tools facilitate the examination of representation structure and quality across layers. We evaluate HOLE on standard datasets using a range of discriminative models, focusing on representation quality, interpretability across layers, and robustness to input perturbations and model compression. The results indicate that topological analysis reveals patterns associated with class separation, feature disentanglement, and model robustness, providing a complementary perspective for understanding and improving deep learning systems. + oai:arXiv.org:2512.07988v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.GR + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Arthur Mukwaya, Nancy Kasamala, Nana Kankam Gyimah, Judith Mwakalonge, Gurcan Comert, Saidi Siuhi, Denis Ruganuza, Mark Ngotonie + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Sudhanva Manjunath Athreya, Paul Rosen - WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving - https://arxiv.org/abs/2512.06112 - arXiv:2512.06112v1 Announce Type: new -Abstract: We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressive decoders, WAM-Flow performs fully parallel, bidirectional denoising, enabling coarse-to-fine refinement with a tunable compute-accuracy trade-off. Specifically, the approach combines a metric-aligned numerical tokenizer that preserves scalar geometry via triplet-margin learning, a geometry-aware flow objective and a simulator-guided GRPO alignment that integrates safety, ego progress, and comfort rewards while retaining parallel generation. A multi-stage adaptation converts a pre-trained auto-regressive backbone (Janus-1.5B) from causal decoding to non-causal flow model and strengthens road-scene competence through continued multimodal pretraining. Thanks to the inherent nature of consistency model training and parallel decoding inference, WAM-Flow achieves superior closed-loop performance against autoregressive and diffusion-based VLA baselines, with 1-step inference attaining 89.1 PDMS and 5-step inference reaching 90.3 PDMS on NAVSIM v1 benchmark. These results establish discrete flow matching as a new promising paradigm for end-to-end autonomous driving. The code will be publicly available soon. - oai:arXiv.org:2512.06112v1 - cs.RO + A Gray Literature Study on Fairness Requirements in AI-enabled Software Engineering + https://arxiv.org/abs/2512.07990 + arXiv:2512.07990v1 Announce Type: new +Abstract: Today, with the growing obsession with applying Artificial Intelligence (AI), particularly Machine Learning (ML), to software across various contexts, much of the focus has been on the effectiveness of AI models, often measured through common metrics such as F1- score, while fairness receives relatively little attention. This paper presents a review of existing gray literature, examining fairness requirements in AI context, with a focus on how they are defined across various application domains, managed throughout the Software Development Life Cycle (SDLC), and the causes, as well as the corresponding consequences of their violation by AI models. Our gray literature investigation shows various definitions of fairness requirements in AI systems, commonly emphasizing non-discrimination and equal treatment across different demographic and social attributes. Fairness requirement management practices vary across the SDLC, particularly in model training and bias mitigation, fairness monitoring and evaluation, and data handling practices. Fairness requirement violations are frequently linked, but not limited, to data representation bias, algorithmic and model design bias, human judgment, and evaluation and transparency gaps. The corresponding consequences include harm in a broad sense, encompassing specific professional and societal impacts as key examples, stereotype reinforcement, data and privacy risks, and loss of trust and legitimacy in AI-supported decisions. These findings emphasize the need for consistent frameworks and practices to integrate fairness into AI software, paying as much attention to fairness as to effectiveness. + oai:arXiv.org:2512.07990v1 + cs.SE cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yifang Xu, Jiahao Cui, Feipeng Cai, Zhihao Zhu, Hanlin Shang, Shan Luan, Mingwang Xu, Neng Zhang, Yaoyi Li, Jia Cai, Siyu Zhu + Thanh Nguyen, Chaima Boufaied, Ronnie de Souza Santos - Hardware Software Optimizations for Fast Model Recovery on Reconfigurable Architectures - https://arxiv.org/abs/2512.06113 - arXiv:2512.06113v1 Announce Type: new -Abstract: Model Recovery (MR) is a core primitive for physical AI and real-time digital twins, but GPUs often execute MR inefficiently due to iterative dependencies, kernel-launch overheads, underutilized memory bandwidth, and high data-movement latency. We present MERINDA, an FPGA-accelerated MR framework that restructures computation as a streaming dataflow pipeline. MERINDA exploits on-chip locality through BRAM tiling, fixed-point kernels, and the concurrent use of LUT fabric and carry-chain adders to expose fine-grained spatial parallelism while minimizing off-chip traffic. This hardware-aware formulation removes synchronization bottlenecks and sustains high throughput across the iterative updates in MR. On representative MR workloads, MERINDA delivers up to 6.3x fewer cycles than an FPGA-based LTC baseline, enabling real-time performance for time-critical physical systems. - oai:arXiv.org:2512.06113v1 - cs.AR + Bridging the Clinical Expertise Gap: Development of a Web-Based Platform for Accessible Time Series Forecasting and Analysis + https://arxiv.org/abs/2512.07992 + arXiv:2512.07992v1 Announce Type: new +Abstract: Time series forecasting has applications across domains and industries, especially in healthcare, but the technical expertise required to analyze data, build models, and interpret results can be a barrier to using these techniques. This article presents a web platform that makes the process of analyzing and plotting data, training forecasting models, and interpreting and viewing results accessible to researchers and clinicians. Users can upload data and generate plots to showcase their variables and the relationships between them. The platform supports multiple forecasting models and training techniques which are highly customizable according to the user's needs. Additionally, recommendations and explanations can be generated from a large language model that can help the user choose appropriate parameters for their data and understand the results for each model. The goal is to integrate this platform into learning health systems for continuous data collection and inference from clinical pipelines. + oai:arXiv.org:2512.07992v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Bin Xu, Ayan Banerjee, Sandeep Gupta + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Aaron D. Mullen, Daniel R. Harris, Svetla Slavova, V. K. Cody Bumgardner - Toward Patch Robustness Certification and Detection for Deep Learning Systems Beyond Consistent Samples - https://arxiv.org/abs/2512.06123 - arXiv:2512.06123v1 Announce Type: new -Abstract: Patch robustness certification is an emerging kind of provable defense technique against adversarial patch attacks for deep learning systems. Certified detection ensures the detection of all patched harmful versions of certified samples, which mitigates the failures of empirical defense techniques that could (easily) be compromised. However, existing certified detection methods are ineffective in certifying samples that are misclassified or whose mutants are inconsistently pre icted to different labels. This paper proposes HiCert, a novel masking-based certified detection technique. By focusing on the problem of mutants predicted with a label different from the true label with our formal analysis, HiCert formulates a novel formal relation between harmful samples generated by identified loopholes and their benign counterparts. By checking the bound of the maximum confidence among these potentially harmful (i.e., inconsistent) mutants of each benign sample, HiCert ensures that each harmful sample either has the minimum confidence among mutants that are predicted the same as the harmful sample itself below this bound, or has at least one mutant predicted with a label different from the harmful sample itself, formulated after two novel insights. As such, HiCert systematically certifies those inconsistent samples and consistent samples to a large extent. To our knowledge, HiCert is the first work capable of providing such a comprehensive patch robustness certification for certified detection. Our experiments show the high effectiveness of HiCert with a new state-of the-art performance: It certifies significantly more benign samples, including those inconsistent and consistent, and achieves significantly higher accuracy on those samples without warnings and a significantly lower false silent ratio. - oai:arXiv.org:2512.06123v1 - cs.SE + SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models + https://arxiv.org/abs/2512.07993 + arXiv:2512.07993v1 Announce Type: new +Abstract: Large reasoning models (LRMs) often cost significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning process. This costs both memory and throughput bottleneck limiting their efficient deployment. Towards reducing KV cache size during inference, we first investigate the effectiveness of existing KV cache eviction methods for CoT reasoning. Interestingly, we find that due to unstable token-wise scoring and the reduced effective KV budget caused by padding tokens, state-of-the-art (SoTA) eviction methods fail to maintain accuracy in the multi-batch setting. Additionally, these methods often generate longer sequences than the original model, as semantic-unaware token-wise eviction leads to repeated revalidation during reasoning. To address these issues, we present \textbf{SkipKV}, a \textbf{\textit{training-free}} KV compression method for selective \textit{eviction} and \textit{generation} operating at a coarse-grained sentence-level sequence removal for efficient CoT reasoning. In specific, it introduces a \textit{sentence-scoring metric} to identify and remove highly similar sentences while maintaining semantic coherence. To suppress redundant generation, SkipKV dynamically adjusts a steering vector to update the hidden activation states during inference enforcing the LRM to generate concise response. Extensive evaluations on multiple reasoning benchmarks demonstrate the effectiveness of SkipKV in maintaining up to $\mathbf{26.7}\%$ improved accuracy compared to the alternatives, at a similar compression budget. Additionally, compared to SoTA, SkipKV yields up to $\mathbf{1.6}\times$ fewer generation length while improving throughput up to $\mathbf{1.7}\times$. + oai:arXiv.org:2512.07993v1 cs.AI - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Qilin Zhou, Zhengyuan Wei, Haipeng Wang, Zhuo Wang, W. K. Chan + http://creativecommons.org/licenses/by/4.0/ + Jiayi Tian, Seyedarmin Azizi, Yequan Zhao, Erfan Baghaei Potraghloo, Sean McPherson, Sharath Nittur Sridhar, Zhengyang Wang, Zheng Zhang, Massoud Pedram, Souvik Kundu - Variable L0 Guidance Strategy: Enlarged Operational Envelope and Path-Following - https://arxiv.org/abs/2512.06124 - arXiv:2512.06124v1 Announce Type: new -Abstract: This paper presents a geometric and theoretical study of an exponentially varying look-ahead parameter for UAV path-following guidance. Conventional guidance laws with a fixed look-ahead distance often drive the vehicle into turn-rate saturation when the heading or cross-track error is large, leading to constrained maneuvers and higher control effort. The proposed variable L0 strategy reshapes the look-ahead profile so that the guidance command adapts to the evolving tracking error geometry. A detailed investigation shows that this adaptation significantly enlarges the region in which the commanded turn rate remains unsaturated, allowing the vehicle to operate smoothly over a broader range of error conditions. For representative settings, the unsaturated operational envelope increases by more than 70% relative to the constant L0 formulation. These geometric insights translate to smoother trajectories, earlier recovery from saturation, and reduced control demand. Simulation studies on straight-line and elliptical paths demonstrate the merits of the variable look-ahead strategy, highlighting its control-efficient and reliable path-following performance. - oai:arXiv.org:2512.06124v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + On semantics of first-order justification logic with binding modalities + https://arxiv.org/abs/2512.07994 + arXiv:2512.07994v1 Announce Type: new +Abstract: We introduce the first order logic of proofs $FOLP^\Box$ in the joint language combining justification terms and binding modalities. The main issue is Kripke--style semantics for this logic. We describe models for $FOLP^\Box$ in terms of valuations of individual variables instead of introducing constants to the language. This approach requires a new format of the evidence function. This allows us to assign semantic meaning to formulas that contain free variables. The main results are soundness and completeness of $FOLP^\Box$ with respect to the described semantics. + oai:arXiv.org:2512.07994v1 + cs.LO + math.LO + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Amit Shivam, Manuel C. R. M. Fernandes, Fernando A. C. C. Fontes, Lorenzo Fagiano + Tatiana Yavorskaya (Steklov Mathematical Institute of Russian Academy of Science), Elena Popova (Steklov Mathematical Institute of Russian Academy of Science) - Rabble-Rousers in the New King's Court: Algorithmic Effects on Account Visibility in Pre-X Twitter - https://arxiv.org/abs/2512.06129 - arXiv:2512.06129v1 Announce Type: new -Abstract: Algorithmic effects on social media platforms have come under recent scrutiny, with several works reporting that right-leaning accounts tend to receive more exposure. In this paper, we expand upon this body of work using data collected from user feeds after Twitter's change of ownership but before its re-branding to X. We replicate findings from prior work regarding the increased exposure of right-leaning accounts to wider audiences in algorithmically curated compared to reverse-chronological feeds, and, crucially, we further unpack this effect to understand what correlated (and did not correlate) with these differences. Our results reveal that right-leaning accounts benefited not necessarily due to their political affiliation, but possibly because they behaved in ways associated with algorithmic rewards; namely, posting more agitating content and receiving attention from the platform's owner, Elon Musk, who was the most central network account. We also demonstrate that legacy-verified accounts, like businesses and government officials, received less exposure in the algorithmic feed compared to non-verified or Twitter Blue-verified accounts. We discuss implications of these findings for the intersection between behavioral incentives for algorithmic reach and online trust and safety. - oai:arXiv.org:2512.06129v1 - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 + A Comparative Study of EMG- and IMU-based Gesture Recognition at the Wrist and Forearm + https://arxiv.org/abs/2512.07997 + arXiv:2512.07997v1 Announce Type: new +Abstract: Gestures are an integral part of our daily interactions with the environment. Hand gesture recognition (HGR) is the process of interpreting human intent through various input modalities, such as visual data (images and videos) and bio-signals. Bio-signals are widely used in HGR due to their ability to be captured non-invasively via sensors placed on the arm. Among these, surface electromyography (sEMG), which measures the electrical activity of muscles, is the most extensively studied modality. However, less-explored alternatives such as inertial measurement units (IMUs) can provide complementary information on subtle muscle movements, which makes them valuable for gesture recognition. In this study, we investigate the potential of using IMU signals from different muscle groups to capture user intent. Our results demonstrate that IMU signals contain sufficient information to serve as the sole input sensor for static gesture recognition. Moreover, we compare different muscle groups and check the quality of pattern recognition on individual muscle groups. We further found that tendon-induced micro-movement captured by IMUs is a major contributor to static gesture recognition. We believe that leveraging muscle micro-movement information can enhance the usability of prosthetic arms for amputees. This approach also offers new possibilities for hand gesture recognition in fields such as robotics, teleoperation, sign language interpretation, and beyond. + oai:arXiv.org:2512.07997v1 + cs.HC + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Alexandros Efstratiou, Kayla Duskin, Kate Starbird, Emma Spiro + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Soroush Baghernezhad, Elaheh Mohammadreza, Vinicius Prado da Fonseca, Ting Zou, Xianta Jiang - Probabilistic Weapon Engagement Zones for a Turn Constrained Pursuer - https://arxiv.org/abs/2512.06130 - arXiv:2512.06130v1 Announce Type: new -Abstract: Curve-straight probabilistic engagement zones (CSPEZ) quantify the spatial regions an evader should avoid to reduce capture risk from a turn-rate-limited pursuer following a curve-straight path with uncertain parameters including position, heading, velocity, range, and maximum turn rate. This paper presents methods for generating evader trajectories that minimize capture risk under such uncertainty. We first derive an analytic solution for the deterministic curve-straight basic engagement zone (CSBEZ), then extend this formulation to a probabilistic framework using four uncertainty-propagation approaches: Monte Carlo sampling, linearization, quadratic approximation, and neural-network regression. We evaluate the accuracy and computational cost of each approximation method and demonstrate how CSPEZ constraints can be integrated into a trajectory-optimization algorithm to produce safe paths that explicitly account for pursuer uncertainty. - oai:arXiv.org:2512.06130v1 + DIJIT: A Robotic Head for an Active Observer + https://arxiv.org/abs/2512.07998 + arXiv:2512.07998v1 Announce Type: new +Abstract: We present DIJIT, a novel binocular robotic head expressly designed for mobile agents that behave as active observers. DIJIT's unique breadth of functionality enables active vision research and the study of human-like eye and head-neck motions, their interrelationships, and how each contributes to visual ability. DIJIT is also being used to explore the differences between how human vision employs eye/head movements to solve visual tasks and current computer vision methods. DIJIT's design features nine mechanical degrees of freedom, while the cameras and lenses provide an additional four optical degrees of freedom. The ranges and speeds of the mechanical design are comparable to human performance. Our design includes the ranges of motion required for convergent stereo, namely, vergence, version, and cyclotorsion. The exploration of the utility of these to both human and machine vision is ongoing. Here, we present the design of DIJIT and evaluate aspects of its performance. We present a new method for saccadic camera movements. In this method, a direct relationship between camera orientation and motor values is developed. The resulting saccadic camera movements are close to human movements in terms of their accuracy. + oai:arXiv.org:2512.07998v1 cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Grant Stagg, Isaac E. Weintraub, Cameron K. Peterson + Mostafa Kamali Tabrizi, Mingshi Chi, Bir Bikram Dey, Yu Qing Yuan, Markus D. Solbach, Yiqian Liu, Michael Jenkin, John K. Tsotsos - A Nonlinear Observer for Air-Velocity and Attitude Estimation Using Pitot and Barometric Measurements - https://arxiv.org/abs/2512.06133 - arXiv:2512.06133v1 Announce Type: new -Abstract: This paper addresses the problem of estimating air velocity and full attitude for unmanned aerial vehicles (UAVs) in GNSS-denied environments using minimal onboard sensing-an interesting and practically relevant challenge for UAV navigation. The contribution of the paper is twofold: (i) an observability analysis establishing the conditions for uniform observability, which are useful for trajectory planning and motion control of the UAV; and (ii) the design of a nonlinear observer on SO3R3R that incorporates pitot-tube, barometric altitude, and magnetometer measurements as outputs, with IMU data used as inputs, within a unified framework. Simulation results are presented to confirm the convergence and robustness of the proposed design, including under minimally excited trajectories. - oai:arXiv.org:2512.06133v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Modeling the Potential of Message-Free Communication via CXL.mem + https://arxiv.org/abs/2512.08005 + arXiv:2512.08005v1 Announce Type: new +Abstract: Heterogeneous memory technologies are increasingly important instruments in addressing the memory wall in HPC systems. While most are deployed in single node setups, CXL.mem is a technology that implements memories that can be attached to multiple nodes simultaneously, enabling shared memory pooling. This opens new possibilities, particularly for efficient inter-node communication. + In this paper, we present a novel performance evaluation toolchain combined with an extended performance model for message-based communication, which can be used to predict potential performance benefits from using CXL.mem for data exchange. Our approach analyzes data access patterns of MPI applications: it analyzes on-node accesses to/from MPI buffers, as well as cross-node MPI traffic to gather a full understanding of the impact of memory performance. We combine this data in an extended performance model to predict which data transfers could benefit from direct CXL.mem implementations as compared to traditional MPI messages. Our model works on a per-MPI call granularity, allowing the identification and later optimizations of those MPI invocations in the code with the highest potential for speedup by using CXL.mem. + For our toolchain, we extend the memory trace sampling tool Mitos and use it to extract data access behavior. In the post-processing step, the raw data is automatically analyzed to provide performance models for each individual MPI call. We validate the models on two sample applications -- a 2D heat transfer miniapp and the HPCG benchmark -- and use them to demonstrate their support for targeted optimizations by integrating CXL.mem. + oai:arXiv.org:2512.08005v1 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Melone Nyoba Tchonkeu, Soulaimane Berkane, Tarek Hamel + 10.1145/3773656.3773661 + Stepan Vanecek, Matthew Turner, Manisha Gajbe, Matthew Wolf, Martin Schulz - Physics-Informed Neural Koopman Machine for Interpretable Longitudinal Personalized Alzheimer's Disease Forecasting - https://arxiv.org/abs/2512.06134 - arXiv:2512.06134v1 Announce Type: new -Abstract: Early forecasting of individual cognitive decline in Alzheimer's disease (AD) is central to disease evaluation and management. Despite advances, it is as of yet challenging for existing methodological frameworks to integrate multimodal data for longitudinal personalized forecasting while maintaining interpretability. To address this gap, we present the Neural Koopman Machine (NKM), a new machine learning architecture inspired by dynamical systems and attention mechanisms, designed to forecast multiple cognitive scores simultaneously using multimodal genetic, neuroimaging, proteomic, and demographic data. NKM integrates analytical ($\alpha$) and biological ($\beta$) knowledge to guide feature grouping and control the hierarchical attention mechanisms to extract relevant patterns. By implementing Fusion Group-Aware Hierarchical Attention within the Koopman operator framework, NKM transforms complex nonlinear trajectories into interpretable linear representations. To demonstrate NKM's efficacy, we applied it to study the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our results suggest that NKM consistently outperforms both traditional machine learning methods and deep learning models in forecasting trajectories of cognitive decline. Specifically, NKM (1) forecasts changes of multiple cognitive scores simultaneously, (2) quantifies differential biomarker contributions to predicting distinctive cognitive scores, and (3) identifies brain regions most predictive of cognitive deterioration. Together, NKM advances personalized, interpretable forecasting of future cognitive decline in AD using past multimodal data through an explainable, explicit system and reveals potential multimodal biological underpinnings of AD progression. - oai:arXiv.org:2512.06134v1 - cs.LG - cs.AI - q-bio.NC - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 + Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS + https://arxiv.org/abs/2512.08006 + arXiv:2512.08006v1 Announce Type: new +Abstract: Lightweight, real-time text-to-speech systems are crucial for accessibility. However, the most efficient TTS models often rely on lightweight phonemizers that struggle with context-dependent challenges. In contrast, more advanced phonemizers with a deeper linguistic understanding typically incur high computational costs, which prevents real-time performance. + This paper examines the trade-off between phonemization quality and inference speed in G2P-aided TTS systems, introducing a practical framework to bridge this gap. We propose lightweight strategies for context-aware phonemization and a service-oriented TTS architecture that executes these modules as independent services. This design decouples heavy context-aware components from the core TTS engine, effectively breaking the latency barrier and enabling real-time use of high-quality phonemization models. Experimental results confirm that the proposed system improves pronunciation soundness and linguistic accuracy while maintaining real-time responsiveness, making it well-suited for offline and end-device TTS applications. + oai:arXiv.org:2512.08006v1 + cs.SD + cs.CL + eess.AS + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Georgi Hrusanov, Duy-Thanh Vu, Duy-Cat Can, Sophie Tascedda, Margaret Ryan, Julien Bodelet, Katarzyna Koscielska, Carsten Magnus, Oliver Y. Ch\'en + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Mahta Fetrat, Donya Navabi, Zahra Dehghanian, Morteza Abolghasemi, Hamid R. Rabiee - Entropic Regularization in the Deep Linear Network - https://arxiv.org/abs/2512.06137 - arXiv:2512.06137v1 Announce Type: new -Abstract: We study regularization for the deep linear network (DLN) using the entropy formula introduced in arXiv:2509.09088. The equilibria and gradient flow of the free energy on the Riemannian manifold of end-to-end maps of the DLN are characterized for energies that depend symmetrically on the singular values of the end-to-end matrix. - The only equilibria are minimizers and the set of minimizers is an orbit of the orthogonal group. In contrast with random matrix theory there is no singular value repulsion. The corresponding gradient flow reduces to a one-dimensional ordinary differential equation whose solution gives explicit relaxation rates toward the minimizers. We also study the concavity of the entropy in the chamber of singular values. The entropy is shown to be strictly concave in the Euclidean geometry on the chamber but not in the Riemannian geometry defined by the DLN metric. - oai:arXiv.org:2512.06137v1 + Resonant and Stochastic Vibration in Neurorehabilitation + https://arxiv.org/abs/2512.08009 + arXiv:2512.08009v1 Announce Type: new +Abstract: Neurological injuries and age-related decline can impair sensory processing and disrupt motor coordination, gait, and balance. As mechanisms of neuroplasticity have become better understood, vibration-based interventions have gained attention as potential tools to stimulate sensory pathways and motor circuits to support functional recovery. This survey reviews stochastic and resonant vibration modalities, describing their mechanisms, therapeutic rationales, and clinical applications. We synthesize evidence on whole-body vibration for improving balance, mobility, and fine motor function in aging adults, stroke survivors, and individuals with Parkinson's disease, with attention to challenges in parameter optimization, generalizability, and safety. We also assess recent developments in focused muscle vibration and wearable stochastic resonance devices for upper-limb rehabilitation, evaluating their clinical promise along with limitations in scalability, ecological validity, and standardization. Across these modalities, we identify key variables that shape therapeutic outcomes and highlight ongoing efforts to refine protocols, improve usability, and integrate vibration techniques into broader neurorehabilitation frameworks. We conclude by outlining the most important research needs for translating vibration-based interventions into reliable and deployable clinical tools. + oai:arXiv.org:2512.08009v1 + cs.ET + cs.HC cs.NE - math.DS - math.PR - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Alan Chen, Tejas Kotwal, Govind Menon + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ava Hays, Nolan Kosnic, Ryan Miller, Kunal Siddhawar - RationalFunctionApproximation.jl: Rational Approximation On Discrete and Continuous Domains - https://arxiv.org/abs/2512.06140 - arXiv:2512.06140v1 Announce Type: new -Abstract: Unlike polynomials, rational functions can represent functions having poles or branch cuts with root-exponential convergence and no Runge phenomenon. Recent developments of the AAA and greedy Thiele algorithms have sparked renewed interest in computational rational approximation. The \textsf{RationalFunctionApproximation} package supplies the fastest known implementations of these methods and the only arbitrary-precision ones. Combined with the \textsf{ComplexRegions} package, it can produce compact and accurate representations of a huge variety of functions over intervals, circles, or other domains in the complex plane. - oai:arXiv.org:2512.06140v1 - math.NA - cs.NA - math.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Sensor Attack Detection Method for Encrypted State Observers + https://arxiv.org/abs/2512.08010 + arXiv:2512.08010v1 Announce Type: new +Abstract: This paper proposes an encrypted state observer that is capable of detecting sensor attacks without decryption. We first design a state observer that operates over a finite field of integers with the modular arithmetic. The observer generates a residue signal that indicates the presence of attacks under sparse attack and sensing redundancy conditions. Then, we develop a homomorphic encryption scheme that enables the observer to operate over encrypted data while automatically disclosing the residue signal. Unlike our previous work restricted to single-input single-output systems, the proposed scheme is applicable to general multi-input multi-output systems. Given that the disclosed residue signal remains below a prescribed threshold, the full state can be recovered as an encrypted message. + oai:arXiv.org:2512.08010v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Tobin A. Driscoll + Yeongjun Jang, Sangwon Lee, Junsoo Kim - A fast algorithm for the Hecke representation of the braid group, and applications to the computation of the HOMFLY-PT polynomial and the search for interesting braids - https://arxiv.org/abs/2512.06142 - arXiv:2512.06142v1 Announce Type: new -Abstract: Knot theory is an active field of mathematics, in which combinatorial and computational methods play an important role. One side of computational knot theory, that has gained interest in recent years, both for complexity analysis and practical algorithms, is quantum topology and the computation of topological invariants issued from the theory. - In this article, we leverage the rigidity brought by the representation-theoretic origins of the quantum invariants for algorithmic purposes. We do so by exploiting braids and the algebraic properties of the braid group to describe, analyze, and implement a fast algorithm to compute the Hecke representation of the braid group. We apply this construction to design a parameterized algorithm to compute the HOMFLY-PT polynomial of knots, and demonstrate its interest experimentally. Finally, we combine our fast Hecke representation algorithm with Garside theory, to implement a reservoir sampling search and find non-trivial braids with trivial Hecke representations with coefficients in $\mathbb{Z}/p\mathbb{Z}$. We find several such braids, in particular proving that the Hecke representation of $B_5$ with $\mathbb{Z}/2\mathbb{Z}$ coefficients is non-faithful, a previously unknown fact. - oai:arXiv.org:2512.06142v1 - cs.CG - math.GT - Tue, 09 Dec 2025 00:00:00 -0500 + Benchmarking Offline Multi-Objective Reinforcement Learning in Critical Care + https://arxiv.org/abs/2512.08012 + arXiv:2512.08012v1 Announce Type: new +Abstract: In critical care settings such as the Intensive Care Unit, clinicians face the complex challenge of balancing conflicting objectives, primarily maximizing patient survival while minimizing resource utilization (e.g., length of stay). Single-objective Reinforcement Learning approaches typically address this by optimizing a fixed scalarized reward function, resulting in rigid policies that fail to adapt to varying clinical priorities. Multi-objective Reinforcement Learning (MORL) offers a solution by learning a set of optimal policies along the Pareto Frontier, allowing for dynamic preference selection at test time. However, applying MORL in healthcare necessitates strict offline learning from historical data. + In this paper, we benchmark three offline MORL algorithms, Conditioned Conservative Pareto Q-Learning (CPQL), Adaptive CPQL, and a modified Pareto Efficient Decision Agent (PEDA) Decision Transformer (PEDA DT), against three scalarized single-objective baselines (BC, CQL, and DDQN) on the MIMIC-IV dataset. Using Off-Policy Evaluation (OPE) metrics, we demonstrate that PEDA DT algorithm offers superior flexibility compared to static scalarized baselines. Notably, our results extend previous findings on single-objective Decision Transformers in healthcare, confirming that sequence modeling architectures remain robust and effective when scaled to multi-objective conditioned generation. These findings suggest that offline MORL is a promising framework for enabling personalized, adjustable decision-making in critical care without the need for retraining. + oai:arXiv.org:2512.08012v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Cl\'ement Maria, Hoel Queffelec + Aryaman Bansal, Divya Sharma - gp2Scale: A Class of Compactly-Supported Non-Stationary Kernels and Distributed Computing for Exact Gaussian Processes on 10 Million Data Points - https://arxiv.org/abs/2512.06143 - arXiv:2512.06143v1 Announce Type: new -Abstract: Despite a large corpus of recent work on scaling up Gaussian processes, a stubborn trade-off between computational speed, prediction and uncertainty quantification accuracy, and customizability persists. This is because the vast majority of existing methodologies exploit various levels of approximations that lower accuracy and limit the flexibility of kernel and noise-model designs -- an unacceptable drawback at a time when expressive non-stationary kernels are on the rise in many fields. Here, we propose a methodology we term \emph{gp2Scale} that scales exact Gaussian processes to more than 10 million data points without relying on inducing points, kernel interpolation, or neighborhood-based approximations, and instead leveraging the existing capabilities of a GP: its kernel design. Highly flexible, compactly supported, and non-stationary kernels lead to the identification of naturally occurring sparse structure in the covariance matrix, which is then exploited for the calculations of the linear system solution and the log-determinant for training. We demonstrate our method's functionality on several real-world datasets and compare it with state-of-the-art approximation algorithms. Although we show superior approximation performance in many cases, the method's real power lies in its agnosticism toward arbitrary GP customizations -- core kernel design, noise, and mean functions -- and the type of input space, making it optimally suited for modern Gaussian process applications. - oai:arXiv.org:2512.06143v1 + Learning Dynamics from Infrequent Output Measurements for Uncertainty-Aware Optimal Control + https://arxiv.org/abs/2512.08013 + arXiv:2512.08013v1 Announce Type: new +Abstract: Reliable optimal control is challenging when the dynamics of a nonlinear system are unknown and only infrequent, noisy output measurements are available. This work addresses this setting of limited sensing by formulating a Bayesian prior over the continuous-time dynamics and latent state trajectory in state-space form and updating it through a targeted marginal Metropolis-Hastings sampler equipped with a numerical ODE integrator. The resulting posterior samples are used to formulate a scenario-based optimal control problem that accounts for both model and measurement uncertainty and is solved using standard nonlinear programming methods. The approach is validated in a numerical case study on glucose regulation using a Type 1 diabetes model. + oai:arXiv.org:2512.08013v1 + eess.SY cs.LG - math.PR - Tue, 09 Dec 2025 00:00:00 -0500 + cs.SY + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Marcus M. Noack, Mark D. Risser, Hengrui Luo, Vardaan Tekriwal, Ronald J. Pandolfi + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Robert Lefringhausen, Theodor Springer, Sandra Hirche - An abstraction for solving multi-domain problems using finite element methods - https://arxiv.org/abs/2512.06146 - arXiv:2512.06146v1 Announce Type: new -Abstract: We introduce a new abstraction for the representation and solution of multi-domain problems using finite element methods. This is an advance over previous work in that it achieves a single higher-level abstraction that represents multi-domain problems in the mixed variational problem formalism. We implemented our new abstraction in UFL and Firedrake, and validated our implementations solving a quad-triangle mixed-cell-type problem, a hex-quad mixed-cell-type problem, and a fluid-structure interaction benchmark problem. - oai:arXiv.org:2512.06146v1 - cs.MS - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 + FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models + https://arxiv.org/abs/2512.08016 + arXiv:2512.08016v1 Announce Type: new +Abstract: Cartographic reasoning is the skill of interpreting geographic relationships by aligning legends, map scales, compass directions, map texts, and geometries across one or more map images. Although essential as a concrete cognitive capability and for critical tasks such as disaster response and urban planning, it remains largely unevaluated. Building on progress in chart and infographic understanding, recent large vision language model studies on map visual question-answering often treat maps as a special case of charts. In contrast, map VQA demands comprehension of layered symbology (e.g., symbols, geometries, and text labels) as well as spatial relations tied to orientation and distance that often span multiple maps and are not captured by chart-style evaluations. To address this gap, we introduce FRIEDA, a benchmark for testing complex open-ended cartographic reasoning in LVLMs. FRIEDA sources real map images from documents and reports in various domains and geographical areas. Following classifications in Geographic Information System (GIS) literature, FRIEDA targets all three categories of spatial relations: topological (border, equal, intersect, within), metric (distance), and directional (orientation). All questions require multi-step inference, and many require cross-map grounding and reasoning. We evaluate eleven state-of-the-art LVLMs under two settings: (1) the direct setting, where we provide the maps relevant to the question, and (2) the contextual setting, where the model may have to identify the maps relevant to the question before reasoning. Even the strongest models, Gemini-2.5-Pro and GPT-5-Think, achieve only 38.20% and 37.20% accuracy, respectively, far below human performance of 84.87%. These results reveal a persistent gap in multi-step cartographic reasoning, positioning FRIEDA as a rigorous benchmark to drive progress on spatial intelligence in LVLMs. + oai:arXiv.org:2512.08016v1 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Koki Sagiyama, Lawrence Mitchell, David A. Ham + Jiyoon Pyo, Yuankun Jiao, Dongwon Jung, Zekun Li, Leeje Jang, Sofia Kirsanova, Jina Kim, Yijun Lin, Qin Liu, Junyi Xie, Hadi Askari, Nan Xu, Muhao Chen, Yao-Yi Chiang - GuideNav: User-Informed Development of a Vision-Only Robotic Navigation Assistant For Blind Travelers - https://arxiv.org/abs/2512.06147 - arXiv:2512.06147v1 Announce Type: new -Abstract: While commendable progress has been made in user-centric research on mobile assistive systems for blind and low-vision (BLV) individuals, references that directly inform robot navigation design remain rare. To bridge this gap, we conducted a comprehensive human study involving interviews with 26 guide dog handlers, four white cane users, nine guide dog trainers, and one O\&M trainer, along with 15+ hours of observing guide dog-assisted walking. After de-identification, we open-sourced the dataset to promote human-centered development and informed decision-making for assistive systems for BLV people. Building on insights from this formative study, we developed GuideNav, a vision-only, teach-and-repeat navigation system. Inspired by how guide dogs are trained and assist their handlers, GuideNav autonomously repeats a path demonstrated by a sighted person using a robot. Specifically, the system constructs a topological representation of the taught route, integrates visual place recognition with temporal filtering, and employs a relative pose estimator to compute navigation actions - all without relying on costly, heavy, power-hungry sensors such as LiDAR. In field tests, GuideNav consistently achieved kilometer-scale route following across five outdoor environments, maintaining reliability despite noticeable scene variations between teach and repeat runs. A user study with 3 guide dog handlers and 1 guide dog trainer further confirmed the system's feasibility, marking (to our knowledge) the first demonstration of a quadruped mobile system retrieving a path in a manner comparable to guide dogs. - oai:arXiv.org:2512.06147v1 - cs.RO - cs.CV + Structure Theorems (and Fast Algorithms) for List Recovery of Subspace-Design Codes + https://arxiv.org/abs/2512.08017 + arXiv:2512.08017v1 Announce Type: new +Abstract: List recovery of error-correcting codes has emerged as a fundamental notion with broad applications across coding theory and theoretical computer science. Folded Reed-Solomon (FRS) and univariate multiplicity codes are explicit constructions which can be efficiently list-recovered up to capacity, namely a fraction of errors approaching $1-R$ where $R$ is the code rate. + Chen and Zhang and related works showed that folded Reed-Solomon codes and linear codes must have list sizes exponential in $1/\epsilon$ for list-recovering from an error-fraction $1-R-\epsilon$. These results suggest that one cannot list-recover FRS codes in time that is also polynomial in $1/\epsilon$. In contrast to such limitations, we show, extending algorithmic advances of Ashvinkumar, Habib, and Srivastava for list decoding, that even if the lists in the case of list-recovery are large, they are highly structured. In particular, we can output a compact description of a set of size only $\ell^{O((\log \ell)/\epsilon)}$ which contains the relevant list, while running in time only polynomial in $1/\epsilon$ (the previously known compact description due to Guruswami and Wang had size $\approx n^{\ell/\epsilon}$). We also improve on the state-of-the-art algorithmic results for the task of list-recovery. + oai:arXiv.org:2512.08017v1 + cs.IT + cs.CC + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Rohan Goyal, Venkatesan Guruswami + + + "Your Privacy is Your Responsibility": Understanding How Users Collectively Navigate the Complexity of Privacy on Quora + https://arxiv.org/abs/2512.08025 + arXiv:2512.08025v1 Announce Type: new +Abstract: In the current technology environment, users are often in a vulnerable position when it comes to protecting their privacy. Previous efforts to promote privacy protection have largely focused on top-down approaches such as regulation and technology design, missing opportunities to understand how to empower users through bottom-up, collective approaches. Our paper addresses this by analyzing what and how privacy-related topics are discussed on Quora. We identified a wide range of interconnected privacy topics brought up by the users, including privacy risks and dangers, protection strategies, organizational practices, and existing laws and regulations. Our results highlight the interplay among the individual, technological, organizational, and societal factors affecting users' privacy attitudes. Moreover, we provide implications for designing community-based tools to better support users' collective efforts in navigating privacy, tools that incorporate users' diverse privacy-related behaviors and preferences, simplify information access and sharing, and connect designers and developers with the user community. + oai:arXiv.org:2512.08025v1 cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hochul Hwang, Soowan Yang, Jahir Sadik Monon, Nicholas A Giudice, Sunghoon Ivan Lee, Joydeep Biswas, Donghyun Kim + http://creativecommons.org/licenses/by-sa/4.0/ + Varun Shiri, Maggie Xiong, Jin L. C. Guo, Jinghui Cheng - AIMNET: An IoT-Empowered Digital Twin for Continuous Gas Emission Monitoring and Early Hazard Detection - https://arxiv.org/abs/2512.06148 - arXiv:2512.06148v1 Announce Type: new -Abstract: A Digital Twin (DT) framework to enhance carbon-based gas plume monitoring is critical for supporting timely and effective mitigation responses to environmental hazards such as industrial gas leaks, or wildfire outbreaks carrying large carbon emissions. We present AIMNET, a one-of-a-kind DT framework that integrates a built-in-house Internet of Things (IoT)-based continuous sensing network with a physics-based multi-scale weather-gas transport model, that enables high-resolution and real-time simulation and detection of carbon gas emissions. AIMNET features a three-layer system architecture: (i) physical world: custom-built devices for continuous monitoring; (ii) bidirectional information feedback links: intelligent data transmission and reverse control; and (iii) digital twin world: AI-driven analytics for prediction, anomaly detection, and dynamic weather-gas coupled molecule transport modeling. Designed for scalable, energy-efficient deployment in remote environments, AIMNET architecture is realized through a small-scale distributed sensing network over an oil and gas production basin. To demonstrate the high-resolution, fast-responding concept, an equivalent mobile-based emission monitoring network was deployed around a wastewater treatment plant that constantly emits methane plumes. Our preliminary results through which, have successfully captured the methane emission events whose dynamics have been further resolved by the tiered model simulations. This work supports our position that AIMNET provides a promising DT framework for reliable, real-time monitoring and predictive risk assessment. In the end, we also discuss key implementation challenges and outline future directions for advancing such a new DT framework for translation deployment. - oai:arXiv.org:2512.06148v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 + Toward an AI Reasoning-Enabled System for Patient-Clinical Trial Matching + https://arxiv.org/abs/2512.08026 + arXiv:2512.08026v1 Announce Type: new +Abstract: Screening patients for clinical trial eligibility remains a manual, time-consuming, and resource-intensive process. We present a secure, scalable proof-of-concept system for Artificial Intelligence (AI)-augmented patient-trial matching that addresses key implementation challenges: integrating heterogeneous electronic health record (EHR) data, facilitating expert review, and maintaining rigorous security standards. Leveraging open-source, reasoning-enabled large language models (LLMs), the system moves beyond binary classification to generate structured eligibility assessments with interpretable reasoning chains that support human-in-the-loop review. This decision support tool represents eligibility as a dynamic state rather than a fixed determination, identifying matches when available and offering actionable recommendations that could render a patient eligible in the future. The system aims to reduce coordinator burden, intelligently broaden the set of trials considered for each patient and guarantee comprehensive auditability of all AI-generated outputs. + oai:arXiv.org:2512.08026v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1109/MIOT.2025.3638271 - Zifan Zhou, Xuan Wang, Yang Yan, Lkhanaajav Mijiddorj, Yu Ding, Tyler Beringer, Parisa Masnadi Khiabani, Wolfgang G. Jentner, Xiao-Ming Hu, Chenghao Wang, Bryan M. Carroll, Ming Xue, David Ebert, Bin Li, Binbin Weng + http://creativecommons.org/licenses/by/4.0/ + Caroline N. Leach, Mitchell A. Klusty, Samuel E. Armstrong, Justine C. Pickarski, Kristen L. Hankins, Emily B. Collier, Maya Shah, Aaron D. Mullen, V. K. Cody Bumgardner - Real-Time Spatiotemporal Tubes for Dynamic Unsafe Sets - https://arxiv.org/abs/2512.06151 - arXiv:2512.06151v1 Announce Type: new -Abstract: This paper presents a real-time control framework for nonlinear pure-feedback systems with unknown dynamics to satisfy reach-avoid-stay tasks within a prescribed time in dynamic environments. To achieve this, we introduce a real-time spatiotemporal tube (STT) framework. An STT is defined as a time-varying ball in the state space whose center and radius adapt online using only real-time sensory input. A closed-form, approximation-free control law is then derived to constrain the system output within the STT, ensuring safety and task satisfaction. We provide formal guarantees for obstacle avoidance and on-time task completion. The effectiveness and scalability of the framework are demonstrated through simulations and hardware experiments on a mobile robot and an aerial vehicle, navigating in cluttered dynamic environments. - oai:arXiv.org:2512.06151v1 + Optimized Area Coverage in Disaster Response Utilizing Autonomous UAV Swarm Formations + https://arxiv.org/abs/2512.08028 + arXiv:2512.08028v1 Announce Type: new +Abstract: This paper presents a UAV swarm system designed to assist first responders in disaster scenarios like wildfires. By distributing sensors across multiple agents, the system extends flight duration and enhances data availability, reducing the risk of mission failure due to collisions. To mitigate this risk further, we introduce an autonomous navigation framework that utilizes a local Euclidean Signed Distance Field (ESDF) map for obstacle avoidance while maintaining swarm formation with minimal path deviation. Additionally, we incorporate a Traveling Salesman Problem (TSP) variant to optimize area coverage, prioritizing Points of Interest (POIs) based on preassigned values derived from environmental behavior and critical infrastructure. The proposed system is validated through simulations with varying swarm sizes, demonstrating its ability to maximize coverage while ensuring collision avoidance between UAVs and obstacles. + oai:arXiv.org:2512.08028v1 cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ratnangshu Das, Siddhartha Upadhyay, Pushpak Jagtap + http://creativecommons.org/licenses/by-nc-nd/4.0/ + 10.1109/MED64031.2025.11073337 + Lampis Papakostas, Aristeidis Geladaris, Athanasios Mastrogeorgiou, Jim Sharples, Gautier Hattenberger, Panagiotis Chatzakos, Panagiotis Polygerinos - Learning Invariant Graph Representations Through Redundant Information - https://arxiv.org/abs/2512.06154 - arXiv:2512.06154v1 Announce Type: new -Abstract: Learning invariant graph representations for out-of-distribution (OOD) generalization remains challenging because the learned representations often retain spurious components. To address this challenge, this work introduces a new tool from information theory called Partial Information Decomposition (PID) that goes beyond classical information-theoretic measures. We identify limitations in existing approaches for invariant representation learning that solely rely on classical information-theoretic measures, motivating the need to precisely focus on redundant information about the target $Y$ shared between spurious subgraphs $G_s$ and invariant subgraphs $G_c$ obtained via PID. Next, we propose a new multi-level optimization framework that we call -- Redundancy-guided Invariant Graph learning (RIG) -- that maximizes redundant information while isolating spurious and causal subgraphs, enabling OOD generalization under diverse distribution shifts. Our approach relies on alternating between estimating a lower bound of redundant information (which itself requires an optimization) and maximizing it along with additional objectives. Experiments on both synthetic and real-world graph datasets demonstrate the generalization capabilities of our proposed RIG framework. - oai:arXiv.org:2512.06154v1 + CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space + https://arxiv.org/abs/2512.08029 + arXiv:2512.08029v1 Announce Type: new +Abstract: Clinical decision-making in oncology requires predicting dynamic disease evolution, a task current static AI predictors cannot perform. While world models (WMs) offer a paradigm for generative prediction, existing medical applications remain limited. Existing methods often rely on stochastic diffusion models, focusing on visual reconstruction rather than causal, physiological transitions. Furthermore, in medical domain, models like MeWM typically ignore patient-specific temporal and clinical contexts and lack a feedback mechanism to link predictions to treatment decisions. To address these gaps, we introduce CLARITY, a medical world model that forecasts disease evolution directly within a structured latent space. It explicitly integrates time intervals (temporal context) and patient-specific data (clinical context) to model treatment-conditioned progression as a smooth, interpretable trajectory, and thus generate physiologically faithful, individualized treatment plans. Finally, CLARITY introduces a novel prediction-to-decision framework, translating latent rollouts into transparent, actionable recommendations. CLARITY demonstrates state-of-the-art performance in treatment planning. On the MU-Glioma-Post dataset, our approach outperforms recent MeWM by 12\%, and significantly surpasses all other medical-specific large language models. + oai:arXiv.org:2512.08029v1 cs.LG - cs.AI - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Barproda Halder, Pasan Dissanayake, Sanghamitra Dutta + Tianxingjian Ding, Yuanhao Zou, Chen Chen, Mubarak Shah, Yu Tian - Sift or Get Off the PoC: Applying Information Retrieval to Vulnerability Research with SiftRank - https://arxiv.org/abs/2512.06155 - arXiv:2512.06155v1 Announce Type: new -Abstract: Security research is fundamentally a problem of resource constraint and consequent prioritization. There is simply too much attack surface and too little time and energy to spend analyzing it all. The most effective security researchers are often those who are most skilled at intuitively deciding which part of an expansive attack surface to investigate. We demonstrate that this problem of selecting the most promising option from among many possibilities can be reframed as an information retrieval problem, and solved using document ranking techniques with LLMs performing the heavy lifting as general-purpose rankers. We present SiftRank, a ranking algorithm achieving O(n) complexity through three key mechanisms: listwise ranking using an LLM to order documents in small batches of approximately 10 items at a time; inflection-based convergence detection that adaptively terminates ranking when score distributions have stabilized; and iterative refinement that progressively focuses ranking effort on the most relevant documents. Unlike existing reranking approaches that require a separate first-stage retrieval step to narrow datasets to approximately 100 candidates, SiftRank operates directly on thousands of items, with each document evaluated across multiple randomized batches to mitigate inconsistent judgments by an LLM. We demonstrate practical effectiveness on N-day vulnerability analysis, successfully identifying a vulnerability-fixing function among 2,197 changed functions in a stripped binary firmware patch within 99 seconds at an inference cost of $0.82. Our approach enables scalable security prioritization for problems that are generally constrained by manual analysis, requiring only standard LLM API access without specialized infrastructure, embedding, or domain-specific fine-tuning. An open-source implementation of SiftRank may be found at https://github.com/noperator/siftrank. - oai:arXiv.org:2512.06155v1 - cs.CR - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 + What Pulls the Strings? Understanding the Characteristics and Role of Argumentation in Open-Source Software Usability Discussions + https://arxiv.org/abs/2512.08032 + arXiv:2512.08032v1 Announce Type: new +Abstract: The usability of open-source software (OSS) is important but frequently overlooked in favor of technical and functional complexity. Argumentation can be a pivotal device for diverse stakeholders in OSS usability discussions to express opinions and persuade others. However, the characteristics of argument discourse in those discussions remain unknown, resulting in difficulties in providing effective support for discussion participants. We address this through a comprehensive analysis of argument discourse and quality in five OSS projects. Our results indicated that usability discussions are predominantly argument-driven, although their qualities vary. Issue comments exhibit lower-quality arguments than the issue posts, suggesting a shortage of collective intelligence about usability in OSS communities. Moreover, argument discourse and quality have various impacts on the subsequent behavior of participants. Overall, this research offers insights to help OSS stakeholders build more effective arguments and eventually improve OSS usability. These insights can also inform studies about other distributed collaborative communities. + oai:arXiv.org:2512.08032v1 + cs.SE + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Caleb Gross + http://creativecommons.org/licenses/by-sa/4.0/ + Arghavan Sanei, Chaima Amiri, Atefeh Shokrizadeh, Jinghui Cheng - Hybrid Beamfocusing Design for RSMA-Enabled Near-Field Wideband Communications - https://arxiv.org/abs/2512.06156 - arXiv:2512.06156v1 Announce Type: new -Abstract: Future wireless networks will utilize extremely large-scale antenna arrays (ELAAs) over high-frequency bands, which, however, produce near-field spherical wavefronts and spatial wideband effects. To exploit and mitigate these, this paper proposes a rate-splitting multiple access (RSMA)-enabled transmit scheme for wideband near-field communications (NFC). Our solution leverages true-time-delay (TTD)-based hybrid beamfocusing architectures to mitigate spatial wideband effect and reduce radio frequency chain requirements. The objective is to maximize the minimum rate by jointly optimizing frequency-dependent analog beamfocusing, frequency-independent analog beamfocusing, digital beamfocusing, and common rate allocation. To solve this complicated non-convex problem, we develop a penalty-based iterative algorithm that partitions the variables into three blocks and then employs block coordinate descent (BCD) to optimize each block alternately. This algorithm is further extended to support the sub-connected TTD-based analog beamfocusing architectures. Comprehensive simulation results indicate that our transmit scheme: 1) effectively compensates for spatial wideband effect, addressing a critical challenge in wideband operation; 2) achieves performance comparable to full digital beamfocusing while maintaining lower hardware complexity; 3) achieves substantial performance gains over the other two benchmarks. - oai:arXiv.org:2512.06156v1 + Expectations in Expectation Propagation + https://arxiv.org/abs/2512.08034 + arXiv:2512.08034v1 Announce Type: new +Abstract: Expectation Propagation (EP) is a widely used message-passing algorithm that decomposes a global inference problem into multiple local ones. It approximates marginal distributions (beliefs) using intermediate functions (messages). While beliefs must be proper probability distributions that integrate to one, messages may have infinite integral values. In Gaussian-projected EP, such messages take a Gaussian form and appear as if they have "negative" variances. Although allowed within the EP framework, these negative-variance messages can impede algorithmic progress. + In this paper, we investigate EP in linear models and analyze the relationship between the corresponding beliefs. Based on the analysis, we propose both non-persistent and persistent approaches that prevent the algorithm from being blocked by messages with infinite integral values. + Furthermore, by examining the relationship between the EP messages in linear models, we develop an additional approach that avoids the occurrence of messages with infinite integral values. + oai:arXiv.org:2512.08034v1 cs.IT + eess.SP math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + stat.CO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiasi Zhou, Chintha Tellambura + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Zilu Zhao, Fangqing Xiao, Dirk Slock - Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation - https://arxiv.org/abs/2512.06158 - arXiv:2512.06158v1 Announce Type: new -Abstract: Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artifacts and temporal drift. We hypothesize that the view discrepancy arises from supervision limited to pixel- or latent-space video-diffusion losses, which lack explicitly temporally aware, feature-level tracking guidance. We present \emph{Track4DGen}, a two-stage framework that couples a multi-view video diffusion model with a foundation point tracker and a hybrid 4D Gaussian Splatting (4D-GS) reconstructor. The central idea is to explicitly inject tracker-derived motion priors into intermediate feature representations for both multi-view video generation and 4D-GS. In Stage One, we enforce dense, feature-level point correspondences inside the diffusion generator, producing temporally consistent features that curb appearance drift and enhance cross-view coherence. In Stage Two, we reconstruct a dynamic 4D-GS using a hybrid motion encoding that concatenates co-located diffusion features (carrying Stage-One tracking priors) with Hex-plane features, and augment them with 4D Spherical Harmonics for higher-fidelity dynamics modeling. \emph{Track4DGen} surpasses baselines on both multi-view video generation and 4D generation benchmarks, yielding temporally stable, text-editable 4D assets. Lastly, we curate \emph{Sketchfab28}, a high-quality dataset for benchmarking object-centric 4D generation and fostering future research. - oai:arXiv.org:2512.06158v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Joint Activity Design Heuristics for Enhancing Human-Machine Collaboration + https://arxiv.org/abs/2512.08036 + arXiv:2512.08036v1 Announce Type: new +Abstract: Joint activity describes when more than one agent (human or machine) contributes to the completion of a task or activity. Designing for joint activity focuses on explicitly supporting the interdependencies between agents necessary for effective coordination among agents engaged in the joint activity. This builds and expands upon designing for usability to further address how technologies can be designed to act as effective team players. Effective joint activity requires supporting, at minimum, five primary macrocognitive functions within teams: Event Detection, Sensemaking, Adaptability, Perspective-Shifting, and Coordination. Supporting these functions is equally as important as making technologies usable. We synthesized fourteen heuristics from relevant literature including display design, human factors, cognitive systems engineering, cognitive psychology, and computer science to aid the design, development, and evaluation of technologies that support joint human-machine activity. + oai:arXiv.org:2512.08036v1 + cs.HC + cs.AI + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Su Sun, Cheng Zhao, Himangi Mittal, Gaurav Mittal, Rohith Kukkala, Yingjie Victor Chen, Mei Chen + Mohammadreza Jalaeian, Dane A. Morey, Michael F. Rayo - Deep learning for autism detection using clinical notes: A comparison of transfer learning for a transparent and black-box approach - https://arxiv.org/abs/2512.06161 - arXiv:2512.06161v1 Announce Type: new -Abstract: Autism spectrum disorder (ASD) is a complex neurodevelopmental condition whose rising prevalence places increasing demands on a lengthy diagnostic process. Machine learning (ML) has shown promise in automating ASD diagnosis, but most existing models operate as black boxes and are typically trained on a single dataset, limiting their generalizability. In this study, we introduce a transparent and interpretable ML approach that leverages BioBERT, a state-of-the-art language model, to analyze unstructured clinical text. The model is trained to label descriptions of behaviors and map them to diagnostic criteria, which are then used to assign a final label (ASD or not). We evaluate transfer learning, the ability to transfer knowledge to new data, using two distinct real-world datasets. We trained on datasets sequentially and mixed together and compared the performance of the best models and their ability to transfer to new data. We also created a black-box approach and repeated this transfer process for comparison. Our transparent model demonstrated robust performance, with the mixed-data training strategy yielding the best results (97 % sensitivity, 98 % specificity). Sequential training across datasets led to a slight drop in performance, highlighting the importance of training data order. The black-box model performed worse (90 % sensitivity, 96 % specificity) when trained sequentially or with mixed data. Overall, our transparent approach outperformed the black-box approach. Mixing datasets during training resulted in slightly better performance and should be the preferred approach when practically possible. This work paves the way for more trustworthy, generalizable, and clinically actionable AI tools in neurodevelopmental diagnostics. - oai:arXiv.org:2512.06161v1 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification + https://arxiv.org/abs/2512.08038 + arXiv:2512.08038v1 Announce Type: new +Abstract: Neural networks are frequently used in medical diagnosis. However, due to their black-box nature, model explainers are used to help clinicians understand better and trust model outputs. This paper introduces an explainer method for classifying Retinopathy of Prematurity (ROP) from fundus images. Previous methods fail to generate explanations that preserve input image structures such as smoothness and sparsity. We introduce Sparse and Smooth Explainer (SSplain), a method that generates pixel-wise explanations while preserving image structures by enforcing smoothness and sparsity. This results in realistic explanations to enhance the understanding of the given black-box model. To achieve this goal, we define an optimization problem with combinatorial constraints and solve it using the Alternating Direction Method of Multipliers (ADMM). Experimental results show that SSplain outperforms commonly used explainers in terms of both post-hoc accuracy and smoothness analyses. Additionally, SSplain identifies features that are consistent with domain-understandable features that clinicians consider as discriminative factors for ROP. We also show SSplain's generalization by applying it to additional publicly available datasets. Code is available at https://github.com/neu-spiral/SSplain. + oai:arXiv.org:2512.08038v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1016/j.artmed.2025.103318 - Artificial Intelligence in Medicine, February, 2026 - Gondy Leroy, Prakash Bisht, Sai Madhuri Kandula, Nell Maltman, Sydney Rice + Elifnur Sunger, Tales Imbiriba, Peter Campbell, Deniz Erdogmus, Stratis Ioannidis, Jennifer Dy - A polynomial dimension-dependence analysis of Bramble--Pasciak--Xu preconditioners - https://arxiv.org/abs/2512.06166 - arXiv:2512.06166v1 Announce Type: new -Abstract: We investigate the dimension dependence of Bramble--Pasciak--Xu (BPX) preconditioners for high-dimensional partial differential equations and establish that the condition numbers of BPX-preconditioned systems grow only polynomially with the spatial dimension. Our analysis requires a careful derivation of the dimension dependence of several fundamental tools in the theory of finite element methods, including the elliptic regularity, Bramble--Hilbert lemma, trace inequalities, and inverse inequalities. We further introduce a new quasi-interpolation operator into finite element spaces, a variant of the classical Scott--Zhang interpolation, whose associated constants scale polynomially with the dimension. Building on these ingredients, we prove a multilevel norm equivalence theorem and derive a BPX preconditioner with explicit polynomial bounds on its dimensional dependence. This result has notable implications for emerging quantum computing methodologies: recent studies indicate that polynomial dependence of BPX preconditioners on dimension can yield exponential speedups for quantum-algorithmic approaches over their classical counterparts. - oai:arXiv.org:2512.06166v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 + Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment + https://arxiv.org/abs/2512.08040 + arXiv:2512.08040v1 Announce Type: new +Abstract: Our aim is to develop a unified model for sign language understanding, that performs sign language translation (SLT) and sign-subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken language text and also the temporal alignment of signing with subtitles -- both essential for practical communication, large-scale corpus construction, and educational applications. To achieve this, our approach is built upon three components: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images while preserving signer privacy; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings to bridge the vision-text gap; and (iii) a multi-task scalable training strategy that jointly optimises SLT and SSA, reinforcing both linguistic and temporal alignment. To promote cross-linguistic generalisation, we pretrain our model on large-scale sign-text corpora covering British Sign Language (BSL) and American Sign Language (ASL) from the BOBSL and YouTube-SL-25 datasets. With this multilingual pretraining and strong model design, we achieve state-of-the-art results on the challenging BOBSL (BSL) dataset for both SLT and SSA. Our model also demonstrates robust zero-shot generalisation and finetuned SLT performance on How2Sign (ASL), highlighting the potential of scalable translation across different sign languages. + oai:arXiv.org:2512.08040v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Boou Jiang, Jongho Park, Jinchao Xu - - - Morphologically-Informed Tokenizers for Languages with Non-Concatenative Morphology: A case study of Yolox\'ochtil Mixtec ASR - https://arxiv.org/abs/2512.06169 - arXiv:2512.06169v1 Announce Type: new -Abstract: This paper investigates the impact of using morphologically-informed tokenizers to aid and streamline the interlinear gloss annotation of an audio corpus of Yolox\'ochitl Mixtec (YM) using a combination of ASR and text-based sequence-to-sequence tools, with the goal of improving efficiency while reducing the workload of a human annotator. We present two novel tokenization schemes that separate words in a nonlinear manner, preserving information about tonal morphology as much as possible. One of these approaches, a Segment and Melody tokenizer, simply extracts the tones without predicting segmentation. The other, a Sequence of Processes tokenizer, predicts segmentation for the words, which could allow an end-to-end ASR system to produce segmented and unsegmented transcriptions in a single pass. We find that these novel tokenizers are competitive with BPE and Unigram models, and the Segment-and-Melody model outperforms traditional tokenizers in terms of word error rate but does not reach the same character error rate. In addition, we analyze tokenizers on morphological and information-theoretic metrics to find predictive correlations with downstream performance. Our results suggest that nonlinear tokenizers designed specifically for the non-concatenative morphology of a language are competitive with conventional BPE and Unigram models for ASR. Further research will be necessary to determine the applicability of these tokenizers in downstream processing tasks. - oai:arXiv.org:2512.06169v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Chris Crawford + Youngjoon Jang, Liliane Momeni, Zifan Jiang, Joon Son Chung, G\"ul Varol, Andrew Zisserman - Automated Annotation of Shearographic Measurements Enabling Weakly Supervised Defect Detection - https://arxiv.org/abs/2512.06171 - arXiv:2512.06171v1 Announce Type: new -Abstract: Shearography is an interferometric technique sensitive to surface displacement gradients, providing high sensitivity for detecting subsurface defects in safety-critical components. A key limitation to industrial adoption is the lack of high-quality annotated datasets, since manual labeling remains labor-intensive, subjective, and difficult to standardize. We introduce an automated workflow that generates defect annotations from shearography measurements using deep learning, producing high-resolution segmentation and bounding-box labels. Evaluation against expert-labeled data demonstrates sufficient accuracy to enable weakly supervised training, reducing manual effort and supporting scalable dataset creation for robust defect detection. - oai:arXiv.org:2512.06171v1 + Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking + https://arxiv.org/abs/2512.08042 + arXiv:2512.08042v1 Announce Type: new +Abstract: Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones. This requires robust generalization to new and unseen deepfakes, which emerge frequently, while minimizing computational overhead to enable large-scale deepfake screening, a critical objective in the era of Green AI. In this work, we explore frequency-domain masking as a training strategy for deepfake detectors. Unlike traditional methods that rely heavily on spatial features or large-scale pretrained models, our approach introduces random masking and geometric transformations, with a focus on frequency masking due to its superior generalization properties. We demonstrate that frequency masking not only enhances detection accuracy across diverse generators but also maintains performance under significant model pruning, offering a scalable and resource-conscious solution. Our method achieves state-of-the-art generalization on GAN- and diffusion-generated image datasets and exhibits consistent robustness under structured pruning. These results highlight the potential of frequency-based masking as a practical step toward sustainable and generalizable deepfake detection. Code and models are available at: [https://github.com/chandlerbing65nm/FakeImageDetection](https://github.com/chandlerbing65nm/FakeImageDetection). + oai:arXiv.org:2512.08042v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jessica Plassmann, Nicolas Schuler, Michael Schuth, Georg von Freymann + http://creativecommons.org/licenses/by/4.0/ + Chandler Timm C. Doloriel, Habib Ullah, Kristian Hovde Liland, Fadi Al Machot, Ngai-Man Cheung - DEFEND: Poisoned Model Detection and Malicious Client Exclusion Mechanism for Secure Federated Learning-based Road Condition Classification - https://arxiv.org/abs/2512.06172 - arXiv:2512.06172v1 Announce Type: new -Abstract: Federated Learning (FL) has drawn the attention of the Intelligent Transportation Systems (ITS) community. FL can train various models for ITS tasks, notably camera-based Road Condition Classification (RCC), in a privacy-preserving collaborative way. However, opening up to collaboration also opens FL-based RCC systems to adversaries, i.e., misbehaving participants that can launch Targeted Label-Flipping Attacks (TLFAs) and threaten transportation safety. Adversaries mounting TLFAs poison training data to misguide model predictions, from an actual source class (e.g., wet road) to a wrongly perceived target class (e.g., dry road). Existing countermeasures against poisoning attacks cannot maintain model performance under TLFAs close to the performance level in attack-free scenarios, because they lack specific model misbehavior detection for TLFAs and neglect client exclusion after the detection. To close this research gap, we propose DEFEND, which includes a poisoned model detection strategy that leverages neuron-wise magnitude analysis for attack goal identification and Gaussian Mixture Model (GMM)-based clustering. DEFEND discards poisoned model contributions in each round and adapts accordingly client ratings, eventually excluding malicious clients. Extensive evaluation involving various FL-RCC models and tasks shows that DEFEND can thwart TLFAs and outperform seven baseline countermeasures, with at least 15.78% improvement, with DEFEND remarkably achieving under attack the same performance as in attack-free scenarios. - oai:arXiv.org:2512.06172v1 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Scaffolding Reshapes Dialogic Engagement in Collaborative Problem Solving: Comparative Analysis of Two Approaches + https://arxiv.org/abs/2512.08045 + arXiv:2512.08045v1 Announce Type: new +Abstract: Supporting learners during Collaborative Problem Solving (CPS) is a necessity. Existing studies have compared scaffolds with maximal and minimal instructional support by studying their effects on learning and behaviour. However, our understanding of how such scaffolds could differently shape the distribution of individual dialogic engagement and behaviours across different CPS phases remains limited. This study applied Heterogeneous Interaction Network Analysis (HINA) and Sequential Pattern Mining (SPM) to uncover the structural effects of scaffolding on different phases of the CPS process among K-12 students in authentic educational settings. Students with a maximal scaffold demonstrated higher dialogic engagement across more phases than those with a minimal scaffold. However, they were extensively demonstrating scripting behaviours across the phases, evidencing the presence of overscripting. Although students with the minimal scaffold demonstrated more problem solving behaviours and fewer scripting behaviours across the phases, they repeated particular behaviours in multiple phases and progressed more to socialising behaviours. In both scaffold conditions, problem solving behaviours rarely progressed to other problem solving behaviours. The paper discusses the implications of these findings for scaffold design and teaching practice of CPS, and highlights the distinct yet complementary value of HINA and SPM approaches to investigate students' learning processes during CPS. + oai:arXiv.org:2512.08045v1 + cs.SI + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Sheng Liu, Panos Papadimitratos + http://creativecommons.org/licenses/by/4.0/ + Kester Wong, Feng Shihui, Sahan Bulathwela, Mutlu Cukurova - Physics-Grounded Shadow Generation from Monocular 3D Geometry Priors and Approximate Light Direction - https://arxiv.org/abs/2512.06174 - arXiv:2512.06174v1 Announce Type: new -Abstract: Shadow generation aims to produce photorealistic shadows that are visually consistent with object geometry and scene illumination. In the physics of shadow formation, the occluder blocks some light rays casting from the light source that would otherwise arrive at the surface, creating a shadow that follows the silhouette of the occluder. However, such explicit physical modeling has rarely been used in deep-learning-based shadow generation. In this paper, we propose a novel framework that embeds explicit physical modeling - geometry and illumination - into deep-learning-based shadow generation. First, given a monocular RGB image, we obtain approximate 3D geometry in the form of dense point maps and predict a single dominant light direction. These signals allow us to recover fairly accurate shadow location and shape based on the physics of shadow formation. We then integrate this physics-based initial estimate into a diffusion framework that refines the shadow into a realistic, high-fidelity appearance while ensuring consistency with scene geometry and illumination. Trained on DESOBAV2, our model produces shadows that are both visually realistic and physically coherent, outperforming existing approaches, especially in scenes with complex geometry or ambiguous lighting. - oai:arXiv.org:2512.06174v1 + Mask to Adapt: Simple Random Masking Enables Robust Continual Test-Time Learning + https://arxiv.org/abs/2512.08048 + arXiv:2512.08048v1 Announce Type: new +Abstract: Distribution shifts at test time degrade image classifiers. Recent continual test-time adaptation (CTTA) methods use masking to regulate learning, but often depend on calibrated uncertainty or stable attention scores and introduce added complexity. We ask: do we need custom-made masking designs, or can a simple random masking schedule suffice under strong corruption? We introduce Mask to Adapt (M2A), a simple CTTA approach that generates a short sequence of masked views (spatial or frequency) and adapts with two objectives: a mask consistency loss that aligns predictions across different views and an entropy minimization loss that encourages confident outputs. Motivated by masked image modeling, we study two common masking families -- spatial masking and frequency masking -- and further compare subtypes within each (spatial: patch vs.\ pixel; frequency: all vs.\ low vs.\ high). On CIFAR10C/CIFAR100C/ImageNetC (severity~5), M2A (Spatial) attains 8.3\%/19.8\%/39.2\% mean error, outperforming or matching strong CTTA baselines, while M2A (Frequency) lags behind. Ablations further show that simple random masking is effective and robust. These results indicate that a simple random masking schedule, coupled with consistency and entropy objectives, is sufficient to drive effective test-time adaptation without relying on uncertainty or attention signals. + oai:arXiv.org:2512.08048v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Shilin Hu, Jingyi Xu, Akshat Dave, Dimitris Samaras, Hieu Le + Chandler Timm C. Doloriel - From PyTorch to Calyx: An Open-Source Compiler Toolchain for ML Accelerators - https://arxiv.org/abs/2512.06177 - arXiv:2512.06177v1 Announce Type: new -Abstract: We present an end-to-end open-source compiler toolchain that targets synthesizable SystemVerilog from ML models written in PyTorch. Our toolchain leverages the accelerator design language Allo, the hardware intermediate representation (IR) Calyx, and the CIRCT project under LLVM. We also implement a set of compiler passes for memory partitioning, enabling effective parallelism in memory-intensive ML workloads. Experimental results demonstrate that our compiler can effectively generate optimized FPGA-implementable hardware designs that perform reasonably well against closed-source industry-grade tools such as Vitis HLS. - oai:arXiv.org:2512.06177v1 - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 + An Introduction to Deep Reinforcement and Imitation Learning + https://arxiv.org/abs/2512.08052 + arXiv:2512.08052v1 Announce Type: new +Abstract: Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually, learning-based approaches have emerged as promising alternatives, most notably Deep Reinforcement Learning (DRL) and Deep Imitation Learning (DIL). DRL leverages reward signals to optimize behavior, while DIL uses expert demonstrations to guide learning. This document introduces DRL and DIL in the context of embodied agents, adopting a concise, depth-first approach to the literature. It is self-contained, presenting all necessary mathematical and machine learning concepts as they are needed. It is not intended as a survey of the field; rather, it focuses on a small set of foundational algorithms and techniques, prioritizing in-depth understanding over broad coverage. The material ranges from Markov Decision Processes to REINFORCE and Proximal Policy Optimization (PPO) for DRL, and from Behavioral Cloning to Dataset Aggregation (DAgger) and Generative Adversarial Imitation Learning (GAIL) for DIL. + oai:arXiv.org:2512.08052v1 + cs.RO + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Pedro Santana + + + Fairness-aware PageRank via Edge Reweighting + https://arxiv.org/abs/2512.08055 + arXiv:2512.08055v1 Announce Type: new +Abstract: Link-analysis algorithms, such as PageRank, are instrumental in understanding the structural dynamics of networks by evaluating the importance of individual vertices based on their connectivity. Recently, with the rising importance of responsible AI, the question of fairness in link-analysis algorithms has gained traction. In this paper, we present a new approach for incorporating group fairness into the PageRank algorithm by reweighting the transition probabilities in the underlying transition matrix. We formulate the problem of achieving fair PageRank by seeking to minimize the fairness loss, which is the difference between the original group-wise PageRank distribution and a target PageRank distribution. We further define a group-adapted fairness notion, which accounts for group homophily by considering random walks with group-biased restart for each group. Since the fairness loss is non-convex, we propose an efficient projected gradient-descent method for computing locally-optimal edge weights. Unlike earlier approaches, we do not recommend adding new edges to the network, nor do we adjust the restart vector. Instead, we keep the topology of the underlying network unchanged and only modify the relative importance of existing edges. We empirically compare our approach with state-of-the-art baselines and demonstrate the efficacy of our method, where very small changes in the transition matrix lead to significant improvement in the fairness of the PageRank algorithm. + oai:arXiv.org:2512.08055v1 + cs.SI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Jiahan Xie, Evan Williams, Adrian Sampson + 10.1145/3773966.3777991 + WSDM 2026 + Honglian Wang, Haoyun Chen, Aristides Gionis - Systematically Thinking about the Complexity of Code Structuring Exercises at Introductory Level - https://arxiv.org/abs/2512.06178 - arXiv:2512.06178v1 Announce Type: new -Abstract: Decomposition and abstraction is an essential component of computational thinking, yet it is not always emphasized in introductory programming courses. In addition, as generative AI further reduces the focus on syntax and increases the importance of higher-level code reasoning, there is renewed opportunity to teach DA explicitly. In this paper, we introduce a framework for systematically assessing the complexity of code structuring tasks, where students must identify and separate meaningful abstractions within existing, unstructured code. The framework defines three dimensions of task complexity, each with multiple levels: repetition, code pattern, and data dependency. To support practical use, we provide example tasks mapped to these levels and offer an interactive tool for generating and exploring DA problems. The framework is designed to support the development of educational tasks that build students' skills with DA in the procedural paradigm. - oai:arXiv.org:2512.06178v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Large Language Models for Education and Research: An Empirical and User Survey-based Analysis + https://arxiv.org/abs/2512.08057 + arXiv:2512.08057v1 Announce Type: new +Abstract: Pretrained Large Language Models (LLMs) have achieved remarkable success across diverse domains, with education and research emerging as particularly impactful areas. Among current state-of-the-art LLMs, ChatGPT and DeepSeek exhibit strong capabilities in mathematics, science, medicine, literature, and programming. In this study, we present a comprehensive evaluation of these two LLMs through background technology analysis, empirical experiments, and a real-world user survey. The evaluation explores trade-offs among model accuracy, computational efficiency, and user experience in educational and research affairs. We benchmarked these LLMs performance in text generation, programming, and specialized problem-solving. Experimental results show that ChatGPT excels in general language understanding and text generation, while DeepSeek demonstrates superior performance in programming tasks due to its efficiency- focused design. Moreover, both models deliver medically accurate diagnostic outputs and effectively solve complex mathematical problems. Complementing these quantitative findings, a survey of students, educators, and researchers highlights the practical benefits and limitations of these models, offering deeper insights into their role in advancing education and research. + oai:arXiv.org:2512.08057v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1145/3770762.3772633 - Georgiana Haldeman, Peter Ohmann, Paul Denny + Md Mostafizer Rahman, Ariful Islam Shiplu, Md Faizul Ibne Amin, Yutaka Watanobe, Lu Peng - Physics-Grounded Attached Shadow Detection Using Approximate 3D Geometry and Light Direction - https://arxiv.org/abs/2512.06179 - arXiv:2512.06179v1 Announce Type: new -Abstract: Attached shadows occur on the surface of the occluder where light cannot reach because of self-occlusion. They are crucial for defining the three-dimensional structure of objects and enhancing scene understanding. Yet existing shadow detection methods mainly target cast shadows, and there are no dedicated datasets or models for detecting attached shadows. To address this gap, we introduce a framework that jointly detects cast and attached shadows by reasoning about their mutual relationship with scene illumination and geometry. Our system consists of a shadow detection module that predicts both shadow types separately, and a light estimation module that infers the light direction from the detected shadows. The estimated light direction, combined with surface normals, allows us to derive a geometry-consistent partial map that identifies regions likely to be self-occluded. This partial map is then fed back to refine shadow predictions, forming a closed-loop reasoning process that iteratively improves both shadow segmentation and light estimation. In order to train our method, we have constructed a dataset of 1,458 images with separate annotations for cast and attached shadows, enabling training and quantitative evaluation of both. Experimental results demonstrate that this iterative geometry-illumination reasoning substantially improves the detection of attached shadows, with at least 33% BER reduction, while maintaining strong full and cast shadow performance. - oai:arXiv.org:2512.06179v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + LUNA: Linear Universal Neural Attention with Generalization Guarantees + https://arxiv.org/abs/2512.08061 + arXiv:2512.08061v1 Announce Type: new +Abstract: Scaling attention faces a critical bottleneck: the $\mathcal{O}(n^2)$ quadratic computational cost of softmax attention, which limits its application in long-sequence domains. While linear attention mechanisms reduce this cost to $\mathcal{O}(n)$, they typically rely on fixed random feature maps, such as random Fourier features or hand-crafted functions. This reliance on static, data-agnostic kernels creates a fundamental trade-off, forcing practitioners to sacrifice significant model accuracy for computational efficiency. We introduce \textsc{LUNA}, a kernelized linear attention mechanism that eliminates this trade-off, retaining linear cost while matching and surpassing the accuracy of quadratic attention. \textsc{LUNA} is built on the key insight that the kernel feature map itself should be learned rather than fixed a priori. By parameterizing the kernel, \textsc{LUNA} learns a feature basis tailored to the specific data and task, overcoming the expressive limitations of fixed-feature methods. \textsc{Luna} implements this with a learnable feature map that induces a positive-definite kernel and admits a streaming form, yielding linear time and memory scaling in the sequence length. Empirical evaluations validate our approach across diverse settings. On the Long Range Arena (LRA), \textsc{Luna} achieves state-of-the-art average accuracy among efficient Transformers under compute parity, using the same parameter count, training steps, and approximate FLOPs. \textsc{Luna} also excels at post-hoc conversion: replacing softmax in fine-tuned BERT and ViT-B/16 checkpoints and briefly fine-tuning recovers most of the original performance, substantially outperforming fixed linearizations. + oai:arXiv.org:2512.08061v1 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Shilin Hu, Jingyi Xu, Sagnik Das, Dimitris Samaras, Hieu Le + Ashkan Shahbazi, Ping He, Ali Abbasi, Yikun Bai, Xinran Liu, Elaheh Akbari, Darian Salehi, Navid NaderiAlizadeh, Soheil Kolouri - Strategic Experimentation with Private Payoffs - https://arxiv.org/abs/2512.06180 - arXiv:2512.06180v1 Announce Type: new -Abstract: We study a strategic experimentation game with exponential bandits, in which experiment outcomes are private. The equilibrium amount of experimentation is always higher than in the benchmark case where experiment outcomes are publicly observed. In addition, for pure equilibria, the equilibrium amount of experimentation is at least socially optimal, and possibly higher. We provide a tight bound on the degree of over-experimentation. The analysis rests on a new form of encouragement effect, according to which a player may hide the absence of a success to encourage future experimentation by the other player, which incentivizes current experimentation. - oai:arXiv.org:2512.06180v1 - cs.GT - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Deep Kernel Aalen-Johansen Estimator: An Interpretable and Flexible Neural Net Framework for Competing Risks + https://arxiv.org/abs/2512.08063 + arXiv:2512.08063v1 Announce Type: new +Abstract: We propose an interpretable deep competing risks model called the Deep Kernel Aalen-Johansen (DKAJ) estimator, which generalizes the classical Aalen-Johansen nonparametric estimate of cumulative incidence functions (CIFs). Each data point (e.g., patient) is represented as a weighted combination of clusters. If a data point has nonzero weight only for one cluster, then its predicted CIFs correspond to those of the classical Aalen-Johansen estimator restricted to data points from that cluster. These weights come from an automatically learned kernel function that measures how similar any two data points are. On four standard competing risks datasets, we show that DKAJ is competitive with state-of-the-art baselines while being able to provide visualizations to assist model interpretation. + oai:arXiv.org:2512.08063v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - J\'er\^ome Renault, Eilon Solan, Nicolas Vieille + Xiaobin Shen, George H. Chen - Situation-Aware Interactive MPC Switching for Autonomous Driving - https://arxiv.org/abs/2512.06182 - arXiv:2512.06182v1 Announce Type: new -Abstract: To enable autonomous driving in interactive traffic scenarios, various model predictive control (MPC) formulations have been proposed, each employing different interaction models. While higher-fidelity models enable more intelligent behavior, they incur increased computational cost. Since strong interactions are relatively infrequent in traffic, a practical strategy for balancing performance and computational overhead is to invoke an appropriate controller based on situational demands. To achieve this approach, we first conduct a comparative study to assess and hierarchize the interactive capabilities of different MPC formulations. Furthermore, we develop a neural network-based classifier to enable situation-aware switching among controllers with different levels of interactive capability. We demonstrate that this situation-aware switching can both substantially improve overall performance by activating the most advanced interactive MPC in rare but critical situations, and significantly reduce computational load by using a basic MPC in the majority of scenarios. - oai:arXiv.org:2512.06182v1 - cs.RO - cs.SY + Cabin Layout, Seat Density, and Passenger Segmentation in Air Transport: Implications for Prices, Ancillary Revenues, and Efficiency + https://arxiv.org/abs/2512.08066 + arXiv:2512.08066v1 Announce Type: new +Abstract: This study investigates how the layout and density of seats in aircraft cabins influence the pricing of airline tickets on domestic flights. The analysis is based on microdata from boarding passes linked to face-to-face interviews with passengers, allowing us to relate the price paid to the location on the aircraft seat map, as well as market characteristics and flight operations. Econometric models were estimated using the Post-Double-Selection LASSO (PDS-LASSO) procedure, which selects numerous controls for unobservable factors linked to commercial and operational aspects, thus enabling better identification of the effect of variables such as advance purchase, reason for travel, fuel price, market structure, and load factor, among others. The results suggest that a higher density of seat rows is associated with lower prices, reflecting economies of scale with the increase in aircraft size and gains in operational efficiency. An unexpected result was also obtained: in situations where there was no seat selection fee, passengers with more expensive tickets were often allocated middle seats due to purchasing at short notice, when the side alternatives were no longer available. This behavior helps explain the economic logic behind one of the main ancillary revenues of airlines. In addition to quantitative analysis, the study incorporates an exploratory approach to innovative cabin concepts and their possible effects on density and comfort on board. + oai:arXiv.org:2512.08066v1 eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + cs.SY + econ.GN + q-fin.EC + stat.AP + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Shuhao Qi, Qiling Aori, Luyao Zhang, Mircea Lazar, Sofie Haesaert + 10.5281/zenodo.17860616 + Communications in Airline Economics Research, 202117818, 2025 + Alessandro V. M. Oliveira, Moises D. Vassallo - PMA-Diffusion: A Physics-guided Mask-Aware Diffusion Framework for TSE from Sparse Observations - https://arxiv.org/abs/2512.06183 - arXiv:2512.06183v1 Announce Type: new -Abstract: High-resolution highway traffic state information is essential for Intelligent Transportation Systems, but typical traffic data acquired from loop detectors and probe vehicles are often too sparse and noisy to capture the detailed dynamics of traffic flow. We propose PMA-Diffusion, a physics-guided mask-aware diffusion framework that reconstructs unobserved highway speed fields from sparse, incomplete observations. Our approach trains a diffusion prior directly on sparsely observed speed fields using two mask-aware training strategies: Single-Mask and Double-Mask. At the inference phase, the physics-guided posterior sampler alternates reverse-diffusion updates, observation projection, and physics-guided projection based on adaptive anisotropic smoothing to reconstruct the missing speed fields. The proposed framework is tested on the I-24 MOTION dataset with varying visibility ratios. Even under severe sparsity, with only 5% visibility, PMA-Diffusion outperforms other baselines across three reconstruction error metrics. Furthermore, PMA-diffusion trained with sparse observation nearly matches the performance of the baseline model trained on fully observed speed fields. The results indicate that combining mask-aware diffusion priors with a physics-guided posterior sampler provides a reliable and flexible solution for traffic state estimation under realistic sensing sparsity. - oai:arXiv.org:2512.06183v1 + CapsuleFS A Multi-credential DataCapsule Filesystem + https://arxiv.org/abs/2512.08067 + arXiv:2512.08067v1 Announce Type: new +Abstract: CapsuleFS (CFS) is the first filesystem to integrate multi-credential functionality within a POSIX-compliant framework, utilizing DataCapsule as the storage provider. This innovative system is established based on the Global Data Plane in the area of edge computing. Our comprehensive design and implementation of CFS successfully fulfill the objective of providing a multi-credential Common Access API. The architecture of CFS is methodically segmented into three integral components: Firstly, the DataCapsule server, tasked with the storage, dissemination, and replication of DataCapsules on the edge. Secondly, the middleware, a crucial element running in a Trusted Execution Environment responsible for the enforcement and management of write permissions and requests. Finally, the client component, which manifests as a POSIX-compliant filesystem, is adaptable and operational across many architectures. Experimental evaluations of CFS reveal that, while its read and write performances are comparatively modest, it upholds a high degree of functional correctness. This attribute distinctly positions CFS as a viable candidate for application in real-world software development scenarios. The paper also delineates potential future enhancements, aimed at augmenting the practicality of CFS in the landscape of software development. + oai:arXiv.org:2512.08067v1 + cs.DC + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Qingyang Hu, Yucheng Huang, Manshi Yang + + + CAMO: Causality-Guided Adversarial Multimodal Domain Generalization for Crisis Classification + https://arxiv.org/abs/2512.08071 + arXiv:2512.08071v1 Announce Type: new +Abstract: Crisis classification in social media aims to extract actionable disaster-related information from multimodal posts, which is a crucial task for enhancing situational awareness and facilitating timely emergency responses. However, the wide variation in crisis types makes achieving generalizable performance across unseen disasters a persistent challenge. Existing approaches primarily leverage deep learning to fuse textual and visual cues for crisis classification, achieving numerically plausible results under in-domain settings. However, they exhibit poor generalization across unseen crisis types because they 1. do not disentangle spurious and causal features, resulting in performance degradation under domain shift, and 2. fail to align heterogeneous modality representations within a shared space, which hinders the direct adaptation of established single-modality domain generalization (DG) techniques to the multimodal setting. To address these issues, we introduce a causality-guided multimodal domain generalization (MMDG) framework that combines adversarial disentanglement with unified representation learning for crisis classification. The adversarial objective encourages the model to disentangle and focus on domain-invariant causal features, leading to more generalizable classifications grounded in stable causal mechanisms. The unified representation aligns features from different modalities within a shared latent space, enabling single-modality DG strategies to be seamlessly extended to multimodal learning. Experiments on the different datasets demonstrate that our approach achieves the best performance in unseen disaster scenarios. + oai:arXiv.org:2512.08071v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Lindong Liu, Zhixiong Jin, Seongjin Choi + Pingchuan Ma, Chengshuai Zhao, Bohan Jiang, Saketh Vishnubhatla, Ujun Jeong, Alimohammad Beigi, Adrienne Raglin, Huan Liu - SPOOF: Simple Pixel Operations for Out-of-Distribution Fooling - https://arxiv.org/abs/2512.06185 - arXiv:2512.06185v1 Announce Type: new -Abstract: Deep neural networks (DNNs) excel across image recognition tasks, yet continue to exhibit overconfidence on inputs that bear no resemblance to natural images. Revisiting the "fooling images" work introduced by Nguyen et al. (2015), we re-implement both CPPN-based and direct-encoding-based evolutionary fooling attacks on modern architectures, including convolutional and transformer classifiers. Our re-implementation confirm that high-confidence fooling persists even in state-of-the-art networks, with transformer-based ViT-B/16 emerging as the most susceptible--achieving near-certain misclassifications with substantially fewer queries than convolution-based models. We then introduce SPOOF, a minimalist, consistent, and more efficient black-box attack generating high-confidence fooling images. Despite its simplicity, SPOOF generates unrecognizable fooling images with minimal pixel modifications and drastically reduced compute. Furthermore, retraining with fooling images as an additional class provides only partial resistance, as SPOOF continues to fool consistently with slightly higher query budgets--highlighting persistent fragility of modern deep classifiers. - oai:arXiv.org:2512.06185v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Detecting Privileged Documents by Ranking Connected Network Entities + https://arxiv.org/abs/2512.08073 + arXiv:2512.08073v1 Announce Type: new +Abstract: This paper presents a link analysis approach for identifying privileged documents by constructing a network of human entities derived from email header metadata. Entities are classified as either counsel or non-counsel based on a predefined list of known legal professionals. The core assumption is that individuals with frequent interactions with lawyers are more likely to participate in privileged communications. To quantify this likelihood, an algorithm assigns a score to each entity within the network. By utilizing both entity scores and the strength of their connections, the method enhances the identification of privileged documents. Experimental results demonstrate the algorithm's effectiveness in ranking legal entities for privileged document detection. + oai:arXiv.org:2512.08073v1 + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ankit Gupta (Michigan State University), Christoph Adami (Michigan State University), Emily Dolson (Michigan State University) + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Jianping Zhang, Han Qin, Nathaniel Huber-Fliflet - On the hardness of recognizing graphs of small mim-width and its variants - https://arxiv.org/abs/2512.06186 - arXiv:2512.06186v1 Announce Type: new -Abstract: The mim-width of a graph is a powerful structural parameter that, when bounded by a constant, allows several hard problems to be polynomial-time solvable - with a recent meta-theorem encompassing a large class of problems [SODA2023]. Since its introduction, several variants such as sim-width and omim-width were developed, along with a linear version of these parameters. It was recently shown that mim-width and all these variants all paraNP-hard, a consequence of the NP-hardness of distinguishing between graphs of linear mim-width at most 1211 and graphs of sim-width at least 1216 [ICALP2025]. The complexity of recognizing graphs of small width, particularly those close to $1$, remained open, despite their especially attractive algorithmic applications. - In this work, we show that the width recognition problems remain NP-hard even on small widths. Specifically, after introducing the novel parameter Omim-width sandwiched between omim-width and mim-width, we show that: (1) deciding whether a graph has sim-width = 1, omim-width = 1, or Omin-width = 1 is NP-hard, and the same is true for their linear variants; (2) the problems of deciding whether mim-width $\leq$ 2 or linear mim-width $\leq$ 2 are both NP-hard. Interestingly, our reductions are relatively simple and are from the Unrooted Quartet Consistency problem, which is of great interest in computational biology but is not commonly used (if ever) in the theory of algorithms. - oai:arXiv.org:2512.06186v1 - cs.DM - cs.CC - math.CO - Tue, 09 Dec 2025 00:00:00 -0500 + Identification of Deforestation Areas in the Amazon Rainforest Using Change Detection Models + https://arxiv.org/abs/2512.08075 + arXiv:2512.08075v1 Announce Type: new +Abstract: The preservation of the Amazon Rainforest is one of the global priorities in combating climate change, protecting biodiversity, and safeguarding indigenous cultures. The Satellite-based Monitoring Project of Deforestation in the Brazilian Legal Amazon (PRODES), a project of the National Institute for Space Research (INPE), stands out as a fundamental initiative in this effort, annually monitoring deforested areas not only in the Amazon but also in other Brazilian biomes. Recently, machine learning models have been developed using PRODES data to support this effort through the comparative analysis of multitemporal satellite images, treating deforestation detection as a change detection problem. However, existing approaches present significant limitations: models evaluated in the literature still show unsatisfactory effectiveness, many do not incorporate modern architectures, such as those based on self-attention mechanisms, and there is a lack of methodological standardization that allows direct comparisons between different studies. In this work, we address these gaps by evaluating various change detection models in a unified dataset, including fully convolutional models and networks incorporating self-attention mechanisms based on Transformers. We investigate the impact of different pre- and post-processing techniques, such as filtering deforested areas predicted by the models based on the size of connected components, texture replacement, and image enhancements; we demonstrate that such approaches can significantly improve individual model effectiveness. Additionally, we test different strategies for combining the evaluated models to achieve results superior to those obtained individually, reaching an F1-score of 80.41%, a value comparable to other recent works in the literature. + oai:arXiv.org:2512.08075v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Max Dupr\'e la Tour, Manuel Lafond, Ndiam\'e Ndiaye + Christian Massao Konishi, Helio Pedrini - Sparse Neural Approximations for Bilevel Adversarial Problems in Power Grids - https://arxiv.org/abs/2512.06187 - arXiv:2512.06187v1 Announce Type: new -Abstract: The adversarial worst-case load shedding (AWLS) problem is pivotal for identifying critical contingencies under line outages. It is naturally cast as a bilevel program: the upper level simulates an attacker determining worst-case line failures, and the lower level corresponds to the defender's generator redispatch operations. Conventional techniques using optimality conditions render the bilevel, mixed-integer formulation computationally prohibitive due to the combinatorial number of topologies and the nonconvexity of AC power flow constraints. To address these challenges, we develop a novel single-level optimal value-function (OVF) reformulation and further leverage a data-driven neural network (NN) surrogate of the follower's optimal value. To ensure physical realizability, we embed the trained surrogate in a physics-constrained NN (PCNN) formulation that couples the OVF inequality with (relaxed) AC feasibility, yielding a mixed-integer convex model amenable to off-the-shelf solvers. To achieve scalability, we learn a sparse, area-partitioned NN via spectral clustering; the resulting block-sparse architecture scales essentially linearly with system size while preserving accuracy. Notably, our approach produces near-optimal worst-case failures and generalizes across loading conditions and unseen topologies, enabling rapid online recomputation. Numerical experiments on the IEEE 14- and 118-bus systems demonstrate the method's scalability and solution quality for large-scale contingency analysis, with an average optimality gap of 5.8% compared to conventional methods, while maintaining computation times under one minute. - oai:arXiv.org:2512.06187v1 + Mitigation of Datacenter Demand Ramping and Fluctuation using Hybrid ESS and Supercapacitor + https://arxiv.org/abs/2512.08076 + arXiv:2512.08076v1 Announce Type: new +Abstract: This paper proposes a hybrid energy storage system (HESS)-based control framework that enables comprehensive power smoothing for hyperscale AI datacenters with large load variations. Datacenters impose severe ramping and fluctuation-induced stresses on the grid frequency and voltage stability. To mitigate such disturbances, the proposed HESS integrates a battery energy storage system (BESS) and a supercapacitor (SC) through coordinated multi-timescale control. A high-pass filter (HPF) separates the datacenter demand into slow and fast components, allocating them respectively to the ESS via a leaky-integral controller and to the SC via a phase-lead proportional-derivative controller enhanced with feedforward and ramp-tracking compensation. Adaptive weighting and repetitive control mechanisms further improve transient and periodic responses. Case studies verify that the proposed method effectively suppresses both ramping and fluctuations, stabilizes the system frequency, and maintains sustainable state-of-charge (SoC) trajectories for both ESS and SC under prolonged, stochastic training cycles. + oai:arXiv.org:2512.08076v1 eess.SY cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Young-ho Cho, Harsha Nagarajan, Deepjyoti Deka, Hao Zhu + Min-Seung Ko, Jae Woong Shim, Hao Zhu - Multi-Modal Zero-Shot Prediction of Color Trajectories in Food Drying - https://arxiv.org/abs/2512.06190 - arXiv:2512.06190v1 Announce Type: new -Abstract: Food drying is widely used to reduce moisture content, ensure safety, and extend shelf life. Color evolution of food samples is an important indicator of product quality in food drying. Although existing studies have examined color changes under different drying conditions, current approaches primarily rely on low-dimensional color features and cannot fully capture the complex, dynamic color trajectories of food samples. Moreover, existing modeling approaches lack the ability to generalize to unseen process conditions. To address these limitations, we develop a novel multi-modal color-trajectory prediction method that integrates high-dimensional temporal color information with drying process parameters to enable accurate and data-efficient color trajectory prediction. Under unseen drying conditions, the model attains RMSEs of 2.12 for cookie drying and 1.29 for apple drying, reducing errors by over 90% compared with baseline models. These experimental results demonstrate the model's superior accuracy, robustness, and broad applicability. - oai:arXiv.org:2512.06190v1 - cs.CV - cs.AI + Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders + https://arxiv.org/abs/2512.08077 + arXiv:2512.08077v1 Announce Type: new +Abstract: Since the advent of machine learning, interpretability has remained a persistent challenge, becoming increasingly urgent as generative models support high-stakes applications in drug and material discovery. Recent advances in large language model (LLM) architectures have yielded chemistry language models (CLMs) with impressive capabilities in molecular property prediction and molecular generation. However, how these models internally represent chemical knowledge remains poorly understood. In this work, we extend sparse autoencoder techniques to uncover and examine interpretable features within CLMs. Applying our methodology to the Foundation Models for Materials (FM4M) SMI-TED chemistry foundation model, we extract semantically meaningful latent features and analyse their activation patterns across diverse molecular datasets. Our findings reveal that these models encode a rich landscape of chemical concepts. We identify correlations between specific latent features and distinct domains of chemical knowledge, including structural motifs, physicochemical properties, and pharmacological drug classes. Our approach provides a generalisable framework for uncovering latent knowledge in chemistry-focused AI systems. This work has implications for both foundational understanding and practical deployment; with the potential to accelerate computational chemistry research. + oai:arXiv.org:2512.08077v1 cs.LG - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Jaron Cohen, Alexander G. Hasson, Sara Tanovic + + + A Comparative Study of Retrieval Methods in Azure AI Search + https://arxiv.org/abs/2512.08078 + arXiv:2512.08078v1 Announce Type: new +Abstract: Increasingly, attorneys are interested in moving beyond keyword and semantic search to improve the efficiency of how they find key information during a document review task. Large language models (LLMs) are now seen as tools that attorneys can use to ask natural language questions of their data during document review to receive accurate and concise answers. This study evaluates retrieval strategies within Microsoft Azure's Retrieval-Augmented Generation (RAG) framework to identify effective approaches for Early Case Assessment (ECA) in eDiscovery. During ECA, legal teams analyze data at the outset of a matter to gain a general understanding of the data and attempt to determine key facts and risks before beginning full-scale review. In this paper, we compare the performance of Azure AI Search's keyword, semantic, vector, hybrid, and hybrid-semantic retrieval methods. We then present the accuracy, relevance, and consistency of each method's AI-generated responses. Legal practitioners can use the results of this study to enhance how they select RAG configurations in the future. + oai:arXiv.org:2512.08078v1 + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-nc-nd/4.0/ - Shichen Li, Ahmadreza Eslaminia, Chenhui Shao + Qiang Mao, Han Qin, Robert Neary, Charles Wang, Fusheng Wei, Jianping Zhang, Nathaniel Huber-Fliflet - REWW-ARM -- Remote Wire-Driven Mobile Robot: Design, Control, and Experimental Validation - https://arxiv.org/abs/2512.06192 - arXiv:2512.06192v1 Announce Type: new -Abstract: Electronic devices are essential for robots but limit their usable environments. To overcome this, methods excluding electronics from the operating environment while retaining advanced electronic control and actuation have been explored. These include the remote hydraulic drive of electronics-free mobile robots, which offer high reachability, and long wire-driven robot arms with motors consolidated at the base, which offer high environmental resistance. To combine the advantages of both, this study proposes a new system, "Remote Wire Drive." As a proof-of-concept, we designed and developed the Remote Wire-Driven robot "REWW-ARM", which consists of the following components: 1) a novel power transmission mechanism, the "Remote Wire Transmission Mechanism" (RWTM), the key technology of the Remote Wire Drive; 2) an electronics-free distal mobile robot driven by it; and 3) a motor-unit that generates power and provides electronic closed-loop control based on state estimation via the RWTM. In this study, we evaluated the mechanical and control performance of REWW-ARM through several experiments, demonstrating its capability for locomotion, posture control, and object manipulation both on land and underwater. This suggests the potential for applying the Remote Wire-Driven system to various types of robots, thereby expanding their operational range. - oai:arXiv.org:2512.06192v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Leveraging Machine Learning and Large Language Models for Automated Image Clustering and Description in Legal Discovery + https://arxiv.org/abs/2512.08079 + arXiv:2512.08079v1 Announce Type: new +Abstract: The rapid increase in digital image creation and retention presents substantial challenges during legal discovery, digital archive, and content management. Corporations and legal teams must organize, analyze, and extract meaningful insights from large image collections under strict time pressures, making manual review impractical and costly. These demands have intensified interest in automated methods that can efficiently organize and describe large-scale image datasets. This paper presents a systematic investigation of automated cluster description generation through the integration of image clustering, image captioning, and large language models (LLMs). We apply K-means clustering to group images into 20 visually coherent clusters and generate base captions using the Azure AI Vision API. We then evaluate three critical dimensions of the cluster description process: (1) image sampling strategies, comparing random, centroid-based, stratified, hybrid, and density-based sampling against using all cluster images; (2) prompting techniques, contrasting standard prompting with chain-of-thought prompting; and (3) description generation methods, comparing LLM-based generation with traditional TF-IDF and template-based approaches. We assess description quality using semantic similarity and coverage metrics. Results show that strategic sampling with 20 images per cluster performs comparably to exhaustive inclusion while significantly reducing computational cost, with only stratified sampling showing modest degradation. LLM-based methods consistently outperform TF-IDF baselines, and standard prompts outperform chain-of-thought prompts for this task. These findings provide practical guidance for deploying scalable, accurate cluster description systems that support high-volume workflows in legal discovery and other domains requiring automated organization of large image collections. + oai:arXiv.org:2512.08079v1 + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1002/aisy.202501034 - Takahiro Hattori, Kento Kawaharazuka, Temma Suzuki, Keita Yoneda, Kei Okada + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Qiang Mao, Fusheng Wei, Robert Neary, Charles Wang, Han Qin, Jianping Zhang, Nathaniel Huber-Fliflet - Do You Feel Comfortable? Detecting Hidden Conversational Escalation in AI Chatbots - https://arxiv.org/abs/2512.06193 - arXiv:2512.06193v1 Announce Type: new -Abstract: Large Language Models (LLM) are increasingly integrated into everyday interactions, serving not only as information assistants but also as emotional companions. Even in the absence of explicit toxicity, repeated emotional reinforcement or affective drift can gradually escalate distress in a form of \textit{implicit harm} that traditional toxicity filters fail to detect. Existing guardrail mechanisms often rely on external classifiers or clinical rubrics that may lag behind the nuanced, real-time dynamics of a developing conversation. To address this gap, we propose GAUGE (Guarding Affective Utterance Generation Escalation), a lightweight, logit-based framework for the real-time detection of hidden conversational escalation. GAUGE measures how an LLM's output probabilistically shifts the affective state of a dialogue. - oai:arXiv.org:2512.06193v1 + Short-Context Dominance: How Much Local Context Natural Language Actually Needs? + https://arxiv.org/abs/2512.08082 + arXiv:2512.08082v1 Announce Type: new +Abstract: We investigate the short-context dominance hypothesis: that for most sequences, a small local prefix suffices to predict their next tokens. Using large language models as statistical oracles, we measure the minimum context length (MCL) needed to reproduce accurate full-context predictions across datasets with sequences of varying lengths. For sequences with 1-7k tokens from long-context documents, we consistently find that 75-80% require only the last 96 tokens at most. Given the dominance of short-context tokens, we then ask whether it is possible to detect challenging long-context sequences for which a short local prefix does not suffice for prediction. We introduce a practical proxy to MCL, called Distributionally Aware MCL (DaMCL), that does not require knowledge of the actual next-token and is compatible with sampling strategies beyond greedy decoding. Our experiments validate that simple thresholding of the metric defining DaMCL achieves high performance in detecting long vs. short context sequences. Finally, to counter the bias that short-context dominance induces in LLM output distributions, we develop an intuitive decoding algorithm that leverages our detector to identify and boost tokens that are long-range-relevant. Across Q&A tasks and model architectures, we confirm that mitigating the bias improves performance. + oai:arXiv.org:2512.08082v1 cs.CL cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Jihyung Park, Saleh Afroogh, Junfeng Jiao + http://creativecommons.org/licenses/by/4.0/ + Vala Vakilian, Zimeng Wang, Ankit Singh Rawat, Christos Thrampoulidis - Explainable LP-MPC: Shadow Price Contributions Reveal MV-CV Pairings - https://arxiv.org/abs/2512.06194 - arXiv:2512.06194v1 Announce Type: new -Abstract: Large industrial LP-MPC (Linear Program-Model Predictive Control) systems contain tens to hundreds of manipulated variables (MVs) and controlled variables (CVs) for honoring constraints while operating at plant-wide economic optima. The LP is a white-box model, yet for a number of reasons, abnormal behaviors in industrial controllers are often difficult to rationalize. We introduce a novel, post-hoc LP explainability method by recasting the role of shadow prices in the LP solution as an attribution mechanism for MV-CV relationships. The core idea is that CV shadow prices are not just intrinsic properties of the optimal solution, but an aggregate of the cost sensitivities contributed by MVs in enforcing CV constraints, which is then resolved into one-to-one MV-CV pairings using a linear sum assignment solution. The proposed MV-CV pairing framework serves as a practical explainability tool for online LP-MPC systems, enabling practitioners to diagnose suboptimal constraints and verify alignment of the controller's behavior with its original design intent and historical constraints. - oai:arXiv.org:2512.06194v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Exploiting the Randomness of Large Language Models (LLM) in Text Classification Tasks: Locating Privileged Documents in Legal Matters + https://arxiv.org/abs/2512.08083 + arXiv:2512.08083v1 Announce Type: new +Abstract: In legal matters, text classification models are most often used to filter through large datasets in search of documents that meet certain pre-selected criteria like relevance to a certain subject matter, such as legally privileged communications and attorney-directed documents. In this context, large language models have demonstrated strong performance. This paper presents an empirical study investigating the role of randomness in LLM-based classification for attorney-client privileged document detection, focusing on four key dimensions: (1) the effectiveness of LLMs in identifying legally privileged documents, (2) the influence of randomness control parameters on classification outputs, (3) their impact on overall classification performance, and (4) a methodology for leveraging randomness to enhance accuracy. Experimental results showed that LLMs can identify privileged documents effectively, randomness control parameters have minimal impact on classification performance, and importantly, our developed methodology for leveraging randomness can have a significant impact on improving accuracy. Notably, this methodology that leverages randomness could also enhance a corporation's confidence in an LLM's output when incorporated into its sanctions-compliance processes. As organizations increasingly rely on LLMs to augment compliance workflows, reducing output variability helps build internal and regulatory confidence in LLM-derived sanctions-screening decisions. + oai:arXiv.org:2512.08083v1 + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Lim C. Siang, Daniel L. O'Connor + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Keith Huffman, Jianping Zhang, Nathaniel Huber-Fliflet, Fusheng Wei, Peter Gronvall - ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment - https://arxiv.org/abs/2512.06196 - arXiv:2512.06196v1 Announce Type: new -Abstract: As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are interpretable so that stakeholders can understand and audit model objectives. Moreover, reward models must be capable of steering agents at interaction time, allowing preference shifts to be incorporated without retraining. We introduce ARCANE, a framework that frames alignment as a multi-agent collaboration problem that dynamically represents stakeholder preferences as natural-language rubrics: weighted sets of verifiable criteria that can be generated on-the-fly from task context. Inspired by utility theory, we formulate rubric learning as a reconstruction problem and apply a regularized Group-Sequence Policy Optimization (GSPO) procedure that balances interpretability, faithfulness, and computational efficiency. Using a corpus of 219 labeled rubrics derived from the GDPVal benchmark, we evaluate ARCANE on challenging tasks requiring multi-step reasoning and tool use. The learned rubrics produce compact, legible evaluations and enable configurable trade-offs (e.g., correctness vs. conciseness) without retraining. Our results show that rubric-based reward models offer a promising path toward interpretable, test-time adaptive alignment for complex, long-horizon AI systems. - oai:arXiv.org:2512.06196v1 - cs.AI + Adaptation of Embedding Models to Financial Filings via LLM Distillation + https://arxiv.org/abs/2512.08088 + arXiv:2512.08088v1 Announce Type: new +Abstract: Despite advances in generative large language models (LLMs), practical application of specialized conversational AI agents remains constrained by computation costs, latency requirements, and the need for precise domain-specific relevance measures. While existing embedding models address the first two constraints, they underperform on information retrieval in specialized domains like finance. This paper introduces a scalable pipeline that trains specialized models from an unlabeled corpus using a general purpose retrieval embedding model as foundation. Our method yields an average of 27.7% improvement in MRR$\texttt{@}$5, 44.6% improvement in mean DCG$\texttt{@}$5 across 14 financial filing types measured over 21,800 query-document pairs, and improved NDCG on 3 of 4 document classes in FinanceBench. We adapt retrieval embeddings (bi-encoder) for RAG, not LLM generators, using LLM-judged relevance to distill domain knowledge into a compact retriever. There are prior works which pair synthetically generated queries with real passages to directly fine-tune the retrieval model. Our pipeline differs from these by introducing interaction between student and teacher models that interleaves retrieval-based mining of hard positive/negative examples from the unlabeled corpus with iterative retraining of the student model's weights using these examples. Each retrieval iteration uses the refined student model to mine the corpus for progressively harder training examples for the subsequent training iteration. The methodology provides a cost-effective solution to bridging the gap between general-purpose models and specialized domains without requiring labor-intensive human annotation. + oai:arXiv.org:2512.08088v1 cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Charlie Masters, Marta Grze\'skiewicz, Stefano V. Albrecht + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Eliot Brenner, Dominic Seyler, Manjunath Hegde, Andrei Simion, Koustuv Dasgupta, Bing Xiang - Cascaded Tightly-Coupled Observer Design for Single-Range-Aided Inertial Navigation - https://arxiv.org/abs/2512.06198 - arXiv:2512.06198v1 Announce Type: new -Abstract: This work introduces a single-range-aided navigation observer that reconstructs the full state of a rigid body using only an Inertial Measurement Unit (IMU), a body-frame vector measurement (e.g., magnetometer), and a distance measurement from a fixed anchor point. The design first formulates an extended linear time-varying (LTV) system to estimate body-frame position, body-frame velocity, and the gravity direction. The recovered gravity direction, combined with the body-frame vector measurement, is then used to reconstruct the full orientation on $\mathrm{SO}(3)$, resulting in a cascaded observer architecture. Almost Global Asymptotic Stability (AGAS) of the cascaded design is established under a uniform observability condition, ensuring robustness to sensor noise and trajectory variations. Simulation studies on three-dimensional trajectories demonstrate accurate estimation of position, velocity, and orientation, highlighting single-range aiding as a lightweight and effective modality for autonomous navigation. - oai:arXiv.org:2512.06198v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + NysX: An Accurate and Energy-Efficient FPGA Accelerator for Hyperdimensional Graph Classification at the Edge + https://arxiv.org/abs/2512.08089 + arXiv:2512.08089v1 Announce Type: new +Abstract: Real-time, energy-efficient inference on edge devices is essential for graph classification across a range of applications. Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm that encodes input features into low-precision, high-dimensional vectors with simple element-wise operations, making it well-suited for resource-constrained edge platforms. Recent work enhances HDC accuracy for graph classification via Nystr\"om kernel approximations. Edge acceleration of such methods faces several challenges: (i) redundancy among (landmark) samples selected via uniform sampling, (ii) storing the Nystr\"om projection matrix under limited on-chip memory, (iii) expensive, contention-prone codebook lookups, and (iv) load imbalance due to irregular sparsity in SpMV. To address these challenges, we propose NysX, the first end-to-end FPGA accelerator for Nystr\"om-based HDC graph classification at the edge. NysX integrates four key optimizations: (i) a hybrid landmark selection strategy combining uniform sampling with determinantal point processes (DPPs) to reduce redundancy while improving accuracy; (ii) a streaming architecture for Nystr\"om projection matrix maximizing external memory bandwidth utilization; (iii) a minimal-perfect-hash lookup engine enabling $O(1)$ key-to-index mapping with low on-chip memory overhead; and (iv) sparsity-aware SpMV engines with static load balancing. Together, these innovations enable real-time, energy-efficient inference on resource-constrained platforms. Implemented on an AMD Zynq UltraScale+ (ZCU104) FPGA, NysX achieves $6.85\times$ ($4.32\times$) speedup and $169\times$ ($314\times$) energy efficiency gains over optimized CPU (GPU) baselines, while improving classification accuracy by $3.4\%$ on average across TUDataset benchmarks, a widely used standard for graph classification. + oai:arXiv.org:2512.08089v1 + cs.AR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Oussama Sifour, Soulaimane Berkane, Abdelhamid Tayebi + Jebacyril Arockiaraj, Dhruv Parikh, Viktor Prasanna - How Should We Evaluate Data Deletion in Graph-Based ANN Indexes? - https://arxiv.org/abs/2512.06200 - arXiv:2512.06200v1 Announce Type: new -Abstract: Approximate Nearest Neighbor Search (ANNS) has recently gained significant attention due to its many applications, such as Retrieval-Augmented Generation. Such applications require ANNS algorithms that support dynamic data, so the ANNS problem on dynamic data has attracted considerable interest. However, a comprehensive evaluation methodology for data deletion in ANNS has yet to be established. This study proposes an experimental framework and comprehensive evaluation metrics to assess the efficiency of data deletion for ANNS indexes under practical use cases. Specifically, we categorize data deletion methods in graph-based ANNS into three approaches and formalize them mathematically. The performance is assessed in terms of accuracy, query speed, and other relevant metrics. Finally, we apply the proposed evaluation framework to Hierarchical Navigable Small World, one of the state-of-the-art ANNS methods, to analyze the effects of data deletion, and propose Deletion Control, a method which dynamically selects the appropriate deletion method under a required search accuracy. - oai:arXiv.org:2512.06200v1 + Complexity of One-Dimensional ReLU DNNs + https://arxiv.org/abs/2512.08091 + arXiv:2512.08091v1 Announce Type: new +Abstract: We study the expressivity of one-dimensional (1D) ReLU deep neural networks through the lens of their linear regions. For randomly initialized, fully connected 1D ReLU networks (He scaling with nonzero bias) in the infinite-width limit, we prove that the expected number of linear regions grows as $\sum_{i = 1}^L n_i + \mathop{{o}}\left(\sum_{i = 1}^L{n_i}\right) + 1$, where $n_\ell$ denotes the number of neurons in the $\ell$-th hidden layer. We also propose a function-adaptive notion of sparsity that compares the expected regions used by the network to the minimal number needed to approximate a target within a fixed tolerance. + oai:arXiv.org:2512.08091v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tomohiro Yamashita, Daichi Amagata, Yusuke Matsui + Jonathan Kogan, Hayden Jananthan, Jeremy Kepner - K2-V2: A 360-Open, Reasoning-Enhanced LLM - https://arxiv.org/abs/2512.06201 - arXiv:2512.06201v1 Announce Type: new -Abstract: We introduce K2-V2, a 360-open LLM built from scratch as a superior base for reasoning adaptation, in addition to functions such as conversation and knowledge retrieval from general LLMs. It stands as the strongest fully open model, rivals open-weight leaders in its size class, outperforms Qwen2.5-72B and approaches the performance of Qwen3-235B. We actively infuse domain knowledge, reasoning, long-context, and tool use throughout the training process. This explicitly prepares the model for complex reasoning tasks. We demonstrate this potential using simple supervised fine-tuning, establishing a strong baseline that indicates significant headroom for advanced alignment. By releasing the full training history and data composition, we maximize the effectiveness of continuous training, a key open source production scenario. We release the model weights and signature LLM360 artifacts, such as complete training data, to empower the community with a capable, reasoning-centric foundation. - oai:arXiv.org:2512.06201v1 + Training LLMs for Honesty via Confessions + https://arxiv.org/abs/2512.08093 + arXiv:2512.08093v1 Announce Type: new +Abstract: Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the effects of reinforcement learning (RL), where challenges with reward shaping can result in a training process that inadvertently incentivizes the model to lie or misrepresent its actions. + In this work we propose a method for eliciting an honest expression of an LLM's shortcomings via a self-reported *confession*. A confession is an output, provided upon request after a model's original answer, that is meant to serve as a full account of the model's compliance with the letter and spirit of its policies and instructions. The reward assigned to a confession during training is solely based on its honesty, and does not impact positively or negatively the main answer's reward. As long as the "path of least resistance" for maximizing confession reward is to surface misbehavior rather than covering it up, this incentivizes models to be honest in their confessions. Our findings provide some justification this empirical assumption, especially in the case of egregious model misbehavior. + To demonstrate the viability of our approach, we train GPT-5-Thinking to produce confessions, and we evaluate its honesty in out-of-distribution scenarios measuring hallucination, instruction following, scheming, and reward hacking. We find that when the model lies or omits shortcomings in its "main" answer, it often confesses to these behaviors honestly, and this confession honesty modestly improves with training. Confessions can enable a number of inference-time interventions including monitoring, rejection sampling, and surfacing issues to the user. + oai:arXiv.org:2512.08093v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Manas Joglekar, Jeremy Chen, Gabriel Wu, Jason Yosinski, Jasmine Wang, Boaz Barak, Amelia Glaese + + + Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing + https://arxiv.org/abs/2512.08094 + arXiv:2512.08094v1 Announce Type: new +Abstract: The goal of this work is to develop a universal approach for aligning subtitles (i.e., spoken language text with corresponding timestamps) to continuous sign language videos. Prior approaches typically rely on end-to-end training tied to a specific language or dataset, which limits their generality. In contrast, our method Segment, Embed, and Align (SEA) provides a single framework that works across multiple languages and domains. SEA leverages two pretrained models: the first to segment a video frame sequence into individual signs and the second to embed the video clip of each sign into a shared latent space with text. Alignment is subsequently performed with a lightweight dynamic programming procedure that runs efficiently on CPUs within a minute, even for hour-long episodes. SEA is flexible and can adapt to a wide range of scenarios, utilizing resources from small lexicons to large continuous corpora. Experiments on four sign language datasets demonstrate state-of-the-art alignment performance, highlighting the potential of SEA to generate high-quality parallel data for advancing sign language processing. SEA's code and models are openly available. + oai:arXiv.org:2512.08094v1 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - K2 Team, Zhengzhong Liu, Liping Tang, Linghao Jin, Haonan Li, Nikhil Ranjan, Desai Fan, Shaurya Rohatgi, Richard Fan, Omkar Pangarkar, Huijuan Wang, Zhoujun Cheng, Suqi Sun, Seungwook Han, Bowen Tan, Gurpreet Gosal, Xudong Han, Varad Pimpalkhute, Shibo Hao, Ming Shan Hee, Joel Hestness, Haolong Jia, Liqun Ma, Aaryamonvikram Singh, Daria Soboleva, Natalia Vassilieva, Renxi Wang, Yingquan Wu, Yuekai Sun, Taylor Killian, Alexander Moreno, John Maggs, Hector Ren, Guowei He, Hongyi Wang, Xuezhe Ma, Yuqi Wang, Mikhail Yurochkin, Eric P. Xing + Zifan Jiang, Youngjoon Jang, Liliane Momeni, G\"ul Varol, Sarah Ebling, Andrew Zisserman - Formal State-Machine Models for Uniswap v3 Concentrated-Liquidity AMMs: Priced Timed Automata, Finite-State Transducers, and Provable Rounding Bounds - https://arxiv.org/abs/2512.06203 - arXiv:2512.06203v1 Announce Type: new -Abstract: Concentrated-liquidity automated market makers (CLAMMs), as exemplified by Uniswap v3, are now a common primitive in decentralized finance frameworks. Their design combines continuous trading on constant-function curves with discrete tick boundaries at which liquidity positions change and rounding effects accumulate. While there is a body of economic and game-theoretic analysis of CLAMMs, there is negligible work that treats Uniswap v3 at the level of formal state machines amenable to model checking or theorem proving. - In this paper we propose a formal modeling approach for Uniswap v3-style CLAMMs using (i) networks of priced timed automata (PTA), and (ii) finite-state transducers (FST) over discrete ticks. Positions are treated as stateful objects that transition only when the pool price crosses the ticks that bound their active range. We show how to encode the piecewise constant-product invariant, fee-growth variables, and tick-crossing rules in a PTA suitable for tools such as UPPAAL, and how to derive a tick-level FST abstraction for specification in TLA+. - We define an explicit tick-wise invariant for a discretized, single-tick CLAMM model and prove that it is preserved up to a tight additive rounding bound under fee-free swaps. This provides a formal justification for the "$\epsilon$-slack" used in invariance properties and shows how rounding enters as a controlled perturbation. We then instantiate these models in TLA+ and use TLC to exhaustively check the resulting invariants on structurally faithful instances, including a three-tick concentrated-liquidity configuration and a bounded no-rounding-only-arbitrage property in a bidirectional single-tick model. We discuss how these constructions lift to the tick-wise structure of Uniswap v3 via virtual reserves, and how the resulting properties can be phrased as PTA/TLA+ invariants about cross-tick behaviour and rounding safety. - oai:arXiv.org:2512.06203v1 - cs.LO - q-fin.MF - Tue, 09 Dec 2025 00:00:00 -0500 + Selling Privacy in Blockchain Transactions + https://arxiv.org/abs/2512.08096 + arXiv:2512.08096v1 Announce Type: new +Abstract: We study methods to enhance privacy in blockchain transactions from an economic angle. We consider mechanisms for privacy-aware users whose utility depends not only on the outcome of the mechanism but also negatively on the exposure of their economic preferences. Specifically, we study two auction-theoretic settings with privacy-aware users. First, we analyze an order flow auction, where a user auctions off to specialized agents, called searchers, the right to execute her transaction while maintaining a degree of privacy. We examine how the degree of privacy affects the revenue of the auction and, broadly, the net utility of the privacy-aware user. In this new setting, we describe the optimal auction, which is a sealed-bid auction. Subsequently, we analyze a variant of a Dutch auction in which the user gradually decreases the price and the degree of privacy until the transaction is sold. We compare the revenue of this auction to that of the optimal one as a function of the number of communication rounds. Then, we introduce a two-sided market - a privacy marketplace - with multiple users selling their transactions under their privacy preferences to multiple searchers. We propose a posted-price mechanism for the two-sided market that guarantees constant approximation of the optimal social welfare while maintaining incentive compatibility (from both sides of the market) and budget balance. This work builds on the emerging line of research that attempts to improve the performance of economic mechanisms by appending cryptographic primitives to them. + oai:arXiv.org:2512.08096v1 + cs.GT + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Julius Tranquilli, Naman Gupta + Georgios Chionas, Olga Gorelkina, Piotr Krysta, Rida Laraki - Quantifying Memory Use in Reinforcement Learning with Temporal Range - https://arxiv.org/abs/2512.06204 - arXiv:2512.06204v1 Announce Type: new -Abstract: How much does a trained RL policy actually use its past observations? We propose \emph{Temporal Range}, a model-agnostic metric that treats first-order sensitivities of multiple vector outputs across a temporal window to the input sequence as a temporal influence profile and summarizes it by the magnitude-weighted average lag. Temporal Range is computed via reverse-mode automatic differentiation from the Jacobian blocks $\partial y_s/\partial x_t\in\mathbb{R}^{c\times d}$ averaged over final timesteps $s\in\{t+1,\dots,T\}$ and is well-characterized in the linear setting by a small set of natural axioms. Across diagnostic and control tasks (POPGym; flicker/occlusion; Copy-$k$) and architectures (MLPs, RNNs, SSMs), Temporal Range (i) remains small in fully observed control, (ii) scales with the task's ground-truth lag in Copy-$k$, and (iii) aligns with the minimum history window required for near-optimal return as confirmed by window ablations. We also report Temporal Range for a compact Long Expressive Memory (LEM) policy trained on the task, using it as a proxy readout of task-level memory. Our axiomatic treatment draws on recent work on range measures, specialized here to temporal lag and extended to vector-valued outputs in the RL setting. Temporal Range thus offers a practical per-sequence readout of memory dependence for comparing agents and environments and for selecting the shortest sufficient context. - oai:arXiv.org:2512.06204v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Generalizations of the Normalized Radon Cumulative Distribution Transform for Limited Data Recognition + https://arxiv.org/abs/2512.08099 + arXiv:2512.08099v1 Announce Type: new +Abstract: The Radon cumulative distribution transform (R-CDT) exploits one-dimensional Wasserstein transport and the Radon transform to represent prominent features in images. It is closely related to the sliced Wasserstein distance and facilitates classification tasks, especially in the small data regime, like the recognition of watermarks in filigranology. Here, a typical issue is that the given data may be subject to affine transformations caused by the measuring process. To make the R-CDT invariant under arbitrary affine transformations, a two-step normalization of the R-CDT has been proposed in our earlier works. The aim of this paper is twofold. First, we propose a family of generalized normalizations to enhance flexibility for applications. Second, we study multi-dimensional and non-Euclidean settings by making use of generalized Radon transforms. We prove that our novel feature representations are invariant under certain transformations and allow for linear separation in feature space. Our theoretical results are supported by numerical experiments based on 2d images, 3d shapes and 3d rotation matrices, showing near perfect classification accuracies and clustering results. + oai:arXiv.org:2512.08099v1 + math.NA + cs.CV + cs.IT + cs.NA + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Rodney Lafuente-Mercado, Daniela Rus, T. Konstantin Rusch + Matthias Beckmann, Robert Beinert, Jonas Bresch - On measuring grounding and generalizing grounding problems - https://arxiv.org/abs/2512.06205 - arXiv:2512.06205v1 Announce Type: new -Abstract: The symbol grounding problem asks how tokens like cat can be about cats, as opposed to mere shapes manipulated in a calculus. We recast grounding from a binary judgment into an audit across desiderata, each indexed by an evaluation tuple (context, meaning type, threat model, reference distribution): authenticity (mechanisms reside inside the agent and, for strong claims, were acquired through learning or evolution); preservation (atomic meanings remain intact); faithfulness, both correlational (realized meanings match intended ones) and etiological (internal mechanisms causally contribute to success); robustness (graceful degradation under declared perturbations); compositionality (the whole is built systematically from the parts). We apply this framework to four grounding modes (symbolic; referential; vectorial; relational) and three case studies: model-theoretic semantics achieves exact composition but lacks etiological warrant; large language models show correlational fit and local robustness for linguistic tasks, yet lack selection-for-success on world tasks without grounded interaction; human language meets the desiderata under strong authenticity through evolutionary and developmental acquisition. By operationalizing a philosophical inquiry about representation, we equip philosophers of science, computer scientists, linguists, and mathematicians with a common language and technical framework for systematic investigation of grounding and meaning. - oai:arXiv.org:2512.06205v1 - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Broadband Thermoelectric Energy Harvesting for Wearable Biosensors Using Plasmonic Field-Enhancement and Machine-Learning-Guided Device Optimization + https://arxiv.org/abs/2512.08103 + arXiv:2512.08103v1 Announce Type: new +Abstract: Wearable biosensors increasingly require continuous and battery-free power sources, but conventional skin-mounted thermoelectric generators are limited by the small temperature differences available in real environments. This work introduces a hybrid thermoplasmonic and thermoelectric energy harvester that combines multiband plasmonic absorption with machine-learning-guided optimization to improve on-body energy conversion. A broadband metasurface made of cross-bowtie nanoantennas is designed to absorb infrared radiation across the 2 to 12 micron range, capturing human body emission, ambient infrared radiation, and near-infrared sunlight. Electromagnetic simulations show strong field enhancement in nanoscale antenna gaps, producing localized thermoplasmonic heating directly above flexible Bi2Te3 thermoelectric junctions. Coupled optical, thermal, and electrical modeling indicates that this localized heating increases the effective temperature difference from the typical 3 to 4 degrees C of standard wearable thermoelectric generators to approximately 13 degrees C. This results in a power density of about 0.15 mW per cm^2 under indoor-relevant infrared flux, representing a four- to six-fold improvement over existing flexible devices. A machine-learning surrogate model trained on multiphysics data predicts temperature rise and electrical output with high accuracy (R2 greater than 0.92) and identifies optimal device geometries through Pareto-front analysis. The proposed hybrid thermoplasmonic, thermoelectric, and machine-learning framework provides a scalable route toward more efficient, compact, and flexible energy harvesters for autonomous and long-term wearable physiological monitoring. + oai:arXiv.org:2512.08103v1 + cs.CE + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Daniel Quigley, Eric Maynard + Hamidreza Moradi, Melika Filvantorkaman - The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning - https://arxiv.org/abs/2512.06206 - arXiv:2512.06206v1 Announce Type: new -Abstract: We present the design and results of the MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024, which focuses on federated learning (FL) for glioma sub-region segmentation in multi-parametric MRI and evaluates new weight aggregation methods aimed at improving robustness and efficiency. Six participating teams were evaluated using a standardized FL setup and a multi-institutional dataset derived from the BraTS glioma benchmark, consisting of 1,251 training cases, 219 validation cases, and 570 hidden test cases with segmentations for enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Teams were ranked using a cumulative scoring system that considered both segmentation performance, measured by Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95), and communication efficiency assessed through the convergence score. A PID-controller-based method achieved the top overall ranking, obtaining mean DSC values of 0.733, 0.761, and 0.751 for ET, TC, and WT, respectively, with corresponding HD95 values of 33.922 mm, 33.623 mm, and 32.309 mm, while also demonstrating the highest communication efficiency with a convergence score of 0.764. These findings advance the state of federated learning for medical imaging, surpassing top-performing methods from previous challenge iterations and highlighting PID controllers as effective mechanisms for stabilizing and optimizing weight aggregation in FL. The challenge code is available at https://github.com/FeTS-AI/Challenge. - oai:arXiv.org:2512.06206v1 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration + https://arxiv.org/abs/2512.08104 + arXiv:2512.08104v1 Announce Type: new +Abstract: As AI agents increasingly operate in real-world, multi-agent environments, ensuring reliable and context-aware privacy in agent communication is critical, especially to comply with evolving regulatory requirements. Traditional access controls are insufficient, as privacy risks often arise after access is granted; agents may use information in ways that compromise privacy, such as messaging humans, sharing context with other agents, making tool calls, persisting data, or generating derived private information. Existing approaches often treat privacy as a binary constraint, whether data is shareable or not, overlooking nuanced, role-specific, and computation-dependent privacy needs essential for regulatory compliance. + Agents, including those based on large language models, are inherently probabilistic and heuristic. There is no formal guarantee of how an agent will behave for any query, making them ill-suited for operations critical to security. To address this, we introduce AgentCrypt, a four-tiered framework for fine-grained, encrypted agent communication that adds a protection layer atop any AI agent platform. AgentCrypt spans unrestricted data exchange (Level 1) to fully encrypted computation using techniques such as homomorphic encryption (Level 4). Crucially, it guarantees the privacy of tagged data is always maintained, prioritizing privacy above correctness. + AgentCrypt ensures privacy across diverse interactions and enables computation on otherwise inaccessible data, overcoming barriers such as data silos. We implemented and tested it with Langgraph and Google ADK, demonstrating versatility across platforms. We also introduce a benchmark dataset simulating privacy-critical tasks at all privacy levels, enabling systematic evaluation and fostering the development of regulatable machine learning systems for secure agent communication and computation. + oai:arXiv.org:2512.08104v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.59275/j.melba.2025-5242 - Machine.Learning.for.Biomedical.Imaging. 3 (2025) - Akis Linardos, Sarthak Pati, Ujjwal Baid, Brandon Edwards, Patrick Foley, Kevin Ta, Verena Chung, Micah Sheller, Muhammad Irfan Khan, Mojtaba Jafaritadi, Elina Kontio, Suleiman Khan, Leon M\"achler, Ivan Ezhov, Suprosanna Shit, Johannes C. Paetzold, Gustav Grimberg, Manuel A. Nickel, David Naccache, Vasilis Siomos, Jonathan Passerat-Palmbach, Giacomo Tarroni, Daewoon Kim, Leonard L. Klausmann, Prashant Shah, Bjoern Menze, Dimitrios Makris, Spyridon Bakas + Harish Karthikeyan, Yue Guo, Leo de Castro, Antigoni Polychroniadou, Leo Ardon, Udari Madhushani Sehwag, Sumitra Ganesh, Manuela Veloso - Where to Fly, What to Send: Communication-Aware Aerial Support for Ground Robots - https://arxiv.org/abs/2512.06207 - arXiv:2512.06207v1 Announce Type: new -Abstract: In this work we consider a multi-robot team operating in an unknown environment where one aerial agent is tasked to map the environment and transmit (a portion of) the mapped environment to a group of ground agents that are trying to reach their goals. The entire operation takes place over a bandwidth-limited communication channel, which motivates the problem of determining what and how much information the assisting agent should transmit and when while simultaneously performing exploration/mapping. The proposed framework enables the assisting aerial agent to decide what information to transmit based on the Value-of-Information (VoI), how much to transmit using a Mixed-Integer Linear Programming (MILP), and how to acquire additional information through an utility score-based environment exploration strategy. We perform a communication-motion trade-off analysis between the total amount of map data communicated by the aerial agent and the navigation cost incurred by the ground agents. - oai:arXiv.org:2512.06207v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Beyond Revenue and Welfare: Counterfactual Analysis of Spectrum Auctions with Application to Canada's 3800MHz Allocation + https://arxiv.org/abs/2512.08106 + arXiv:2512.08106v1 Announce Type: new +Abstract: Spectrum auctions are the primary mechanism through which governments allocate scarce radio frequencies, with outcomes that shape competition, coverage, and innovation in telecommunications markets. While traditional models of spectrum auctions often rely on strong equilibrium assumptions, we take a more parsimonious approach by modeling bidders as myopic and straightforward: in each round, firms simply demand the bundle that maximizes their utility given current prices. Despite its simplicity, this model proves effective in predicting the outcomes of Canada's 2023 auction of 3800 MHz spectrum licenses. Using detailed round-by-round bidding data, we estimate bidders' valuations through a linear programming framework and validate that our model reproduces key features of the observed allocation and price evolution. We then use these estimated valuations to simulate a counterfactual auction under an alternative mechanism that incentivizes deployment in rural and remote regions, aligning with one of the key objectives set out in the Canadian Telecommunications Act. The results show that the proposed mechanism substantially improves population coverage in underserved areas. These findings demonstrate that a behavioral model with minimal assumptions is sufficient to generate reliable counterfactual predictions, making it a practical tool for policymakers to evaluate how alternative auction designs may influence future outcomes. In particular, our study demonstrates a method for counterfactual mechanism design, providing a framework to evaluate how alternative auction rules could advance policy goals such as equitable deployment across Canada. + oai:arXiv.org:2512.08106v1 + cs.GT + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Harshil Suthar, Dipankar Maity + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Sara Jalili Shani, Kris Joseph, Michael B. McNally, James R. Wright - SparsePixels: Efficient Convolution for Sparse Data on FPGAs - https://arxiv.org/abs/2512.06208 - arXiv:2512.06208v1 Announce Type: new -Abstract: Inference of standard CNNs on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value, especially when the image size is large. However, in some image data, input features can be spatially sparse, and semantic information may occupy only a small fraction of the input pixels. In this case most computation would be wasted on empty regions. In this work, we introduce SparsePixels, a framework for efficient convolution for spatially sparse image data on FPGAs, targeting fast inference applications in constrained environments with latency requirements of microseconds or below. Our approach implements a special class of CNNs that selectively retain and compute on a small subset of pixels that are active while ignoring the rest. We show that, for example, in a neutrino physics dataset for identifying neutrino interactions in LArTPC images that have around 4k input pixels but are naturally very sparse, a standard CNN with a compact size of 4k parameters incurs an inference latency of 48.665 $\mu$s on an FPGA, whereas a sparse CNN of the same base architecture computing on less than 1% of the input pixels results in a $\times 73$ inference speedup to 0.665 $\mu$s, with resource utilization well within on-chip budgets, trading only a small percent-level performance loss. At least one-order-of magnitude speedups with comparable performance are also demonstrated in similar datasets with sparse image patterns. This work aims to benefit future algorithm developments for fast and efficient data readout in modern experiments such as the trigger and data acquisition systems at the CERN Large Hadron Collider. For easy adoption, we have developed a library to support building sparse CNNs with quantization-aware training, as well as an HLS implementation for FPGA deployment. - oai:arXiv.org:2512.06208v1 - cs.AR + Detecting Ambiguity Aversion in Cyberattack Behavior to Inform Cognitive Defense Strategies + https://arxiv.org/abs/2512.08107 + arXiv:2512.08107v1 Announce Type: new +Abstract: Adversaries (hackers) attempting to infiltrate networks frequently face uncertainty in their operational environments. This research explores the ability to model and detect when they exhibit ambiguity aversion, a cognitive bias reflecting a preference for known (versus unknown) probabilities. We introduce a novel methodological framework that (1) leverages rich, multi-modal data from human-subjects red-team experiments, (2) employs a large language model (LLM) pipeline to parse unstructured logs into MITRE ATT&CK-mapped action sequences, and (3) applies a new computational model to infer an attacker's ambiguity aversion level in near-real time. By operationalizing this cognitive trait, our work provides a foundational component for developing adaptive cognitive defense strategies. + oai:arXiv.org:2512.08107v1 + cs.CR + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Stephan Carney, Soham Hans, Sofia Hirschmann, Stacey Marsella, Yvonne Fonken, Peggy Wu, Nikolos Gurney + + + Scalable Offline Model-Based RL with Action Chunks + https://arxiv.org/abs/2512.08108 + arXiv:2512.08108v1 Announce Type: new +Abstract: In this paper, we study whether model-based reinforcement learning (RL), in particular model-based value expansion, can provide a scalable recipe for tackling complex, long-horizon tasks in offline RL. Model-based value expansion fits an on-policy value function using length-n imaginary rollouts generated by the current policy and a learned dynamics model. While larger n reduces bias in value bootstrapping, it amplifies accumulated model errors over long horizons, degrading future predictions. We address this trade-off with an \emph{action-chunk} model that predicts a future state from a sequence of actions (an "action chunk") instead of a single action, which reduces compounding errors. In addition, instead of directly training a policy to maximize rewards, we employ rejection sampling from an expressive behavioral action-chunk policy, which prevents model exploitation from out-of-distribution actions. We call this recipe \textbf{Model-Based RL with Action Chunks (MAC)}. Through experiments on highly challenging tasks with large-scale datasets of up to 100M transitions, we show that MAC achieves the best performance among offline model-based RL algorithms, especially on challenging long-horizon tasks. + oai:arXiv.org:2512.08108v1 cs.LG - hep-ex - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ho Fung Tsoi, Dylan Rankin, Vladimir Loncar, Philip Harris + Kwanyoung Park, Seohong Park, Youngwoon Lee, Sergey Levine - A Broader View on Clustering under Cluster-Aware Norm Objectives - https://arxiv.org/abs/2512.06211 - arXiv:2512.06211v1 Announce Type: new -Abstract: We revisit the $(f,g)$-clustering problem that we introduced in a recent work [SODA'25], and which subsumes fundamental clustering problems such as $k$-Center, $k$-Median, Min-Sum of Radii, and Min-Load $k$-Clustering. This problem assigns each of the $k$ clusters a cost determined by the monotone, symmetric norm $f$ applied to the vector distances in the cluster, and aims at minimizing the norm $g$ applied to the vector of cluster costs. Previously, we focused on certain special cases for which we designed constant-factor approximation algorithms. Our bounds for more general settings left, however, large gaps to the known bounds for the basic problems they capture. - In this work, we provide a clearer picture of the approximability of these more general settings. First, we design an $O(\log^2 n)$-approximation algorithm for $(f, L_{1})$-clustering for any $f$. This improves upon our previous $\widetilde{O}(\sqrt{n})$-approximation. Second, we provide an $O(k)$-approximation for the general $(f,g)$-clustering problem, which improves upon our previous $\widetilde{O}(\sqrt{kn})$-approximation algorithm and matches the best-known upper bound for Min-Load $k$-Clustering. - We then design an approximation algorithm for $(f,g)$-clustering that interpolates, up to polylog factors, between the best known bounds for $k$-Center, $k$-Median, Min-Sum of Radii, Min-Load $k$-Clustering, (Top, $L_{1}$)-clustering, and $(L_{\infty},g)$-clustering based on a newly defined parameter of $f$ and $g$. - oai:arXiv.org:2512.06211v1 + The Bichromatic Two-Center Problem on Graphs + https://arxiv.org/abs/2512.08111 + arXiv:2512.08111v1 Announce Type: new +Abstract: In this paper, we study the (weighted) bichromatic two-center problem on graphs. The input consists of a graph $G$ of $n$ (weighted) vertices and $m$ edges, and a set $\mathcal{P}$ of pairs of distinct vertices, where no vertex appears in more than one pair. The problem aims to find two points (i.e., centers) on $G$ by assigning vertices of each pair to different centers so as to minimize the maximum (weighted) distance of vertices to their assigned centers (so that the graph can be bi-colored with this goal). To the best of our knowledge, this problem has not been studied on graphs, including tree graphs. In this paper, we propose an $O(m^2n\log n\log mn)$ algorithm for solving the problem on an undirected graph provided with the distance matrix, an $O(n\log n)$-time algorithm for the problem on trees, and a linear-time approach for the unweighted tree version. + oai:arXiv.org:2512.08111v1 cs.DS - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Martin G. Herold, Evangelos Kipouridis, Joachim Spoerhase + Qi Sun, Jingru Zhang - Average-reward reinforcement learning in semi-Markov decision processes via relative value iteration - https://arxiv.org/abs/2512.06218 - arXiv:2512.06218v1 Announce Type: new -Abstract: This paper applies the authors' recent results on asynchronous stochastic approximation (SA) in the Borkar-Meyn framework to reinforcement learning in average-reward semi-Markov decision processes (SMDPs). We establish the convergence of an asynchronous SA analogue of Schweitzer's classical relative value iteration algorithm, RVI Q-learning, for finite-space, weakly communicating SMDPs. In particular, we show that the algorithm converges almost surely to a compact, connected subset of solutions to the average-reward optimality equation, with convergence to a unique, sample path-dependent solution under additional stepsize and asynchrony conditions. Moreover, to make full use of the SA framework, we introduce new monotonicity conditions for estimating the optimal reward rate in RVI Q-learning. These conditions substantially expand the previously considered algorithmic framework and are addressed through novel arguments in the stability and convergence analysis of RVI Q-learning. - oai:arXiv.org:2512.06218v1 + Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden's J statistic + https://arxiv.org/abs/2512.08121 + arXiv:2512.08121v1 Announce Type: new +Abstract: Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier, either an LLM-as-a-judge or human annotators, making the choice of classifier central to trustworthy evaluation. Common metrics used for this choice, such as Accuracy, Precision, and F1, are sensitive to class imbalance and to arbitrary choices of positive class, and can favor judges that distort prevalence estimates. We show that Youden's $J$ statistic is theoretically aligned with choosing the best judge to compare models, and that Balanced Accuracy is an equivalent linear transformation of $J$. Through both analytical arguments and empirical examples and simulations, we demonstrate how selecting judges using Balanced Accuracy leads to better, more robust classifier selection. + oai:arXiv.org:2512.08121v1 cs.LG - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Huizhen Yu, Yi Wan, Richard S. Sutton + Stephane Collot, Colin Fraser, Justin Zhao, William F. Shen, Timon Willi, Ilias Leontiadis - Revisiting SVD and Wavelet Difference Reduction for Lossy Image Compression: A Reproducibility Study - https://arxiv.org/abs/2512.06221 - arXiv:2512.06221v1 Announce Type: new -Abstract: This work presents an independent reproducibility study of a lossy image compression technique that integrates singular value decomposition (SVD) and wavelet difference reduction (WDR). The original paper claims that combining SVD and WDR yields better visual quality and higher compression ratios than JPEG2000 and standalone WDR. I re-implemented the proposed method, carefully examined missing implementation details, and replicated the original experiments as closely as possible. I then conducted additional experiments on new images and evaluated performance using PSNR and SSIM. In contrast to the original claims, my results indicate that the SVD+WDR technique generally does not surpass JPEG2000 or WDR in terms of PSNR, and only partially improves SSIM relative to JPEG2000. The study highlights ambiguities in the original description (e.g., quantization and threshold initialization) and illustrates how such gaps can significantly impact reproducibility and reported performance. - oai:arXiv.org:2512.06221v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Evolutionary perspective of large language models on shaping research insights into healthcare disparities + https://arxiv.org/abs/2512.08122 + arXiv:2512.08122v1 Announce Type: new +Abstract: Introduction. Advances in large language models (LLMs) offer a chance to act as scientific assistants, helping people grasp complex research areas. This study examines how LLMs evolve in healthcare disparities research, with attention to public access to relevant information. Methods. We studied three well-known LLMs: ChatGPT, Copilot, and Gemini. Each week, we asked them a consistent prompt about research themes in healthcare disparities and tracked how their answers changed over a one-month period. Analysis. The themes produced by the LLMs were categorized and cross-checked against H-index values from the Web of Science to verify relevance. This dual approach shows how the outputs of LLMs develop over time and how such progress could help researchers navigate trends. Results. The outputs aligned with actual scientific impact and trends in the field, indicating that LLMs can help people understand the healthcare disparities landscape. Time-series comparisons showed differences among the models in how broadly and deeply they identified and classified themes. Conclusion. The study offers a framework that uses the evolution of multiple LLMs to illuminate AI tools for studying healthcare disparities, informing future research and public engagement strategies. + oai:arXiv.org:2512.08122v1 + cs.CY + cs.SI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alena Makarova + David An - Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety - https://arxiv.org/abs/2512.06227 - arXiv:2512.06227v1 Announce Type: new -Abstract: Real-world indicators are important for improving natural language processing (NLP) tasks such as life events for mental health analysis and risky behaviour for online safety, yet labelling such information in NLP training datasets is often costly and/or difficult given the dynamic nature of such events. This paper compares several LLM-based data enrichment methods and introduces a novel Confidence-Aware Fine-Grained Debate (CFD) framework in which multiple LLM agents simulate human annotators and exchange fine-grained evidence to reach consensus. We describe two new expert-annotated datasets, a mental health Reddit wellbeing dataset and an online safety Facebook sharenting risk dataset. Our CFD framework achieves the most robust data enrichment performance compared to a range of baselines and we show that this type of data enrichment consistently improves downstream tasks. Enriched features incorporated via debate transcripts yield the largest gains, outperforming the non-enriched baseline by 10.1% for the online safety task. - oai:arXiv.org:2512.06227v1 + Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation + https://arxiv.org/abs/2512.08123 + arXiv:2512.08123v1 Announce Type: new +Abstract: Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to compare and limiting transferability. We study universal adversarial suffixes: short token sequences (4-10 tokens) that, when appended to any input, broadly reduce accuracy across tasks and models. Our approach learns the suffix in a differentiable "soft" form using Gumbel-Softmax relaxation and then discretizes it for inference. Training maximizes calibrated cross-entropy on the label region while masking gold tokens to prevent trivial leakage, with entropy regularization to avoid collapse. A single suffix trained on one model transfers effectively to others, consistently lowering both accuracy and calibrated confidence. Experiments on sentiment analysis, natural language inference, paraphrase detection, commonsense QA, and physical reasoning with Qwen2-1.5B, Phi-1.5, and TinyLlama-1.1B demonstrate consistent attack effectiveness and transfer across tasks and model families. + oai:arXiv.org:2512.08123v1 cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junyu Mao, Anthony Hills, Talia Tseriotou, Maria Liakata, Aya Shamir, Dan Sayda, Dana Atzil-Slonim, Natalie Djohari, Arpan Mandal, Silke Roth, Pamela Ugwudike, Mahesan Niranjan, Stuart E. Middleton + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Sampriti Soor, Suklav Ghosh, Arijit Sur - Policy-based Sentence Simplification: Replacing Parallel Corpora with LLM-as-a-Judge - https://arxiv.org/abs/2512.06228 - arXiv:2512.06228v1 Announce Type: new -Abstract: Sentence simplification aims to modify a sentence to make it easier to read and understand while preserving the meaning. Different applications require distinct simplification policies, such as replacing only complex words at the lexical level or rewriting the entire sentence while trading off details for simplicity. However, achieving such policy-driven control remains an open challenge. In this work, we introduce a simple yet powerful approach that leverages Large Language Model-as-a-Judge (LLM-as-a-Judge) to automatically construct policy-aligned training data, completely removing the need for costly human annotation or parallel corpora. Our method enables building simplification systems that adapt to diverse simplification policies. Remarkably, even small-scale open-source LLMs such as Phi-3-mini-3.8B surpass GPT-4o on lexical-oriented simplification, while achieving comparable performance on overall rewriting, as verified by both automatic metrics and human evaluations. The consistent improvements across model families and sizes demonstrate the robustness of our approach. - oai:arXiv.org:2512.06228v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Long-only cryptocurrency portfolio management by ranking the assets: a neural network approach + https://arxiv.org/abs/2512.08124 + arXiv:2512.08124v1 Announce Type: new +Abstract: This paper will propose a novel machine learning based portfolio management method in the context of the cryptocurrency market. Previous researchers mainly focus on the prediction of the movement for specific cryptocurrency such as the bitcoin(BTC) and then trade according to the prediction. In contrast to the previous work that treats the cryptocurrencies independently, this paper manages a group of cryptocurrencies by analyzing the relative relationship. Specifically, in each time step, we utilize the neural network to predict the rank of the future return of the managed cryptocurrencies and place weights accordingly. By incorporating such cross-sectional information, the proposed methods is shown to profitable based on the backtesting experiments on the real daily cryptocurrency market data from May, 2020 to Nov, 2023. During this 3.5 years, the market experiences the full cycle of bullish, bearish and stagnant market conditions. Despite under such complex market conditions, the proposed method outperforms the existing methods and achieves a Sharpe ratio of 1.01 and annualized return of 64.26%. Additionally, the proposed method is shown to be robust to the increase of transaction fee. + oai:arXiv.org:2512.08124v1 + cs.LG + cs.AI + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Xuanxin Wu, Yuki Arase, Masaaki Nagata + 10.1109/IJCNN64981.2025.11228268 + 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025, pp. 1-8 + Zijiang Yang - GPU-GLMB: Assessing the Scalability of GPU-Accelerated Multi-Hypothesis Tracking - https://arxiv.org/abs/2512.06230 - arXiv:2512.06230v1 Announce Type: new -Abstract: Much recent research on multi-target tracking has focused on multi-hypothesis approaches leveraging random finite sets. Of particular interest are labeled random finite set methods that maintain temporally coherent labels for each object. While these methods enjoy important theoretical properties as closed-form solutions to the multi-target Bayes filter, the maintenance of multiple hypotheses under the standard measurement model is highly computationally expensive, even when hypothesis pruning approximations are applied. In this work, we focus on the Generalized Labeled Multi-Bernoulli (GLMB) filter as an example of this class of methods. We investigate a variant of the filter that allows multiple detections per object from the same sensor, a critical capability when deploying tracking in the context of distributed networks of machine learning-based virtual sensors. We show that this breaks the inter-detection dependencies in the filter updates of the standard GLMB filter, allowing updates with significantly improved parallel scalability and enabling efficient deployment on GPU hardware. We report the results of a preliminary analysis of a GPU-accelerated implementation of our proposed GLMB tracker, with a focus on run time scalability with respect to the number of objects and the maximum number of retained hypotheses. - oai:arXiv.org:2512.06230v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization + https://arxiv.org/abs/2512.08129 + arXiv:2512.08129v1 Announce Type: new +Abstract: Most post-training backdoor detection methods rely on attacked models exhibiting extreme outlier detection statistics for the target class of an attack, compared to non-target classes. However, these approaches may fail: (1) when some (non-target) classes are easily discriminable from all others, in which case they may naturally achieve extreme detection statistics (e.g., decision confidence); and (2) when the backdoor is subtle, i.e., with its features weak relative to intrinsic class-discriminative features. A key observation is that the backdoor target class has contributions to its detection statistic from both the backdoor trigger and from its intrinsic features, whereas non-target classes only have contributions from their intrinsic features. To achieve more sensitive detectors, we thus propose to suppress intrinsic features while optimizing the detection statistic for a given class. For non-target classes, such suppression will drastically reduce the achievable statistic, whereas for the target class the (significant) contribution from the backdoor trigger remains. In practice, we formulate a constrained optimization problem, leveraging a small set of clean examples from a given class, and optimizing the detection statistic while orthogonalizing with respect to the class's intrinsic features. We dub this plug-and-play approach Class Subspace Orthogonalization (CSO) and assess it against challenging mixed-label and adaptive attacks. + oai:arXiv.org:2512.08129v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pranav Balakrishnan, Sidisha Barik, Sean M. O'Rourke, Benjamin M. Marlin + Guangmingmei Yang, David J. Miller, George Kesidis - Opinion: Learning Intuitive Physics May Require More than Visual Data - https://arxiv.org/abs/2512.06232 - arXiv:2512.06232v1 Announce Type: new -Abstract: Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics. Meanwhile, despite training on vast quantities of internet video data, state-of-the-art deep learning models still fall short of human-level performance on intuitive physics benchmarks. This work investigates whether data distribution, rather than volume, is the key to learning these principles. We pretrain a Video Joint Embedding Predictive Architecture (V-JEPA) model on SAYCam, a developmentally realistic, egocentric video dataset partially capturing three children's everyday visual experiences. We find that training on this dataset, which represents 0.01% of the data volume used to train SOTA models, does not lead to significant performance improvements on the IntPhys2 benchmark. Our results suggest that merely training on a developmentally realistic dataset is insufficient for current architectures to learn representations that support intuitive physics. We conclude that varying visual data volume and distribution alone may not be sufficient for building systems with artificial intuitive physics. - oai:arXiv.org:2512.06232v1 - cs.CV + Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models I: The Task-Query Architecture + https://arxiv.org/abs/2512.08130 + arXiv:2512.08130v1 Announce Type: new +Abstract: Both model developers and policymakers seek to quantify and mitigate the risk of rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons. An important element of such efforts is the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper describes the first component of a novel Biothreat Benchmark Generation (BBG) Framework. The BBG approach is designed to help model developers and evaluators reliably measure and assess the biosecurity risk uplift and general harm potential of existing and future AI models, while accounting for key aspects of the threat itself that are often overlooked in other benchmarking efforts, including different actor capability levels, and operational (in addition to purely technical) risk factors. As a pilot, the BBG is first being developed to address bacterial biological threats only. The BBG is built upon a hierarchical structure of biothreat categories, elements and tasks, which then serves as the basis for the development of task-aligned queries. This paper outlines the development of this biothreat task-query architecture, which we have named the Bacterial Biothreat Schema, while future papers will describe follow-on efforts to turn queries into model prompts, as well as how the resulting benchmarks can be implemented for model evaluation. Overall, the BBG Framework, including the Bacterial Biothreat Schema, seeks to offer a robust, re-usable structure for evaluating bacterial biological risks arising from LLMs across multiple levels of aggregation, which captures the full scope of technical and operational requirements for biological adversaries, and which accounts for a wide spectrum of biological adversary capabilities. + oai:arXiv.org:2512.08130v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ellen Su, Solim Legris, Todd M. Gureckis, Mengye Ren + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Gary Ackerman, Brandon Behlendorf, Zachary Kallenborn, Sheriff Almakki, Doug Clifford, Jenna LaTourette, Hayley Peterson, Noah Sheinbaum, Olivia Shoemaker, Anna Wetzel - Back to Author Console Empowering GNNs for Domain Adaptation via Denoising Target Graph - https://arxiv.org/abs/2512.06236 - arXiv:2512.06236v1 Announce Type: new -Abstract: We explore the node classification task in the context of graph domain adaptation, which uses both source and target graph structures along with source labels to enhance the generalization capabilities of Graph Neural Networks (GNNs) on target graphs. Structure domain shifts frequently occur, especially when graph data are collected at different times or from varying areas, resulting in poor performance of GNNs on target graphs. Surprisingly, we find that simply incorporating an auxiliary loss function for denoising graph edges on target graphs can be extremely effective in enhancing GNN performance on target graphs. Based on this insight, we propose our framework, GraphDeT, a framework that integrates this auxiliary edge task into GNN training for node classification under domain adaptation. Our theoretical analysis connects this auxiliary edge task to the graph generalization bound with -distance, demonstrating such auxiliary task can imposes a constraint which tightens the bound and thereby improves generalization. The experimental results demonstrate superior performance compared to the existing baselines in handling both time and regional domain graph shifts. - oai:arXiv.org:2512.06236v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Universal Adversarial Suffixes for Language Models Using Reinforcement Learning with Calibrated Reward + https://arxiv.org/abs/2512.08131 + arXiv:2512.08131v1 Announce Type: new +Abstract: Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied to a single task or model. In this paper, a reinforcement learning framework is used where the suffix is treated as a policy and trained with Proximal Policy Optimization against a frozen model as a reward oracle. Rewards are shaped using calibrated cross-entropy, removing label bias and aggregating across surface forms to improve transferability. The proposed method is evaluated on five diverse NLP benchmark datasets, covering sentiment, natural language inference, paraphrase, and commonsense reasoning, using three distinct language models: Qwen2-1.5B Instruct, TinyLlama-1.1B Chat, and Phi-1.5. Results show that RL-trained suffixes consistently degrade accuracy and transfer more effectively across tasks and models than previous adversarial triggers of similar genres. + oai:arXiv.org:2512.08131v1 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-nc-sa/4.0/ - Haiyang Yu, Meng-Chieh Lee, Xiang song, Qi Zhu, Christos Faloutsos - - - Non-Asymptotic Error Bounds for Causally Conditioned Directed Information Rates of Gaussian Sequences - https://arxiv.org/abs/2512.06238 - arXiv:2512.06238v1 Announce Type: new -Abstract: Directed information and its causally conditioned variations are often used to measure causal influences between random processes. In practice, these quantities must be measured from data. Non-asymptotic error bounds for these estimates are known for sequences over finite alphabets, but less is known for real-valued data. This paper examines the case in which the data are sequences of Gaussian vectors. We provide an explicit formula for causally conditioned directed information rate based on optimal prediction and define an estimator based on this formula. We show that our estimator gives an error of order $O\left(N^{-1/2}\log(N)\right)$ with high probability, where $N$ is the total sample size. - oai:arXiv.org:2512.06238v1 - cs.IT - math.IT - math.ST - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yuping Zheng, Andrew Lamperski + Sampriti Soor, Suklav Ghosh, Arijit Sur - LOCUS: A System and Method for Low-Cost Customization for Universal Specialization - https://arxiv.org/abs/2512.06239 - arXiv:2512.06239v1 Announce Type: new -Abstract: We present LOCUS (LOw-cost Customization for Universal Specialization), a pipeline that consumes few-shot data to streamline the construction and training of NLP models through targeted retrieval, synthetic data generation, and parameter-efficient tuning. With only a small number of labeled examples, LOCUS discovers pertinent data in a broad repository, synthesizes additional training samples via in-context data generation, and fine-tunes models using either full or low-rank (LoRA) parameter adaptation. Our approach targets named entity recognition (NER) and text classification (TC) benchmarks, consistently outperforming strong baselines (including GPT-4o) while substantially lowering costs and model sizes. Our resultant memory-optimized models retain 99% of fully fine-tuned accuracy while using barely 5% of the memory footprint, also beating GPT-4o on several benchmarks with less than 1% of its parameters. - oai:arXiv.org:2512.06239v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Multi-agent learning under uncertainty: Recurrence vs. concentration + https://arxiv.org/abs/2512.08132 + arXiv:2512.08132v1 Announce Type: new +Abstract: In this paper, we examine the convergence landscape of multi-agent learning under uncertainty. Specifically, we analyze two stochastic models of regularized learning in continuous games -- one in continuous and one in discrete time with the aim of characterizing the long-run behavior of the induced sequence of play. In stark contrast to deterministic, full-information models of learning (or models with a vanishing learning rate), we show that the resulting dynamics do not converge in general. In lieu of this, we ask instead which actions are played more often in the long run, and by how much. We show that, in strongly monotone games, the dynamics of regularized learning may wander away from equilibrium infinitely often, but they always return to its vicinity in finite time (which we estimate), and their long-run distribution is sharply concentrated around a neighborhood thereof. We quantify the degree of this concentration, and we show that these favorable properties may all break down if the underlying game is not strongly monotone -- underscoring in this way the limits of regularized learning in the presence of persistent randomness and uncertainty. + oai:arXiv.org:2512.08132v1 + cs.GT + cs.LG + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Dhanasekar Sundararaman, Keying Li, Wayne Xiong, Aashna Garg + Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, Jose Blanchet - AI Application in Anti-Money Laundering for Sustainable and Transparent Financial Systems - https://arxiv.org/abs/2512.06240 - arXiv:2512.06240v1 Announce Type: new -Abstract: Money laundering and financial fraud remain major threats to global financial stability, costing trillions annually and challenging regulatory oversight. This paper reviews how artificial intelligence (AI) applications can modernize Anti-Money Laundering (AML) workflows by improving detection accuracy, lowering false-positive rates, and reducing the operational burden of manual investigations, thereby supporting more sustainable development. It further highlights future research directions including federated learning for privacy-preserving collaboration, fairness-aware and interpretable AI, reinforcement learning for adaptive defenses, and human-in-the-loop visualization systems to ensure that next-generation AML architectures remain transparent, accountable, and robust. In the final part, the paper proposes an AI-driven KYC application that integrates graph-based retrieval-augmented generation (RAG Graph) with generative models to enhance efficiency, transparency, and decision support in KYC processes related to money-laundering detection. Experimental results show that the RAG-Graph architecture delivers high faithfulness and strong answer relevancy across diverse evaluation settings, thereby enhancing the efficiency and transparency of KYC CDD/EDD workflows and contributing to more sustainable, resource-optimized compliance practices. - oai:arXiv.org:2512.06240v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + A Dynamic Coding Scheme to Prevent Covert Cyber-Attacks in Cyber-Physical Systems + https://arxiv.org/abs/2512.08134 + arXiv:2512.08134v1 Announce Type: new +Abstract: In this paper, we address two main problems in the context of covert cyber-attacks in cyber-physical systems (CPS). First, we aim to investigate and develop necessary and sufficient conditions in terms of disruption resources of the CPS that enable adversaries to execute covert cyber-attacks. These conditions can be utilized to identify the input and output communication channels that are needed by adversaries to execute these attacks. Second, this paper introduces and develops a dynamic coding scheme as a countermeasure against covert cyber-attacks. Under certain conditions and assuming the existence of one secure input and two secure output communication channels, the proposed dynamic coding scheme prevents adversaries from executing covert cyber-attacks. A numerical case study of a flight control system is provided to demonstrate the capabilities of our proposed and developed dynamic coding scheme. + oai:arXiv.org:2512.08134v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chuanhao Nie, Yunbo Liu, Chao Wang + Mahdi Taheri, Khashayar Khorasani, Nader Meskin - Reasoning about concurrent loops and recursion with rely-guarantee rules - https://arxiv.org/abs/2512.06242 - arXiv:2512.06242v1 Announce Type: new -Abstract: The objective of this paper is to present general, mechanically verified, refinement rules for reasoning about recursive programs and while loops in the context of concurrency. Unlike many approaches to concurrency, we do not assume that expression evaluation is atomic. We make use of the rely-guarantee approach to concurrency that facilitates reasoning about interference from concurrent threads in a compositional manner. Recursive programs can be defined as fixed points over a lattice of commands and hence we develop laws for reasoning about fixed points. Loops can be defined in terms of fixed points and hence the laws for recursion can be applied to develop laws for loops. - oai:arXiv.org:2512.06242v1 - cs.LO - cs.PL - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning + https://arxiv.org/abs/2512.08135 + arXiv:2512.08135v1 Announce Type: new +Abstract: We present a central-peripheral vision-inspired framework (CVP), a simple yet effective multimodal model for spatial reasoning that draws inspiration from the two types of human visual fields -- central vision and peripheral vision. Existing approaches primarily rely on unstructured representations, such as point clouds, voxels, or patch features, and inject scene context implicitly via coordinate embeddings. However, this often results in limited spatial reasoning capabilities due to the lack of explicit, high-level structural understanding. To address this limitation, we introduce two complementary components into a Large Multimodal Model-based architecture: target-affinity token, analogous to central vision, that guides the model's attention toward query-relevant objects; and allocentric grid, akin to peripheral vision, that captures global scene context and spatial arrangements. These components work in tandem to enable structured, context-aware understanding of complex 3D environments. Experiments show that CVP achieves state-of-the-art performance across a range of 3D scene understanding benchmarks. + oai:arXiv.org:2512.08135v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ian J. Hayes, Larissa A. Meinicke, Cliff B. Jones + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zeyuan Chen, Xiang Zhang, Haiyang Xu, Jianwen Xie, Zhuowen Tu - Quantization Blindspots: How Model Compression Breaks Backdoor Defenses - https://arxiv.org/abs/2512.06243 - arXiv:2512.06243v1 Announce Type: new -Abstract: Backdoor attacks embed input-dependent malicious behavior into neural networks while preserving high clean accuracy, making them a persistent threat for deployed ML systems. At the same time, real-world deployments almost never serve full-precision models: post-training quantization to INT8 or lower precision is now standard practice for reducing memory and latency. This work asks a simple question: how do existing backdoor defenses behave under standard quantization pipelines? We conduct a systematic empirical study of five representative defenses across three precision settings (FP32, INT8 dynamic, INT4 simulated) and two standard vision benchmarks using a canonical BadNet attack. We observe that INT8 quantization reduces the detection rate of all evaluated defenses to 0% while leaving attack success rates above 99%. For INT4, we find a pronounced dataset dependence: Neural Cleanse remains effective on GTSRB but fails on CIFAR-10, even though backdoors continue to survive quantization with attack success rates above 90%. Our results expose a mismatch between how defenses are commonly evaluated (on FP32 models) and how models are actually deployed (in quantized form), and they highlight quantization robustness as a necessary axis in future evaluations and designs of backdoor defenses. - oai:arXiv.org:2512.06243v1 + Robust equilibria in continuous games: From strategic to dynamic robustness + https://arxiv.org/abs/2512.08138 + arXiv:2512.08138v1 Announce Type: new +Abstract: In this paper, we examine the robustness of Nash equilibria in continuous games, under both strategic and dynamic uncertainty. Starting with the former, we introduce the notion of a robust equilibrium as those equilibria that remain invariant to small -- but otherwise arbitrary -- perturbations to the game's payoff structure, and we provide a crisp geometric characterization thereof. Subsequently, we turn to the question of dynamic robustness, and we examine which equilibria may arise as stable limit points of the dynamics of "follow the regularized leader" (FTRL) in the presence of randomness and uncertainty. Despite their very distinct origins, we establish a structural correspondence between these two notions of robustness: strategic robustness implies dynamic robustness, and, conversely, the requirement of strategic robustness cannot be relaxed if dynamic robustness is to be maintained. Finally, we examine the rate of convergence to robust equilibria as a function of the underlying regularizer, and we show that entropically regularized learning converges at a geometric rate in games with affinely constrained action spaces. + oai:arXiv.org:2512.08138v1 + cs.GT cs.LG - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Rohan Pandey, Eric Ye + Kyriakos Lotidis, Panayotis Mertikopoulos, Nicholas Bambos, Jose Blanchet - Auto-exploration for online reinforcement learning - https://arxiv.org/abs/2512.06244 - arXiv:2512.06244v1 Announce Type: new -Abstract: The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient exploration over both state and action spaces. However, this yields non-implementable algorithms and sub-optimal performance. To resolve these limitations, we introduce a new class of methods with auto-exploration, or methods that automatically explore both state and action spaces in a parameter-free way, i.e.,~without a priori knowledge of problem-dependent parameters. We present two variants: one for the tabular setting and one for linear function approximation. Under algorithm-independent assumptions on the existence of an exploring optimal policy, both methods attain $O(\epsilon^{-2})$ sample complexity to solve to $\epsilon$ error. Crucially, these complexities are novel since they are void of algorithm-dependent parameters seen in prior works, which may be arbitrarily large. The methods are also simple to implement because they are parameter-free and do not directly estimate the unknown parameters. These feats are achieved by new algorithmic innovations for RL, including a dynamic mixing time, a discounted state distribution for sampling, a simple robust gradient estimator, and a recent advantage gap function to certify convergence. - oai:arXiv.org:2512.06244v1 + Robust Agents in Open-Ended Worlds + https://arxiv.org/abs/2512.08139 + arXiv:2512.08139v1 Announce Type: new +Abstract: The growing prevalence of artificial intelligence (AI) in various applications underscores the need for agents that can successfully navigate and adapt to an ever-changing, open-ended world. A key challenge is ensuring these AI agents are robust, excelling not only in familiar settings observed during training but also effectively generalising to previously unseen and varied scenarios. In this thesis, we harness methodologies from open-endedness and multi-agent learning to train and evaluate robust AI agents capable of generalising to novel environments, out-of-distribution inputs, and interactions with other co-player agents. We begin by introducing MiniHack, a sandbox framework for creating diverse environments through procedural content generation. Based on the game of NetHack, MiniHack enables the construction of new tasks for reinforcement learning (RL) agents with a focus on generalisation. We then present Maestro, a novel approach for generating adversarial curricula that progressively enhance the robustness and generality of RL agents in two-player zero-sum games. We further probe robustness in multi-agent domains, utilising quality-diversity methods to systematically identify vulnerabilities in state-of-the-art, pre-trained RL policies within the complex video game football domain, characterised by intertwined cooperative and competitive dynamics. Finally, we extend our exploration of robustness to the domain of LLMs. Here, our focus is on diagnosing and enhancing the robustness of LLMs against adversarial prompts, employing evolutionary search to generate a diverse range of effective inputs that aim to elicit undesirable outputs from an LLM. This work collectively paves the way for future advancements in AI robustness, enabling the development of agents that not only adapt to an ever-evolving world but also thrive in the face of unforeseen challenges and interactions. + oai:arXiv.org:2512.08139v1 cs.LG - cs.AI - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Caleb Ju, Guanghui Lan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Mikayel Samvelyan - Quadratic Formula-based Nonlinear Approximation - https://arxiv.org/abs/2512.06246 - arXiv:2512.06246v1 Announce Type: new -Abstract: This paper presents a quadratic formula-based nonlinear representation for a given single-variable function f(x), $-1 \leq x \leq 1$. First, we construct the explicit polynomial coefficient functions a(x), b(x), and c(x) using a least-squares approach. Then, f is reconstructed by solving the degree-2 polynomial equation a(x) f^2 - b(x) f - c(x)=0 for any $x \in [-1,1]$, where an index function is used to select the correct sign in the quadratic formula. The quadratic formula-based nonlinear approximation (degree-2 in f) outperforms classical orthogonal polynomial-based least-squares approximation (degree-0 in f) and rational approximation (degree-1 in f) for functions with sharp transitions or discontinuities. As a potential application, we apply the degree-2 representation to data denoising. Instead of relying on more complex "edge-preserving" metric-based optimization techniques, the smooth coefficient functions a(x), b(x), and c(x) enable effective least-squares-based denoising on the low-dimensional manifold described by the algebraic variety a(x) f^2 - b(x) f - c(x)=0. Denoising the index function, which determines the appropriate root to select, can be achieved using classical statistical or modern classification/clustering techniques. Numerical results and data denoising examples are provided to demonstrate the effectiveness of the degree-2 nonlinear approximation technique. The new nonlinear, quadratic formula-based representation also raises theoretical and numerical questions, including strategies for identifying numerically stable representations, developing optimal algorithms to construct the polynomial coefficient functions a(x), b(x), and c(x), and achieving economical representation and denoising of the index function. - oai:arXiv.org:2512.06246v1 + Well-posedness of a novel Lagrange multiplier formulation for fluid-poroelastic interaction + https://arxiv.org/abs/2512.08142 + arXiv:2512.08142v1 Announce Type: new +Abstract: We introduce a novel monolithic formulation that employs Lagrange multipliers (LMs) to couple a fluid flow governed by the time-dependent Stokes equations with a poroelastic structure described by the Biot equations. The formulation is developed in detail, and we establish the well-posedness of both the semi-discrete and fully discrete saddle point problems. We further prove the stability of the fully discrete system. This saddle point formulation, which utilizes three LMs, is designed to enable a partitioned approach that completely decouples the Stokes and Biot subdomains, and this approach will be explored in a subsequent work. + oai:arXiv.org:2512.08142v1 math.NA cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ziqin He, Can Chen, Min Hyung Cho, Jingfang Huang, Yichao Wu + http://creativecommons.org/licenses/by/4.0/ + Amy de Castro, Hyesuk Lee - DUET: Agentic Design Understanding via Experimentation and Testing - https://arxiv.org/abs/2512.06247 - arXiv:2512.06247v1 Announce Type: new -Abstract: AI agents powered by large language models (LLMs) are being used to solve increasingly complex software engineering challenges, but struggle with hardware design tasks. Register Transfer Level (RTL) code presents a unique challenge for LLMs, as it encodes complex, dynamic, time-evolving behaviors using the low-level language features of SystemVerilog. LLMs struggle to infer these complex behaviors from the syntax of RTL alone, which limits their ability to complete all downstream tasks like code completion, documentation, or verification. In response to this issue, we present DUET: a general methodology for developing Design Understanding via Experimentation and Testing. DUET mimics how hardware design experts develop an understanding of complex designs: not just via a one-off readthrough of the RTL, but via iterative experimentation using a number of tools. DUET iteratively generates hypotheses, tests them with EDA tools (e.g., simulation, waveform inspection, and formal verification), and integrates the results to build a bottom-up understanding of the design. In our evaluations, we show that DUET improves AI agent performance on formal verification, when compared to a baseline flow without experimentation. - oai:arXiv.org:2512.06247v1 - cs.SE - cs.AI - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 + PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection + https://arxiv.org/abs/2512.08143 + arXiv:2512.08143v1 Announce Type: new +Abstract: Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. Errors at this stage can cascade into downstream failures, setting a high bar for accuracy. Yet, existing language identification tools struggle with key cases--such as music requests where the song title and user language differ. Open-source tools like LangDetect, FastText are fast but less accurate, while large language models, though effective, are often too costly for low-latency or low-resource settings. We introduce PolyLingua, a lightweight Transformer-based model for in-domain language detection and fine-grained language classification. It employs a two-level contrastive learning framework combining instance-level separation and class-level alignment with adaptive margins, yielding compact and well-separated embeddings even for closely related languages. Evaluated on two challenging datasets--Amazon Massive (multilingual digital assistant utterances) and a Song dataset (music requests with frequent code-switching)--PolyLingua achieves 99.25% F1 and 98.15% F1, respectively, surpassing Sonnet 3.5 while using 10x fewer parameters, making it ideal for compute- and latency-constrained environments. + oai:arXiv.org:2512.08143v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Gus Henry Smith, Sandesh Adhikary, Vineet Thumuluri, Karthik Suresh, Vivek Pandit, Kartik Hegde, Hamid Shojaei, Chandra Bhagavatula + Ali Lotfi Rezaabad, Bikram Khanal, Shashwat Chaurasia, Lu Zeng, Dezhi Hong, Hossein Beshashati, Thomas Butler, Megan Ganji - CFCEval: Evaluating Security Aspects in Code Generated by Large Language Models - https://arxiv.org/abs/2512.06248 - arXiv:2512.06248v1 Announce Type: new -Abstract: Code-focused Large Language Models (LLMs), such as CodeX and Star-Coder, have demonstrated remarkable capabilities in enhancing developer productivity through context-aware code generation. However, evaluating the quality and security of LLM-generated code remains a significant challenge. Existing evaluation protocols for Code LLMs lack both methodological rigor and comprehensive scope. A key limitation is dataset bias, which arises from unintentional overlap between training and testing data. Furthermore, while CodeBLEU, a BLEU-based metric, is widely used to assess code similarity, it suffers from critical shortcomings, including imprecise tokenization, structural limitations, and low reference diversity. To address these challenges, we introduce CFCEval, a novel framework for evaluating the quality and security of code generated by LLMs. CFCEval mitigates dataset bias by creating a new benchmark, MLVBench, and incorporates ELRM, a new metric designed to assess the relevance between reference code and generated code. CFCEval evaluates generated code across four dimensions: programming quality, vulnerability-fixing capability, post-transformation fixing capability, and relevance. Our experiments show that CFCEval not only captures both quality and security aspects of generated code more effectively but also that its ELRM aligns more closely with human judgments than CodeBLEU, thus paving the way for future advancements in Code LLMs evaluation. - oai:arXiv.org:2512.06248v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Chat with UAV -- Human-UAV Interaction Based on Large Language Models + https://arxiv.org/abs/2512.08145 + arXiv:2512.08145v1 Announce Type: new +Abstract: The future of UAV interaction systems is evolving from engineer-driven to user-driven, aiming to replace traditional predefined Human-UAV Interaction designs. This shift focuses on enabling more personalized task planning and design, thereby achieving a higher quality of interaction experience and greater flexibility, which can be used in many fileds, such as agriculture, aerial photography, logistics, and environmental monitoring. However, due to the lack of a common language between users and the UAVs, such interactions are often difficult to be achieved. The developments of Large Language Models possess the ability to understand nature languages and Robots' (UAVs') behaviors, marking the possibility of personalized Human-UAV Interaction. Recently, some HUI frameworks based on LLMs have been proposed, but they commonly suffer from difficulties in mixed task planning and execution, leading to low adaptability in complex scenarios. In this paper, we propose a novel dual-agent HUI framework. This framework constructs two independent LLM agents (a task planning agent, and an execution agent) and applies different Prompt Engineering to separately handle the understanding, planning, and execution of tasks. To verify the effectiveness and performance of the framework, we have built a task database covering four typical application scenarios of UAVs and quantified the performance of the HUI framework using three independent metrics. Meanwhile different LLM models are selected to control the UAVs with compared performance. Our user study experimental results demonstrate that the framework improves the smoothness of HUI and the flexibility of task execution in the tasks scenario we set up, effectively meeting users' personalized needs. + oai:arXiv.org:2512.08145v1 + cs.RO + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-sa/4.0/ - Cheng Cheng, Jinqiu Yang + Haoran Wang, Zhuohang Chen, Guang Li, Bo Ma, Chuanghuang Li - Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning - https://arxiv.org/abs/2512.06250 - arXiv:2512.06250v1 Announce Type: new -Abstract: Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds between two orthogonal navigation policies. Using maze navigation as a case study, this work demonstrates how an agent can dynamically transition between systematic exploration (coverage) and goal-directed pathfinding (convergence) to improve task performance. Unlike fixed-threshold approaches, the agent uses Q-learning to adapt switching behavior based on coverage percentage and distance to goal, requiring only minimal domain knowledge: maze dimensions and target location. The agent does not require prior knowledge of wall positions, optimal threshold values, or hand-crafted heuristics; instead, it discovers effective switching strategies dynamically during each run. The agent discretizes its state space into coverage and distance buckets, then adapts which coverage threshold (20-60\%) to apply based on observed progress signals. Experiments across 240 test configurations (4 maze sizes from 16$\times$16 to 128$\times$128 $\times$ 10 unique mazes $\times$ 6 agent variants) demonstrate that adaptive threshold learning outperforms both single-strategy agents and fixed 40\% threshold baselines. Results show 23-55\% improvements in completion time, 83\% reduction in runtime variance, and 71\% improvement in worst-case scenarios. The learned switching behavior generalizes within each size class to unseen wall configurations. Performance gains scale with problem complexity: 23\% improvement for 16$\times$16 mazes, 34\% for 32$\times$32, and 55\% for 64$\times$64, demonstrating that as the space of possible maze structures grows, the value of adaptive policy selection over fixed heuristics increases proportionally. - oai:arXiv.org:2512.06250v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Scalable Back-End for an AI-Based Diabetes Prediction Application + https://arxiv.org/abs/2512.08147 + arXiv:2512.08147v1 Announce Type: new +Abstract: The rising global prevalence of diabetes necessitates early detection to prevent severe complications. While AI-powered prediction applications offer a promising solution, they require a responsive and scalable back-end architecture to serve a large user base effectively. This paper details the development and evaluation of a scalable back-end system designed for a mobile diabetes prediction application. The primary objective was to maintain a failure rate below 5% and an average latency of under 1000 ms. The architecture leverages horizontal scaling, database sharding, and asynchronous communication via a message queue. Performance evaluation showed that 83% of the system's features (20 out of 24) met the specified performance targets. Key functionalities such as user profile management, activity tracking, and read-intensive prediction operations successfully achieved the desired performance. The system demonstrated the ability to handle up to 10,000 concurrent users without issues, validating its scalability. The implementation of asynchronous communication using RabbitMQ proved crucial in minimizing the error rate for computationally intensive prediction requests, ensuring system reliability by queuing requests and preventing data loss under heavy load. + oai:arXiv.org:2512.08147v1 + cs.AI + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Chris Tava + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Henry Anand Septian Radityo, Bernardus Willson, Reynard Tanadi, Latifa Dwiyanti, Saiful Akbar - NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks - https://arxiv.org/abs/2512.06251 - arXiv:2512.06251v1 Announce Type: new -Abstract: Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks, leaving the more realistic challenge of learning from structurally diverse tasks unexplored. To this end, we introduce NexusFlow, a novel, lightweight, and plug-and-play framework effective in both settings. NexusFlow introduces a set of surrogate networks with invertible coupling layers to align the latent feature distributions of tasks, creating a unified representation that enables effective knowledge transfer. The coupling layers are bijective, preserving information while mapping features into a shared canonical space. This invertibility avoids representational collapse and enables alignment across structurally different tasks without reducing expressive capacity. We first evaluate NexusFlow on the core challenge of domain-partitioned autonomous driving, where dense map reconstruction and sparse multi-object tracking are supervised in different geographic regions, creating both structural disparity and a strong domain gap. NexusFlow sets a new state-of-the-art result on nuScenes, outperforming strong partially supervised baselines. To demonstrate generality, we further test NexusFlow on NYUv2 using three homogeneous dense prediction tasks, segmentation, depth, and surface normals, as a representative N-task PS-MTL scenario. NexusFlow yields consistent gains across all tasks, confirming its broad applicability. - oai:arXiv.org:2512.06251v1 + TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models + https://arxiv.org/abs/2512.08153 + arXiv:2512.08153v1 Announce Type: new +Abstract: Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption. We introduce \textbf{TreeGRPO}, a novel RL framework that dramatically improves training efficiency by recasting the denoising process as a search tree. From shared initial noise samples, TreeGRPO strategically branches to generate multiple candidate trajectories while efficiently reusing their common prefixes. This tree-structured approach delivers three key advantages: (1) \emph{High sample efficiency}, achieving better performance under same training samples (2) \emph{Fine-grained credit assignment} via reward backpropagation that computes step-specific advantages, overcoming the uniform credit assignment limitation of trajectory-based methods, and (3) \emph{Amortized computation} where multi-child branching enables multiple policy updates per forward pass. Extensive experiments on both diffusion and flow-based models demonstrate that TreeGRPO achieves \textbf{2.4$\times$ faster training} while establishing a superior Pareto frontier in the efficiency-reward trade-off space. Our method consistently outperforms GRPO baselines across multiple benchmarks and reward models, providing a scalable and effective pathway for RL-based visual generative model alignment. The project website is available at treegrpo.github.io. + oai:arXiv.org:2512.08153v1 + cs.LG + cs.AI cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Fangzhou Lin, Yuping Wang, Yuliang Guo, Zixun Huang, Xinyu Huang, Haichong Zhang, Kazunori Yamada, Zhengzhong Tu, Liu Ren, Ziming Zhang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zheng Ding, Weirui Ye - Learning Without Time-Based Embodiment Resets in Soft-Actor Critic - https://arxiv.org/abs/2512.06252 - arXiv:2512.06252v1 Announce Type: new -Abstract: When creating new reinforcement learning tasks, practitioners often accelerate the learning process by incorporating into the task several accessory components, such as breaking the environment interaction into independent episodes and frequently resetting the environment. Although they can enable the learning of complex intelligent behaviors, such task accessories can result in unnatural task setups and hinder long-term performance in the real world. In this work, we explore the challenges of learning without episode terminations and robot embodiment resets using the Soft Actor-Critic (SAC) algorithm. To learn without terminations, we present a continuing version of the SAC algorithm and show that, with simple modifications to the reward functions of existing tasks, continuing SAC can perform as well as or better than episodic SAC while reducing the sensitivity of performance to the value of the discount rate $\gamma$. On a modified Gym Reacher task, we investigate possible explanations for the failure of continuing SAC when learning without embodiment resets. Our results suggest that embodiment resets help with exploration of the state space in the SAC algorithm, and removing embodiment resets can lead to poor exploration of the state space and failure of or significantly slower learning. Finally, on additional simulated tasks and a real-robot vision task, we show that increasing the entropy of the policy when performance trends worse or remains static is an effective intervention for recovering the performance lost due to not using embodiment resets. - oai:arXiv.org:2512.06252v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Adaptive Matched Filtering for Sensing With Communication Signals in Cluttered Environments + https://arxiv.org/abs/2512.08157 + arXiv:2512.08157v1 Announce Type: new +Abstract: This paper investigates the performance of the adaptive matched filtering (AMF) in cluttered environments, particularly when operating with superimposed signals. Since the instantaneous signal-to-clutter-plus-noise ratio (SCNR) is a random variable dependent on the data payload, using it directly as a design objective poses severe practical challenges, such as prohibitive computational burdens and signaling overhead. To address this, we propose shifting the optimization objective from an instantaneous to a statistical metric, which focuses on maximizing the average SCNR over all possible payloads. Due to its analytical intractability, we leverage tools from random matrix theory (RMT) to derive an asymptotic approximation for the average SCNR, which remains accurate even in moderate-dimensional regimes. A key finding from our theoretical analysis is that, for a fixed modulation basis, the PSK achieves a superior average SCNR compared to QAM and the pure Gaussian constellation. Furthermore, for any given constellation, the OFDM achieves a higher average SCNR than SC and AFDM. Then, we propose two pilot design schemes to enhance system performance: a Data-Payload-Dependent (DPD) scheme and a Data-Payload-Independent (DPI) scheme. The DPD approach maximizes the instantaneous SCNR for each transmission. Conversely, the DPI scheme optimizes the average SCNR, offering a flexible trade-off between sensing performance and implementation complexity. Then, we develop two dedicated optimization algorithms for DPD and DPI schemes. In particular, for the DPD problem, we employ fractional optimization and the KKT conditions to derive a closed-form solution. For the DPI problem, we adopt a manifold optimization approach to handle the inherent rank-one constraint efficiently. Simulation results validate the accuracy of our theoretical analysis and demonstrate the effectiveness of the proposed methods. + oai:arXiv.org:2512.08157v1 + cs.IT + eess.SP + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Homayoon Farrahi, A. Rupam Mahmood + Lei Xie, Hengtao He, Yifeng Xiong, Fan Liu, Shi Jin - Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure - https://arxiv.org/abs/2512.06253 - arXiv:2512.06253v1 Announce Type: new -Abstract: Noise perturbation is one of the most fundamental approaches for achieving $(\epsilon,\delta)$-differential privacy (DP) guarantees when releasing the result of a query or function $f(\cdot)\in\mathbb{R}^M$ evaluated on a sensitive dataset $\mathbf{x}$. In this approach, calibrated noise $\mathbf{n}\in\mathbb{R}^M$ is used to obscure the difference vector $f(\mathbf{x})-f(\mathbf{x}')$, where $\mathbf{x}'$ is known as a neighboring dataset. A DP guarantee is obtained by studying the tail probability bound of a privacy loss random variable (PLRV), defined as the Radon-Nikodym derivative between two distributions. When $\mathbf{n}$ follows a multivariate Gaussian distribution, the PLRV is characterized as a specific univariate Gaussian. In this paper, we propose a novel scheme to generate $\mathbf{n}$ by leveraging the fact that the perturbation noise is typically spherically symmetric (i.e., the distribution is rotationally invariant around the origin). The new noise generation scheme allows us to investigate the privacy loss from a geometric perspective and express the resulting PLRV using a product measure, $W\times U$; measure $W$ is related to a radius random variable controlling the magnitude of $\mathbf{n}$, while measure $U$ involves a directional random variable governing the angle between $\mathbf{n}$ and the difference $f(\mathbf{x})-f(\mathbf{x}')$. We derive a closed-form moment bound on the product measure to prove $(\epsilon,\delta)$-DP. Under the same $(\epsilon,\delta)$-DP guarantee, our mechanism yields a smaller expected noise magnitude than the classic Gaussian noise in high dimensions, thereby significantly improving the utility of the noisy result $f(\mathbf{x})+\mathbf{n}$. To validate this, we consider convex and non-convex empirical risk minimization (ERM) problems in high dimensional space and apply the proposed product noise to achieve privacy. - oai:arXiv.org:2512.06253v1 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Reeb Graph of Sample Thickenings + https://arxiv.org/abs/2512.08159 + arXiv:2512.08159v1 Announce Type: new +Abstract: We consider the Reeb graph of a thickening of points sampled from an unknown space. Our main contribution is a framework to transfer reconstruction results similar to the well-known work of Niyogi, Smale, and Weinberger to the setting of Reeb graphs. To this end, we first generalize and study the interleaving distances for Reeb graphs. We find that many of the results previously established for constructible spaces also hold for general topological spaces. We use this to show that under certain conditions for topological spaces with real-valued Lipschitz maps, the Reeb graph of a sample thickening approximates the Reeb graph of the underlying space. Finally, we provide an algorithm for computing the Reeb graph of a sample thickening. + oai:arXiv.org:2512.08159v1 + cs.CG + math.AT + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Shuainan Liu, Tianxi Ji, Zhongshuo Fang, Lu Wei, Pan Li + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + H{\aa}vard Bakke Bjerkevik, Nello Blaser, Lars M. Salbu - Language-driven Fine-grained Retrieval - https://arxiv.org/abs/2512.06255 - arXiv:2512.06255v1 Announce Type: new -Abstract: Existing fine-grained image retrieval (FGIR) methods learn discriminative embeddings by adopting semantically sparse one-hot labels derived from category names as supervision. While effective on seen classes, such supervision overlooks the rich semantics encoded in category names, hindering the modeling of comparability among cross-category details and, in turn, limiting generalization to unseen categories. To tackle this, we introduce LaFG, a Language-driven framework for Fine-Grained Retrieval that converts class names into attribute-level supervision using large language models (LLMs) and vision-language models (VLMs). Treating each name as a semantic anchor, LaFG prompts an LLM to generate detailed, attribute-oriented descriptions. To mitigate attribute omission in these descriptions, it leverages a frozen VLM to project them into a vision-aligned space, clustering them into a dataset-wide attribute vocabulary while harvesting complementary attributes from related categories. Leveraging this vocabulary, a global prompt template selects category-relevant attributes, which are aggregated into category-specific linguistic prototypes. These prototypes supervise the retrieval model to steer - oai:arXiv.org:2512.06255v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + LayerPipe2: Multistage Pipelining and Weight Recompute via Improved Exponential Moving Average for Training Neural Networks + https://arxiv.org/abs/2512.08160 + arXiv:2512.08160v1 Announce Type: new +Abstract: In our prior work, LayerPipe, we had introduced an approach to accelerate training of convolutional, fully connected, and spiking neural networks by overlapping forward and backward computation. However, despite empirical success, a principled understanding of how much gradient delay needs to be introduced at each layer to achieve desired level of pipelining was not addressed. This paper, LayerPipe2, fills that gap by formally deriving LayerPipe using variable delayed gradient adaptation and retiming. We identify where delays may be legally inserted and show that the required amount of delay follows directly from the network structure where inner layers require fewer delays and outer layers require longer delays. When pipelining is applied at every layer, the amount of delay depends only on the number of remaining downstream stages. When layers are pipelined in groups, all layers in the group share the same assignment of delays. These insights not only explain previously observed scheduling patterns but also expose an often overlooked challenge that pipelining implicitly requires storage of historical weights. We overcome this storage bottleneck by developing a pipeline--aware moving average that reconstructs the required past states rather than storing them explicitly. This reduces memory cost without sacrificing the accuracy guarantees that makes pipelined learning viable. The result is a principled framework that illustrates how to construct LayerPipe architectures, predicts their delay requirements, and mitigates their storage burden, thereby enabling scalable pipelined training with controlled communication computation tradeoffs. + oai:arXiv.org:2512.08160v1 + cs.LG + cs.AI + cs.AR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Shijie Wang, Xin Yu, Yadan Luo, Zijian Wang, Pengfei Zhang, Zi Huang + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Nanda K. Unnikrishnan, Keshab K. Parhi - Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setup - https://arxiv.org/abs/2512.06256 - arXiv:2512.06256v1 Announce Type: new -Abstract: In this work, we report what happens when two large language models respond to each other for many turns without any outside input in a multi-agent setup. The setup begins with a short seed sentence. After that, each model reads the other's output and generates a response. This continues for a fixed number of steps. We used Mistral Nemo Base 2407 and Llama 2 13B hf. We observed that most conversations start coherently but later fall into repetition. In many runs, a short phrase appears and repeats across turns. Once repetition begins, both models tend to produce similar output rather than introducing a new direction in the conversation. This leads to a loop where the same or similar text is produced repeatedly. We describe this behavior as a form of convergence. It occurs even though the models are large, trained separately, and not given any prompt instructions. To study this behavior, we apply lexical and embedding-based metrics to measure how far the conversation drifts from the initial seed and how similar the outputs of the two models becomes as the conversation progresses. - oai:arXiv.org:2512.06256v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing + https://arxiv.org/abs/2512.08161 + arXiv:2512.08161v1 Announce Type: new +Abstract: Image dehazing is crucial for reliable visual perception, yet it remains highly challenging under real-world non-uniform haze conditions. Although Transformer-based methods excel at capturing global context, their quadratic computational complexity hinders real-time deployment. To address this, we propose Fourier Receptance Weighted Key Value (Fourier-RWKV), a novel dehazing framework based on a Multi-State Perception paradigm. The model achieves comprehensive haze degradation modeling with linear complexity by synergistically integrating three distinct perceptual states: (1) Spatial-form Perception, realized through the Deformable Quad-directional Token Shift (DQ-Shift) operation, which dynamically adjusts receptive fields to accommodate local haze variations; (2) Frequency-domain Perception, implemented within the Fourier Mix block, which extends the core WKV attention mechanism of RWKV from the spatial domain to the Fourier domain, preserving the long-range dependencies essential for global haze estimation while mitigating spatial attenuation; (3) Semantic-relation Perception, facilitated by the Semantic Bridge Module (SBM), which utilizes Dynamic Semantic Kernel Fusion (DSK-Fusion) to precisely align encoder-decoder features and suppress artifacts. Extensive experiments on multiple benchmarks demonstrate that Fourier-RWKV delivers state-of-the-art performance across diverse haze scenarios while significantly reducing computational overhead, establishing a favorable trade-off between restoration quality and practical efficiency. Code is available at: https://github.com/Dilizlr/Fourier-RWKV. + oai:arXiv.org:2512.08161v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Aniruddha Maiti, Satya Nimmagadda, Kartha Veerya Jammuladinne, Niladri Sengupta, Ananya Jana + Lirong Zheng, Yanshan Li, Rui Yu, Kaihao Zhang - Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs - https://arxiv.org/abs/2512.06258 - arXiv:2512.06258v1 Announce Type: new -Abstract: We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs): even when these models know the correct answer, they frequently arrive there through incorrect reasoning paths. The core issue is not a lack of knowledge, but a path selection bias within the vast reasoning search space. Although LVLMs are often capable of sampling correct solution trajectories, they disproportionately favor unstable or logically inconsistent ones, leading to erratic and unreliable outcomes. The substantial disparity between Pass@K (with large K) and Pass@1 across numerous models provides compelling evidence that such failures primarily stem from misreasoning rather than ignorance. To systematically investigate and address this issue, we propose PSO (Path-Select Optimization), a two-stage post-training framework designed to enhance both the reasoning performance and stability of existing LVLMs. In the first stage, we employ Group Relative Policy Optimization (GRPO) with template and answer-based rewards to cultivate structured, step-by-step reasoning. In the second stage, we conduct online preference optimization, where the model samples reasoning paths from GRPO-generated data, self-evaluates them, and aligns itself toward the preferred trajectories. Incorrect or suboptimal paths are concurrently stored in a Negative Replay Memory (NRM) as hard negatives, which are periodically revisited to prevent the model from repeating prior mistakes and to facilitate continual reasoning refinement. Extensive experiments show that PSO effectively prunes invalid reasoning paths, substantially enhances reasoning accuracy (with 7.4% improvements on average), and yields more stable and consistent chains of thought. Our code will be available at https://github.com/aiming-lab/PSO. - oai:arXiv.org:2512.06258v1 + Accuracy Does Not Guarantee Human-Likeness in Monocular Depth Estimators + https://arxiv.org/abs/2512.08163 + arXiv:2512.08163v1 Announce Type: new +Abstract: Monocular depth estimation is a fundamental capability for real-world applications such as autonomous driving and robotics. Although deep neural networks (DNNs) have achieved superhuman accuracy on physical-based benchmarks, a key challenge remains: aligning model representations with human perception, a promising strategy for enhancing model robustness and interpretability. Research in object recognition has revealed a complex trade-off between model accuracy and human-like behavior, raising a question whether a similar divergence exist in depth estimation, particularly for natural outdoor scenes where benchmarks rely on sensor-based ground truth rather than human perceptual estimates. In this study, we systematically investigated the relationship between model accuracy and human similarity across 69 monocular depth estimators using the KITTI dataset. To dissect the structure of error patterns on a factor-by-factor basis, we applied affine fitting to decompose prediction errors into interpretable components. Intriguingly, our results reveal while humans and DNNs share certain estimation biases (positive error correlations), we observed distinct trade-off relationships between model accuracy and human similarity. This finding indicates that improving accuracy does not necessarily lead to more human-like behavior, underscoring the necessity of developing multifaceted, human-centric evaluations beyond traditional accuracy. + oai:arXiv.org:2512.08163v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Chaoyang Wang, Yangfan He, Yiyang Zhou, Yixuan Wang, Jiaqi Liu, Peng Xia, Zhengzhong Tu, Mohit Bansal, Huaxiu Yao + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yuki Kubota, Taiki Fukiage - Who Will Top the Charts? Multimodal Music Popularity Prediction via Adaptive Fusion of Modality Experts and Temporal Engagement Modeling - https://arxiv.org/abs/2512.06259 - arXiv:2512.06259v1 Announce Type: new -Abstract: Predicting a song's commercial success prior to its release remains an open and critical research challenge for the music industry. Early prediction of music popularity informs strategic decisions, creative planning, and marketing. Existing methods suffer from four limitations:(i) temporal dynamics in audio and lyrics are averaged away; (ii) lyrics are represented as a bag of words, disregarding compositional structure and affective semantics; (iii) artist- and song-level historical performance is ignored; and (iv) multimodal fusion approaches rely on simple feature concatenation, resulting in poorly aligned shared representations. To address these limitations, we introduce GAMENet, an end-to-end multimodal deep learning architecture for music popularity prediction. GAMENet integrates modality-specific experts for audio, lyrics, and social metadata through an adaptive gating mechanism. We use audio features from Music4AllOnion processed via OnionEnsembleAENet, a network of autoencoders designed for robust feature extraction; lyric embeddings derived through a large language model pipeline; and newly introduced Career Trajectory Dynamics (CTD) features that capture multi-year artist career momentum and song-level trajectory statistics. Using the Music4All dataset (113k tracks), previously explored in MIR tasks but not popularity prediction, GAMENet achieves a 12% improvement in R^2 over direct multimodal feature concatenation. Spotify audio descriptors alone yield an R^2 of 0.13. Integrating aggregate CTD features increases this to 0.69, with an additional 7% gain from temporal CTD features. We further validate robustness using the SpotGenTrack Popularity Dataset (100k tracks), achieving a 16% improvement over the previous baseline. Extensive ablations confirm the model's effectiveness and the distinct contribution of each modality. - oai:arXiv.org:2512.06259v1 - cs.SD + Information-Dense Reasoning for Efficient and Auditable Security Alert Triage + https://arxiv.org/abs/2512.08169 + arXiv:2512.08169v1 Announce Type: new +Abstract: Security Operations Centers face massive, heterogeneous alert streams under minute-level service windows, creating the Alert Triage Latency Paradox: verbose reasoning chains ensure accuracy and compliance but incur prohibitive latency and token costs, while minimal chains sacrifice transparency and auditability. Existing solutions fail: signature systems are brittle, anomaly methods lack actionability, and fully cloud-hosted LLMs raise latency, cost, and privacy concerns. We propose AIDR, a hybrid cloud-edge framework that addresses this trade-off through constrained information-density optimization. The core innovation is gradient-based compression of reasoning chains to retain only decision-critical steps--minimal evidence sufficient to justify predictions while respecting token and latency budgets. We demonstrate that this approach preserves decision-relevant information while minimizing complexity. We construct compact datasets by distilling alerts into 3-5 high-information bullets (68% token reduction), train domain-specialized experts via LoRA, and deploy a cloud-edge architecture: a cloud LLM routes alerts to on-premises experts generating SOAR-ready JSON. Experiments demonstrate AIDR achieves higher accuracy and 40.6% latency reduction versus Chain-of-Thought, with robustness to data corruption and out-of-distribution generalization, enabling auditable and efficient SOC triage with full data residency compliance. + oai:arXiv.org:2512.08169v1 + cs.CR cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Yash Choudhary, Preeti Rao, Pushpak Bhattacharyya + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Guangze Zhao, Yongzheng Zhang, Changbo Tian, Dan Xie, Hongri Liu, Bailing Wang - Safe Model Predictive Diffusion with Shielding - https://arxiv.org/abs/2512.06261 - arXiv:2512.06261v1 Announce Type: new -Abstract: Generating safe, kinodynamically feasible, and optimal trajectories for complex robotic systems is a central challenge in robotics. This paper presents Safe Model Predictive Diffusion (Safe MPD), a training-free diffusion planner that unifies a model-based diffusion framework with a safety shield to generate trajectories that are both kinodynamically feasible and safe by construction. By enforcing feasibility and safety on all samples during the denoising process, our method avoids the common pitfalls of post-processing corrections, such as computational intractability and loss of feasibility. We validate our approach on challenging non-convex planning problems, including kinematic and acceleration-controlled tractor-trailer systems. The results show that it substantially outperforms existing safety strategies in success rate and safety, while achieving sub-second computation times. - oai:arXiv.org:2512.06261v1 + RAVES-Calib: Robust, Accurate and Versatile Extrinsic Self Calibration Using Optimal Geometric Features + https://arxiv.org/abs/2512.08170 + arXiv:2512.08170v1 Announce Type: new +Abstract: In this paper, we present a user-friendly LiDAR-camera calibration toolkit that is compatible with various LiDAR and camera sensors and requires only a single pair of laser points and a camera image in targetless environments. Our approach eliminates the need for an initial transform and remains robust even with large positional and rotational LiDAR-camera extrinsic parameters. We employ the Gluestick pipeline to establish 2D-3D point and line feature correspondences for a robust and automatic initial guess. To enhance accuracy, we quantitatively analyze the impact of feature distribution on calibration results and adaptively weight the cost of each feature based on these metrics. As a result, extrinsic parameters are optimized by filtering out the adverse effects of inferior features. We validated our method through extensive experiments across various LiDAR-camera sensors in both indoor and outdoor settings. The results demonstrate that our method provides superior robustness and accuracy compared to SOTA techniques. Our code is open-sourced on GitHub to benefit the community. + oai:arXiv.org:2512.08170v1 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Taekyung Kim, Keyvan Majd, Hideki Okamoto, Bardh Hoxha, Dimitra Panagou, Georgios Fainekos + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Haoxin Zhang, Shuaixin Li, Xiaozhou Zhu, Hongbo Chen, Wen Yao - Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models - https://arxiv.org/abs/2512.06266 - arXiv:2512.06266v1 Announce Type: new -Abstract: We present Nanbeige4-3B, a family of small-scale but high-performing language models. Pretrained on 23T high-quality tokens and finetuned on over 30 million diverse instructions, we extend the boundary of the scaling law for small language models. In pre-training, we design a Fine-Grained Warmup-Stable-Decay (FG-WSD) training scheduler, which progressively refines data mixtures across stages to boost model performance. In post-training, to improve the quality of the SFT data, we design a joint mechanism that integrates deliberative generation refinement and chain-of-thought reconstruction, yielding substantial gains on complex tasks. Following SFT, we employ our flagship reasoning model to distill Nanbeige4-3B through our proposed Dual Preference Distillation (DPD) method, which leads to further performance gains. Finally, a multi-stage reinforcement learning phase was applied, leveraging verifiable rewards and preference modeling to strengthen abilities on both reasoning and human alignment. Extensive evaluations show that Nanbeige4-3B not only significantly outperforms models of comparable parameter scale but also rivals much larger models across a wide range of benchmarks. The model checkpoints are available at https://huggingface.co/Nanbeige. - oai:arXiv.org:2512.06266v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Security Analysis of Integer Learning with Errors with Rejection Sampling + https://arxiv.org/abs/2512.08172 + arXiv:2512.08172v1 Announce Type: new +Abstract: At ASIACRYPT 2018, a digital attack based on linear least squares was introduced for a variant of the learning with errors (LWE) problem which omits modular reduction known as the integer learning with errors problem (ILWE). In this paper, we present a theoretical and experimental study of the effectiveness of the attack when applied directly to small parameter ILWE instances found in popular digital signature schemes such as CRYSTALS-Dilithium which utilize rejection sampling. Unlike other studies which form ILWE instances based on additional information obtained from side-channel attacks, we take a more direct approach to the problem by constructing our ILWE instance from only the obtained signatures. We outline and introduce novel techniques in our simulation designs such as modular polynomial arithmetic via matrices in $\mathbb{R}$, as well as algorithms for handling large sample sizes efficiently. Our experimental results reinforce the proclaimed security of signature schemes based on ILWE. We additionally discuss the implications of our work and digital signatures as a whole in regards to real-world applications such as in Intelligent Transportation Systems (ITS). + oai:arXiv.org:2512.08172v1 + cs.CR + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Chen Yang, Guangyue Peng, Jiaying Zhu, Ran Le, Ruixiang Feng, Tao Zhang, Wei Ruan, Xiaoqi Liu, Xiaoxue Cheng, Xiyun Xu, Yang Song, Yanzipeng Gao, Yiming Jia, Yun Xing, Yuntao Wen, Zekai Wang, Zhenwei An, Zhicong Sun, Zongchao Chen + Kyle Yates, Antsa Pierrottet, Abdullah Al Mamun, Ryann Cartor, Mashrur Chowdhury, Shuhong Gao - A Physics-Informed Fixed Skyroad Model for Continuous UAS Traffic Management (C-UTM) - https://arxiv.org/abs/2512.06268 - arXiv:2512.06268v1 Announce Type: new -Abstract: Unlike traditional multi-agent coordination frameworks, which assume a fixed number of agents, UAS traffic management (UTM) requires a platform that enables Uncrewed Aerial Systems (UAS) to freely enter or exit constrained low-altitude airspace. Consequently, the number of UAS operating in a given region is time-varying, with vehicles dynamically joining or leaving even in dense, obstacle-laden environments. The primary goal of this paper is to develop a computationally efficient management system that maximizes airspace usability while ensuring safety and efficiency. To achieve this, we first introduce physics-informed methods to structure fixed skyroads across multiple altitude layers of urban airspace, with the directionality of each skyroad designed to guarantee full reachability. We then present a novel Continuous UTM (C-UTM) framework that optimally allocates skyroads to UAS requests while accounting for the time-varying capacity of the airspace. Collectively, the proposed model addresses the key challenges of low-altitude UTM by providing a scalable, safe, and efficient solution for urban airspace usability. - oai:arXiv.org:2512.06268v1 - eess.SY - cs.MA - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + The Instability of Painlev\'e Equations in Recovering Largest Eigenvalue Distributions of GUE, LUE, JUE and an Attempt of Solution to It + https://arxiv.org/abs/2512.08178 + arXiv:2512.08178v1 Announce Type: new +Abstract: The distribution of the largest eigenvalue for the three classical unitary ensembles -- GUE, LUE, and JUE -- admits two complementary exact descriptions: (i) as Fredholm determinants of their orthogonal--polynomial correlation kernels and (ii) as isomonodromic $\tau$--functions governed by Painlev\'e equations. For finite $n$, the associated Jimbo--Miwa--Okamoto $\sigma$--forms are $\PIV$ (GUE), $\mathrm{PV}$ (LUE), and $\PVI$ (JUE); under soft- or hard-edge scalings these degenerate to $\PII$ or $\PIIIp$ descriptions of the Tracy--Widom and hard-edge laws \cite{tracy1994level,forrester2003painleve,deift1999orthogonal}. + It is well known among random matrix theorists (for example Folkmar Bornemann) that the Fredholm determinant is a more numerically stable and accurate way to compute the CDF of the largest eigenvalue for GUE, LUE, JUE than direct Painlev\'e integration. The aim of this paper is not to improve on Fredholm methods, but to see to what extent one can numerically recover the \emph{correct} Painlev\'e solution from finite-$n$ data and how unstable this reconstruction is. Numerically, we verify the equality between the Fredholm- and Painlev\'e-based CDFs by combining (a) high-accuracy Nystr\"om discretizations of the finite-$n$ Fredholm determinants \cite{bornemann2010numerical} with (b) an anchored, branch-locked integration of the $\sigma$--form ODEs, where anchors are extracted from local least-squares fits to $\log\det(I-\mathsf K)$. Our results confirm agreement across GUE/LUE/JUE with precision of $O(10^{-3})$ to $O(10^{-5})$ (occasionally $O(10^{-2})$) and illustrate the finite-$n$ to scaling-limit transition. The theoretical connections to $\tau$--functions and Virasoro constraints follow the framework of \cite{adler2000random,forrester2003painleve} + oai:arXiv.org:2512.08178v1 + math.NA + cs.NA + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Muhammad Junayed Hasan Zahed, Hossein Rastgoftar + Haonan Gu - TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting - https://arxiv.org/abs/2512.06269 - arXiv:2512.06269v1 Announce Type: new -Abstract: 3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by penalizing the deviation of a rendered 3D point from a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility. - oai:arXiv.org:2512.06269v1 + GeoLoom: High-quality Geometric Diagram Generation from Textual Input + https://arxiv.org/abs/2512.08180 + arXiv:2512.08180v1 Announce Type: new +Abstract: High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geometry problem solving that employ formal languages and symbolic solvers for enhanced correctness and interpretability, we propose GeoLoom, a novel framework for text-to-diagram generation in geometric domains. GeoLoom comprises two core components: an autoformalization module that translates natural language into a specifically designed generation-oriented formal language GeoLingua, and a coordinate solver that maps formal constraints to precise coordinates using the efficient Monte Carlo optimization. To support this framework, we introduce GeoNF, a dataset aligning natural language geometric descriptions with formal GeoLingua descriptions. We further propose a constraint-based evaluation metric that quantifies structural deviation, offering mathematically grounded supervision for iterative refinement. Empirical results demonstrate that GeoLoom significantly outperforms state-of-the-art baselines in structural fidelity, providing a principled foundation for interpretable and scalable diagram generation. + oai:arXiv.org:2512.08180v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xiaojing Wei, Ting Zhang, Wei He, Jingdong Wang, Hua Huang + + + Framing Climate Change on YouTube: North-South Divides in Narratives and Public Engagement + https://arxiv.org/abs/2512.08183 + arXiv:2512.08183v1 Announce Type: new +Abstract: Climate change debates have gained increasing visibility on social media, with YouTube emerging as one of the most influential platforms for political communication. Reaching billions of users worldwide, it functions both as a news outlet and as a space for public discourse. While existing studies of climate discourse on YouTube often adopt a global perspective, this study examines the platform through the lens of the Global North-South divide. We analyse a dataset of 758 climate-related videos and their comment sections, applying topic modelling and sentiment analysis to identify recurring discursive patterns. Through these patterns, we recognise parallels with respect to debates in international climate negotiations. The findings reveal notable differences. Videos from the Global North and Global South reflect real-world divides, with the North emphasising the need for policies to curb carbon emissions, while the South highlights developmental priorities. A key area of convergence between the regions lies in the shared recognition of the importance of emissions reduction and international agreements. Audience responses, however, diverge more sharply: comment sections under Global North videos are dominated by criticism, conspiracy, and climate fatigue, whereas those under Global South videos are generally more supportive, constructive, and knowledge-oriented. Overall, the study demonstrates how YouTube reflects and reshapes global climate politics, while also revealing the gap between curated narratives and public sentiment. Bridging these divides may contribute to more inclusive and cooperative approaches to climate action. + oai:arXiv.org:2512.08183v1 + cs.SI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - WACV 2026 - Quan Tran, Tuan Dang + Sanika Damle, Radhika Krishnan - Networked Restless Multi-Arm Bandits with Reinforcement Learning - https://arxiv.org/abs/2512.06274 - arXiv:2512.06274v1 Announce Type: new -Abstract: Restless Multi-Armed Bandits (RMABs) are a powerful framework for sequential decision-making, widely applied in resource allocation and intervention optimization challenges in public health. However, traditional RMABs assume independence among arms, limiting their ability to account for interactions between individuals that can be common and significant in a real-world environment. This paper introduces Networked RMAB, a novel framework that integrates the RMAB model with the independent cascade model to capture interactions between arms in networked environments. We define the Bellman equation for networked RMAB and present its computational challenge due to exponentially large action and state spaces. To resolve the computational challenge, we establish the submodularity of Bellman equation and apply the hill-climbing algorithm to achieve a $1-\frac{1}{e}$ approximation guarantee in Bellman updates. Lastly, we prove that the approximate Bellman updates are guaranteed to converge by a modified contraction analysis. We experimentally verify these results by developing an efficient Q-learning algorithm tailored to the networked setting. Experimental results on real-world graph data demonstrate that our Q-learning approach outperforms both $k$-step look-ahead and network-blind approaches, highlighting the importance of capturing and leveraging network effects where they exist. - oai:arXiv.org:2512.06274v1 - cs.LG + A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities Across Clinical Specialties + https://arxiv.org/abs/2512.08185 + arXiv:2512.08185v1 Announce Type: new +Abstract: Medical Large Language Models (LLMs) are increasingly deployed for clinical decision support across diverse specialties, yet systematic evaluation of their robustness to adversarial misuse and privacy leakage remains inaccessible to most researchers. Existing security benchmarks require GPU clusters, commercial API access, or protected health data -- barriers that limit community participation in this critical research area. We propose a practical, fully reproducible framework for evaluating medical AI security under realistic resource constraints. Our framework design covers multiple medical specialties stratified by clinical risk -- from high-risk domains such as emergency medicine and psychiatry to general practice -- addressing jailbreaking attacks (role-playing, authority impersonation, multi-turn manipulation) and privacy extraction attacks. All evaluation utilizes synthetic patient records requiring no IRB approval. The framework is designed to run entirely on consumer CPU hardware using freely available models, eliminating cost barriers. We present the framework specification including threat models, data generation methodology, evaluation protocols, and scoring rubrics. This proposal establishes a foundation for comparative security assessment of medical-specialist models and defense mechanisms, advancing the broader goal of ensuring safe and trustworthy medical AI systems. + oai:arXiv.org:2512.08185v1 + cs.CR cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Hanmo Zhang, Zenghui Sun, Kai Wang + Jinghao Wang, Ping Zhang, Carter Yagemann - FacePhys: State of the Heart Learning - https://arxiv.org/abs/2512.06275 - arXiv:2512.06275v1 Announce Type: new -Abstract: Vital sign measurement using cameras presents opportunities for comfortable, ubiquitous health monitoring. Remote photoplethysmography (rPPG), a foundational technology, enables cardiac measurement through minute changes in light reflected from the skin. However, practical deployment is limited by the computational constraints of performing analysis on front-end devices and the accuracy degradation of transmitting data through compressive channels that reduce signal quality. We propose a memory efficient rPPG algorithm - \emph{FacePhys} - built on temporal-spatial state space duality, which resolves the trilemma of model scalability, cross-dataset generalization, and real-time operation. Leveraging a transferable heart state, FacePhys captures subtle periodic variations across video frames while maintaining a minimal computational overhead, enabling training on extended video sequences and supporting low-latency inference. FacePhys establishes a new state-of-the-art, with a substantial 49\% reduction in error. Our solution enables real-time inference with a memory footprint of 3.6 MB and per-frame latency of 9.46 ms -- surpassing existing methods by 83\% to 99\%. These results translate into reliable real-time performance in practical deployments, and a live demo is available at https://www.facephys.com/. - oai:arXiv.org:2512.06275v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation + https://arxiv.org/abs/2512.08186 + arXiv:2512.08186v1 Announce Type: new +Abstract: While recent large vision-language models (VLMs) have improved generalization in vision-language navigation (VLN), existing methods typically rely on end-to-end pipelines that map vision-language inputs directly to short-horizon discrete actions. Such designs often produce fragmented motions, incur high latency, and struggle with real-world challenges like dynamic obstacle avoidance. We propose DualVLN, the first dual-system VLN foundation model that synergistically integrates high-level reasoning with low-level action execution. System 2, a VLM-based global planner, "grounds slowly" by predicting mid-term waypoint goals via image-grounded reasoning. System 1, a lightweight, multi-modal conditioning Diffusion Transformer policy, "moves fast" by leveraging both explicit pixel goals and latent features from System 2 to generate smooth and accurate trajectories. The dual-system design enables robust real-time control and adaptive local decision-making in complex, dynamic environments. By decoupling training, the VLM retains its generalization, while System 1 achieves interpretable and effective local navigation. DualVLN outperforms prior methods across all VLN benchmarks and real-world experiments demonstrate robust long-horizon planning and real-time adaptability in dynamic environments. + oai:arXiv.org:2512.08186v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Kegang Wang, Jiankai Tang, Yuntao Wang, Xin Liu, Yuxuan Fan, Jiatong Ji, Yuanchun Shi, Daniel McDuff + http://creativecommons.org/licenses/by/4.0/ + Meng Wei, Chenyang Wan, Jiaqi Peng, Xiqian Yu, Yuqiang Yang, Delin Feng, Wenzhe Cai, Chenming Zhu, Tai Wang, Jiangmiao Pang, Xihui Liu - RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension - https://arxiv.org/abs/2512.06276 - arXiv:2512.06276v1 Announce Type: new -Abstract: Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description. Existing REC benchmarks primarily evaluate perceptual capabilities and lack interpretable scoring mechanisms, which cannot reveal the grounding capability of Multi-modal Large Language Model (MLLM) across different cognitive abilities. To address this limitation, we introduce RefBench-PRO, a comprehensive REC benchmark, which decomposes referring expressions into two core dimensions, i.e., perception and reasoning, and further subdivides them into six progressively challenging tasks, such as attribute, position, interaction, commonsense, relation and reject. We also develop a fully automated data-generation pipeline that produces diverse referring expressions across these six sub-dimensions. Furthermore, We propose Ref-R1, an RL-based learning scheme, which incorporates Dynamic IoU-based GRPO to improve localization accuracy under increasingly complex reasoning conditions, establishing a stronger baseline for REC. Extensive experiments demonstrate that our RefBench-PRO enables interpretable evaluation of MLLM on referring expression comprehension, presenting greater challenges in both perception and reasoning. - oai:arXiv.org:2512.06276v1 - cs.CV + Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model + https://arxiv.org/abs/2512.08188 + arXiv:2512.08188v1 Announce Type: new +Abstract: World models have emerged as a pivotal component in robot manipulation planning, enabling agents to predict future environmental states and reason about the consequences of actions before execution. While video-generation models are increasingly adopted, they often lack rigorous physical grounding, leading to hallucinations and a failure to maintain consistency in long-horizon physical constraints. To address these limitations, we propose Embodied Tree of Thoughts (EToT), a novel Real2Sim2Real planning framework that leverages a physics-based interactive digital twin as an embodied world model. EToT formulates manipulation planning as a tree search expanded through two synergistic mechanisms: (1) Priori Branching, which generates diverse candidate execution paths based on semantic and spatial analysis; and (2) Reflective Branching, which utilizes VLMs to diagnose execution failures within the simulator and iteratively refine the planning tree with corrective actions. By grounding high-level reasoning in a physics simulator, our framework ensures that generated plans adhere to rigid-body dynamics and collision constraints. We validate EToT on a suite of short- and long-horizon manipulation tasks, where it consistently outperforms baselines by effectively predicting physical dynamics and adapting to potential failures. Website at https://embodied-tree-of-thoughts.github.io . + oai:arXiv.org:2512.08188v1 + cs.RO cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tianyi Gao, Hao Li, Han Fang, Xin Wei, Xiaodong Dong, Hongbo Sun, Ye Yuan, Zhongjiang He, Jinglin Xu, Jingmin Xin, Hao Sun + Wenjiang Xu, Cindy Wang, Rui Fang, Mingkang Zhang, Lusong Li, Jing Xu, Jiayuan Gu, Zecui Zeng, Rui Chen - Scale-free weak output synchronization of multi-agent systems with adaptive protocols - https://arxiv.org/abs/2512.06278 - arXiv:2512.06278v1 Announce Type: new -Abstract: In this paper, we study output synchronization for multi-agent systems. The objective is to design a protocol which only depends on the agent dynamics and does not require any knowledge of the network. If the network has a directed spanning tree then the protocols designed in this paper achieve classical output synchronization. Otherwise, the protocol achieves weak synchronization which is induced by network stability in the sense that the signals exchanged over the network converge to zero. Weak sychronization is explained in detail in this paper. Even though we consider linear agents, it is known that this in general requires nonlinear protocols. In the paper we use adaptive protocols. In the literature, two classes of protocols are considered often called collaborative protocols (with additional communication between the protocols and non-collaborative protocols (sometimes referred to as fully decentralized where the additional communication is not present). This paper considers both of these cases. - oai:arXiv.org:2512.06278v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access + https://arxiv.org/abs/2512.08193 + arXiv:2512.08193v1 Announce Type: new +Abstract: We present ClinicalTrialsHub, an interactive search-focused platform that consolidates all data from ClinicalTrials.gov and augments it by automatically extracting and structuring trial-relevant information from PubMed research articles. Our system effectively increases access to structured clinical trial data by 83.8% compared to relying on ClinicalTrials.gov alone, with potential to make access easier for patients, clinicians, researchers, and policymakers, advancing evidence-based medicine. ClinicalTrialsHub uses large language models such as GPT-5.1 and Gemini-3-Pro to enhance accessibility. The platform automatically parses full-text research articles to extract structured trial information, translates user queries into structured database searches, and provides an attributed question-answering system that generates evidence-grounded answers linked to specific source sentences. We demonstrate its utility through a user study involving clinicians, clinical researchers, and PhD students of pharmaceutical sciences and nursing, and a systematic automatic evaluation of its information extraction and question answering capabilities. + oai:arXiv.org:2512.08193v1 + cs.CL + cs.AI + cs.HC + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Anton A. Stoorvogel, Ali Saberi, Zhenwei Liu, Qiaofeng Wen + http://creativecommons.org/licenses/by/4.0/ + Jiwoo Park, Ruoqi Liu, Avani Jagdale, Andrew Srisuwananukorn, Jing Zhao, Lang Li, Ping Zhang, Sachin Kumar - Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models - https://arxiv.org/abs/2512.06281 - arXiv:2512.06281v1 Announce Type: new -Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalance issue, where visual information is often underutilized compared to textual representations in deeper layers, leading to degraded visual performance or hallucinations. This issue stems from the predominant reliance on next-text-token-prediction during training, which fails to provide direct visual supervisory signals, resulting in progressive homogenization of visual representations throughout the layers. To this end, we propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discriminative visual representations via masked image modeling in the joint latent semantic space of LLM. Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information. Extensive experiments across diverse benchmarks prove the superiority of our approach in various scenarios, especially those requiring dense visual capabilities. Code of LaVer is available at https://github.com/Fir-lat/LaVer. - oai:arXiv.org:2512.06281v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Integrating Delay-Absorption Capability into Flight Departure Delay Prediction + https://arxiv.org/abs/2512.08197 + arXiv:2512.08197v1 Announce Type: new +Abstract: Accurately forecasting flight departure delays is essential for improving operational efficiency and mitigating the cascading disruptions that propagate through tightly coupled aircraft rotations. Traditional machine learning approaches often treat upstream delays as static variables, overlooking the dynamic recovery processes that determine whether a delay is absorbed or transmitted to subsequent legs. This study introduces a two-stage machine learning framework that explicitly models delay-absorption behavior and incorporates it into downstream delay prediction. In Stage I, a CatBoost classifier estimates the probability that a flight successfully absorbs an upstream delay based on operational, temporal, and meteorological features. This probability, termed AbsorbScore, quantifies airport- and flight-specific resilience to delay propagation. In Stage II, an XGBoost classifier integrates AbsorbScore with schedule, weather, and congestion indicators to predict whether a flight will depart more than 15 minutes late. Using U.S. domestic flight and NOAA weather data from Summer 2023, the proposed framework achieves substantial improvements over baseline models, increasing ROC-AUC from 0.865 to 0.898 and enhancing precision to 89.2% in identifying delayed flights. The results demonstrate that modeling delay absorption as an intermediate mechanism significantly improves predictive performance and yields interpretable insights into airport recovery dynamics, offering a practical foundation for data-driven delay management and proactive operational planning. + oai:arXiv.org:2512.08197v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Hengzhuang Li, Xinsong Zhang, Qiming Peng, Bin Luo, Han Hu, Dengyang Jiang, Han-Jia Ye, Teng Zhang, Hai Jin + Jianyang Zhou - A Sleep Monitoring System Based on Audio, Video and Depth Information - https://arxiv.org/abs/2512.06282 - arXiv:2512.06282v1 Announce Type: new -Abstract: For quantitative evaluation of sleep disturbances, a noninvasive monitoring system is developed by introducing an event-based method. We observe sleeping in home context and classify the sleep disturbances into three types of events: motion events, light-on/off events and noise events. A device with an infrared depth sensor, a RGB camera, and a four-microphone array is used in sleep monitoring in an environment with barely light sources. One background model is established in depth signals for measuring magnitude of movements. Because depth signals cannot observe lighting changes, another background model is established in color images for measuring magnitude of lighting effects. An event detection algorithm is used to detect occurrences of events from the processed data of the three types of sensors. The system was tested in sleep condition and the experiment result validates the system reliability. - oai:arXiv.org:2512.06282v1 + Animal Re-Identification on Microcontrollers + https://arxiv.org/abs/2512.08198 + arXiv:2512.08198v1 Announce Type: new +Abstract: Camera-based animal re-identification (Animal Re-ID) can support wildlife monitoring and precision livestock management in large outdoor environments with limited wireless connectivity. In these settings, inference must run directly on collar tags or low-power edge nodes built around microcontrollers (MCUs), yet most Animal Re-ID models are designed for workstations or servers and are too large for devices with small memory and low-resolution inputs. We propose an on-device framework. First, we characterise the gap between state-of-the-art Animal Re-ID models and MCU-class hardware, showing that straightforward knowledge distillation from large teachers offers limited benefit once memory and input resolution are constrained. Second, guided by this analysis, we design a high-accuracy Animal Re-ID architecture by systematically scaling a CNN-based MobileNetV2 backbone for low-resolution inputs. Third, we evaluate the framework with a real-world dataset and introduce a data-efficient fine-tuning strategy to enable fast adaptation with just three images per animal identity at a new site. Across six public Animal Re-ID datasets, our compact model achieves competitive retrieval accuracy while reducing model size by over two orders of magnitude. On a self-collected cattle dataset, the deployed model performs fully on-device inference with only a small accuracy drop and unchanged Top-1 accuracy relative to its cluster version. We demonstrate that practical, adaptable Animal Re-ID is achievable on MCU-class devices, paving the way for scalable deployment in real field environments. + oai:arXiv.org:2512.08198v1 cs.CV - cs.MM - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lyn Chao-ling Chen, Kuan-Wen Chen, Yi-Ping Hung + http://creativecommons.org/licenses/by/4.0/ + Yubo Chen, Di Zhao, Yun Sing Koh, Talia Xu - Optimal Platoon Formation and Stable Benefit Allocation in Mixed-Energy Truck Fleets under Size Limitations - https://arxiv.org/abs/2512.06283 - arXiv:2512.06283v1 Announce Type: new -Abstract: In this paper, we investigate cooperative platoon formation and benefit allocation in mixed-energy truck fleets composed of both electric and fuel-powered trucks. The central challenge arises from the platoon-size constraint, which limits the number of trucks permitted in each platoon and introduces combinatorial coupling into the search for optimal platoon formation structures. We formulate this problem as a coalitional game with bounded coalition sizes and derive a closed-form characterization of the optimal coalition structure that maximizes the fleet-wide platooning benefit. Building on this structure, we develop a type-based least-core payoff allocation scheme that guarantees stability within the coalition-structure core (CS-core). For cases in which the CS-core is empty, we compute the least-core radius to determine the minimal relaxation required to achieve approximate stability. Through numerical studies, we demonstrate that the proposed framework consistently achieves the highest total platooning benefit among all feasible formation configurations while providing stable benefit allocations that outperform existing baseline methods. - oai:arXiv.org:2512.06283v1 + Bounding the Minimal Current Harmonic Distortion in Optimal Modulation of Single-Phase Power Converters + https://arxiv.org/abs/2512.08201 + arXiv:2512.08201v1 Announce Type: new +Abstract: Optimal pulse patterns (OPPs) are a modulation technique in which a switching signal is computed offline through an optimization process that accounts for selected performance criteria, such as current harmonic distortion. The optimization determines both the switching angles (i.e., switching times) and the pattern structure (i.e., the sequence of voltage levels). This optimization task is a challenging mixed-integer nonconvex problem, involving integer-valued voltage levels and trigono metric nonlinearities in both the objective and the constraints. We address this challenge by reinterpreting OPP design as a periodic mode-selecting optimal control problem of a hybrid system, where selecting angles and levels corresponds to choosing jump times in a transition graph. This time-domain formulation enables the direct use of convex-relaxation techniques from optimal control, producing a hierarchy of semidefinite programs that lower-bound the minimal achievable harmonic distortion and scale subquadratically with the number of converter levels and switching angles. Numerical results demonstrate the effectiveness of the proposed approachs + oai:arXiv.org:2512.08201v1 eess.SY cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ting Bai, Xinfeng Ru, Andreas A. Malikopoulos + Jared Miller, Petros Karamanakos, Tobias Geyer - Distributionally Robust Kalman Filter - https://arxiv.org/abs/2512.06286 - arXiv:2512.06286v1 Announce Type: new -Abstract: In this work, we propose a noise-centric formulation of the distributionally robust Kalman filter (DRKF) for discrete-time linear stochastic systems with uncertain noise statistics. By placing Wasserstein ambiguity sets directly on the process and measurement noise distributions, the proposed DRKF preserves the analytical structure of the classical Kalman filter while providing a priori spectral bounds on all feasible covariances. In the time-invariant setting, we derive a steady-state DRKF from a single stationary semidefinite program, yielding a constant-gain estimator with the same per-step computational complexity as the standard Kalman filter. We establish conditions guaranteeing the existence, uniqueness, and convergence of this steady-state solution, and we prove its asymptotic minimax optimality with respect to the worst-case mean-square error. Numerical experiments validate the theory and demonstrate that the proposed DRKF improves estimation accuracy under unknown or uncertain noise models while offering computational advantages over existing robust and distributionally robust filters. - oai:arXiv.org:2512.06286v1 - eess.SY - cs.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Error-Resilient Semantic Communication for Speech Transmission over Packet-Loss Networks + https://arxiv.org/abs/2512.08203 + arXiv:2512.08203v1 Announce Type: new +Abstract: Real-time speech communication over wireless networks remains challenging, as conventional channel protection mechanisms cannot effectively counter packet loss under stringent bandwidth and latency constraints. Semantic communication has emerged as a promising paradigm for enhancing the robustness of speech transmission by means of joint source-channel coding (JSCC). However, its cross-layer design hinders practical deployment due to the incompatibility with existing digital communication systems. In this case, the robustness of speech communication is consequently evaluated primarily by the error-resilience to packet loss over wireless networks. To address these challenges, we propose \emph{Glaris}, a generative latent-prior-based resilient speech semantic communication framework that performs resilient speech coding in the generative latent space. Generative latent priors enable high-quality packet loss concealment (PLC) at the receiver side, well-balancing semantic consistency and reconstruction fidelity. Additionally, an integrated error resilience mechanism is designed to mitigate the error propagation and improve the effectiveness of PLC. Compared with traditional packet-level forward error correction (FEC) strategies, our new method achieves enhanced robustness over dynamic wireless networks while reducing redundancy overhead significantly. Experimental results on the LibriSpeech dataset demonstrate that \emph{Glaris} consistently outperforms existing error-resilient codecs, achieving JSCC-level robustness while maintaining seamless compatibility with existing systems, and it also strikes a favorable balance between transmission efficiency and speech reconstruction quality. + oai:arXiv.org:2512.08203v1 + cs.SD + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Minhyuk Jang, Astghik Hakobyan, Insoon Yang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zhuohang Han, Jincheng Dai, Shengshi Yao, Junyi Wang, Yanlong Li, Kai Niu, Wenjun Xu, Ping Zhang - A Hybrid Physics-Based and Reinforcement Learning Framework for Electric Vehicle Charging Time Prediction - https://arxiv.org/abs/2512.06287 - arXiv:2512.06287v1 Announce Type: new -Abstract: In this paper, we develop a hybrid prediction framework for accurate electric vehicle (EV) charging time estimation, a capability that is critical for trip planning, user satisfaction, and efficient operation of charging infrastructure. We combine a physics-based analytical model with a reinforcement learning (RL) approach. The analytical component captures the nonlinear constant-current/constant-voltage (CC--CV) charging dynamics and explicitly models state-of-health (SoH)--dependent capacity and power fade, providing a reliable baseline when historical data are limited. Building on this foundation, we introduce an RL component that progressively refines charging-time predictions as operational data accumulate, enabling improved long-term adaptation. Both models incorporate SoH degradation to maintain predictive accuracy over the battery lifetime. We evaluate the framework using $5{,}000$ simulated charging sessions calibrated to manufacturer specifications and publicly available EV charging datasets. Our results show that the analytical model achieves $R^{2}=98.5\%$ and $\mathrm{MAPE}=2.1\%$, while the RL model further improves performance to $R^{2}=99.2\%$ and $\mathrm{MAPE}=1.6\%$, corresponding to a $23\%$ accuracy gain and $35\%$ improved robustness to battery aging. - oai:arXiv.org:2512.06287v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Evaluating Vulnerabilities of Connected Vehicles Under Cyber Attacks by Attack-Defense Tree + https://arxiv.org/abs/2512.08204 + arXiv:2512.08204v1 Announce Type: new +Abstract: Connected vehicles represent a key enabler of intelligent transportation systems, where vehicles are equipped with advanced communication, sensing, and computing technologies to interact not only with one another but also with surrounding infrastructures and the environment. Through continuous data exchange, such vehicles are capable of enhancing road safety, improving traffic efficiency, and ensuring more reliable mobility services. Further, when these capabilities are integrated with advanced automation technologies, the concept essentially evolves into connected and autonomous vehicles (CAVs). While connected vehicles primarily focus on seamless information sharing, autonomous vehicles are mainly dependent on advanced perception, decision-making, and control mechanisms to operate with minimal or without human intervention. However, as a result of connectivity, an adversary with malicious intentions might be able to compromise successfully by breaching the system components of CAVs. In this paper, we present an attack-tree based methodology for evaluating cyber security vulnerabilities in CAVs. In particular, we utilize the attack-defense tree formulation to systematically assess attack-leaf vulnerabilities, and before analyzing the vulnerability indices, we also define a measure of vulnerabilities, which is based on existing cyber security threats and corresponding defensive countermeasures. + oai:arXiv.org:2512.08204v1 + cs.CR + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Praharshitha Aryasomayajula, Ting Bai, Andreas A. Malikopoulos + Muhammad Baqer Mollah, Honggang Wang, Hua Fang - Theoretical Compression Bounds for Wide Multilayer Perceptrons - https://arxiv.org/abs/2512.06288 - arXiv:2512.06288v1 Announce Type: new -Abstract: Pruning and quantization techniques have been broadly successful in reducing the number of parameters needed for large neural networks, yet theoretical justification for their empirical success falls short. We consider a randomized greedy compression algorithm for pruning and quantization post-training and use it to rigorously show the existence of pruned/quantized subnetworks of multilayer perceptrons (MLPs) with competitive performance. We further extend our results to structured pruning of MLPs and convolutional neural networks (CNNs), thus providing a unified analysis of pruning in wide networks. Our results are free of data assumptions, and showcase a tradeoff between compressibility and network width. The algorithm we consider bears some similarities with Optimal Brain Damage (OBD) and can be viewed as a post-training randomized version of it. The theoretical results we derive bridge the gap between theory and application for pruning/quantization, and provide a justification for the empirical success of compression in wide multilayer perceptrons. - oai:arXiv.org:2512.06288v1 - cs.LG - math.ST - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 + High-Performance Dual-Arm Task and Motion Planning for Tabletop Rearrangement + https://arxiv.org/abs/2512.08206 + arXiv:2512.08206v1 Announce Type: new +Abstract: We propose Synchronous Dual-Arm Rearrange- ment Planner (SDAR), a task and motion planning (TAMP) framework for tabletop rearrangement, where two robot arms equipped with 2-finger grippers must work together in close proximity to rearrange objects whose start and goal config- urations are strongly entangled. To tackle such challenges, SDAR tightly knit together its dependency-driven task planner (SDAR-T) and synchronous dual-arm motion planner (SDAR- M), to intelligently sift through a large number of possible task and motion plans. Specifically, SDAR-T applies a simple yet effective strategy to decompose the global object dependency graph induced by the rearrangement task, to produce more optimal dual-arm task plans than solutions derived from optimal task plans for a single arm. Leveraging state-of-the-art GPU SIMD-based motion planning tools, SDAR-M employs a layered motion planning strategy to sift through many task plans for the best synchronous dual-arm motion plan while ensuring high levels of success rate. Comprehensive evaluation demonstrates that SDAR delivers a 100% success rate in solving complex, non-monotone, long-horizon tabletop rearrangement tasks with solution quality far exceeding the previous state- of-the-art. Experiments on two UR-5e arms further confirm SDAR directly and reliably transfers to robot hardware. + oai:arXiv.org:2512.08206v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Houssam El Cheairi, David Gamarnik, Rahul Mazumder + http://creativecommons.org/licenses/by/4.0/ + Duo Zhang, Junshan Huang, Jingjin Yu - StrokeNet: Unveiling How to Learn Fine-Grained Interactions in Online Handwritten Stroke Classification - https://arxiv.org/abs/2512.06290 - arXiv:2512.06290v1 Announce Type: new -Abstract: Stroke classification remains challenging due to variations in writing style, ambiguous content, and dynamic writing positions. The core challenge in stroke classification is modeling the semantic relationships between strokes. Our observations indicate that stroke interactions are typically localized, making it difficult for existing deep learning methods to capture such fine-grained relationships. Although viewing strokes from a point-level perspective can address this issue, it introduces redundancy. However, by selecting reference points and using their sequential order to represent strokes in a fine-grained manner, this problem can be effectively solved. This insight inspired StrokeNet, a novel network architecture encoding strokes as reference pair representations (points + feature vectors), where reference points enable spatial queries and features mediate interaction modeling. Specifically, we dynamically select reference points for each stroke and sequence them, employing an Inline Sequence Attention (ISA) module to construct contextual features. To capture spatial feature interactions, we devised a Cross-Ellipse Query (CEQ) mechanism that clusters reference points and extracts features across varying spatial scales. Finally, a joint optimization framework simultaneously predicts stroke categories via reference points regression and adjacent stroke semantic transition modeling through an Auxiliary Branch (Aux-Branch). Experimental results show that our method achieves state-of-the-art performance on multiple public online handwritten datasets. Notably, on the CASIA-onDo dataset, the accuracy improves from 93.81$\%$ to 95.54$\%$, demonstrating the effectiveness and robustness of our approach. - oai:arXiv.org:2512.06290v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Duct boundary conditions for incompressible fluid flows: finite element discretizations and parameter estimation in coronary blood flow + https://arxiv.org/abs/2512.08207 + arXiv:2512.08207v1 Announce Type: new +Abstract: 3D-0D coupled flow models are widely used across many application fields but remain challenging to solve. Implicit coupling introduces non-local terms, whereas explicit coupling results in only conditionally stable schemes. Furthermore, incorporating inertial effects alongside viscous resistance enlarges the parameter space, making calibration more difficult. + In this work, we propose a new type of boundary condition based on the method of asymptotic partial decomposition of a domain (MAPDD), which we denote as the Duct Boundary Condition (DuBC). This approach enables the incorporation of geometrically reduced domains as a boundary term with only local coupling in the implicit case. Moreover, the DuBC accounts for both viscous and inertial effects simultaneously using a single physical parameter. Additionally, we derive a fractional-step time-marching scheme including the DuBC. We demonstrate the features of the DuBC in coronary artery blood flow simulations, including sequential parameter estimation from noisy velocity data. + oai:arXiv.org:2512.08207v1 + math.NA + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1007/978-3-032-04624-6_12 - ICDAR 2025 - Yiheng Huang, Shuang She, Zewei Wei, Jianmin Lin, Ming Yang, Wenyin Liu + http://creativecommons.org/licenses/by/4.0/ + Jerem\'ias Garay, David Nolte, Crist\'obal Bertoglio - Importance-aware Topic Modeling for Discovering Public Transit Risk from Noisy Social Media - https://arxiv.org/abs/2512.06293 - arXiv:2512.06293v1 Announce Type: new -Abstract: Urban transit agencies increasingly turn to social media to monitor emerging service risks such as crowding, delays, and safety incidents, yet the signals of concern are sparse, short, and easily drowned by routine chatter. We address this challenge by jointly modeling linguistic interactions and user influence. First, we construct an influence-weighted keyword co-occurrence graph from cleaned posts so that socially impactful posts contributes proportionally to the underlying evidence. The core of our framework is a Poisson Deconvolution Factorization (PDF) that decomposes this graph into a low-rank topical structure and topic-localized residual interactions, producing an interpretable topic--keyword basis together with topic importance scores. A decorrelation regularizer \emph{promotes} distinct topics, and a lightweight optimization procedure ensures stable convergence under nonnegativity and normalization constraints. Finally, the number of topics is selected through a coherence-driven sweep that evaluates the quality and distinctness of the learned topics. On large-scale social streams, the proposed model achieves state-of-the-art topic coherence and strong diversity compared with leading baselines. The code and dataset are publicly available at https://github.com/pangjunbiao/Topic-Modeling_ITS.git - oai:arXiv.org:2512.06293v1 + MobileFineTuner: A Unified End-to-End Framework for Fine-Tuning LLMs on Mobile Phones + https://arxiv.org/abs/2512.08211 + arXiv:2512.08211v1 Announce Type: new +Abstract: Mobile phones are the most ubiquitous end devices, generating vast amounts of human-authored data and serving as the primary platform for end-side applications. As high-quality public data for large language models (LLMs) approaches exhaustion, on-device fine-tuning provides an opportunity to leverage private user data while preserving privacy. However, existing approaches are predominantly simulation-based or rely on IoT devices and PCs, leaving commodity mobile phones largely unexplored. A key gap is the absence of an open-source framework that enables practical LLM fine-tuning on mobile phones. We present MobileFineTuner, a unified open-source framework that enables end-to-end LLM fine-tuning directly on commodity mobile phones. MobileFineTuner is designed for efficiency, scalability, and usability, supporting full-parameters fine-tuning (Full-FT) and parameter-efficient fine-tuning (PEFT). To address the memory and energy limitations inherent to mobile phones, we introduce system-level optimizations including parameter sharding, gradient accumulation, and energy-aware computation scheduling. We demonstrate the practicality of MobileFineTuner by fine-tuning GPT-2, Gemma 3, and Qwen 2.5 on real mobile phones. Extensive experiments and ablation studies validate the effectiveness of the proposed optimizations and establish MobileFineTuner as a viable foundation for future research on on-device LLM training. + oai:arXiv.org:2512.08211v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fatima Ashraf, Muhammad Ayub Sabir, Jiaxin Deng, Junbiao Pang, Haitao Yu + Jiaxiang Geng, Lunyu Zhao, Yiyi Lu, Bing Luo - How Sharp and Bias-Robust is a Model? Dual Evaluation Perspectives on Knowledge Graph Completion - https://arxiv.org/abs/2512.06296 - arXiv:2512.06296v1 Announce Type: new -Abstract: Knowledge graph completion (KGC) aims to predict missing facts from the observed KG. While a number of KGC models have been studied, the evaluation of KGC still remain underexplored. In this paper, we observe that existing metrics overlook two key perspectives for KGC evaluation: (A1) predictive sharpness -- the degree of strictness in evaluating an individual prediction, and (A2) popularity-bias robustness -- the ability to predict low-popularity entities. Toward reflecting both perspectives, we propose a novel evaluation framework (PROBE), which consists of a rank transformer (RT) estimating the score of each prediction based on a required level of predictive sharpness and a rank aggregator (RA) aggregating all the scores in a popularity-aware manner. Experiments on real-world KGs reveal that existing metrics tend to over- or under-estimate the accuracy of KGC models, whereas PROBE yields a comprehensive understanding of KGC models and reliable evaluation results. - oai:arXiv.org:2512.06296v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Secure or Suspect? Investigating Package Hallucinations of Shell Command in Original and Quantized LLMs + https://arxiv.org/abs/2512.08213 + arXiv:2512.08213v1 Announce Type: new +Abstract: Large Language Models for code (LLMs4Code) are increasingly used to generate software artifacts, including library and package recommendations in languages such as Go. However, recent evidence shows that LLMs frequently hallucinate package names or generate dependencies containing known security vulnerabilities, posing significant risks to developers and downstream software supply chains. At the same time, quantization has become a widely adopted technique to reduce inference cost and enable deployment of LLMs on resource-constrained environments. Despite its popularity, little is known about how quantization affects the correctness and security of LLM-generated software dependencies while generating shell commands for package installation. + In this work, we conduct the first systematic empirical study of the impact of quantization on package hallucination and vulnerability risks in LLM-generated Go packages. We evaluate five Qwen model sizes under full-precision, 8-bit, and 4-bit quantization across three datasets (SO, MBPP, and paraphrase). Our results show that quantization substantially increases the package hallucination rate (PHR), with 4-bit models exhibiting the most severe degradation. We further find that even among the correctly generated packages, the vulnerability presence rate (VPR) rises as precision decreases, indicating elevated security risk in lower-precision models. Finally, our analysis of hallucinated outputs reveals that most fabricated packages resemble realistic URL-based Go module paths, such as most commonly malformed or non-existent GitHub and golang.org repositories, highlighting a systematic pattern in how LLMs hallucinate dependencies. Overall, our findings provide actionable insights into the reliability and security implications of deploying quantized LLMs for code generation and dependency recommendation. + oai:arXiv.org:2512.08213v1 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1145/3773966.3779401 - Sooho Moon, Yunyong Ko + Md Nazmul Haque, Elizabeth Lin, Lawrence Arkoh, Biruk Tadesse, Bowen Xu + + + Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement + https://arxiv.org/abs/2512.08215 + arXiv:2512.08215v1 Announce Type: new +Abstract: The creation of lifelike human avatars capable of realistic pose variation and viewpoint flexibility remains a fundamental challenge in computer vision and graphics. Current approaches typically yield either geometrically inconsistent multi-view images or sacrifice photorealism, resulting in blurry outputs under diverse viewing angles and complex motions. To address these issues, we propose Blur2Sharp, a novel framework integrating 3D-aware neural rendering and diffusion models to generate sharp, geometrically consistent novel-view images from only a single reference view. Our method employs a dual-conditioning architecture: initially, a Human NeRF model generates geometrically coherent multi-view renderings for target poses, explicitly encoding 3D structural guidance. Subsequently, a diffusion model conditioned on these renderings refines the generated images, preserving fine-grained details and structural fidelity. We further enhance visual quality through hierarchical feature fusion, incorporating texture, normal, and semantic priors extracted from parametric SMPL models to simultaneously improve global coherence and local detail accuracy. Extensive experiments demonstrate that Blur2Sharp consistently surpasses state-of-the-art techniques in both novel pose and view generation tasks, particularly excelling under challenging scenarios involving loose clothing and occlusions. + oai:arXiv.org:2512.08215v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Chia-Hern Lai, I-Hsuan Lo, Yen-Ku Yeh, Thanh-Nguyen Truong, Ching-Chun Huang - Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks - https://arxiv.org/abs/2512.06297 - arXiv:2512.06297v1 Announce Type: new -Abstract: Modern neural networks exhibit a striking property: basins of attraction in the loss landscape are often connected by low-loss paths, yet optimization dynamics generally remain confined to a single convex basin and rarely explore intermediate points. We resolve this paradox by identifying entropic barriers arising from the interplay between curvature variations along these paths and noise in optimization dynamics. Empirically, we find that curvature systematically rises away from minima, producing effective forces that bias noisy dynamics back toward the endpoints - even when the loss remains nearly flat. These barriers persist longer than energetic barriers, shaping the late-time localization of solutions in parameter space. Our results highlight the role of curvature-induced entropic forces in governing both connectivity and confinement in deep learning landscapes. - oai:arXiv.org:2512.06297v1 + Correction of Decoupled Weight Decay + https://arxiv.org/abs/2512.08217 + arXiv:2512.08217v1 Announce Type: new +Abstract: Decoupled weight decay, solely responsible for the performance advantage of AdamW over Adam, has long been set to proportional to learning rate $\gamma$ without questioning. Some researchers have recently challenged such assumption and argued that decoupled weight decay should be set $\propto \gamma^2$ instead based on orthogonality arguments at steady state. To the contrary, we find that eliminating the contribution of the perpendicular component of the update to the weight norm leads to little change to the training dynamics. Instead, we derive that decoupled weight decay $\propto \gamma^2$ results in stable weight norm based on the simple assumption that updates become independent of the weights at steady state, regardless of the nature of the optimizer. Based on the same assumption, we derive and empirically verify that the Total Update Contribution (TUC) of a minibatch under the Scion optimizer is better characterized by the momentum-dependent effective learning rate whose optimal value transfers and we show that decoupled weight decay $\propto \gamma^2$ leads to stable weight and gradient norms and allows us to better control the training dynamics and improve the model performance. + oai:arXiv.org:2512.08217v1 cs.LG - cond-mat.dis-nn - cond-mat.stat-mech - cs.AI - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Luca Di Carlo, Chase Goddard, David J. Schwab + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jason Chuan-Chih Chou - Chemistry Integrated Language Model using Hierarchical Molecular Representation for Polymer Informatics - https://arxiv.org/abs/2512.06301 - arXiv:2512.06301v1 Announce Type: new -Abstract: Machine learning has transformed material discovery for inorganic compounds and small molecules, yet polymers remain largely inaccessible to these methods. While data scarcity is often cited as the primary bottleneck, we demonstrate that strategic molecular representations can overcome this limitation. We introduce CI-LLM (Chemically Informed Language Model), a framework combining HAPPY (Hierarchically Abstracted rePeat unit of PolYmer), which encodes chemical substructures as tokens, with numerical descriptors within transformer architectures. For property prediction, De$^3$BERTa, our descriptor-enriched encoder, achieves 3.5x faster inference than SMILES-based models with improved accuracy ($R^2$ score gains of 0.9-4.1 percent across four properties), while providing interpretable structure-property insights at the subgroup level. For inverse design, our GPT-based generator produces polymers with targeted properties, achieving 100 percent scaffold retention and successful multi-property optimization for negatively correlated objectives. This comprehensive framework demonstrates both forward prediction and inverse design capabilities, showcasing how strategic molecular representation advances machine learning applications in polymer science. - oai:arXiv.org:2512.06301v1 + PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning + https://arxiv.org/abs/2512.08218 + arXiv:2512.08218v1 Announce Type: new +Abstract: Capsule Networks (CapsNets) show exceptional graph representation capacity via dynamic routing and vectorized hierarchical representations, but they model the complex geometries of real\-world graphs poorly by fixed\-curvature space due to the inherent geodesical disconnectedness issues, leading to suboptimal performance. Recent works find that non\-Euclidean pseudo\-Riemannian manifolds provide specific inductive biases for embedding graph data, but how to leverage them to improve CapsNets is still underexplored. Here, we extend the Euclidean capsule routing into geodesically disconnected pseudo\-Riemannian manifolds and derive a Pseudo\-Riemannian Capsule Network (PR\-CapsNet), which models data in pseudo\-Riemannian manifolds of adaptive curvature, for graph representation learning. Specifically, PR\-CapsNet enhances the CapsNet with Adaptive Pseudo\-Riemannian Tangent Space Routing by utilizing pseudo\-Riemannian geometry. Unlike single\-curvature or subspace\-partitioning methods, PR\-CapsNet concurrently models hierarchical and cluster or cyclic graph structures via its versatile pseudo\-Riemannian metric. It first deploys Pseudo\-Riemannian Tangent Space Routing to decompose capsule states into spherical\-temporal and Euclidean\-spatial subspaces with diffeomorphic transformations. Then, an Adaptive Curvature Routing is developed to adaptively fuse features from different curvature spaces for complex graphs via a learnable curvature tensor with geometric attention from local manifold properties. Finally, a geometric properties\-preserved Pseudo\-Riemannian Capsule Classifier is developed to project capsule embeddings to tangent spaces and use curvature\-weighted softmax for classification. Extensive experiments on node and graph classification benchmarks show PR\-CapsNet outperforms SOTA models, validating PR\-CapsNet's strong representation power for complex graph structures. + oai:arXiv.org:2512.08218v1 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Jihun Ahn, Gabriella Pasya Irianti, Vikram Thapar, Su-Mi Hur + http://creativecommons.org/licenses/by/4.0/ + Ye Qin, Jingchao Wang, Yang Shi, Haiying Huang, Junxu Li, Weijian Liu, Tinghui Chen, Jinghui Qin - Multimodal Graph Neural Networks for Prognostic Modeling of Brain Network Reorganization - https://arxiv.org/abs/2512.06303 - arXiv:2512.06303v1 Announce Type: new -Abstract: Understanding the dynamic reorganization of brain networks is critical for predicting cognitive decline, neurological progression, and individual variability in clinical outcomes. This work proposes a multimodal graph neural network framework that integrates structural MRI, diffusion tensor imaging, and functional MRI to model spatiotemporal brain network reorganization. Brain regions are represented as nodes and structural and functional connectivity as edges, forming longitudinal brain graphs for each subject. Temporal evolution is captured via fractional stochastic differential operators embedded within graph-based recurrent networks, enabling the modeling of long-term dependencies and stochastic fluctuations in network dynamics. Attention mechanisms fuse multimodal information and generate interpretable biomarkers, including network energy entropy, graph curvature, fractional memory indices, and modality-specific attention scores. These biomarkers are combined into a composite prognostic index to quantify individual risk of network instability or cognitive decline. Experiments on longitudinal neuroimaging datasets demonstrate both predictive accuracy and interpretability. The results highlight the potential of mathematically rigorous, multimodal graph-based approaches for deriving clinically meaningful biomarkers from existing imaging data without requiring new data collection. - oai:arXiv.org:2512.06303v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Any Old Tom, Dick or Harry: The Citation Impact of First Name Genderedness + https://arxiv.org/abs/2512.08219 + arXiv:2512.08219v1 Announce Type: new +Abstract: This paper attempts a first analysis of citation distributions based on the genderedness of authors' first name. Following the extraction of first name and sex data from all human entity triplets contained in Wikidata, a first name genderedness table is first created based on compiled sex frequencies, then merged with bibliometric data from eponymous, US-affiliated authors. Comparisons of various cumulative distributions show that citation concentrations fluctuations are highest at the opposite ends of the genderedness spectrum, as authors with very feminine and masculine first names respectively get a lower and higher share of citations for every article published, irrespective of their contribution role. + oai:arXiv.org:2512.08219v1 + cs.DL + stat.AP + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Preksha Girish, Rachana Mysore, Kiran K. N., Hiranmayee R., Shipra Prashanth, Shrey Kumar + Maxime Holmberg Sainte-Marie, Vincent Larivi\`ere - Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation - https://arxiv.org/abs/2512.06306 - arXiv:2512.06306v1 Announce Type: new -Abstract: Human pose estimation focuses on predicting body keypoints to analyze human motion. Event cameras provide high temporal resolution and low latency, enabling robust estimation under challenging conditions. However, most existing methods convert event streams into dense event frames, which adds extra computation and sacrifices the high temporal resolution of the event signal. In this work, we aim to exploit the spatiotemporal properties of event streams based on point cloud-based framework, designed to enhance human pose estimation performance. We design Event Temporal Slicing Convolution module to capture short-term dependencies across event slices, and combine it with Event Slice Sequencing module for structured temporal modeling. We also apply edge enhancement in point cloud-based event representation to enhance spatial edge information under sparse event conditions to further improve performance. Experiments on the DHP19 dataset show our proposed method consistently improves performance across three representative point cloud backbones: PointNet, DGCNN, and Point Transformer. - oai:arXiv.org:2512.06306v1 + VisKnow: Constructing Visual Knowledge Base for Object Understanding + https://arxiv.org/abs/2512.08221 + arXiv:2512.08221v1 Announce Type: new +Abstract: Understanding objects is fundamental to computer vision. Beyond object recognition that provides only a category label as typical output, in-depth object understanding represents a comprehensive perception of an object category, involving its components, appearance characteristics, inter-category relationships, contextual background knowledge, etc. Developing such capability requires sufficient multi-modal data, including visual annotations such as parts, attributes, and co-occurrences for specific tasks, as well as textual knowledge to support high-level tasks like reasoning and question answering. However, these data are generally task-oriented and not systematically organized enough to achieve the expected understanding of object categories. In response, we propose the Visual Knowledge Base that structures multi-modal object knowledge as graphs, and present a construction framework named VisKnow that extracts multi-modal, object-level knowledge for object understanding. This framework integrates enriched aligned text and image-source knowledge with region annotations at both object and part levels through a combination of expert design and large-scale model application. As a specific case study, we construct AnimalKB, a structured animal knowledge base covering 406 animal categories, which contains 22K textual knowledge triplets extracted from encyclopedic documents, 420K images, and corresponding region annotations. A series of experiments showcase how AnimalKB enhances object-level visual tasks such as zero-shot recognition and fine-grained VQA, and serves as challenging benchmarks for knowledge graph completion and part segmentation. Our findings highlight the potential of automatically constructing visual knowledge bases to advance visual understanding and its practical applications. The project page is available at https://vipl-vsu.github.io/VisKnow. + oai:arXiv.org:2512.08221v1 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-nc-sa/4.0/ - Haoxian Zhou, Chuanzhi Xu, Langyi Chen, Haodong Chen, Yuk Ying Chung, Qiang Qu, Xaoming Chen, Weidong Cai + Ziwei Yao, Qiyang Wan, Ruiping Wang, Xilin Chen - Performance Bounds on Pliable Index Coding Using Absent Receivers - https://arxiv.org/abs/2512.06312 - arXiv:2512.06312v1 Announce Type: new -Abstract: We characterise bounds on the optimal broadcast rate for a few classes of pliable-index-coding instances. Unlike the majority of currently solved instances, which belong to a special class where all receivers with a certain side-information cardinality are either present or absent, we consider more general instances without this constraint. We devise a novel algorithm that constructs a decoding chain by iteratively adding a message that can be decoded by a receiver whose side information is already in the chain. If the decoding chain cannot proceed due to the absence of a receiver with the required messages, we skip a message by adding it to the chain regardless. We prove that a lower bound on the optimal broadcast rate is a function of the number of skipped messages, across all possible decoding choices of the receivers and any realisation of the algorithm for each decoding choice. While this result is not computationally feasible in isolation, it serves as a basis for deriving explicit lower bounds on the broadcast rate for specific classes of pliable-index-coding instances. These lower bounds depend on the number of absent receivers or the pattern of their side-information sets. Specifically, we explicitly characterise the optimal broadcast rate for instances with up to and including four absent receivers with any side-information pattern, as well as instances where the side-information sets are nested in particular ways. - oai:arXiv.org:2512.06312v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + SOP^2: Transfer Learning with Scene-Oriented Prompt Pool on 3D Object Detection + https://arxiv.org/abs/2512.08223 + arXiv:2512.08223v1 Announce Type: new +Abstract: With the rise of Large Language Models (LLMs) such as GPT-3, these models exhibit strong generalization capabilities. Through transfer learning techniques such as fine-tuning and prompt tuning, they can be adapted to various downstream tasks with minimal parameter adjustments. This approach is particularly common in the field of Natural Language Processing (NLP). This paper aims to explore the effectiveness of common prompt tuning methods in 3D object detection. We investigate whether a model trained on the large-scale Waymo dataset can serve as a foundation model and adapt to other scenarios within the 3D object detection field. This paper sequentially examines the impact of prompt tokens and prompt generators, and further proposes a Scene-Oriented Prompt Pool (\textbf{SOP$^2$}). We demonstrate the effectiveness of prompt pools in 3D object detection, with the goal of inspiring future researchers to delve deeper into the potential of prompts in the 3D field. + oai:arXiv.org:2512.08223v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/TIT.2025.3632399 - IEEE Transactions on Information Theory, 2025 - Lawrence Ong, Badri N. Vellambi, Parastoo Sadeghi, J\"org Kliewer + http://creativecommons.org/licenses/by-nc-sa/4.0/ + 10.1109/AVSS65446.2025.11149933 + Ching-Hung Cheng, Hsiu-Fu Wu, Bing-Chen Wu, Khanh-Phong Bui, Van-Tin Luu, Ching-Chun Huang - Control-Oriented System Identification: Classical, Learning, and Physics-Informed Approaches - https://arxiv.org/abs/2512.06315 - arXiv:2512.06315v1 Announce Type: new -Abstract: We survey classical, machine learning, and data-driven system identification approaches to learn control-relevant and physics-informed models of dynamical systems. Recently, machine learning approaches have enabled system identification from noisy, high-dimensional, and complex data. However, their utility is limited by their ability to provide provable guarantees on control-relevant properties. Meanwhile, control theory has identified several properties that are useful in analysis and control synthesis, such as dissipativity, monotonicity, energy conservation, and symmetry-preserving structures. We posit that merging system identification with such control-relevant or physics-informed properties can provide useful inductive bias, enhance explainability, enable control synthesis with provable guarantees, and improve sample complexity. We formulate system identification as an optimization problem where control-relevant properties can be enforced through direct parameterization (constraining the model structure to satisfy a desired property by construction), soft constraints (encouraging control-relevant properties through regularization or penalty terms), and hard constraints (imposing control-relevant properties as constraints in the optimization problem). Through this lens, we survey methods to learn physics-informed and control-relevant models spanning classical linear and nonlinear system identification, machine learning approaches, and direct identification through data-driven and behavioral representations. We also provide several expository examples that are accompanied by code and brief tutorials on a public Github repository. We also describe challenging directions for future research, including identification in networked, switched, and time-varying systems, experiment design, and bridging the gaps between data-driven, learning-based, and control-oriented approaches. - oai:arXiv.org:2512.06315v1 - eess.SY - cs.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + New VVC profiles targeting Feature Coding for Machines + https://arxiv.org/abs/2512.08227 + arXiv:2512.08227v1 Announce Type: new +Abstract: Modern video codecs have been extensively optimized to preserve perceptual quality, leveraging models of the human visual system. However, in split inference systems-where intermediate features from neural network are transmitted instead of pixel data-these assumptions no longer apply. Intermediate features are abstract, sparse, and task-specific, making perceptual fidelity irrelevant. In this paper, we investigate the use of Versatile Video Coding (VVC) for compressing such features under the MPEG-AI Feature Coding for Machines (FCM) standard. We perform a tool-level analysis to understand the impact of individual coding components on compression efficiency and downstream vision task accuracy. Based on these insights, we propose three lightweight essential VVC profiles-Fast, Faster, and Fastest. The Fast profile provides 2.96% BD-Rate gain while reducing encoding time by 21.8%. Faster achieves a 1.85% BD-Rate gain with a 51.5% speedup. Fastest reduces encoding time by 95.6% with only a 1.71% loss in BD-Rate. + oai:arXiv.org:2512.08227v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - S. Sivaranjani, Yuanyuan Shi, Nikolay Atanasov, Thai Duong, Jie Feng, Tim Martin, Yuezhu Xu, Vijay Gupta, Frank Allg\"ower + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Md Eimran Hossain Eimon, Ashan Perera, Juan Merlos, Velibor Adzic, Hari Kalva - ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models - https://arxiv.org/abs/2512.06328 - arXiv:2512.06328v1 Announce Type: new -Abstract: We present ReCAD, a reinforcement learning (RL) framework that bootstraps pretrained large models (PLMs) to generate precise parametric computer-aided design (CAD) models from multimodal inputs by leveraging their inherent generative capabilities. With just access to simple functional interfaces (e.g., point coordinates), our approach enables the emergence of complex CAD operations (e.g., pattern replication and mirror). This stands in contrast to previous methods, which typically rely on knowledge injected through supervised fine-tuning (SFT), offer limited support for editability, and fail to exploit the strong generative priors of PLMs. Specifically, the ReCAD framework begins by fine-tuning vision-language models (VLMs) to equip them with basic CAD model generation capabilities, where we rewrite CAD scripts into parameterized code that is leveraged to generate accurate textual descriptions for supervision. Then, we propose a novel RL strategy that incorporates parameterized code as guidance to enhance the model's reasoning on challenging questions. Furthermore, we employ a hierarchical primitive learning process to progressively teach structured and compositional skills under a unified reward function that ensures both geometric accuracy and semantic fidelity. ReCAD sets a new state-of-the-art in both text-to-CAD and image-to-CAD tasks, significantly improving geometric accuracy across in-distribution and out-of-distribution settings. In the image-to-CAD task, for instance, it reduces the mean Chamfer Distance from 73.47 to 29.61 (in-distribution) and from 272.06 to 80.23 (out-of-distribution), outperforming existing baselines by a substantial margin. - oai:arXiv.org:2512.06328v1 + MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models + https://arxiv.org/abs/2512.08228 + arXiv:2512.08228v1 Announce Type: new +Abstract: The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critical question remains: is such reasoning genuinely grounded in visual evidence and logically coherent? Existing benchmarks emphasize generation but neglect verification, i.e., the capacity to assess whether a reasoning chain is both visually consistent and logically valid. To fill this gap, we introduce MM-CoT, a diagnostic benchmark specifically designed to probe the visual grounding and logical coherence of CoT reasoning in MMs. Instead of generating free-form explanations, models must select the sole event chain that satisfies two orthogonal constraints: (i) visual consistency, ensuring all steps are anchored in observable evidence, and (ii) logical coherence, ensuring causal and commonsense validity. Adversarial distractors are engineered to violate one of these constraints, exposing distinct reasoning failures. We evaluate leading vision-language models on MM-CoT and find that even the most advanced systems struggle, revealing a sharp discrepancy between generative fluency and true reasoning fidelity. MM-CoT shows low correlation with existing benchmarks, confirming that it measures a unique combination of visual grounding and logical reasoning. This benchmark provides a foundation for developing future models that reason not just plausibly, but faithfully and coherently within the visual world. + oai:arXiv.org:2512.08228v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Jiahao Li, Yusheng Luo, Yunzhong Lou, Xiangdong Zhou + Jusheng Zhang, Kaitong Cai, Xiaoyang Guo, Sidi Liu, Qinhan Lv, Ruiqi Chen, Jing Yang, Yijia Fan, Xiaofei Sun, Jian Wang, Ziliang Chen, Liang Lin, Keze Wang - S2WMamba: A Spectral-Spatial Wavelet Mamba for Pansharpening - https://arxiv.org/abs/2512.06330 - arXiv:2512.06330v1 Announce Type: new -Abstract: Pansharpening fuses a high-resolution PAN image with a low-resolution multispectral (LRMS) image to produce an HRMS image. A key difficulty is that jointly processing PAN and MS often entangles spatial detail with spectral fidelity. We propose S2WMamba, which explicitly disentangles frequency information and then performs lightweight cross-modal interaction. Concretely, a 2D Haar DWT is applied to PAN to localize spatial edges and textures, while a channel-wise 1D Haar DWT treats each pixel's spectrum as a 1D signal to separate low/high-frequency components and limit spectral distortion. The resulting Spectral branch injects wavelet-extracted spatial details into MS features, and the Spatial branch refines PAN features using spectra from the 1D pyramid; the two branches exchange information through Mamba-based cross-modulation that models long-range dependencies with linear complexity. A multi-scale dynamic gate (multiplicative + additive) then adaptively fuses branch outputs.On WV3, GF2, and QB, S2WMamba matches or surpasses recent strong baselines (FusionMamba, CANNet, U2Net, ARConv), improving PSNR by up to 0.23 dB and reaching HQNR 0.956 on full-resolution WV3. Ablations justify the choice of 2D/1D DWT placement, parallel dual branches, and the fusion gate. Our code is available at https://github.com/KagUYa66/S2WMamba. - oai:arXiv.org:2512.06330v1 + Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systems + https://arxiv.org/abs/2512.08229 + arXiv:2512.08229v1 Announce Type: new +Abstract: Accurate three-dimensional perception is essential for modern industrial robotic systems that perform manipulation, inspection, and navigation tasks. RGB-D and stereo vision sensors are widely used for this purpose, but the depth maps they produce are often noisy, incomplete, or biased due to sensor limitations and environmental conditions. Depth completion methods aim to generate dense, reliable depth maps from RGB images and sparse depth input. However, a key limitation in current depth completion pipelines is the unrealistic generation of sparse depth: sparse pixels are typically selected uniformly at random from dense ground-truth depth, ignoring the fact that real sensors exhibit geometry-dependent and spatially nonuniform reliability. In this work, we propose a normal-guided sparse depth sampling strategy that leverages PCA-based surface normal estimation on the RGB-D point cloud to compute a per-pixel depth reliability measure. The sparse depth samples are then drawn according to this reliability distribution. We integrate this sampling method with the Marigold-DC diffusion-based depth completion model and evaluate it on NYU Depth v2 using the standard metrics. Experiments show that our geometry-aware sparse depth improves accuracy, reduces artifacts near edges and discontinuities, and produces more realistic training conditions that better reflect real sensor behavior. + oai:arXiv.org:2512.08229v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Haoyu Zhang, Junhan Luo, Yugang Cao, Siran Peng, Jie Huang, Liangjian-Deng + http://creativecommons.org/licenses/by/4.0/ + Tony Salloom, Dandi Zhou, Xinhai Sun - Defending Event-Triggered Systems against Out-of-Envelope Environments - https://arxiv.org/abs/2512.06331 - arXiv:2512.06331v1 Announce Type: new -Abstract: The design of real-time systems is based on assumptions about environmental conditions in which they will operate. We call this their safe operational envelope. Violation of these assumptions, i.e., out-of-envelope environments, can jeopardize timeliness and safety of real-time systems, e.g., by overwhelming them with interrupt storms. A long-lasting debate has been going on over which design paradigm, the time- or event-triggered, is more robust against such behavior. In this work, we investigate the claim that time-triggered systems are immune against out-of-envelope behavior and how event-triggered systems can be constructed to defend against being overwhelmed by interrupt showers. We introduce importance (independently of priority and criticality) as a means to express which tasks should still be scheduled in case environmental design assumptions cease to hold, draw parallels to mixed-criticality scheduling, and demonstrate how event-triggered systems can defend against out-of-envelope behavior. - oai:arXiv.org:2512.06331v1 - cs.OS - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions + https://arxiv.org/abs/2512.08230 + arXiv:2512.08230v1 Announce Type: new +Abstract: Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard techniques of deep learning. In contrast, cognitive scientists have applied advances in our formal understanding of causation in computer science, particularly within the Causal Bayes Net formalism, to understand human causal learning. In the very different tradition of reinforcement learning, researchers have described an intrinsic reward signal called "empowerment" which maximizes mutual information between actions and their outcomes. "Empowerment" may be an important bridge between classical Bayesian causal learning and reinforcement learning and may help to characterize causal learning in humans and enable it in machines. If an agent learns an accurate causal world model, they will necessarily increase their empowerment, and increasing empowerment will lead to a more accurate causal world model. Empowerment may also explain distinctive features of childrens causal learning, as well as providing a more tractable computational account of how that learning is possible. In an empirical study, we systematically test how children and adults use cues to empowerment to infer causal relations, and design effective causal interventions. + oai:arXiv.org:2512.08230v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Marcus V\"olp, Mohammad Ibrahim Alkoudsi, Azin Bayrami Asl, Kristin Kr\"uger, Julio Rodrigues Mendonca da Neto, Gerhard Fohler + http://creativecommons.org/licenses/by/4.0/ + Eunice Yiu, Kelsey Allen, Shiry Ginosar, Alison Gopnik - CryoHype: Reconstructing a thousand cryo-EM structures with transformer-based hypernetworks - https://arxiv.org/abs/2512.06332 - arXiv:2512.06332v1 Announce Type: new -Abstract: Cryo-electron microscopy (cryo-EM) is an indispensable technique for determining the 3D structures of dynamic biomolecular complexes. While typically applied to image a single molecular species, cryo-EM has the potential for structure determination of many targets simultaneously in a high-throughput fashion. However, existing methods typically focus on modeling conformational heterogeneity within a single or a few structures and are not designed to resolve compositional heterogeneity arising from mixtures of many distinct molecular species. To address this challenge, we propose CryoHype, a transformer-based hypernetwork for cryo-EM reconstruction that dynamically adjusts the weights of an implicit neural representation. Using CryoHype, we achieve state-of-the-art results on a challenging benchmark dataset containing 100 structures. We further demonstrate that CryoHype scales to the reconstruction of 1,000 distinct structures from unlabeled cryo-EM images in the fixed-pose setting. - oai:arXiv.org:2512.06332v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Semantic-Metric Bayesian Risk Fields: Learning Robot Safety from Human Videos with a VLM Prior + https://arxiv.org/abs/2512.08233 + arXiv:2512.08233v1 Announce Type: new +Abstract: Humans interpret safety not as a binary signal but as a continuous, context- and spatially-dependent notion of risk. While risk is subjective, humans form rational mental models that guide action selection in dynamic environments. This work proposes a framework for extracting implicit human risk models by introducing a novel, semantically-conditioned and spatially-varying parametrization of risk, supervised directly from safe human demonstration videos and VLM common sense. Notably, we define risk through a Bayesian formulation. The prior is furnished by a pretrained vision-language model. In order to encourage the risk estimate to be more human aligned, a likelihood function modulates the prior to produce a relative metric of risk. Specifically, the likelihood is a learned ViT that maps pretrained features, to pixel-aligned risk values. Our pipeline ingests RGB images and a query object string, producing pixel-dense risk images. These images that can then be used as value-predictors in robot planning tasks or be projected into 3D for use in conventional trajectory optimization to produce human-like motion. This learned mapping enables generalization to novel objects and contexts, and has the potential to scale to much larger training datasets. In particular, the Bayesian framework that is introduced enables fast adaptation of our model to additional observations or common sense rules. We demonstrate that our proposed framework produces contextual risk that aligns with human preferences. Additionally, we illustrate several downstream applications of the model; as a value learner for visuomotor planners or in conjunction with a classical trajectory optimization algorithm. Our results suggest that our framework is a significant step toward enabling autonomous systems to internalize human-like risk. Code and results can be found at https://riskbayesian.github.io/bayesian_risk/. + oai:arXiv.org:2512.08233v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jeffrey Gu, Minkyu Jeon, Ambri Ma, Serena Yeung-Levy, Ellen D. Zhong + http://creativecommons.org/licenses/by/4.0/ + Timothy Chen, Marcus Dominguez-Kuhne, Aiden Swann, Xu Liu, Mac Schwager - Enhanced Multimodal Video Retrieval System: Integrating Query Expansion and Cross-modal Temporal Event Retrieval - https://arxiv.org/abs/2512.06334 - arXiv:2512.06334v1 Announce Type: new -Abstract: Multimedia information retrieval from videos remains a challenging problem. While recent systems have advanced multimodal search through semantic, object, and OCR queries - and can retrieve temporally consecutive scenes - they often rely on a single query modality for an entire sequence, limiting robustness in complex temporal contexts. To overcome this, we propose a cross-modal temporal event retrieval framework that enables different query modalities to describe distinct scenes within a sequence. To determine decision thresholds for scene transition and slide change adaptively, we build Kernel Density Gaussian Mixture Thresholding (KDE-GMM) algorithm, ensuring optimal keyframe selection. These extracted keyframes act as compact, high-quality visual exemplars that retain each segment's semantic essence, improving retrieval precision and efficiency. Additionally, the system incorporates a large language model (LLM) to refine and expand user queries, enhancing overall retrieval performance. The proposed system's effectiveness and robustness were demonstrated through its strong results in the Ho Chi Minh AI Challenge 2025. - oai:arXiv.org:2512.06334v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 + FastBEV++: Fast by Algorithm, Deployable by Design + https://arxiv.org/abs/2512.08237 + arXiv:2512.08237v1 Announce Type: new +Abstract: The advancement of camera-only Bird's-Eye-View(BEV) perception is currently impeded by a fundamental tension between state-of-the-art performance and on-vehicle deployment tractability. This bottleneck stems from a deep-rooted dependency on computationally prohibitive view transformations and bespoke, platform-specific kernels. This paper introduces FastBEV++, a framework engineered to reconcile this tension, demonstrating that high performance and deployment efficiency can be achieved in unison via two guiding principles: Fast by Algorithm and Deployable by Design. We realize the "Deployable by Design" principle through a novel view transformation paradigm that decomposes the monolithic projection into a standard Index-Gather-Reshape pipeline. Enabled by a deterministic pre-sorting strategy, this transformation is executed entirely with elementary, operator native primitives (e.g Gather, Matrix Multiplication), which eliminates the need for specialized CUDA kernels and ensures fully TensorRT-native portability. Concurrently, our framework is "Fast by Algorithm", leveraging this decomposed structure to seamlessly integrate an end-to-end, depth-aware fusion mechanism. This jointly learned depth modulation, further bolstered by temporal aggregation and robust data augmentation, significantly enhances the geometric fidelity of the BEV representation.Empirical validation on the nuScenes benchmark corroborates the efficacy of our approach. FastBEV++ establishes a new state-of-the-art 0.359 NDS while maintaining exceptional real-time performance, exceeding 134 FPS on automotive-grade hardware (e.g Tesla T4). By offering a solution that is free of custom plugins yet highly accurate, FastBEV++ presents a mature and scalable design philosophy for production autonomous systems. The code is released at: https://github.com/ymlab/advanced-fastbev + oai:arXiv.org:2512.08237v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Van-Thinh Vo, Minh-Khoi Nguyen, Minh-Huy Tran, Anh-Quan Nguyen-Tran, Duy-Tan Nguyen, Khanh-Loi Nguyen, Anh-Minh Phan + Yuanpeng Chen, Hui Song, Wei Tao, ShanHui Mo, Shuang Zhang, Xiao Hua, TianKun Zhao - The Role of Smart Cities in Ethical Design Framework Yijun - https://arxiv.org/abs/2512.06336 - arXiv:2512.06336v1 Announce Type: new -Abstract: The integration of digital technologies into urban planning has given rise to "smart cities," aiming to enhance quality of life and operational efficiency. However, the implementation of such technologies introduces ethical challenges, including data privacy, equity, inclusion, and transparency. This article employs the Beard and Longstaff framework to discuss these challenges through a combination of theoretical analysis and case studies. Focusing on principles of self-determination, fairness, accessibility, and purpose, the study examines governance models, stakeholder roles, and ethical dilemmas inherent in smart city initiatives. Recommendations include adopting regulatory sandboxes, fostering participatory governance, and bridging digital divides to ensure that smart cities align with societal values, promoting inclusivity and ethical urban development. - oai:arXiv.org:2512.06336v1 - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + SpeechQualityLLM: LLM-Based Multimodal Assessment of Speech Quality + https://arxiv.org/abs/2512.08238 + arXiv:2512.08238v1 Announce Type: new +Abstract: Objective speech quality assessment is central to telephony, VoIP, and streaming systems, where large volumes of degraded audio must be monitored and optimized at scale. Classical metrics such as PESQ and POLQA approximate human mean opinion scores (MOS) but require carefully controlled conditions and expensive listening tests, while learning-based models such as NISQA regress MOS and multiple perceptual dimensions from waveforms or spectrograms, achieving high correlation with subjective ratings yet remaining rigid: they do not support interactive, natural-language queries and do not natively provide textual rationales. In this work, we introduce SpeechQualityLLM, a multimodal speech quality question-answering (QA) system that couples an audio encoder with a language model and is trained on the NISQA corpus using template-based question-answer pairs covering overall MOS and four perceptual dimensions (noisiness, coloration, discontinuity, and loudness) in both single-ended (degraded only) and double-ended (degraded plus clean reference) setups. Instead of directly regressing scores, our system is supervised to generate textual answers from which numeric predictions are parsed and evaluated with standard regression and ranking metrics; on held-out NISQA clips, the double-ended model attains a MOS mean absolute error (MAE) of 0.41 with Pearson correlation of 0.86, with competitive performance on dimension-wise tasks. Beyond these quantitative gains, it offers a flexible natural-language interface in which the language model acts as an audio quality expert: practitioners can query arbitrary aspects of degradations, prompt the model to emulate different listener profiles to capture human variability and produce diverse but plausible judgments rather than a single deterministic score, and thereby reduce reliance on large-scale crowdsourced tests and their monetary cost. + oai:arXiv.org:2512.08238v1 + cs.SD + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yijun Chen + http://creativecommons.org/licenses/by/4.0/ + Mahathir Monjur, Shahriar Nirjon - DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization - https://arxiv.org/abs/2512.06337 - arXiv:2512.06337v1 Announce Type: new -Abstract: The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for eliciting such post-training reasoning capabilities due to its exceptional performance, it remains plagued by significant training instability and poor sample efficiency. We theoretically identify the root cause of these issues as the lack of distinctiveness within on-policy rollouts: for routine queries, highly homogeneous samples induce destructive gradient conflicts; whereas for hard queries, the scarcity of valid positive samples results in ineffective optimization. To bridge this gap, we propose Distinctiveness-aware Group Relative Policy Optimization (DaGRPO). DaGRPO incorporates two core mechanisms: (1) Sequence-level Gradient Rectification, which utilizes fine-grained scoring to dynamically mask sample pairs with low distinctiveness, thereby eradicating gradient conflicts at the source; and (2) Off-policy Data Augmentation, which introduces high-quality anchors to recover training signals for challenging tasks. Extensive experiments across 9 mathematical reasoning and out-of-distribution (OOD) generalization benchmarks demonstrate that DaGRPO significantly surpasses existing SFT, GRPO, and hybrid baselines, achieving new state-of-the-art performance (e.g., a +4.7% average accuracy gain on math benchmarks). Furthermore, in-depth analysis confirms that DaGRPO effectively mitigates gradient explosion and accelerates the emergence of long-chain reasoning capabilities. - oai:arXiv.org:2512.06337v1 + HybridToken-VLM: Hybrid Token Compression for Vision-Language Models + https://arxiv.org/abs/2512.08240 + arXiv:2512.08240v1 Announce Type: new +Abstract: Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off: continuous compression dilutes high-level semantics such as object identities, while discrete quantization loses fine-grained details such as textures. We introduce HTC-VLM, a hybrid framework that disentangles semantics and appearance through dual channels, i.e., a continuous pathway for fine-grained details via ViT patches and a discrete pathway for symbolic anchors using MGVQ quantization projected to four tokens. These are fused into a 580-token hybrid sequence and compressed into a single voco token via a disentanglement attention mask and bottleneck, ensuring efficient and grounded representations. HTC-VLM achieves an average performance retention of 87.2 percent across seven benchmarks (GQA, VQAv2, MMBench, MME, POPE, SEED-Bench, ScienceQA-Image), outperforming the leading continuous baseline at 81.0 percent with a 580-to-1 compression ratio. Attention analyses show that the compressed token prioritizes the discrete anchor, validating its semantic guidance. Our work demonstrates that a minimalist hybrid design can resolve the efficiency-fidelity dilemma and advance scalable VLMs. + oai:arXiv.org:2512.08240v1 + cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuan Xie, Xuan Wang, Wenjie Wang + http://creativecommons.org/licenses/by/4.0/ + Jusheng Zhang, Xiaoyang Guo, Kaitong Cai, Qinhan Lv, Yijia Fan, Wenhao Chai, Jian Wang, Keze Wang - Interpretive Efficiency: Information-Geometric Foundations of Data Usefulness - https://arxiv.org/abs/2512.06341 - arXiv:2512.06341v1 Announce Type: new -Abstract: Interpretability is central to trustworthy machine learning, yet existing metrics rarely quantify how effectively data support an interpretive representation. We propose Interpretive Efficiency, a normalized, task-aware functional that measures the fraction of task-relevant information transmitted through an interpretive channel. The definition is grounded in five axioms ensuring boundedness, Blackwell-style monotonicity, data-processing stability, admissible invariance, and asymptotic consistency. We relate the functional to mutual information and derive a local Fisher-geometric expansion, then establish asymptotic and finite-sample estimation guarantees using standard empirical-process tools. Experiments on controlled image and signal tasks demonstrate that the measure recovers theoretical orderings, exposes representational redundancy masked by accuracy, and correlates with robustness, making it a practical, theory-backed diagnostic for representation design. - oai:arXiv.org:2512.06341v1 + Persistent Topological Structures and Cohomological Flows as a Mathematical Framework for Brain-Inspired Representation Learning + https://arxiv.org/abs/2512.08241 + arXiv:2512.08241v1 Announce Type: new +Abstract: This paper presents a mathematically rigorous framework for brain-inspired representation learning founded on the interplay between persistent topological structures and cohomological flows. Neural computation is reformulated as the evolution of cochain maps over dynamic simplicial complexes, enabling representations that capture invariants across temporal, spatial, and functional brain states. The proposed architecture integrates algebraic topology with differential geometry to construct cohomological operators that generalize gradient-based learning within a homological landscape. Synthetic data with controlled topological signatures and real neural datasets are jointly analyzed using persistent homology, sheaf cohomology, and spectral Laplacians to quantify stability, continuity, and structural preservation. Empirical results demonstrate that the model achieves superior manifold consistency and noise resilience compared to graph neural and manifold-based deep architectures, establishing a coherent mathematical foundation for topology-driven representation learning. + oai:arXiv.org:2512.08241v1 cs.LG - cs.IR - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ronald Katende + Preksha Girish, Rachana Mysore, Mahanthesha U, Shrey Kumar, Shipra Prashant - When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models - https://arxiv.org/abs/2512.06343 - arXiv:2512.06343v1 Announce Type: new -Abstract: Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling is the Bradley-Terry (BT) loss, which learns from pairwise data consisting of a pair of chosen and rejected responses. In this work, we analyze the per-sample gradient of BT-loss and show that its norm scales with two distinct components: (1) the difference in predicted rewards between chosen and rejected responses, which reflects the prediction error, and critically, (2) representation distance between the pair measured in the output space of the final layer. While the first term captures the intended training signal, we show that the second term can significantly impact the update magnitude and misalign learning. Specifically, pairs with small representation distance often receive vanishingly weak updates, even when misranked, while pairs with large distance receive disproportionately strong updates. This leads to gradients from large-distance pairs to overshadow those from small-distance pairs, where fine-grained distinctions are especially important. To overcome this limitation, we propose NormBT, an adaptive pair-wise normalization scheme that balances representation-driven effects and focuses learning signals on prediction error. NormBT is a lightweight, drop-in integration to BT loss with negligible overhead. Across various LLM backbones and datasets, NormBT improves reward model performance consistently, with notable gains of over 5% on the Reasoning category of RewardBench, which contains numerous small-distance pairs. This work reveals a key limitation in the widely used BT objective and provides a simple, effective correction. - oai:arXiv.org:2512.06343v1 - cs.LG - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Chopper: A Multi-Level GPU Characterization Tool & Derived Insights Into LLM Training Inefficiency + https://arxiv.org/abs/2512.08242 + arXiv:2512.08242v1 Announce Type: new +Abstract: Training large language models (LLMs) efficiently requires a deep understanding of how modern GPU systems behave under real-world distributed training workloads. While prior work has focused primarily on kernel-level performance or single-GPU microbenchmarks, the complex interaction between communication, computation, memory behavior, and power management in multi-GPU LLM training remains poorly characterized. In this work, we introduce Chopper, a profiling and analysis framework that collects, aligns, and visualizes GPU kernel traces and hardware performance counters across multiple granularities (i.e., from individual kernels to operations, layers, phases, iterations, and GPUs). Using Chopper, we perform a comprehensive end-to-end characterization of Llama 3 8B training under fully sharded data parallelism (FSDP) on an eight-GPU AMD InstinctTM MI300X node. Our analysis reveals several previously underexplored bottlenecks and behaviors, such as memory determinism enabling higher, more stable GPU and memory frequencies. We identify several sources of inefficiencies, with frequency overhead (DVFS effects) being the single largest contributor to the gap between theoretical and observed performance, exceeding the impact of MFMA utilization loss, communication/computation overlap, and kernel launch overheads. Overall, Chopper provides the first holistic, multi-granularity characterization of LLM training on AMD InstinctTM MI300X GPUs, yielding actionable insights for optimizing training frameworks, improving power-management strategies, and guiding future GPU architecture and system design. + oai:arXiv.org:2512.08242v1 + cs.DC + cs.AR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Tong Xie, Andrew Bai, Yuanhao Ban, Yunqi Hong, Haoyu Li, Cho-jui Hsieh + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Marco Kurzynski, Shaizeen Aga, Di Wu - Beyond Hallucinations: A Multimodal-Guided Task-Aware Generative Image Compression for Ultra-Low Bitrate - https://arxiv.org/abs/2512.06344 - arXiv:2512.06344v1 Announce Type: new -Abstract: Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic deviations caused by generative hallucinations at ultra-low bitrate (bpp < 0.05), limiting its reliable deployment in bandwidth-constrained 6G semantic communication scenarios. In this work, we reassess the positioning and role of of multimodal guidance, and propose a Multimodal-Guided Task-Aware Generative Image Compression (MTGC) framework. Specifically, MTGC integrates three guidance modalities to enhance semantic consistency: a concise but robust text caption for global semantics, a highly compressed image (HCI) retaining low-level visual information, and Semantic Pseudo-Words (SPWs) for fine-grained task-relevant semantics. The SPWs are generated by our designed Task-Aware Semantic Compression Module (TASCM), which operates in a task-oriented manner to drive the multi-head self-attention mechanism to focus on and extract semantics relevant to the generation task while filtering out redundancy. Subsequently, to facilitate the synergistic guidance of these modalities, we design a Multimodal-Guided Diffusion Decoder (MGDD) employing a dual-path cooperative guidance mechanism that synergizes cross-attention and ControlNet additive residuals to precisely inject these three guidance into the diffusion process, and leverages the diffusion model's powerful generative priors to reconstruct the image. Extensive experiments demonstrate that MTGC consistently improves semantic consistency (e.g., DISTS drops by 10.59% on the DIV2K dataset) while also achieving remarkable gains in perceptual quality and pixel-level fidelity at ultra-low bitrate. - oai:arXiv.org:2512.06344v1 + Residual-SwinCA-Net: A Channel-Aware Integrated Residual CNN-Swin Transformer for Malignant Lesion Segmentation in BUSI + https://arxiv.org/abs/2512.08243 + arXiv:2512.08243v1 Announce Type: new +Abstract: A novel deep hybrid Residual-SwinCA-Net segmentation framework is proposed in the study for addressing such challenges by extracting locally correlated and robust features, incorporating residual CNN modules. Furthermore, for learning global dependencies, Swin Transformer blocks are customized using internal residual pathways, which reinforce gradient stability, refine local patterns, and facilitate global feature fusion. Formerly, for enhancing tissue continuity, ultrasound noise suppressions, and accentuating fine structural transitions Laplacian-of-Gaussian regional operator is applied, and for maintaining the morphological integrity of malignant lesion contours, a boundary-oriented operator has been incorporated. Subsequently, a contraction strategy was applied stage-wise by progressively reducing features-map progressively for capturing scale invariance and enhancing the robustness of structural variability. In addition, each decoder level prior augmentation integrates a new Multi-Scale Channel Attention and Squeezing (MSCAS) module. The MSCAS selectively emphasizes encoder salient maps, retains discriminative global context, and complementary local structures with minimal computational cost while suppressing redundant activations. Finally, the Pixel-Attention module encodes class-relevant spatial cues by adaptively weighing malignant lesion pixels while suppressing background interference. The Residual-SwinCA-Net and existing CNNs/ViTs techniques have been implemented on the publicly available BUSI dataset. The proposed Residual-SwinCA-Net framework outperformed and achieved 99.29% mean accuracy, 98.74% IoU, and 0.9041 Dice for breast lesion segmentation. The proposed Residual-SwinCA-Net framework improves the BUSI lesion diagnostic performance and strengthens timely clinical decision-making. + oai:arXiv.org:2512.08243v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kaile Wang, Lijun He, Haisheng Fu, Haixia Bi, Fan Li + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Saeeda Naz (Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering,Applied Sciences), Saddam Hussain Khan (Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering,Applied Sciences) - CLUENet: Cluster Attention Makes Neural Networks Have Eyes - https://arxiv.org/abs/2512.06345 - arXiv:2512.06345v1 Announce Type: new -Abstract: Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing challenges for tasks requiring high model transparency. Clustering paradigms offer promising interpretability and flexible semantic modeling, but suffer from limited accuracy, low efficiency, and gradient vanishing during training. To address these issues, we propose CLUster attEntion Network (CLUENet), an transparent deep architecture for visual semantic understanding. We propose three key innovations include (i) a Global Soft Aggregation and Hard Assignment with a Temperature-Scaled Cosin Attention and gated residual connections for enhanced local modeling, (ii) inter-block Hard and Shared Feature Dispatching, and (iii) an improved cluster pooling strategy. These enhancements significantly improve both classification performance and visual interpretability. Experiments on CIFAR-100 and Mini-ImageNet demonstrate that CLUENet outperforms existing clustering methods and mainstream visual models, offering a compelling balance of accuracy, efficiency, and transparency. - oai:arXiv.org:2512.06345v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Migrating QAOA from Qiskit 1.x to 2.x: An experience report + https://arxiv.org/abs/2512.08245 + arXiv:2512.08245v1 Announce Type: new +Abstract: Migrating quantum algorithms across evolving frameworks introduces subtle behavioral changes that affect accuracy and reproducibility. This paper reports our experience converting the Quantum Approximate Optimization Algorithm (QAOA) from Qiskit Algorithms with Qiskit 1.x (v1 primitives) to a custom implementation using Qiskit 2.x (v2 primitives). Despite identical circuits, optimizers, and Hamiltonians, the new version produced drastically different results. A systematic analysis revealed the root cause: the sampling budget -- the number of circuit executions (shots) per iteration. The library's implicit use of unlimited shots yielded dense probability distributions, whereas the v2 default of 10 000 shots captured only 23% of the state space. Increasing shots to 250 000 restored library-level accuracy. This study highlights how hidden parameters at the quantum--classical interaction level can dominate hybrid algorithm performance and provides actionable recommendations for developers and framework designers to ensure reproducible results in quantum software migration. + oai:arXiv.org:2512.08245v1 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiangshuai Song, Jun-Jie Huang, Tianrui Liu, Ke Liang, Chang Tang + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Julien Cardinal, Imen Benzarti, Ghizlane El boussaidi, Christophe Pere - Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry - https://arxiv.org/abs/2512.06347 - arXiv:2512.06347v1 Announce Type: new -Abstract: We theoretically demonstrate that the generalization error of interpolators for machine learning models under teacher-student settings becomes 0 once the number of training samples exceeds a certain threshold. Understanding the high generalization ability of large-scale models such as deep neural networks (DNNs) remains one of the central open problems in machine learning theory. While recent theoretical studies have attributed this phenomenon to the implicit bias of stochastic gradient descent (SGD) toward well-generalizing solutions, empirical evidences indicate that it primarily stems from properties of the model itself. Specifically, even randomly sampled interpolators, which are parameters that achieve zero training error, have been observed to generalize effectively. In this study, under a teacher-student framework, we prove that the generalization error of randomly sampled interpolators becomes exactly zero once the number of training samples exceeds a threshold determined by the geometric structure of the interpolator set in parameter space. As a proof technique, we leverage tools from algebraic geometry to mathematically characterize this geometric structure. - oai:arXiv.org:2512.06347v1 + SPROCKET: Extending ROCKET to Distance-Based Time-Series Transformations With Prototypes + https://arxiv.org/abs/2512.08246 + arXiv:2512.08246v1 Announce Type: new +Abstract: Classical Time Series Classification algorithms are dominated by feature engineering strategies. One of the most prominent of these transforms is ROCKET, which achieves strong performance through random kernel features. We introduce SPROCKET (Selected Prototype Random Convolutional Kernel Transform), which implements a new feature engineering strategy based on prototypes. On a majority of the UCR and UEA Time Series Classification archives, SPROCKET achieves performance comparable to existing convolutional algorithms and the new MR-HY-SP ( MultiROCKET-HYDRA-SPROCKET) ensemble's average accuracy ranking exceeds HYDRA-MR, the previous best convolutional ensemble's performance. These experimental results demonstrate that prototype-based feature transformation can enhance both accuracy and robustness in time series classification. + oai:arXiv.org:2512.08246v1 cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Naoki Yoshida, Isao Ishikawa, Masaaki Imaizumi + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Nicholas Harner - Why They Disagree: Decoding Differences in Opinions about AI Risk on the Lex Fridman Podcast - https://arxiv.org/abs/2512.06350 - arXiv:2512.06350v1 Announce Type: new -Abstract: The emergence of transformative technologies often surfaces deep societal divisions, nowhere more evident than in contemporary debates about artificial intelligence (AI). A striking feature of these divisions is that they persist despite shared interests in ensuring that AI benefits humanity and avoiding catastrophic outcomes. This paper analyzes contemporary debates about AI risk, parsing the differences between the "doomer" and "boomer" perspectives into definitional, factual, causal, and moral premises to identify key points of contention. We find that differences in perspectives about existential risk ("X-risk") arise fundamentally from differences in causal premises about design vs. emergence in complex systems, while differences in perspectives about employment risks ("E-risks") pertain to different causal premises about the applicability of past theories (evolution) vs their inapplicability (revolution). Disagreements about these two forms of AI risk appear to share two properties: neither involves significant disagreements on moral values and both can be described in terms of differing views on the extent of boundedness of human rationality. Our approach to analyzing reasoning chains at scale, using an ensemble of LLMs to parse textual data, can be applied to identify key points of contention in debates about risk to the public in any arena. - oai:arXiv.org:2512.06350v1 - cs.CY + Distilling Future Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection + https://arxiv.org/abs/2512.08247 + arXiv:2512.08247v1 Announce Type: new +Abstract: Camera-based temporal 3D object detection has shown impressive results in autonomous driving, with offline models improving accuracy by using future frames. Knowledge distillation (KD) can be an appealing framework for transferring rich information from offline models to online models. However, existing KD methods overlook future frames, as they mainly focus on spatial feature distillation under strict frame alignment or on temporal relational distillation, thereby making it challenging for online models to effectively learn future knowledge. To this end, we propose a sparse query-based approach, Future Temporal Knowledge Distillation (FTKD), which effectively transfers future frame knowledge from an offline teacher model to an online student model. Specifically, we present a future-aware feature reconstruction strategy to encourage the student model to capture future features without strict frame alignment. In addition, we further introduce future-guided logit distillation to leverage the teacher's stable foreground and background context. FTKD is applied to two high-performing 3D object detection baselines, achieving up to 1.3 mAP and 1.3 NDS gains on the nuScenes dataset, as well as the most accurate velocity estimation, without increasing inference cost. + oai:arXiv.org:2512.08247v1 + cs.CV cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Nghi Truong, Phanish Puranam, \"Ozgecan Ko\c{c}ak + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Haowen Zheng, Hu Zhu, Lu Deng, Weihao Gu, Yang Yang, Yanyan Liang - LLM-Upgraded Graph Reinforcement Learning for Carbon-Aware Job Scheduling in Smart Manufacturing - https://arxiv.org/abs/2512.06351 - arXiv:2512.06351v1 Announce Type: new -Abstract: This paper presents \textsc{Luca}, a \underline{l}arge language model (LLM)-\underline{u}pgraded graph reinforcement learning framework for \underline{c}arbon-\underline{a}ware flexible job shop scheduling. \textsc{Luca} addresses the challenges of dynamic and sustainable scheduling in smart manufacturing systems by integrating a graph neural network and an LLM, guided by a carefully designed in-house prompting strategy, to produce a fused embedding that captures both structural characteristics and contextual semantics of the latest scheduling state. This expressive embedding is then processed by a deep reinforcement learning policy network, which generates real-time scheduling decisions optimized for both makespan and carbon emission objectives. To support sustainability goals, \textsc{Luca} incorporates a dual-objective reward function that encourages both energy efficiency and scheduling timeliness. Experimental results on both synthetic and public datasets demonstrate that \textsc{Luca} consistently outperforms comparison algorithms. For instance, on the synthetic dataset, it achieves an average of 4.1\% and up to 12.2\% lower makespan compared to the best-performing comparison algorithm while maintaining the same emission level. On public datasets, additional gains are observed for both makespan and emission. These results demonstrate that \textsc{Luca} is effective and practical for carbon-aware scheduling in smart manufacturing. - oai:arXiv.org:2512.06351v1 - cs.LG - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Learning Spatiotemporal Tubes for Temporal Reach-Avoid-Stay Tasks using Physics-Informed Neural Networks + https://arxiv.org/abs/2512.08248 + arXiv:2512.08248v1 Announce Type: new +Abstract: This paper presents a Spatiotemporal Tube (STT)-based control framework for general control-affine MIMO nonlinear pure-feedback systems with unknown dynamics to satisfy prescribed time reach-avoid-stay tasks under external disturbances. The STT is defined as a time-varying ball, whose center and radius are jointly approximated by a Physics-Informed Neural Network (PINN). The constraints governing the STT are first formulated as loss functions of the PINN, and a training algorithm is proposed to minimize the overall violation. The PINN being trained on certain collocation points, we propose a Lipschitz-based validity condition to formally verify that the learned PINN satisfies the conditions over the continuous time horizon. Building on the learned STT representation, an approximation-free closed-form controller is defined to guarantee satisfaction of the T-RAS specification. Finally, the effectiveness and scalability of the framework are validated through two case studies involving a mobile robot and an aerial vehicle navigating through cluttered environments. + oai:arXiv.org:2512.08248v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Zhiying Yang, Fang Liu, Wei Zhang, Xin Lou, Malcolm Yoke Hean Low, Boon Ping Gan + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Ahan Basu, Ratnangshu Das, Pushpak Jagtap - TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search - https://arxiv.org/abs/2512.06353 - arXiv:2512.06353v1 Announce Type: new -Abstract: Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due to high computational and memory demands. Mixed-Precision Quantization (MPQ), designed to push the limits of quantization, has demonstrated remarkable success in advancing U-Net quantization to sub-4bit settings while significantly reducing computational and memory overhead. Nevertheless, its application to DiT architectures remains limited and underexplored. In this work, we propose TreeQ, a unified framework addressing key challenges in DiT quantization. First, to tackle inefficient search and proxy misalignment, we introduce Tree Structured Search (TSS). This DiT-specific approach leverages the architecture's linear properties to traverse the solution space in O(n) time while improving objective accuracy through comparison-based pruning. Second, to unify optimization objectives, we propose Environmental Noise Guidance (ENG), which aligns Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) configurations using a single hyperparameter. Third, to mitigate information bottlenecks in ultra-low-bit regimes, we design the General Monarch Branch (GMB). This structured sparse branch prevents irreversible information loss, enabling finer detail generation. Through extensive experiments, our TreeQ framework demonstrates state-of-the-art performance on DiT-XL/2 under W3A3 and W4A4 PTQ/PEFT settings. Notably, our work is the first to achieve near-lossless 4-bit PTQ performance on DiT models. The code and models will be available at https://github.com/racoonykc/TreeQ - oai:arXiv.org:2512.06353v1 + Query-aware Hub Prototype Learning for Few-Shot 3D Point Cloud Semantic Segmentation + https://arxiv.org/abs/2512.08253 + arXiv:2512.08253v1 Announce Type: new +Abstract: Few-shot 3D point cloud semantic segmentation (FS-3DSeg) aims to segment novel classes with only a few labeled samples. However, existing metric-based prototype learning methods generate prototypes solely from the support set, without considering their relevance to query data. This often results in prototype bias, where prototypes overfit support-specific characteristics and fail to generalize to the query distribution, especially in the presence of distribution shifts, which leads to degraded segmentation performance. To address this issue, we propose a novel Query-aware Hub Prototype (QHP) learning method that explicitly models semantic correlations between support and query sets. Specifically, we propose a Hub Prototype Generation (HPG) module that constructs a bipartite graph connecting query and support points, identifies frequently linked support hubs, and generates query-relevant prototypes that better capture cross-set semantics. To further mitigate the influence of bad hubs and ambiguous prototypes near class boundaries, we introduce a Prototype Distribution Optimization (PDO) module, which employs a purity-reweighted contrastive loss to refine prototype representations by pulling bad hubs and outlier prototypes closer to their corresponding class centers. Extensive experiments on S3DIS and ScanNet demonstrate that QHP achieves substantial performance gains over state-of-the-art methods, effectively narrowing the semantic gap between prototypes and query sets in FS-3DSeg. + oai:arXiv.org:2512.08253v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Kaicheng Yang, Kaisen Yang, Baiting Wu, Xun Zhang, Qianrui Yang, Haotong Qin, He Zhang, Yulun Zhang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + YiLin Zhou, Lili Wei, Zheming Xu, Ziyi Chen, Congyan Lang - The Missing Variable: Socio-Technical Alignment in Risk Evaluation - https://arxiv.org/abs/2512.06354 - arXiv:2512.06354v1 Announce Type: new -Abstract: This paper addresses a critical gap in the risk assessment of AI-enabled safety-critical systems. While these systems, where AI systems assists human operators, function as complex socio-technical systems, existing risk evaluation methods fail to account for the associated complex interaction between human, technical, and organizational elements. Through a comparative analysis of system attributes from both socio-technical and AI-enabled systems and a review of current risk evaluation methods, we confirm the absence of socio-technical considerations in standard risk expressions. To bridge this gap, we introduce a novel socio-technical alignment $STA$ variable designed to be integrated into the foundational risk equation. This variable estimates the degree of harmonious interaction between the AI systems, human operators, and organizational processes. A case study on an AI-enabled liquid hydrogen bunkering system demonstrates the variable's relevance. By comparing a naive and a safeguarded system design, we illustrate how the $STA$-augmented expression captures socio-technical safety implications that traditional risk evaluation overlooks, providing a more holistic basis for risk evaluation. - oai:arXiv.org:2512.06354v1 - cs.CY - cs.HC - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + SFP: Real-World Scene Recovery Using Spatial and Frequency Priors + https://arxiv.org/abs/2512.08254 + arXiv:2512.08254v1 Announce Type: new +Abstract: Scene recovery serves as a critical task for various computer vision applications. Existing methods typically rely on a single prior, which is inherently insufficient to handle multiple degradations, or employ complex network architectures trained on synthetic data, which suffer from poor generalization for diverse real-world scenarios. In this paper, we propose Spatial and Frequency Priors (SFP) for real-world scene recovery. In the spatial domain, we observe that the inverse of the degraded image exhibits a projection along its spectral direction that resembles the scene transmission. Leveraging this spatial prior, the transmission map is estimated to recover the scene from scattering degradation. In the frequency domain, a mask is constructed for adaptive frequency enhancement, with two parameters estimated using our proposed novel priors. Specifically, one prior assumes that the mean intensity of the degraded image's direct current (DC) components across three channels in the frequency domain closely approximates that of each channel in the clear image. The second prior is based on the observation that, for clear images, the magnitude of low radial frequencies below 0.001 constitutes approximately 1% of the total spectrum. Finally, we design a weighted fusion strategy to integrate spatial-domain restoration, frequency-domain enhancement, and salient features from the input image, yielding the final recovered result. Extensive evaluations demonstrate the effectiveness and superiority of our proposed SFP for scene recovery under various degradation conditions. + oai:arXiv.org:2512.08254v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Niclas Flehmig, Mary Ann Lundteigen, Shen Yin + http://creativecommons.org/licenses/by/4.0/ + Yun Liu, Tao Li, Cosmin Ancuti, Wenqi Ren, Weisi Lin - DDFI: Diverse and Distribution-aware Missing Feature Imputation via Two-step Reconstruction - https://arxiv.org/abs/2512.06356 - arXiv:2512.06356v1 Announce Type: new -Abstract: Incomplete node features are ubiquitous in real-world scenarios, e.g., the attributes of web users may be partly private, which causes the performance of Graph Neural Networks (GNNs) to decline significantly. Feature propagation (FP) is a well-known method that performs well for imputation of missing node features on graphs, but it still has the following three issues: 1) it struggles with graphs that are not fully connected, 2) imputed features face the over-smoothing problem, and 3) FP is tailored for transductive tasks, overlooking the feature distribution shift in inductive tasks. To address these challenges, we introduce DDFI, a Diverse and Distribution-aware Missing Feature Imputation method that combines feature propagation with a graph-based Masked AutoEncoder (MAE) in a nontrivial manner. It first designs a simple yet effective algorithm, namely Co-Label Linking (CLL), that randomly connects nodes in the training set with the same label to enhance the performance on graphs with numerous connected components. Then we develop a novel two-step representation generation process at the inference stage. Specifically, instead of directly using FP-imputed features as input during inference, DDFI further reconstructs the features through the whole MAE to reduce feature distribution shift in the inductive tasks and enhance the diversity of node features. Meanwhile, since existing feature imputation methods for graphs only evaluate by simulating the missing scenes with manually masking the features, we collect a new dataset called Sailing from the records of voyages that contains naturally missing features to help better evaluate the effectiveness. Extensive experiments conducted on six public datasets and Sailing show that DDFI outperforms the state-of-the-art methods under both transductive and inductive settings. - oai:arXiv.org:2512.06356v1 + Wavelet-Accelerated Physics-Informed Quantum Neural Network for Multiscale Partial Differential Equations + https://arxiv.org/abs/2512.08256 + arXiv:2512.08256v1 Announce Type: new +Abstract: This work proposes a wavelet-based physics-informed quantum neural network framework to efficiently address multiscale partial differential equations that involve sharp gradients, stiffness, rapid local variations, and highly oscillatory behavior. Traditional physics-informed neural networks (PINNs) have demonstrated substantial potential in solving differential equations, and their quantum counterparts, quantum-PINNs, exhibit enhanced representational capacity with fewer trainable parameters. However, both approaches face notable challenges in accurately solving multiscale features. Furthermore, their reliance on automatic differentiation for constructing loss functions introduces considerable computational overhead, resulting in longer training times. To overcome these challenges, we developed a wavelet-accelerated physics-informed quantum neural network that eliminates the need for automatic differentiation, significantly reducing computational complexity. The proposed framework incorporates the multiresolution property of wavelets within the quantum neural network architecture, thereby enhancing the network's ability to effectively capture both local and global features of multiscale problems. Numerical experiments demonstrate that our proposed method achieves superior accuracy while requiring less than five percent of the trainable parameters compared to classical wavelet-based PINNs, resulting in faster convergence. Moreover, it offers a speedup of three to five times compared to existing quantum PINNs, highlighting the potential of the proposed approach for efficiently solving challenging multiscale and oscillatory problems. + oai:arXiv.org:2512.08256v1 cs.LG - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 + math.AP + math.QA + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yifan Song, Fenglin Yu, Yihong Luo, Xingjian Tao, Siya Qiu, Kai Han, Jing Tang + Deepak Gupta, Himanshu Pandey, Ratikanta Behera - Proportional integral derivative booster for neural networks-based time-series prediction: Case of water demand prediction - https://arxiv.org/abs/2512.06357 - arXiv:2512.06357v1 Announce Type: new -Abstract: Multi-step time-series prediction is an essential supportive step for decision-makers in several industrial areas. Artificial intelligence techniques, which use a neural network component in various forms, have recently frequently been used to accomplish this step. However, the complexity of the neural network structure still stands up as a critical problem against prediction accuracy. In this paper, a method inspired by the proportional-integral-derivative (PID) control approach is investigated to enhance the performance of neural network models used for multi-step ahead prediction of periodic time-series information while maintaining a negligible impact on the complexity of the system. The PID-based method is applied to the predicted value at each time step to bring that value closer to the real value. The water demand forecasting problem is considered as a case study, where two deep neural network models from the literature are used to prove the effectiveness of the proposed boosting method. Furthermore, to prove the applicability of this PID-based booster to other types of periodic time-series prediction problems, it is applied to enhance the accuracy of a neural network model used for multi-step forecasting of hourly energy consumption. The comparison between the results of the original prediction models and the results after using the proposed technique demonstrates the superiority of the proposed method in terms of prediction accuracy and system complexity. - oai:arXiv.org:2512.06357v1 + Geometric-Stochastic Multimodal Deep Learning for Predictive Modeling of SUDEP and Stroke Vulnerability + https://arxiv.org/abs/2512.08257 + arXiv:2512.08257v1 Announce Type: new +Abstract: Sudden Unexpected Death in Epilepsy (SUDEP) and acute ischemic stroke are life-threatening conditions involving complex interactions across cortical, brainstem, and autonomic systems. We present a unified geometric-stochastic multimodal deep learning framework that integrates EEG, ECG, respiration, SpO2, EMG, and fMRI signals to model SUDEP and stroke vulnerability. The approach combines Riemannian manifold embeddings, Lie-group invariant feature representations, fractional stochastic dynamics, Hamiltonian energy-flow modeling, and cross-modal attention mechanisms. Stroke propagation is modeled using fractional epidemic diffusion over structural brain graphs. Experiments on the MULTI-CLARID dataset demonstrate improved predictive accuracy and interpretable biomarkers derived from manifold curvature, fractional memory indices, attention entropy, and diffusion centrality. The proposed framework provides a mathematically principled foundation for early detection, risk stratification, and interpretable multimodal modeling in neural-autonomic disorders. + oai:arXiv.org:2512.08257v1 cs.LG - cs.AI - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + eess.IV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1016/j.engappai.2021.104570 - Tony Sallooma, Okyay Kaynak, Xinbo Yub, Wei He + Preksha Girish, Rachana Mysore, Mahanthesha U, Shrey Kumar, Misbah Fatimah Annigeri, Tanish Jain - Rectifying Latent Space for Generative Single-Image Reflection Removal - https://arxiv.org/abs/2512.06358 - arXiv:2512.06358v1 Announce Type: new -Abstract: Single-image reflection removal is a highly ill-posed problem, where existing methods struggle to reason about the composition of corrupted regions, causing them to fail at recovery and generalization in the wild. This work reframes an editing-purpose latent diffusion model to effectively perceive and process highly ambiguous, layered image inputs, yielding high-quality outputs. We argue that the challenge of this conversion stems from a critical yet overlooked issue, i.e., the latent space of semantic encoders lacks the inherent structure to interpret a composite image as a linear superposition of its constituent layers. Our approach is built on three synergistic components, including a reflection-equivariant VAE that aligns the latent space with the linear physics of reflection formation, a learnable task-specific text embedding for precise guidance that bypasses ambiguous language, and a depth-guided early-branching sampling strategy to harness generative stochasticity for promising results. Extensive experiments reveal that our model achieves new SOTA performance on multiple benchmarks and generalizes well to challenging real-world cases. - oai:arXiv.org:2512.06358v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Beyond Traditional Diagnostics: Transforming Patient-Side Information into Predictive Insights with Knowledge Graphs and Prototypes + https://arxiv.org/abs/2512.08261 + arXiv:2512.08261v1 Announce Type: new +Abstract: Predicting diseases solely from patient-side information, such as demographics and self-reported symptoms, has attracted significant research attention due to its potential to enhance patient awareness, facilitate early healthcare engagement, and improve healthcare system efficiency. However, existing approaches encounter critical challenges, including imbalanced disease distributions and a lack of interpretability, resulting in biased or unreliable predictions. To address these issues, we propose the Knowledge graph-enhanced, Prototype-aware, and Interpretable (KPI) framework. KPI systematically integrates structured and trusted medical knowledge into a unified disease knowledge graph, constructs clinically meaningful disease prototypes, and employs contrastive learning to enhance predictive accuracy, which is particularly important for long-tailed diseases. Additionally, KPI utilizes large language models (LLMs) to generate patient-specific, medically relevant explanations, thereby improving interpretability and reliability. Extensive experiments on real-world datasets demonstrate that KPI outperforms state-of-the-art methods in predictive accuracy and provides clinically valid explanations that closely align with patient narratives, highlighting its practical value for patient-centered healthcare delivery. + oai:arXiv.org:2512.08261v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Mingjia Li, Jin Hu, Hainuo Wang, Qiming Hu, Jiarui Wang, Xiaojie Guo - - - A 33.6-136.2 TOPS/W Nonlinear Analog Computing-In-Memory Macro for Multi-bit LSTM Accelerator in 65 nm CMOS - https://arxiv.org/abs/2512.06362 - arXiv:2512.06362v1 Announce Type: new -Abstract: The energy efficiency of analog computing-in-memory (ACIM) accelerator for recurrent neural networks, particularly long short-term memory (LSTM) network, is limited by the high proportion of nonlinear (NL) operations typically executed digitally. To address this, we propose an LSTM accelerator incorporating an ACIM macro with reconfigurable (1-5 bit) nonlinear in-memory (NLIM) analog-to-digital converter (ADC) to compute NL activations directly in the analog domain using: 1) a dual 9T bitcell with decoupled read/write paths for signed inputs and ternary weight operations; 2) a read-word-line underdrive Cascode (RUDC) technique achieving 2.8X higher read-bitline dynamic range than single-transistor designs (1.4X better over conventional Cascode structure with 7X lower current variation); 3) a dual-supply 6T-SRAM array for efficient multi-bit weight operations and reducing both bitcell count (7.8X) and latency (4X) for 5-bit weight operations. We experimentally demonstrate 5-bit NLIM ADC for approximating NL activations in LSTM cells, achieving average error <1 LSB. Simulation confirms the robustness of NLIM ADC against temperature variations thanks to the replica bias strategy. Our design achieves 92.0% on-chip inference accuracy for a 12-class keyword-spotting task while demonstrating 2.2X higher system-level normalized energy efficiency and 1.6X better normalized area efficiency than state-of-the-art works. The results combine physical measurements of a macro unit-accounting for the majority of LSTM operations (99% linear and 80% nonlinear operations)-with simulations of the remaining components, including additional LSTM and fully connected layers. - oai:arXiv.org:2512.06362v1 - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junyi Yang, Xinyu Luo, Ye Ke, Zheng Wang, Hongyang Shang, Shuai Dong, Zhengnan Fu, Xiaofeng Yang, Hongjie Liu, Arindam Basu + Yibowen Zhao, Yinan Zhang, Zhixiang Su, Lizhen Cui, Chunyan Miao - Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection - https://arxiv.org/abs/2512.06363 - arXiv:2512.06363v1 Announce Type: new -Abstract: Real-world face recognition systems are vulnerable to both physical presentation attacks (PAs) and digital forgery attacks (DFs). We aim to achieve comprehensive protection of biometric data by implementing a unified physical-digital defense framework with advanced detection. Existing approaches primarily employ CLIP with regularization constraints to enhance model generalization across both tasks. However, these methods suffer from conflicting optimization directions between physical and digital attack detection under same category prompt spaces. To overcome this limitation, we propose a Spoofing-aware Prompt Learning for Unified Attack Detection (SPL-UAD) framework, which decouples optimization branches for physical and digital attacks in the prompt space. Specifically, we construct a learnable parallel prompt branch enhanced with adaptive Spoofing Context Prompt Generation, enabling independent control of optimization for each attack type. Furthermore, we design a Cues-awareness Augmentation that leverages the dual-prompt mechanism to generate challenging sample mining tasks on data, significantly enhancing the model's robustness against unseen attack types. Extensive experiments on the large-scale UniAttackDataPlus dataset demonstrate that the proposed method achieves significant performance improvements in unified attack detection tasks. - oai:arXiv.org:2512.06363v1 + RLCNet: An end-to-end deep learning framework for simultaneous online calibration of LiDAR, RADAR, and Camera + https://arxiv.org/abs/2512.08262 + arXiv:2512.08262v1 Announce Type: new +Abstract: Accurate extrinsic calibration of LiDAR, RADAR, and camera sensors is essential for reliable perception in autonomous vehicles. Still, it remains challenging due to factors such as mechanical vibrations and cumulative sensor drift in dynamic environments. This paper presents RLCNet, a novel end-to-end trainable deep learning framework for the simultaneous online calibration of these multimodal sensors. Validated on real-world datasets, RLCNet is designed for practical deployment and demonstrates robust performance under diverse conditions. To support real-time operation, an online calibration framework is introduced that incorporates a weighted moving average and outlier rejection, enabling dynamic adjustment of calibration parameters with reduced prediction noise and improved resilience to drift. An ablation study highlights the significance of architectural choices, while comparisons with existing methods demonstrate the superior accuracy and robustness of the proposed approach. + oai:arXiv.org:2512.08262v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiabao Guo, Yadian Wang, Hui Ma, Yuhao Fu, Ju Jia, Hui Liu, Shengeng Tang, Lechao Cheng, Yunfeng Diao, Ajian Liu + Hafeez Husain Cholakkal, Stefano Arrigoni, Francesco Braghin - JEEVHITAA -- An End-to-End HCAI System to Support Collective Care - https://arxiv.org/abs/2512.06364 - arXiv:2512.06364v1 Announce Type: new -Abstract: Current mobile health platforms are predominantly individual-centric and lack the necessary primitives for coordinated, auditable, multi-actor workflows. However, in many settings worldwide, health decisions are enacted by multi-actor care networks rather than single users. We present JEEVHITAA, an Android/Flutter system that provides context-sensitive, role-aware sharing and verifiable information flows for care circles. JEEVHITAA ingests platform and device data (via Google Health Connect and BLE connectors), constructs multi-layer user profiles from sensor streams and tiered onboarding, and enforces fine-grained, time-bounded access control across permissioned care graphs. Data are end-to-end encrypted in local stores and during peer sync (Firebase), and provisions are made for document capture by camera or upload as PDF. An integrated retrieval-augmented LLM pipeline (i) produces structured, role-targeted summaries and action plans, (ii) enables users to gather advanced insights on health reports, and (iii) performs evidence-grounded user-relevant verification of arbitrary health content, returning provenance, confidence scores, and source citations. We describe the system architecture, connector abstractions, and security primitives, and evaluate robustness and compatibility using synthetic, ontology-driven simulations and vendor compatibility tests. Finally, we outline plans for longitudinal in-the-wild deployments to measure system performance, the correctness of access control, and the real-world effectiveness of relationship-aware credibility support. - oai:arXiv.org:2512.06364v1 - cs.CR - cs.ET - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Shyama Sastha Krishnamoorthy Srinivasan, Harsh Pala, Mohan Kumar, Pushpendra Singh - - - Human3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos - https://arxiv.org/abs/2512.06368 - arXiv:2512.06368v1 Announce Type: new -Abstract: Monocular dynamic video reconstruction faces significant challenges in dynamic human scenes due to geometric inconsistencies and resolution degradation issues. Existing methods lack 3D human structural understanding, producing geometrically inconsistent results with distorted limb proportions and unnatural human-object fusion, while memory-constrained downsampling causes human boundary drift toward background geometry. To address these limitations, we propose to incorporate hybrid geometric priors that combine SMPL human body models with monocular depth estimation. Our approach leverages structured human priors to maintain surface consistency while capturing fine-grained geometric details in human regions. We introduce Human3R, featuring a hierarchical pipeline with refinement components that processes full-resolution images for overall scene geometry, then applies strategic cropping and cross-attention fusion for human-specific detail enhancement. The method integrates SMPL priors through a Feature Fusion Module to ensure geometrically plausible reconstruction while preserving fine-grained human boundaries. Extensive experiments on TUM Dynamics and GTA-IM datasets demonstrate superior performance in dynamic human reconstruction. - oai:arXiv.org:2512.06368v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Mathematical Foundations of Neural Tangents and Infinite-Width Networks + https://arxiv.org/abs/2512.08264 + arXiv:2512.08264v1 Announce Type: new +Abstract: We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture integrating Fourier feature embeddings, residual connections with layerwise scaling, and stochastic depth to enable rigorous analysis of kernel evolution during training. Our theoretical contributions include deriving bounds on NTK dynamics, characterizing eigenvalue evolution, and linking spectral properties to generalization and optimization stability. Empirical results on synthetic and benchmark datasets validate the predicted kernel behavior and demonstrate improved training stability and generalization. This work provides a comprehensive framework bridging infinite-width theory and practical deep-learning architectures. + oai:arXiv.org:2512.08264v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Weitao Xiong, Zhiyuan Yuan, Jiahao Lu, Chengfeng Zhao, Peng Li, Yuan Liu + Rachana Mysore, Preksha Girish, Kavitha Jayaram, Shrey Kumar, Preksha Girish, Shravan Sanjeev Bagal, Kavitha Jayaram, Shreya Aravind Shastry - Data Generation for Stability Studies of Power Systems with High Penetration of Inverter-Based Resources - https://arxiv.org/abs/2512.06369 - arXiv:2512.06369v1 Announce Type: new -Abstract: The increasing penetration of inverter-based resources (IBRs) is fundamentally reshaping power system dynamics and creating new challenges for stability assessment. Data-driven approaches, and in particular machine learning models, require large and representative datasets that capture how system stability varies across a wide range of operating conditions and control settings. This paper presents an open-source, high-performance computing framework for the systematic generation of such datasets. The proposed tool defines a scalable operating space for large-scale power systems, explores it through an adaptive sampling strategy guided by sensitivity analysis, and performs small-signal stability assessments to populate a high-information-content dataset. The framework efficiently targets regions near the stability margin while maintaining broad coverage of feasible operating conditions. The workflow is fully implemented in Python and designed for parallel execution. The resulting tool enables the creation of high-quality datasets that support data-driven stability studies in modern power systems with high IBR penetration. - oai:arXiv.org:2512.06369v1 + Theoretical Studies of Sub-THz Active Split-Ring Resonators for Near-Field Imaging + https://arxiv.org/abs/2512.08265 + arXiv:2512.08265v1 Announce Type: new +Abstract: This paper develops a theoretical framework for the design of Active Split-Ring Resonators (ASRRs). An ASRR is a Split-Ring Resonator (SRR) equipped with a tunable negative resistor, enabling both switchability and quality factor boosting and tuning. These properties make ASRRs well-suited for integration into dense arrays on silicon chips, where pixelated near-fields are generated and leveraged for high-resolution 2D imaging of samples. Such imagers pave the way for real-time, non-invasive, and low-cost imaging of human body tissue. The paper investigates ASRR coupling to host transmission lines, nonlinear effects, signal flow, and the influence of various noise sources on detection performance. Verified through simulations, these studies provide design guidelines for optimizing the Signal-to-Noise Ratio (SNR) and power consumption of a single pixel, while adhering to the constraints of a scalable array. + oai:arXiv.org:2512.08265v1 eess.SY cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Francesca Rossi, Mauro Garcia Lorenzo, Eduardo Iraola de Acevedo, Elia Mateu Barriendos, Vinicius Albernaz Lacerda, Francesc Lordan-Gomis, Rosa Badia, Eduardo Prieto-Araujo + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ali Ameri, Jun-Chau Chien, Ali M. Niknejad - Optimizing Optimizers for Fast Gradient-Based Learning - https://arxiv.org/abs/2512.06370 - arXiv:2512.06370v1 Announce Type: new -Abstract: We lay the theoretical foundation for automating optimizer design in gradient-based learning. Based on the greedy principle, we formulate the problem of designing optimizers as maximizing the instantaneous decrease in loss. By treating an optimizer as a function that translates loss gradient signals into parameter motions, the problem reduces to a family of convex optimization problems over the space of optimizers. Solving these problems under various constraints not only recovers a wide range of popular optimizers as closed-form solutions, but also produces the optimal hyperparameters of these optimizers with respect to the problems at hand. This enables a systematic approach to design optimizers and tune their hyperparameters according to the gradient statistics that are collected during the training process. Furthermore, this optimization of optimization can be performed dynamically during training. - oai:arXiv.org:2512.06370v1 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand + https://arxiv.org/abs/2512.08266 + arXiv:2512.08266v1 Announce Type: new +Abstract: Large language models (LLMs) have shown exceptional performance in code generation and understanding tasks, yet their high computational costs hinder broader adoption. One important factor is the inherent verbosity of programming languages, such as unnecessary formatting elements and lengthy boilerplate code. This leads to inflated token counts in both input and generated outputs, which increases inference costs and slows down the generation process. Prior work improves this through simplifying programming language grammar, reducing token usage across both code understanding and generation tasks. However, it is confined to syntactic transformations, leaving significant opportunities for token reduction unrealized at the semantic level. + In this work, we propose Token Sugar, a concept that replaces frequent and verbose code patterns with reversible, token-efficient shorthand in the source code. To realize this concept in practice, we designed a systematic solution that mines high-frequency, token-heavy patterns from a code corpus, maps each to a unique shorthand, and integrates them into LLM pretraining via code transformation. With this solution, we obtain 799 (code pattern, shorthand) pairs, which can reduce up to 15.1% token count in the source code and is complementary to existing syntax-focused methods. We further trained three widely used LLMs on Token Sugar-augmented data. Experimental results show that these models not only achieve significant token savings (up to 11.2% reduction) during generation but also maintain near-identical Pass@1 scores compared to baselines trained on unprocessed code. + oai:arXiv.org:2512.08266v1 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jaerin Lee, Kyoung Mu Lee + Zhensu Sun, Chengran Yang, Xiaoning Du, Zhou Yang, Li Li, David Lo - VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning - https://arxiv.org/abs/2512.06373 - arXiv:2512.06373v1 Announce Type: new -Abstract: Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating various visual tools through reinforcement learning, while neglecting to design effective response mechanisms for handling unreliable or erroneous tool outputs. This limitation is particularly pronounced in referring and grounding tasks, where inaccurate detection tool predictions often mislead TiVR models into generating hallucinated reasoning. To address this issue, we propose the VG-Refiner, the first framework aiming at the tool-refined referring grounded reasoning. Technically, we introduce a two-stage think-rethink mechanism that enables the model to explicitly analyze and respond to tool feedback, along with a refinement reward that encourages effective correction in response to poor tool results. In addition, we propose two new metrics and establish fair evaluation protocols to systematically measure the refinement ability of current models. We adopt a small amount of task-specific data to enhance the refinement capability of VG-Refiner, achieving a significant improvement in accuracy and correction ability on referring and reasoning grounding benchmarks while preserving the general capabilities of the pretrained model. - oai:arXiv.org:2512.06373v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + SOFA-FL: Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing + https://arxiv.org/abs/2512.08267 + arXiv:2512.08267v1 Announce Type: new +Abstract: Federated Learning (FL) faces significant challenges in evolving environments, particularly regarding data heterogeneity and the rigidity of fixed network topologies. To address these issues, this paper proposes \textbf{SOFA-FL} (Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing), a novel framework that enables hierarchical federated systems to self-organize and adapt over time. + The framework is built upon three core mechanisms: (1) \textbf{Dynamic Multi-branch Agglomerative Clustering (DMAC)}, which constructs an initial efficient hierarchical structure; (2) \textbf{Self-organizing Hierarchical Adaptive Propagation and Evolution (SHAPE)}, which allows the system to dynamically restructure its topology through atomic operations -- grafting, pruning, consolidation, and purification -- to adapt to changes in data distribution; and (3) \textbf{Adaptive Clustered Data Sharing}, which mitigates data heterogeneity by enabling controlled partial data exchange between clients and cluster nodes. + By integrating these mechanisms, SOFA-FL effectively captures dynamic relationships among clients and enhances personalization capabilities without relying on predetermined cluster structures. + oai:arXiv.org:2512.08267v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Yuji Wang, Wenlong Liu, Jingxuan Niu, Haoji Zhang, Yansong Tang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yi Ni, Xinkun Wang, Han Zhang - Are AI-Generated Driving Videos Ready for Autonomous Driving? A Diagnostic Evaluation Framework - https://arxiv.org/abs/2512.06376 - arXiv:2512.06376v1 Announce Type: new -Abstract: Recent text-to-video models have enabled the generation of high-resolution driving scenes from natural language prompts. These AI-generated driving videos (AIGVs) offer a low-cost, scalable alternative to real or simulator data for autonomous driving (AD). But a key question remains: can such videos reliably support training and evaluation of AD models? We present a diagnostic framework that systematically studies this question. First, we introduce a taxonomy of frequent AIGV failure modes, including visual artifacts, physically implausible motion, and violations of traffic semantics, and demonstrate their negative impact on object detection, tracking, and instance segmentation. To support this analysis, we build ADGV-Bench, a driving-focused benchmark with human quality annotations and dense labels for multiple perception tasks. We then propose ADGVE, a driving-aware evaluator that combines static semantics, temporal cues, lane obedience signals, and Vision-Language Model(VLM)-guided reasoning into a single quality score for each clip. Experiments show that blindly adding raw AIGVs can degrade perception performance, while filtering them with ADGVE consistently improves both general video quality assessment metrics and downstream AD models, and turns AIGVs into a beneficial complement to real-world data. Our study highlights both the risks and the promise of AIGVs, and provides practical tools for safely leveraging large-scale video generation in future AD pipelines. - oai:arXiv.org:2512.06376v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Direct Product Theorems for Randomized Query Complexity + https://arxiv.org/abs/2512.08268 + arXiv:2512.08268v1 Announce Type: new +Abstract: We establish two new direct product theorems for the randomized query complexity of Boolean functions. + The first shows that computing $n$ copies of a function $f$, even with a small success probability of $\gamma^n$, requires $\Theta(n)$ times the "maximum distributional" query complexity of $f$ with success parameter $\gamma$. This result holds for all success parameters $\gamma$, even when $\gamma$ is very close to $1/2$ or to $1$. As a result, it unifies and generalizes Drucker's direct product theorem (2012) for $\gamma$ bounded away from $\frac12$ and $1$ as well as the strong direct sum theorem of Blais and Brody (2019) for $\gamma\approx 1-1/n$. + The second establishes a general "list decoding" direct product theorem that captures many different variants of partial computation tasks related to the function $f^n$ consisting of $n$ copies of $f$. Notably, our list decoding direct product theorem yields a new threshold direct product theorem and other new variants such as the labelled-threshold direct product theorem. + Both of these direct product theorems are obtained by taking a new approach. Instead of directly analyzing the query complexity of algorithms, we introduce a new measure of complexity of functions that we call "discounted score". We show that this measure satisfies a number of useful structural properties, including tensorization, that make it particularly suitable for the study of direct product questions. + oai:arXiv.org:2512.08268v1 + cs.CC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Xinhao Xiang, Abhijeet Rastogi, Jiawei Zhang + http://creativecommons.org/licenses/by-sa/4.0/ + Shalev Ben-David, Eric Blais - VAD-Net: Multidimensional Facial Expression Recognition in Intelligent Education System - https://arxiv.org/abs/2512.06377 - arXiv:2512.06377v1 Announce Type: new -Abstract: Current FER (Facial Expression Recognition) dataset is mostly labeled by emotion categories, such as happy, angry, sad, fear, disgust, surprise, and neutral which are limited in expressiveness. However, future affective computing requires more comprehensive and precise emotion metrics which could be measured by VAD(Valence-Arousal-Dominance) multidimension parameters. To address this, AffectNet has tried to add VA (Valence and Arousal) information, but still lacks D(Dominance). Thus, the research introduces VAD annotation on FER2013 dataset, takes the initiative to label D(Dominance) dimension. Then, to further improve network capacity, it enforces orthogonalized convolution on it, which extracts more diverse and expressive features and will finally increase the prediction accuracy. Experiment results show that D dimension could be measured but is difficult to obtain compared with V and A dimension no matter in manual annotation or regression network prediction. Secondly, the ablation test by introducing orthogonal convolution verifies that better VAD prediction could be obtained in the configuration of orthogonal convolution. Therefore, the research provides an initiative labelling for D dimension on FER dataset, and proposes a better prediction network for VAD prediction through orthogonal convolution. The newly built VAD annotated FER2013 dataset could act as a benchmark to measure VAD multidimensional emotions, while the orthogonalized regression network based on ResNet could act as the facial expression recognition baseline for VAD emotion prediction. The newly labeled dataset and implementation code is publicly available on https://github.com/YeeHoran/VAD-Net . - oai:arXiv.org:2512.06377v1 + EgoX: Egocentric Video Generation from a Single Exocentric Video + https://arxiv.org/abs/2512.08269 + arXiv:2512.08269v1 Announce Type: new +Abstract: Egocentric perception enables humans to experience and understand the world directly from their own point of view. Translating exocentric (third-person) videos into egocentric (first-person) videos opens up new possibilities for immersive understanding but remains highly challenging due to extreme camera pose variations and minimal view overlap. This task requires faithfully preserving visible content while synthesizing unseen regions in a geometrically consistent manner. To achieve this, we present EgoX, a novel framework for generating egocentric videos from a single exocentric input. EgoX leverages the pretrained spatio temporal knowledge of large-scale video diffusion models through lightweight LoRA adaptation and introduces a unified conditioning strategy that combines exocentric and egocentric priors via width and channel wise concatenation. Additionally, a geometry-guided self-attention mechanism selectively attends to spatially relevant regions, ensuring geometric coherence and high visual fidelity. Our approach achieves coherent and realistic egocentric video generation while demonstrating strong scalability and robustness across unseen and in-the-wild videos. + oai:arXiv.org:2512.08269v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/IJCNN60899.2024.10651071 - Yi Huo, Yun Ge + Taewoong Kang, Kinam Kim, Dohyeon Kim, Minho Park, Junha Hyung, Jaegul Choo - OCFER-Net: Recognizing Facial Expression in Online Learning System - https://arxiv.org/abs/2512.06379 - arXiv:2512.06379v1 Announce Type: new -Abstract: Recently, online learning is very popular, especially under the global epidemic of COVID-19. Besides knowledge distribution, emotion interaction is also very important. It can be obtained by employing Facial Expression Recognition (FER). Since the FER accuracy is substantial in assisting teachers to acquire the emotional situation, the project explores a series of FER methods and finds that few works engage in exploiting the orthogonality of convolutional matrix. Therefore, it enforces orthogonality on kernels by a regularizer, which extracts features with more diversity and expressiveness, and delivers OCFER-Net. Experiments are carried out on FER-2013, which is a challenging dataset. Results show superior performance over baselines by 1.087. The code of the research project is publicly available on https://github.com/YeeHoran/OCFERNet. - oai:arXiv.org:2512.06379v1 + Reasoning Models Ace the CFA Exams + https://arxiv.org/abs/2512.08270 + arXiv:2512.08270v1 Announce Type: new +Abstract: Previous research has reported that large language models (LLMs) demonstrate poor performance on the Chartered Financial Analyst (CFA) exams. However, recent reasoning models have achieved strong results on graduate-level academic and professional examinations across various disciplines. In this paper, we evaluate state-of-the-art reasoning models on a set of mock CFA exams consisting of 980 questions across three Level I exams, two Level II exams, and three Level III exams. Using the same pass/fail criteria from prior studies, we find that most models clear all three levels. The models that pass, ordered by overall performance, are Gemini 3.0 Pro, Gemini 2.5 Pro, GPT-5, Grok 4, Claude Opus 4.1, and DeepSeek-V3.1. Specifically, Gemini 3.0 Pro achieves a record score of 97.6% on Level I. Performance is also strong on Level II, led by GPT-5 at 94.3%. On Level III, Gemini 2.5 Pro attains the highest score with 86.4% on multiple-choice questions while Gemini 3.0 Pro achieves 92.0% on constructed-response questions. + oai:arXiv.org:2512.08270v1 + cs.AI + cs.CL + q-fin.GN + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Jaisal Patel, Yunzhe Chen, Kaiwen He, Keyi Wang, David Li, Kairong Xiao, Xiao-Yang Liu + + + Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation + https://arxiv.org/abs/2512.08271 + arXiv:2512.08271v1 Announce Type: new +Abstract: We introduce Zero-Splat TeleAssist, a zero-shot sensor-fusion pipeline that transforms commodity CCTV streams into a shared, 6-DoF world model for multilateral teleoperation. By integrating vision-language segmentation, monocular depth, weighted-PCA pose extraction, and 3D Gaussian Splatting (3DGS), TeleAssist provides every operator with real-time global positions and orientations of multiple robots without fiducials or depth sensors in an interaction-centric teleoperation setup. + oai:arXiv.org:2512.08271v1 + cs.RO cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + eess.IV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3531073.3534470 - Yi Huo, Lei Zhang + Srijan Dokania, Dharini Raghavan - Protecting Bystander Privacy via Selective Hearing in LALMs - https://arxiv.org/abs/2512.06380 - arXiv:2512.06380v1 Announce Type: new -Abstract: Large audio language models (LALMs) are increasingly deployed in real-world settings where they inevitably capture speech from unintended nearby bystanders, raising privacy risks that existing benchmarks and defences largely overlook. We introduce SH-Bench, the first benchmark designed to evaluate selective hearing: a model's ability to attend to an intended main speaker while refusing to process or reveal information about incidental bystander speech. SH-Bench contains 3,968 multi-speaker audio mixtures spanning both real-world and synthetic scenarios, paired with 77k multiple-choice questions that probe models under general and selective operating modes. We propose Selective Efficacy (SE), a unified metric capturing both multi-speaker comprehension and bystander-privacy protection. Our evaluation of state-of-the-art open-source and proprietary LALMs reveals substantial privacy leakage, with strong audio understanding failing to translate into selective protection of bystander privacy. To mitigate this gap, we introduce Bystander Privacy Fine-Tuning (BPFT), a training pipeline that teaches models to refuse bystander-related queries without degrading main-speaker comprehension. BPFT yields substantial gains which improve SE by up to 15.9% over Gemini 2.5 Pro, demonstrating that selective hearing is learnable but far from achieved in current LALMs. SH-Bench and BPFT provide the first systematic framework for measuring and improving bystander privacy in audio foundation models. - oai:arXiv.org:2512.06380v1 - cs.SD + AgentEval: Generative Agents as Reliable Proxies for Human Evaluation of AI-Generated Content + https://arxiv.org/abs/2512.08273 + arXiv:2512.08273v1 Announce Type: new +Abstract: Modern businesses are increasingly challenged by the time and expense required to generate and assess high-quality content. Human writers face time constraints, and extrinsic evaluations can be costly. While Large Language Models (LLMs) offer potential in content creation, concerns about the quality of AI-generated content persist. Traditional evaluation methods, like human surveys, further add operational costs, highlighting the need for efficient, automated solutions. This research introduces Generative Agents as a means to tackle these challenges. These agents can rapidly and cost-effectively evaluate AI-generated content, simulating human judgment by rating aspects such as coherence, interestingness, clarity, fairness, and relevance. By incorporating these agents, businesses can streamline content generation and ensure consistent, high-quality output while minimizing reliance on costly human evaluations. The study provides critical insights into enhancing LLMs for producing business-aligned, high-quality content, offering significant advancements in automated content generation and evaluation. + oai:arXiv.org:2512.08273v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Xiao Zhan, Guangzhi Sun, Jose Such, Phil Woodland + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Thanh Vu, Richi Nayak, Thiru Balasubramaniam - Beyond Existing Retrievals: Cross-Scenario Incremental Sample Learning Framework - https://arxiv.org/abs/2512.06381 - arXiv:2512.06381v1 Announce Type: new -Abstract: The parallelized multi-retrieval architecture has been widely adopted in large-scale recommender systems for its computational efficiency and comprehensive coverage of user interests. Many retrieval methods typically integrate additional cross-scenario samples to enhance the overall performance ceiling. However, those model designs neglect the fact that a part of the cross-scenario samples have already been retrieved by existing models within a system, leading to diminishing marginal utility in delivering incremental performance gains. In this paper, we propose a novel retrieval framework IncRec, specifically for cross-scenario incremental sample learning. The innovations of IncRec can be highlighted as two aspects. Firstly, we construct extreme cross-scenario incremental samples that are not retrieved by any existing model. And we design an incremental sample learning framework which focuses on capturing incremental representation to improve the overall retrieval performance. Secondly, we introduce a consistency-aware alignment module to further make the model prefer incremental samples with high exposure probability. Extensive offline and online A/B tests validate the superiority of our framework over state-of-the-art retrieval methods. In particular, we deploy IncRec in the Taobao homepage recommendation, achieving a 1% increase in online transaction count, demonstrating its practical applicability. - oai:arXiv.org:2512.06381v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 + gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs + https://arxiv.org/abs/2512.08274 + arXiv:2512.08274v1 Announce Type: new +Abstract: Knowledge Graphs (KGs) are a rich source of structured, heterogeneous data, powering a wide range of applications. A common approach to leverage this data is to train a graph neural network (GNN) on the KG. However, existing message-passing GNNs struggle to scale to large KGs because they rely on the iterative message passing process to learn the graph structure, which is inefficient, especially under mini-batch training, where a node sees only a partial view of its neighborhood. In this paper, we address this problem and present gHAWK, a novel and scalable GNN training framework for large KGs. The key idea is to precompute structural features for each node that capture its local and global structure before GNN training even begins. Specifically, gHAWK introduces a preprocessing step that computes: (a)~Bloom filters to compactly encode local neighborhood structure, and (b)~TransE embeddings to represent each node's global position in the graph. These features are then fused with any domain-specific features (e.g., text embeddings), producing a node feature vector that can be incorporated into any GNN technique. By augmenting message-passing training with structural priors, gHAWK significantly reduces memory usage, accelerates convergence, and improves model accuracy. Extensive experiments on large datasets from the Open Graph Benchmark (OGB) demonstrate that gHAWK achieves state-of-the-art accuracy and lower training time on both node property prediction and link prediction tasks, topping the OGB leaderboard for three graphs. + oai:arXiv.org:2512.08274v1 + cs.LG + cs.DB + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Tao Wang, Xun Luo, Jinlong Guo, Yuliang Yan, Jian Wu, Yuning Jiang, Bo Zheng + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Humera Sabir, Fatima Farooq, Ashraf Aboulnaga - Finding a Maximum Common (Induced) Subgraph: Structural Parameters Revisited - https://arxiv.org/abs/2512.06383 - arXiv:2512.06383v1 Announce Type: new -Abstract: We study the parameterized complexity of the problems of finding a maximum common (induced) subgraph of two given graphs. Since these problems generalize several NP-complete problems, they are intractable even when parameterized by strongly restricted structural parameters. Our contribution in this paper is to sharply complement the hardness of the problems by showing fixed-parameter tractable cases: both induced and non-induced problems parameterized by max-leaf number and by neighborhood diversity, and the induced problem parameterized by twin cover number. These results almost completely determine the complexity of the problems with respect to well-studied structural parameters. Also, the result on the twin cover number presents a rather rare example where the induced and non-induced cases have different complexity. - oai:arXiv.org:2512.06383v1 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 + FedLAD: A Modular and Adaptive Testbed for Federated Log Anomaly Detection + https://arxiv.org/abs/2512.08277 + arXiv:2512.08277v1 Announce Type: new +Abstract: Log-based anomaly detection (LAD) is critical for ensuring the reliability of large-scale distributed systems. However, most existing LAD approaches assume centralized training, which is often impractical due to privacy constraints and the decentralized nature of system logs. While federated learning (FL) offers a promising alternative, there is a lack of dedicated testbeds tailored to the needs of LAD in federated settings. To address this, we present FedLAD, a unified platform for training and evaluating LAD models under FL constraints. FedLAD supports plug-and-play integration of diverse LAD models, benchmark datasets, and aggregation strategies, while offering runtime support for validation logging (self-monitoring), parameter tuning (self-configuration), and adaptive strategy control (self-adaptation). By enabling reproducible and scalable experimentation, FedLAD bridges the gap between FL frameworks and LAD requirements, providing a solid foundation for future research. Project code is publicly available at: https://github.com/AA-cityu/FedLAD. + oai:arXiv.org:2512.08277v1 + cs.SE + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tesshu Hanaka, Yuto Okada, Yota Otachi, Lena Volk + Yihan Liao, Jacky Keung, Zhenyu Mao, Jingyu Zhang, Jialong Li - Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence - https://arxiv.org/abs/2512.06387 - arXiv:2512.06387v1 Announce Type: new -Abstract: Embodied AI systems integrate language models with real world sensing, mobility, and cloud connected mobile apps. Yet while model jailbreaks have drawn significant attention, the broader system stack of embodied intelligence remains largely unexplored. In this work, we conduct the first holistic security analysis of the Unitree Go2 platform and uncover ten cross layer vulnerabilities the "Ten Sins of Embodied AI Security." Using BLE sniffing, traffic interception, APK reverse engineering, cloud API testing, and hardware probing, we identify systemic weaknesses across three architectural layers: wireless provisioning, core modules, and external interfaces. These include hard coded keys, predictable handshake tokens, WiFi credential leakage, missing TLS validation, static SSH password, multilingual safety bypass behavior, insecure local relay channels, weak binding logic, and unrestricted firmware access. Together, they allow adversaries to hijack devices, inject arbitrary commands, extract sensitive information, or gain full physical control.Our findings show that securing embodied AI requires far more than aligning the model itself. We conclude with system level lessons learned and recommendations for building embodied platforms that remain robust across their entire software hardware ecosystem. - oai:arXiv.org:2512.06387v1 - cs.CR + Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making + https://arxiv.org/abs/2512.08280 + arXiv:2512.08280v1 Announce Type: new +Abstract: Offline decision-making requires synthesizing reliable behaviors from fixed datasets without further interaction, yet existing generative approaches often yield trajectories that are dynamically infeasible. We propose Model Predictive Diffuser (MPDiffuser), a compositional model-based diffusion framework consisting of: (i) a planner that generates diverse, task-aligned trajectories; (ii) a dynamics model that enforces consistency with the underlying system dynamics; and (iii) a ranker module that selects behaviors aligned with the task objectives. MPDiffuser employs an alternating diffusion sampling scheme, where planner and dynamics updates are interleaved to progressively refine trajectories for both task alignment and feasibility during the sampling process. We also provide a theoretical rationale for this procedure, showing how it balances fidelity to data priors with dynamics consistency. Empirically, the compositional design improves sample efficiency, as it leverages even low-quality data for dynamics learning and adapts seamlessly to novel dynamics. We evaluate MPDiffuser on both unconstrained (D4RL) and constrained (DSRL) offline decision-making benchmarks, demonstrating consistent gains over existing approaches. Furthermore, we present a preliminary study extending MPDiffuser to vision-based control tasks, showing its potential to scale to high-dimensional sensory inputs. Finally, we deploy our method on a real quadrupedal robot, showcasing its practicality for real-world control. + oai:arXiv.org:2512.08280v1 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuhang Huang, Junchao Li, Boyang Ma, Xuelong Dai, Minghui Xu, Kaidi Xu, Yue Zhang, Jianping Wang, Xiuzhen Cheng + Haldun Balim, Na Li, Yilun Du - Web Technologies Security in the AI Era: A Survey of CDN-Enhanced Defenses - https://arxiv.org/abs/2512.06390 - arXiv:2512.06390v1 Announce Type: new -Abstract: The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge computing place programmable defenses closest to users and bots, making them natural enforcement points for machine-learning (ML) driven inspection, throttling, and isolation. This survey synthesizes the landscape of AI-enhanced defenses deployed at the edge: (i) anomaly- and behavior-based Web Application Firewalls (WAFs) within broader Web Application and API Protection (WAAP), (ii) adaptive DDoS detection and mitigation, (iii) bot management that resists human-mimicry, and (iv) API discovery, positive security modeling, and encrypted-traffic anomaly analysis. We add a systematic survey method, a threat taxonomy mapped to edge-observable signals, evaluation metrics, deployment playbooks, and governance guidance. We conclude with a research agenda spanning XAI, adversarial robustness, and autonomous multi-agent defense. Our findings indicate that edge-centric AI measurably improves time-to-detect and time-to-mitigate while reducing data movement and enhancing compliance, yet introduces new risks around model abuse, poisoning, and governance. - oai:arXiv.org:2512.06390v1 - cs.CR - cs.AI + Probabilistic Multi-Agent Aircraft Landing Time Prediction + https://arxiv.org/abs/2512.08281 + arXiv:2512.08281v1 Announce Type: new +Abstract: Accurate and reliable aircraft landing time prediction is essential for effective resource allocation in air traffic management. However, the inherent uncertainty of aircraft trajectories and traffic flows poses significant challenges to both prediction accuracy and trustworthiness. Therefore, prediction models should not only provide point estimates of aircraft landing times but also the uncertainties associated with these predictions. Furthermore, aircraft trajectories are frequently influenced by the presence of nearby aircraft through air traffic control interventions such as radar vectoring. Consequently, landing time prediction models must account for multi-agent interactions in the airspace. In this work, we propose a probabilistic multi-agent aircraft landing time prediction framework that provides the landing times of multiple aircraft as distributions. We evaluate the proposed framework using an air traffic surveillance dataset collected from the terminal airspace of the Incheon International Airport in South Korea. The results demonstrate that the proposed model achieves higher prediction accuracy than the baselines and quantifies the associated uncertainties of its outcomes. In addition, the model uncovered underlying patterns in air traffic control through its attention scores, thereby enhancing explainability. + oai:arXiv.org:2512.08281v1 + cs.MA cs.LG - cs.NI - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - 10.1109/APWiMob67231.2025.11269122 - 2025 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob), Bali, Indonesia, 2025, pp. 180-186 - Mehrab Hosain, Sabbir Alom Shuvo, Matthew Ogbe, Md Shah Jalal Mazumder, Yead Rahman, Md Azizul Hakim, Anukul Pandey + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Kyungmin Kim, Seokbin Yoon, Keumjin Lee - RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs - https://arxiv.org/abs/2512.06392 - arXiv:2512.06392v1 Announce Type: new -Abstract: Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL framework on TPUs. RLAX employs a parameter-server architecture. A master trainer periodically pushes updated model weights to the parameter server while a fleet of inference workers pull the latest weights and generates new rollouts. We introduce a suite of system techniques to enable scalable and preemptible RL for a diverse set of state-of-art RL algorithms. To accelerate convergence and improve model quality, we have devised new dataset curation and alignment techniques. Large-scale evaluations show that RLAX improves QwQ-32B's pass@8 accuracy by 12.8% in just 12 hours 48 minutes on 1024 v5p TPUs, while remaining robust to preemptions during training. - oai:arXiv.org:2512.06392v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + PAVAS: Physics-Aware Video-to-Audio Synthesis + https://arxiv.org/abs/2512.08282 + arXiv:2512.08282v1 Announce Type: new +Abstract: Recent advances in Video-to-Audio (V2A) generation have achieved impressive perceptual quality and temporal synchronization, yet most models remain appearance-driven, capturing visual-acoustic correlations without considering the physical factors that shape real-world sounds. We present Physics-Aware Video-to-Audio Synthesis (PAVAS), a method that incorporates physical reasoning into a latent diffusion-based V2A generation through the Physics-Driven Audio Adapter (Phy-Adapter). The adapter receives object-level physical parameters estimated by the Physical Parameter Estimator (PPE), which uses a Vision-Language Model (VLM) to infer the moving-object mass and a segmentation-based dynamic 3D reconstruction module to recover its motion trajectory for velocity computation. These physical cues enable the model to synthesize sounds that reflect underlying physical factors. To assess physical realism, we curate VGG-Impact, a benchmark focusing on object-object interactions, and introduce Audio-Physics Correlation Coefficient (APCC), an evaluation metric that measures consistency between physical and auditory attributes. Comprehensive experiments show that PAVAS produces physically plausible and perceptually coherent audio, outperforming existing V2A models in both quantitative and qualitative evaluations. Visit https://physics-aware-video-to-audio-synthesis.github.io for demo videos. + oai:arXiv.org:2512.08282v1 + cs.CV + cs.MM + cs.SD + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Runlong Zhou, Lefan Zhang, Shang-Chen Wu, Kelvin Zou, Hanzhi Zhou, Ke Ye, Yihao Feng, Dong Yin, Alex Guillen Garcia, Dmytro Babych, Rohit Chatterjee, Matthew Hopkins, Xiang Kong, Chang Lan, Lezhi Li, Yiping Ma, Daniele Molinari, Senyu Tong, Yanchao Sun, Thomas Voice, Jianyu Wang, Chong Wang, Simon Wang, Floris Weers, Yechen Xu, Guolin Yin, Muyang Yu, Yi Zhang, Zheng Zhou, Danyang Zhuo, Ruoming Pang, Cheng Leong + Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka, Tae-Hyun Oh, Yuki Mitsufuji - Less Is More for Multi-Step Logical Reasoning of LLM Generalisation Under Rule Removal, Paraphrasing, and Compression - https://arxiv.org/abs/2512.06393 - arXiv:2512.06393v1 Announce Type: new -Abstract: Large language models (LLMs) excel across many natural language tasks, yet their generalisation to structural perturbations in logical contexts remains poorly understood. We introduce a controlled evaluation framework that probes reasoning reliability through four targeted stress tests: (1) rule deletion, removing either redundant or essential rules from a multi-step inference chain; (2) contradictory evidence injection; (3) logic-preserving rewrites generated through several families of equivalence laws (contrapositive, double negation, implication, De Morgan, identity, and commutativity); and (4) multi-law equivalence stacking that introduces 2-5 simultaneous logical transformations. - Across three representative model families: BERT, Qwen2, and LLaMA-like models. Our experiments reveal a strikingly consistent pattern: all models achieve perfect accuracy on the base tasks and remain fully generalise to redundant rule deletion and all equivalence-based rewrites (single or multi-law), but fail sharply under essential rule deletion (dropping to 25% accuracy) and collapse completely in the presence of explicit contradictions (0% accuracy). These results demonstrate that LLMs possess stable invariance to semantic-preserving logical transformations, yet remain fundamentally brittle to missing or conflicting evidence. Our framework provides a clean diagnostic tool for isolating such reasoning failure modes and highlights persistent gaps in the logical generalisation abilities of current LLMs. - oai:arXiv.org:2512.06393v1 + Empowering smart app development with SolidGPT: an edge-cloud hybrid AI agent framework + https://arxiv.org/abs/2512.08286 + arXiv:2512.08286v1 Announce Type: new +Abstract: The integration of Large Language Models (LLMs) into mobile and software development workflows faces a persistent tension among three demands: semantic awareness, developer productivity, and data privacy. Traditional cloud-based tools offer strong reasoning but risk data exposure and latency, while on-device solutions lack full-context understanding across codebase and developer tooling. We introduce SolidGPT, an open-source, edge-cloud hybrid developer assistant built on GitHub, designed to enhance code and workspace semantic search. SolidGPT enables developers to: talk to your codebase: interactively query code and project structure, discovering the right methods and modules without manual searching. Automate software project workflows: generate PRDs, task breakdowns, Kanban boards, and even scaffold web app beginnings, with deep integration via VSCode and Notion. Configure private, extensible agents: onboard private code folders (up to approximately 500 files), connect Notion, customize AI agent personas via embedding and in-context training, and deploy via Docker, CLI, or VSCode extension. In practice, SolidGPT empowers developer productivity through: Semantic-rich code navigation: no more hunting through files or wondering where a feature lives. Integrated documentation and task management: seamlessly sync generated PRD content and task boards into developer workflows. Privacy-first design: running locally via Docker or VSCode, with full control over code and data, while optionally reaching out to LLM APIs as needed. By combining interactive code querying, automated project scaffolding, and human-AI collaboration, SolidGPT provides a practical, privacy-respecting edge assistant that accelerates real-world development workflows, ideal for intelligent mobile and software engineering contexts. + oai:arXiv.org:2512.08286v1 + cs.SE cs.AI - cs.CL cs.LG - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Qiming Bao, Xiaoxuan Fu + 10.54254/2977-3903/2025.25283 + Advances in Engineering Innovation 16.7 (2025): 86-92 + Liao Hu, Qiteng Wu, Ruoyu Qi - Enhancing Information Retrieval in Digital Libraries through Unit Harmonisation in Scholarly Knowledge Graphs - https://arxiv.org/abs/2512.06395 - arXiv:2512.06395v1 Announce Type: new -Abstract: Scientists have always used the studies and research of other researchers to achieve new objectives and perspectives. In particular, employing and operating the measured data in previous studies is so practical. Searching the content of other scientists' articles is a challenge that researchers have always struggled with. Nowadays, the use of knowledge graphs as a semantic database has helped a lot in saving and retrieving scholarly knowledge. Such technologies are crucial to upgrading traditional search systems to smart knowledge retrieval, which is crucial to getting the most relevant answers for a user query, especially in information and knowledge management. However, in most cases, only the metadata of a paper is searchable, and it is still cumbersome for scientists to have access to the content of the papers. In this paper, we present a novel method of faceted search \emph{structured content} for comparing and filtering measured data in scholarly knowledge graphs while different units of measurement are used in different studies. This search system proposes applicable units as facets to the user and would dynamically integrate content from further remote knowledge graphs to materialize the scholarly knowledge graph and achieve a higher order of exploration usability on scholarly content, which can be filtered to better satisfy the user's information needs. The state of the art is that, by using our faceted search system, users can not only search the contents of scientific articles, but also compare and filter heterogeneous data. - oai:arXiv.org:2512.06395v1 - cs.DL - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 + Synergizing Monetization, Orchestration, and Semantics in Computing Continuum + https://arxiv.org/abs/2512.08288 + arXiv:2512.08288v1 Announce Type: new +Abstract: Industry demands are growing for hyper-distributed applications that span from the cloud to the edge in domains such as smart manufacturing, transportation, and agriculture. Yet today's solutions struggle to meet these demands due to inherent limitations in scalability, interoperability, and trust. In this article, we introduce HERMES (Heterogeneous Computing Continuum with Resource Monetization, Orchestration, and Semantic) - a novel framework designed to transform connectivity and data utilization across the computing continuum. HERMES establishes an open, seamless, and secure environment where resources, from cloud servers to tiny edge devices, can be orchestrated intelligently, data and services can be monetized in a distributed marketplace, and knowledge is shared through semantic interoperability. By bridging these key facets, HERMES lays a foundation for a new generation of distributed applications that are more efficient, trustworthy, and autonomous. + oai:arXiv.org:2512.08288v1 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Golsa Heidari, Markus Stocker, S\"oren Auer + http://creativecommons.org/licenses/by/4.0/ + Chinmaya Kumar Dehury, Lauri Lov\'en, Praveen Kumar Donta, Ilir Murturi, Schahram Dustdar - AgenticCyber: A GenAI-Powered Multi-Agent System for Multimodal Threat Detection and Adaptive Response in Cybersecurity - https://arxiv.org/abs/2512.06396 - arXiv:2512.06396v1 Announce Type: new -Abstract: The increasing complexity of cyber threats in distributed environments demands advanced frameworks for real-time detection and response across multimodal data streams. This paper introduces AgenticCyber, a generative AI powered multi-agent system that orchestrates specialized agents to monitor cloud logs, surveillance videos, and environmental audio concurrently. The solution achieves 96.2% F1-score in threat detection, reduces response latency to 420 ms, and enables adaptive security posture management using multimodal language models like Google's Gemini coupled with LangChain for agent orchestration. Benchmark datasets, such as AWS CloudTrail logs, UCF-Crime video frames, and UrbanSound8K audio clips, show greater performance over standard intrusion detection systems, reducing mean time to respond (MTTR) by 65% and improving situational awareness. This work introduces a scalable, modular proactive cybersecurity architecture for enterprise networks and IoT ecosystems that overcomes siloed security technologies with cross-modal reasoning and automated remediation. - oai:arXiv.org:2512.06396v1 + MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks + https://arxiv.org/abs/2512.08289 + arXiv:2512.08289v1 Announce Type: new +Abstract: Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While recent studies have demonstrated the potential of such attacks, they typically rely on impractical assumptions, such as white-box access or known user queries, thereby underestimating the difficulty of real-world exploitation. In this paper, we bridge this gap by proposing MIRAGE, a novel multi-stage poisoning pipeline designed for strict black-box and query-agnostic environments. Operating on surrogate model feedback, MIRAGE functions as an automated optimization framework that integrates three key mechanisms: it utilizes persona-driven query synthesis to approximate latent user search distributions, employs semantic anchoring to imperceptibly embed these intents for high retrieval visibility, and leverages an adversarial variant of Test-Time Preference Optimization (TPO) to maximize persuasion. To rigorously evaluate this threat, we construct a new benchmark derived from three long-form, domain-specific datasets. Extensive experiments demonstrate that MIRAGE significantly outperforms existing baselines in both attack efficacy and stealthiness, exhibiting remarkable transferability across diverse retriever-LLM configurations and highlighting the urgent need for robust defense strategies. + oai:arXiv.org:2512.08289v1 cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Shovan Roy + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Tailun Chen, Yu He, Yan Wang, Shuo Shao, Haolun Zheng, Zhihao Liu, Jinfeng Li, Yuefeng Chen, Zhixuan Chu, Zhan Qin - Perceptual Region-Driven Infrared-Visible Co-Fusion for Extreme Scene Enhancement - https://arxiv.org/abs/2512.06400 - arXiv:2512.06400v1 Announce Type: new -Abstract: In photogrammetry, accurately fusing infrared (IR) and visible (VIS) spectra while preserving the geometric fidelity of visible features and incorporating thermal radiation is a significant challenge, particularly under extreme conditions. Existing methods often compromise visible imagery quality, impacting measurement accuracy. To solve this, we propose a region perception-based fusion framework that combines multi-exposure and multi-modal imaging using a spatially varying exposure (SVE) camera. This framework co-fuses multi-modal and multi-exposure data, overcoming single-exposure method limitations in extreme environments. The framework begins with region perception-based feature fusion to ensure precise multi-modal registration, followed by adaptive fusion with contrast enhancement. A structural similarity compensation mechanism, guided by regional saliency maps, optimizes IR-VIS spectral integration. Moreover, the framework adapts to single-exposure scenarios for robust fusion across different conditions. Experiments conducted on both synthetic and real-world data demonstrate superior image clarity and improved performance compared to state-of-the-art methods, as evidenced by both quantitative and visual evaluations. - oai:arXiv.org:2512.06400v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem + https://arxiv.org/abs/2512.08290 + arXiv:2512.08290v1 Announce Type: new +Abstract: The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C for Agentic AI." While this decoupling of context and execution solves critical interoperability challenges, it introduces a profound new threat landscape where the boundary between epistemic errors (hallucinations) and security breaches (unauthorized actions) dissolves. This Systematization of Knowledge (SoK) aims to provide a comprehensive taxonomy of risks in the MCP ecosystem, distinguishing between adversarial security threats (e.g., indirect prompt injection, tool poisoning) and epistemic safety hazards (e.g., alignment failures in distributed tool delegation). We analyze the structural vulnerabilities of MCP primitives, specifically Resources, Prompts, and Tools, and demonstrate how "context" can be weaponized to trigger unauthorized operations in multi-agent environments. Furthermore, we survey state-of-the-art defenses, ranging from cryptographic provenance (ETDI) to runtime intent verification, and conclude with a roadmap for securing the transition from conversational chatbots to autonomous agentic operating systems. + oai:arXiv.org:2512.08290v1 + cs.CR + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jing Tao, Yonghong Zong, Banglei Guana, Pengju Sun, Taihang Lei, Yang Shanga, Qifeng Yu + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Shiva Gaire, Srijan Gyawali, Saroj Mishra, Suman Niroula, Dilip Thakur, Umesh Yadav - LLMCFG-TGen: Using LLM-Generated Control Flow Graphs to Automatically Create Test Cases from Use Cases - https://arxiv.org/abs/2512.06401 - arXiv:2512.06401v1 Announce Type: new -Abstract: Appropriate test case generation is critical in software testing, significantly impacting the quality of the testing. Requirements-Based Test Generation (RBTG) derives test cases from software requirements, aiming to verify whether or not the system's behaviors align with user needs and expectations. Requirements are often documented in Natural Language (NL), with use-case descriptions being a popular method for capturing functional behaviors and interaction flows in a structured form. Large Language Models (LLMs) have shown strong potential for automating test generation directly from NL requirements. However, current LLM-based approaches may not provide comprehensive, non-redundant coverage. They may also fail to capture complex conditional logic in requirements, resulting in incomplete test cases. We propose a new approach that automatically generates test cases from NL use-case descriptions, called Test Generation based on LLM-generated Control Flow Graphs (LLMCFG-TGen). LLMCFG-TGen comprises three main steps: (1) An LLM transforms a use case into a structured CFG that encapsulates all potential branches; (2) The generated CFG is explored, and all complete execution paths are enumerated; and (3) The execution paths are then used to generate the test cases. To evaluate our proposed approach, we conducted a series of experiments. The results show that LLMs can effectively construct well-structured CFGs from NL use cases. Compared with the baseline methods, LLMCFG-TGen achieves full path coverage, improving completeness and ensuring clear and accurate test cases. Practitioner assessments confirm that LLMCFG-TGen produces logically consistent and comprehensive test cases, while substantially reducing manual effort. The findings suggest that coupling LLM-based semantic reasoning with structured modeling effectively bridges the gap between NL requirements and systematic test generation. - oai:arXiv.org:2512.06401v1 + Exposing and Defending Membership Leakage in Vulnerability Prediction Models + https://arxiv.org/abs/2512.08291 + arXiv:2512.08291v1 Announce Type: new +Abstract: Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inference Attacks (MIAs), where adversaries aim to infer whether a particular code sample was used during training, poses serious privacy concerns. While MIA has been widely investigated in NLP and vision domains, its effects on security-critical code analysis tasks remain underexplored. In this work, we conduct the first comprehensive analysis of MIA on VP models, evaluating the attack success across various architectures (LSTM, BiGRU, and CodeBERT) and feature combinations, including embeddings, logits, loss, and confidence. Our threat model aligns with black-box and gray-box settings where prediction outputs are observable, allowing adversaries to infer membership by analyzing output discrepancies between training and non-training samples. The empirical findings reveal that logits and loss are the most informative and vulnerable outputs for membership leakage. Motivated by these observations, we propose a Noise-based Membership Inference Defense (NMID), which is a lightweight defense module that applies output masking and Gaussian noise injection to disrupt adversarial inference. Extensive experiments demonstrate that NMID significantly reduces MIA effectiveness, lowering the attack AUC from nearly 1.0 to below 0.65, while preserving the predictive utility of VP models. Our study highlights critical privacy risks in code analysis and offers actionable defense strategies for securing AI-powered software systems. + oai:arXiv.org:2512.08291v1 + cs.CR cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Zhenzhen Yang, Chenhui Cui, Tao Li, Rubing Huang, Nan Niu, Dave Towey, Shikai Guo + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yihan Liao, Jacky Keung, Xiaoxue Ma, Jingyu Zhang, Yicheng Sun - GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols - https://arxiv.org/abs/2512.06404 - arXiv:2512.06404v1 Announce Type: new -Abstract: Predictive atomistic simulations have propelled materials discovery, yet routine setup and debugging still demand computer specialists. This know-how gap limits Integrated Computational Materials Engineering (ICME), where state-of-the-art codes exist but remain cumbersome for non-experts. We address this bottleneck with GENIUS, an AI-agentic workflow that fuses a smart Quantum ESPRESSO knowledge graph with a tiered hierarchy of large language models supervised by a finite-state error-recovery machine. Here we show that GENIUS translates free-form human-generated prompts into validated input files that run to completion on $\approx$80% of 295 diverse benchmarks, where 76% are autonomously repaired, with success decaying exponentially to a 7% baseline. Compared with LLM-only baselines, GENIUS halves inference costs and virtually eliminates hallucinations. The framework democratizes electronic-structure DFT simulations by intelligently automating protocol generation, validation, and repair, opening large-scale screening and accelerating ICME design loops across academia and industry worldwide. - oai:arXiv.org:2512.06404v1 - cs.AI - cond-mat.mtrl-sci - physics.chem-ph - Tue, 09 Dec 2025 00:00:00 -0500 + OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation + https://arxiv.org/abs/2512.08294 + arXiv:2512.08294v1 Announce Type: new +Abstract: Despite the promising progress in subject-driven image generation, current models often deviate from the reference identities and struggle in complex scenes with multiple subjects. To address this challenge, we introduce OpenSubject, a video-derived large-scale corpus with 2.5M samples and 4.35M images for subject-driven generation and manipulation. The dataset is built with a four-stage pipeline that exploits cross-frame identity priors. (i) Video Curation. We apply resolution and aesthetic filtering to obtain high-quality clips. (ii) Cross-Frame Subject Mining and Pairing. We utilize vision-language model (VLM)-based category consensus, local grounding, and diversity-aware pairing to select image pairs. (iii) Identity-Preserving Reference Image Synthesis. We introduce segmentation map-guided outpainting to synthesize the input images for subject-driven generation and box-guided inpainting to generate input images for subject-driven manipulation, together with geometry-aware augmentations and irregular boundary erosion. (iv) Verification and Captioning. We utilize a VLM to validate synthesized samples, re-synthesize failed samples based on stage (iii), and then construct short and long captions. In addition, we introduce a benchmark covering subject-driven generation and manipulation, and then evaluate identity fidelity, prompt adherence, manipulation consistency, and background consistency with a VLM judge. Extensive experiments show that training with OpenSubject improves generation and manipulation performance, particularly in complex scenes. + oai:arXiv.org:2512.08294v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Mohammad Soleymanibrojeni, Roland Aydin, Diego Guedes-Sobrinho, Alexandre C. Dias, Maur\'icio J. Piotrowski, Wolfgang Wenzel, Celso Ricardo Caldeira R\^ego + Yexin Liu, Manyuan Zhang, Yueze Wang, Hongyu Li, Dian Zheng, Weiming Zhang, Changsheng Lu, Xunliang Cai, Yan Feng, Peng Pei, Harry Yang - UncertaintyZoo: A Unified Toolkit for Quantifying Predictive Uncertainty in Deep Learning Systems - https://arxiv.org/abs/2512.06406 - arXiv:2512.06406v1 Announce Type: new -Abstract: Large language models(LLMs) are increasingly expanding their real-world applications across domains, e.g., question answering, autonomous driving, and automatic software development. Despite this achievement, LLMs, as data-driven systems, often make incorrect predictions, which can lead to potential losses in safety-critical scenarios. To address this issue and measure the confidence of model outputs, multiple uncertainty quantification(UQ) criteria have been proposed. However, even though important, there are limited tools to integrate these methods, hindering the practical usage of UQ methods and future research in this domain. To bridge this gap, in this paper, we introduce UncertaintyZoo, a unified toolkit that integrates 29 uncertainty quantification methods, covering five major categories under a standardized interface. Using UncertaintyZoo, we evaluate the usefulness of existing uncertainty quantification methods under the code vulnerability detection task on CodeBERT and ChatGLM3 models. The results demonstrate that UncertaintyZoo effectively reveals prediction uncertainty. The tool with a demonstration video is available on the project site https://github.com/Paddingbuta/UncertaintyZoo. - oai:arXiv.org:2512.06406v1 + Towards a Science of Scaling Agent Systems + https://arxiv.org/abs/2512.08296 + arXiv:2512.08296v1 Announce Type: new +Abstract: Agents, language model (LM)-based systems that are capable of reasoning, planning, and acting are becoming the dominant paradigm for real-world AI applications. Despite this widespread adoption, the principles that determine their performance remain underexplored, leaving practitioners to rely on heuristics rather than principled design choices. We address this gap by deriving quantitative scaling principles for agent systems. We evaluate this across four diverse benchmarks: Finance-Agent, BrowseComp-Plus, PlanCraft, and Workbench. Using five canonical architectures (Single, Independent, Centralized, Decentralized, Hybrid) instantiated across three LLM families, we perform a controlled evaluation spanning 180 configurations with standardized tools and token budgets. We derive a predictive model using empirical coordination metrics, including efficiency, overhead, error amplification, and redundancy, that achieves cross-validated R^2=0.513. We identify three dominant effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead. (2) a capability saturation: coordination yields diminishing or negative returns (beta=-0.408, p<0.001) once single-agent baselines exceed ~45%. (3) topology-dependent error amplification: independent agents amplify errors 17.2x through unchecked propagation, while centralized coordination contains this to 4.4x. Centralized coordination improves performance by 80.9% on parallelizable tasks like financial reasoning, while decentralized coordination excels on dynamic web navigation (+9.2% vs. +0.2%). Yet for sequential reasoning tasks, all multi-agent variants degraded performance by 39-70%. The framework predicts the optimal coordination strategy for 87% of held-out configurations, providing a predictive principle of agentic scaling based on measurable task properties. + oai:arXiv.org:2512.08296v1 cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Xianzong Wu, Xiaohong Li, Lili Quan, Qiang Hu + Yubin Kim, Ken Gu, Chanwoo Park, Chunjong Park, Samuel Schmidgall, A. Ali Heydari, Yao Yan, Zhihan Zhang, Yuchen Zhuang, Mark Malhotra, Paul Pu Liang, Hae Won Park, Yuzhe Yang, Xuhai Xu, Yilun Du, Shwetak Patel, Tim Althoff, Daniel McDuff, Xin Liu - CommentScope: A Comment-Embedded Assisted Reading System for a Long Text - https://arxiv.org/abs/2512.06408 - arXiv:2512.06408v1 Announce Type: new -Abstract: Long texts are ubiquitous on social platforms, yet readers often face information overload and struggle to locate key content. Comments provide valuable external perspectives for understanding, questioning, and complementing the text, but their potential is hindered by disorganized and unstructured presentation. Few studies have explored embedding comments directly into reading. As an exploratory step, we propose CommentScope, a system with two core modules: a pipeline that classifies comments into five types and aligns them with relevant sentences, and a presentation module that integrates comments inline or as side notes, supported by visual cues such as colors, charts, and highlights. Technical evaluation shows that the hybrid "Rule+LLM" pipeline achieved solid performance in semantic classification (accuracy=0.90) and position alignment (accuracy=0.88). A user study (N=12) further demonstrated that the sentence-end embedding significantly improved comment discovery accuracy and reading fluency while reducing mental demand and perceived effort. - oai:arXiv.org:2512.06408v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Formation and Investigation of Cooperative Platooning at the Early Stage of Connected and Automated Vehicles Deployment + https://arxiv.org/abs/2512.08298 + arXiv:2512.08298v1 Announce Type: new +Abstract: Cooperative platooning, enabled by cooperative adaptive cruise control (CACC), is a cornerstone technology for connected automated vehicles (CAVs), offering significant improvements in safety, comfort, and traffic efficiency over traditional adaptive cruise control (ACC). This paper addresses a key challenge in the initial deployment phase of CAVs: the limited benefits of cooperative platooning due to the sparse distribution of CAVs on the road. To overcome this limitation, we propose an innovative control framework that enhances cooperative platooning in mixed traffic environments. Two techniques are utilized: (1) a mixed cooperative platooning strategy that integrates CACC with unconnected vehicles (CACCu), and (2) a strategic lane-change decision model designed to facilitate safe and efficient lane changes for platoon formation. Additionally, a surrounding vehicle identification system is embedded in the framework to enable CAVs to effectively identify and select potential platooning leaders. Simulation studies across various CV market penetration rates (MPRs) show that incorporating CACCu systems significantly improves safety, comfort, and traffic efficiency compared to existing systems with only CACC and ACC systems, even at CV penetration as low as 10%. The maximized platoon formation increases by up to 24%, accompanied by an 11% reduction in acceleration and a 7% decrease in fuel consumption. Furthermore, the strategic lane-change model enhances CAV performance, achieving notable improvements between 6% and 60% CV penetration, without adversely affecting overall traffic flow. + oai:arXiv.org:2512.08298v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shuai Chen (Jiangsu Ocean University, Lianyungang, China), Lei Han (Jiangsu Ocean University, Lianyungang, China), Haoyu Wang (Jiangsu Ocean University, Lianyungang, China), Zhaoman Zhong (Jiangsu Ocean University, Lianyungang, China) + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Zeyu Mu, Sergei S. Avedisov, Ahmadreza Moradipari, B. Brian Park - KyFrog: A High-Security LWE-Based KEM Inspired by ML-KEM - https://arxiv.org/abs/2512.06411 - arXiv:2512.06411v1 Announce Type: new -Abstract: KyFrog is a conservative Learning-with-Errors (LWE) key-encapsulation mechanism designed to explore an alternative operating point compared to schemes with relatively small public keys and ciphertexts. KyFrog uses a larger dimension (n = 1024) and a small prime modulus q = 1103, together with narrow error distributions with standard deviations sigma_s = sigma_e = 1.4, to target approximately 2^325 classical and quantum security against state-of-the-art lattice attacks under standard cost models, as estimated using the Lattice Estimator. The price paid for this security margin is an extremely large KEM ciphertext (about 0.5 MiB), while public and secret keys remain in the same ballpark as ML-KEM. We describe the design rationale, parameter search methodology, and implementation details of KyFrog, and we compare its asymptotic security and concrete parameter sizes with the ML-KEM standard. All code and data for this work are released as free and open-source software, with the full C++23 implementation and experimental scripts available at: https://github.com/victormeloasm/kyfrog - oai:arXiv.org:2512.06411v1 + Secure Audio Embedding in Images using Nature-Inspired Optimization + https://arxiv.org/abs/2512.08299 + arXiv:2512.08299v1 Announce Type: new +Abstract: In todays digital world, protecting sensitive data is very essential. Steganography hides the existence of secret data instead of its content, providing better security for multimedia communication. This paper proposes a new technique for hiding audio files inside images using the Least Significant Bit (LSB) method optimized by the Harris Hawks Optimization (HHO) algorithm. HHO is a nature-inspired metaheuristic that imitates the hunting behavior of Harris hawks to find optimal pixel positions for embedding data. The proposed method is evaluated using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Mean Square Error (MSE). Experimental results show that HHO achieves better image quality, robustness, and embedding capacity compared to existing methods. + oai:arXiv.org:2512.08299v1 cs.CR - math.RA - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/publicdomain/zero/1.0/ + Aman Kumar, Ankit Chaudhary + + + rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection + https://arxiv.org/abs/2512.08300 + arXiv:2512.08300v1 Announce Type: new +Abstract: Large language models (LLMs) are post-trained through reinforcement learning (RL) to evolve into Reasoning Language Models (RLMs), where the hallmark of this advanced reasoning is ``aha'' moments when they start to perform strategies, such as self-reflection and deep thinking, within chain of thoughts (CoTs). Motivated by this, this paper proposes a novel reinforced strategy injection mechanism (rSIM), that enables any LLM to become an RLM by employing a small planner to guide the LLM's CoT through the adaptive injection of reasoning strategies. To achieve this, the planner (leader agent) is jointly trained with an LLM (follower agent) using multi-agent RL (MARL), based on a leader-follower framework and straightforward rule-based rewards. Experimental results show that rSIM enables Qwen2.5-0.5B to become an RLM and significantly outperform Qwen2.5-14B. Moreover, the planner is generalizable: it only needs to be trained once and can be applied as a plug-in to substantially improve the reasoning capabilities of existing LLMs. In addition, the planner supports continual learning across various tasks, allowing its planning abilities to gradually improve and generalize to a wider range of problems. + oai:arXiv.org:2512.08300v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Victor Duarte Melo, Willian J. Buchanan + Sijia Chen, Baochun Li, Di Niu - Hankel-FNO: Fast Underwater Acoustic Charting Via Physics-Encoded Fourier Neural Operator - https://arxiv.org/abs/2512.06417 - arXiv:2512.06417v1 Announce Type: new -Abstract: Fast and accurate underwater acoustic charting is crucial for downstream tasks such as environment-aware sensor placement optimization and autonomous vehicle path planning. Conventional methods rely on computationally expensive while accurate numerical solvers, which are not scalable for large-scale or real-time applications. Although deep learning-based surrogate models can accelerate these computations, they often suffer from limitations such as fixed-resolution constraints or dependence on explicit partial differential equation formulations. These issues hinder their applicability and generalization across diverse environments. We propose Hankel-FNO, a Fourier Neural Operator (FNO)-based model for efficient and accurate acoustic charting. By incorporating sound propagation knowledge and bathymetry, our method has high accuracy while maintaining high computational speed. Results demonstrate that Hankel-FNO outperforms traditional solvers in speed and surpasses data-driven alternatives in accuracy, especially in long-range predictions. Experiments show the model's adaptability to diverse environments and sound source settings with minimal fine-tuning. - oai:arXiv.org:2512.06417v1 + Jacobian Aligned Random Forests + https://arxiv.org/abs/2512.08306 + arXiv:2512.08306v1 Announce Type: new +Abstract: Axis-aligned decision trees are fast and stable but struggle on datasets with rotated or interaction-dependent decision boundaries, where informative splits require linear combinations of features rather than single-feature thresholds. Oblique forests address this with per-node hyperplane splits, but at added computational cost and implementation complexity. We propose a simple alternative: JARF, Jacobian-Aligned Random Forests. Concretely, we first fit an axis-aligned forest to estimate class probabilities or regression outputs, compute finite-difference gradients of these predictions with respect to each feature, aggregate them into an expected Jacobian outer product that generalizes the expected gradient outer product (EGOP), and use it as a single global linear preconditioner for all inputs. This supervised preconditioner applies a single global rotation of the feature space, then hands the transformed data back to a standard axis-aligned forest, preserving off-the-shelf training pipelines while capturing oblique boundaries and feature interactions that would otherwise require many axis-aligned splits to approximate. The same construction applies to any model that provides gradients, though we focus on random forests and gradient-boosted trees in this work. On tabular classification and regression benchmarks, this preconditioning consistently improves axis-aligned forests and often matches or surpasses oblique baselines while improving training time. Our experimental results and theoretical analysis together indicate that supervised preconditioning can recover much of the accuracy of oblique forests while retaining the simplicity and robustness of axis-aligned trees. + oai:arXiv.org:2512.08306v1 cs.LG - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Yifan Sun (College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China), Lei Cheng (College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China), Jianlong Li (College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China), Peter Gerstoft (Scripps Institution of Oceanography, University of California San Diego, La Jolla, USA) + http://creativecommons.org/licenses/by/4.0/ + Sarwesh Rauniyar - Rethinking Training Dynamics in Scale-wise Autoregressive Generation - https://arxiv.org/abs/2512.06421 - arXiv:2512.06421v1 Announce Type: new -Abstract: Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine manner. However, scale-wise AR models suffer from exposure bias, which undermines generation quality. We identify two primary causes of this issue: (1) train-test mismatch, where the model must rely on its own imperfect predictions during inference, and (2) imbalance in scale-wise learning difficulty, where certain scales exhibit disproportionately higher optimization complexity. Through a comprehensive analysis of training dynamics, we propose Self-Autoregressive Refinement (SAR) to address these limitations. SAR introduces a Stagger-Scale Rollout (SSR) mechanism that performs lightweight autoregressive rollouts to expose the model to its own intermediate predictions, thereby aligning train-test patterns, and a complementary Contrastive Student-Forcing Loss (CSFL) that provides adequate supervision for self-generated contexts to ensure stable training. Experimental results show that applying SAR to pretrained AR models consistently improves generation quality with minimal computational overhead. For instance, SAR yields a 5.2% FID reduction on FlexVAR-d16 trained on ImageNet 256 within 10 epochs (5 hours on 32xA100 GPUs). Given its efficiency, scalability, and effectiveness, we expect SAR to serve as a reliable post-training method for visual autoregressive generation. - oai:arXiv.org:2512.06421v1 + Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation + https://arxiv.org/abs/2512.08309 + arXiv:2512.08309v1 Announce Type: new +Abstract: For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally limited in realism and large-scale coherence. We introduce Terrain Diffusion, an AI-era successor to Perlin noise that bridges the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. At its core is InfiniteDiffusion, a novel algorithm for infinite generation, enabling seamless, real-time synthesis of boundless landscapes. A hierarchical stack of diffusion models couples planetary context with local detail, while a compact Laplacian encoding stabilizes outputs across Earth-scale dynamic ranges. An open-source infinite-tensor framework supports constant-memory manipulation of unbounded tensors, and few-step consistency distillation enables efficient generation. Together, these components establish diffusion models as a practical foundation for procedural world generation, capable of synthesizing entire planets coherently, controllably, and without limits. + oai:arXiv.org:2512.08309v1 cs.CV cs.AI - cs.CL + cs.GR cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Gengze Zhou, Chongjian Ge, Hao Tan, Feng Liu, Yicong Hong + Alexander Goslin - A Perception CNN for Facial Expression Recognition - https://arxiv.org/abs/2512.06422 - arXiv:2512.06422v1 Announce Type: new -Abstract: Convolutional neural networks (CNNs) can automatically learn data patterns to express face images for facial expression recognition (FER). However, they may ignore effect of facial segmentation of FER. In this paper, we propose a perception CNN for FER as well as PCNN. Firstly, PCNN can use five parallel networks to simultaneously learn local facial features based on eyes, cheeks and mouth to realize the sensitive capture of the subtle changes in FER. Secondly, we utilize a multi-domain interaction mechanism to register and fuse between local sense organ features and global facial structural features to better express face images for FER. Finally, we design a two-phase loss function to restrict accuracy of obtained sense information and reconstructed face images to guarantee performance of obtained PCNN in FER. Experimental results show that our PCNN achieves superior results on several lab and real-world FER benchmarks: CK+, JAFFE, FER2013, FERPlus, RAF-DB and Occlusion and Pose Variant Dataset. Its code is available at https://github.com/hellloxiaotian/PCNN. - oai:arXiv.org:2512.06422v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Privacy-Preserving Identifier Checking in 5G + https://arxiv.org/abs/2512.08310 + arXiv:2512.08310v1 Announce Type: new +Abstract: Device identifiers like the International Mobile Equipment Identity (IMEI) are crucial for ensuring device integrity and meeting regulations in 4G and 5G networks. However, sharing these identifiers with Mobile Network Operators (MNOs) brings significant privacy risks by enabling long-term tracking and linking of user activities across sessions. In this work, we propose a privacy-preserving identifier checking method in 5G. This paper introduces a protocol for verifying device identifiers without exposing them to the network while maintaining the same functions as the 3GPP-defined Equipment Identity Register (EIR) process. The proposed solution modifies the PEPSI protocol for a Private Set Membership (PSM) setting using the BFV homomorphic encryption scheme. This lets User Equipment (UE) prove that its identifier is not on an operator's blacklist or greylist while ensuring that the MNO only learns the outcome of the verification. The protocol allows controlled deanonymization through an authorized Law Enforcement (LE) hook, striking a balance between privacy and accountability. Implementation results show that the system can perform online verification within five seconds and requires about 15 to 16 MB of communication per session. This confirms its practical use under post-quantum security standards. The findings highlight the promise of homomorphic encryption for managing identifiers while preserving privacy in 5G, laying the groundwork for scalable and compliant verification systems in future 6G networks. + oai:arXiv.org:2512.08310v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1109/TIP.2025.3637715 - Chunwei Tian, Jingyuan Xie, Lingjun Li, Wangmeng Zuo, Yanning Zhang, David Zhang + http://creativecommons.org/licenses/by/4.0/ + Marcel D. S. K. Gr\"afenstein, Stefan K\"opsell, Maryam Zarezadeh - Leveraging Port-Hamiltonian Theory for Impedance Control Benchmarking - https://arxiv.org/abs/2512.06423 - arXiv:2512.06423v1 Announce Type: new -Abstract: This work proposes PH-based metrics for benchmarking impedance control. A causality-consistent PH model is introduced for mass-spring-damper impedance in Cartesian space. Based on this model, a differentiable, force-torque sensing-independent, n-DoF passivity condition is derived, valid for time-varying references. An impedance fidelity metric is also defined from step-response power in free motion, capturing dynamic decoupling. The proposed metrics are validated in Gazebo simulations with a six-DoF manipulator and a quadruped leg. Results demonstrate the suitability of the PH framework for standardized impedance control benchmarking. - oai:arXiv.org:2512.06423v1 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning + https://arxiv.org/abs/2512.08314 + arXiv:2512.08314v1 Announce Type: new +Abstract: Federated Learning (FL) is an emerging machine learning framework that enables multiple clients (coordinated by a server) to collaboratively train a global model by aggregating the locally trained models without sharing any client's training data. It has been observed in recent works that learning in a federated manner may lead the aggregated global model to converge to a 'sharp minimum' thereby adversely affecting the generalizability of this FL-trained model. Therefore, in this work, we aim to improve the generalization performance of models trained in a federated setup by introducing a 'flatness' constrained FL optimization problem. This flatness constraint is imposed on the top eigenvalue of the Hessian computed from the training loss. As each client trains a model on its local data, we further re-formulate this complex problem utilizing the client loss functions and propose a new computationally efficient regularization technique, dubbed 'MAN,' which Minimizes Activation's Norm of each layer on client-side models. We also theoretically show that minimizing the activation norm reduces the top eigenvalue of the layer-wise Hessian of the client's loss, which in turn decreases the overall Hessian's top eigenvalue, ensuring convergence to a flat minimum. We apply our proposed flatness-constrained optimization to the existing FL techniques and obtain significant improvements, thereby establishing new state-of-the-art. + oai:arXiv.org:2512.08314v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Leonardo F. Dos Santos, Elisa G. Vergamini, C\'icero Zanette, Lucca Maitan, Thiago Boaventura + http://creativecommons.org/licenses/by/4.0/ + M Yashwanth, Gaurav Kumar Nayak, Harsh Rangwani, Arya Singh, R. Venkatesh Babu, Anirban Chakraborty - DragMesh: Interactive 3D Generation Made Easy - https://arxiv.org/abs/2512.06424 - arXiv:2512.06424v1 Announce Type: new -Abstract: While generative models have excelled at creating static 3D content, the pursuit of systems that understand how objects move and respond to interactions remains a fundamental challenge. Current methods for articulated motion lie at a crossroads: they are either physically consistent but too slow for real-time use, or generative but violate basic kinematic constraints. We present DragMesh, a robust framework for real-time interactive 3D articulation built around a lightweight motion generation core. Our core contribution is a novel decoupled kinematic reasoning and motion generation framework. First, we infer the latent joint parameters by decoupling semantic intent reasoning (which determines the joint type) from geometric regression (which determines the axis and origin using our Kinematics Prediction Network (KPP-Net)). Second, to leverage the compact, continuous, and singularity-free properties of dual quaternions for representing rigid body motion, we develop a novel Dual Quaternion VAE (DQ-VAE). This DQ-VAE receives these predicted priors, along with the original user drag, to generate a complete, plausible motion trajectory. To ensure strict adherence to kinematics, we inject the joint priors at every layer of the DQ-VAE's non-autoregressive Transformer decoder using FiLM (Feature-wise Linear Modulation) conditioning. This persistent, multi-scale guidance is complemented by a numerically-stable cross-product loss to guarantee axis alignment. This decoupled design allows DragMesh to achieve real-time performance and enables plausible, generative articulation on novel objects without retraining, offering a practical step toward generative 3D intelligence. Code: https://github.com/AIGeeksGroup/DragMesh. Website: https://aigeeksgroup.github.io/DragMesh. - oai:arXiv.org:2512.06424v1 + GeoDM: Geometry-aware Distribution Matching for Dataset Distillation + https://arxiv.org/abs/2512.08317 + arXiv:2512.08317v1 Announce Type: new +Abstract: Dataset distillation aims to synthesize a compact subset of the original data, enabling models trained on it to achieve performance comparable to those trained on the original large dataset. Existing distribution-matching methods are confined to Euclidean spaces, making them only capture linear structures and overlook the intrinsic geometry of real data, e.g., curvature. However, high-dimensional data often lie on low-dimensional manifolds, suggesting that dataset distillation should have the distilled data manifold aligned with the original data manifold. In this work, we propose a geometry-aware distribution-matching framework, called \textbf{GeoDM}, which operates in the Cartesian product of Euclidean, hyperbolic, and spherical manifolds, with flat, hierarchical, and cyclical structures all captured by a unified representation. To adapt to the underlying data geometry, we introduce learnable curvature and weight parameters for three kinds of geometries. At the same time, we design an optimal transport loss to enhance the distribution fidelity. Our theoretical analysis shows that the geometry-aware distribution matching in a product space yields a smaller generalization error bound than the Euclidean counterparts. Extensive experiments conducted on standard benchmarks demonstrate that our algorithm outperforms state-of-the-art data distillation methods and remains effective across various distribution-matching strategies for the single geometries. + oai:arXiv.org:2512.08317v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Tianshan Zhang, Zeyu Zhang, Hao Tang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xuhui Li, Zhengquan Luo, Zihui Cui, Zhiqiang Xu - When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition - https://arxiv.org/abs/2512.06426 - arXiv:2512.06426v1 Announce Type: new -Abstract: Accurate gender recognition from extreme long-range imagery remains a challenging problem due to limited spatial resolution, viewpoint variability, and loss of facial cues. For such purpose, we present a dual-path transformer framework that leverages CLIP to jointly model visual and attribute-driven cues for gender recognition at a distance. The framework integrates two complementary streams: (1) a direct visual path that refines a pre-trained CLIP image encoder through selective fine-tuning of its upper layers, and (2) an attribute-mediated path that infers gender from a set of soft-biometric prompts (e.g., hairstyle, clothing, accessories) aligned in the CLIP text-image space. Spatial channel attention modules further enhance discriminative localization under occlusion and low resolution. To support large-scale evaluation, we construct U-DetAGReID, a unified long-range gender dataset derived from DetReIDx and AG-ReID.v2, harmonized under a consistent ternary labeling scheme (Male, Female, Unknown). Extensive experiments suggest that the proposed solution surpasses state-of-the-art person-attribute and re-identification baselines across multiple metrics (macro-F1, accuracy, AUC), with consistent robustness to distance, angle, and height variations. Qualitative attention visualizations confirm interpretable attribute localization and responsible abstention behavior. Our results show that language-guided dual-path learning offers a principled, extensible foundation for responsible gender recognition in unconstrained long-range scenarios. - oai:arXiv.org:2512.06426v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Developing a Strong CPS Defender: An Evolutionary Approach + https://arxiv.org/abs/2512.08320 + arXiv:2512.08320v1 Announce Type: new +Abstract: Cyber-physical systems (CPSs) are used extensively in critical infrastructure, underscoring the need for anomaly detection systems that are able to catch even the most motivated attackers. Traditional anomaly detection techniques typically do `one-off' training on datasets crafted by experts or generated by fuzzers, potentially limiting their ability to generalize to unseen and more subtle attack strategies. Stopping at this point misses a key opportunity: a defender can actively challenge the attacker to find more nuanced attacks, which in turn can lead to more effective detection capabilities. Building on this concept, we propose Evo-Defender, an evolutionary framework that iteratively strengthens CPS defenses through a dynamic attacker-defender interaction. Evo-Defender includes a smart attacker that employs guided fuzzing to explore diverse, non-redundant attack strategies, while the self-evolving defender uses incremental learning to adapt to new attack patterns. We implement Evo-Defender on two realistic CPS testbeds: the Tennessee Eastman process and a Robotic Arm Assembly Workstation, injecting over 600 attack scenarios. In end-to-end attack detection experiments, Evo-Defender achieves up to 2.7% higher performance than state-of-the-art baselines on unseen scenarios, while utilizing training data more efficiently for faster and more robust detection. + oai:arXiv.org:2512.08320v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Nzakiese Mbongo, Kailash A. Hambarde, Hugo Proen\c{c}a + Qingyuan Hu, Christopher M. Poskitt, Jun Sun, Yuqi Chen - A new initialisation to Control Gradients in Sinusoidal Neural network - https://arxiv.org/abs/2512.06427 - arXiv:2512.06427v1 Announce Type: new -Abstract: Proper initialisation strategy is of primary importance to mitigate gradient explosion or vanishing when training neural networks. Yet, the impact of initialisation parameters still lacks a precise theoretical understanding for several well-established architectures. Here, we propose a new initialisation for networks with sinusoidal activation functions such as \texttt{SIREN}, focusing on gradients control, their scaling with network depth, their impact on training and on generalization. To achieve this, we identify a closed-form expression for the initialisation of the parameters, differing from the original \texttt{SIREN} scheme. This expression is derived from fixed points obtained through the convergence of pre-activation distribution and the variance of Jacobian sequences. Controlling both gradients and targeting vanishing pre-activation helps preventing the emergence of inappropriate frequencies during estimation, thereby improving generalization. We further show that this initialisation strongly influences training dynamics through the Neural Tangent Kernel framework (NTK). Finally, we benchmark \texttt{SIREN} with the proposed initialisation against the original scheme and other baselines on function fitting and image reconstruction. The new initialisation consistently outperforms state-of-the-art methods across a wide range of reconstruction tasks, including those involving physics-informed neural networks. - oai:arXiv.org:2512.06427v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Emulation of Complex Matrix Multiplication based on the Chinese Remainder Theorem + https://arxiv.org/abs/2512.08321 + arXiv:2512.08321v1 Announce Type: new +Abstract: Modern computing architectures feature low-precision matrix multiplication units that achieve substantially higher throughput than their high-precision counterparts. Motivated by this architectural trend, the emulation of high-precision matrix multiplication using low-precision hardware has attracted significant interest in the high-performance computing community. Ozaki, Uchino, and Imamura introduced the Ozaki-II scheme as a general framework for emulating matrix multiplication. Building on this framework, Uchino, Ozaki, and Imamura developed high-performance and power-efficient techniques for emulating single- and double-precision real matrix multiplication on INT8 matrix engines. Extending this line of research, the present study proposes high-performance emulation methods for single- and double-precision complex matrix multiplication on INT8 matrix engines, based on the Ozaki-II scheme. On an NVIDIA B200 GPU, the proposed methods achieve 4.0x--5.6x and 4.4x--6.5x speedups over the native single- and double-precision complex matrix multiplication routines from cuBLAS, respectively, for sufficiently large problem sizes. When lower accuracy than that of the standard routine is acceptable, the proposed methods can operate at even higher speed. Conversely, with only a modest increase in computation time, they can also deliver higher accuracy than the standard routines. These properties suggest that the proposed approach has the potential to serve as a default algorithm across a wide range of applications. + oai:arXiv.org:2512.08321v1 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Andrea Combette, Antoine Venaille, Nelly Pustelnik + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yuki Uchino, Qianxiang Ma, Toshiyuki Imamura, Katsuhisa Ozaki, Patrick Lars Gutsche - Smart Spatial Planning in Egypt: An Algorithm-Driven Approach to Public Service Evaluation in Qena City - https://arxiv.org/abs/2512.06431 - arXiv:2512.06431v1 Announce Type: new -Abstract: National planning standards for public services in Egypt often fail to align with unique local characteristics. Addressing this gap, this study develops a tailored planning model for Qena City. Using a hybrid methodology (descriptive, analytical, and experimental), the research utilizes Python programming to generate an intelligent spatial analysis algorithm based on Voronoi Diagrams. This approach creates city-specific planning criteria and evaluates the current coverage of public facilities. The primary contribution of this study is the successful derivation of a localized planning standards model and the deployment of an automated algorithm to assess service efficiency. Application of this model reveals a general service coverage average of 81.3%. Ambulance stations demonstrated the highest efficiency (99.8%) due to recent upgrades, while parks and open spaces recorded the lowest coverage (10%) caused by limited land availability. Spatial analysis indicates a high service density in midtown (>45 services/km^2), which diminishes significantly towards the outskirts (<5 services/km^2). Consequently, the Hajer Qena district contains the highest volume of unserved areas, while the First District (Qesm 1) exhibits the highest level of service coverage. This model offers a replicable framework for data-driven urban planning in Egyptian cities. - oai:arXiv.org:2512.06431v1 - cs.AI - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + Collaborative Intelligence for UAV-Satellite Network Slicing: Towards a Joint QoS-Energy-Fairness MADRL Optimization + https://arxiv.org/abs/2512.08322 + arXiv:2512.08322v1 Announce Type: new +Abstract: Non terrestrial networks are critical for achieving global 6G coverage, yet efficient resource management in aerial and space environments remains challenging due to limited onboard power and dynamic operational conditions. Network slicing offers a promising solution for spectrum optimization in UAV based systems serving heterogeneous service demands. For that, this paper proposes a hierarchical network slicing framework for UAV satellite integrated networks supporting eMBB, URLLC, and mMTC services. Specifically, we formulate a joint optimization of UAV trajectory, transmission power, and spectrum allocation as a decentralized partially observable Markov decision process that ensures quality of service while minimizing energy consumption and maximizing resource fairness. To address the computational intractability and partial observability, we develop a multi agent deep reinforcement learning solution under the centralized training and decentralized execution paradigm. In the proposed system, UAV agents act as distributed actors coordinated by a shared critic operating with multi head attention mechanism at a low Earth orbit satellite. Experimental results then demonstrate that our approach outperforms existing methods by up to 33% in cumulative reward while achieving superior energy efficiency and fairness. + oai:arXiv.org:2512.08322v1 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Mohamed Shamroukh, Mohamed Alkhuzamy Aziz + Thanh-Dao Nguyen, Ngoc-Tan Nguyen, Thai-Duong Nguyen, Nguyen Van Huynh, Dinh-Hieu Tran, Symeon Chatzinotas - HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems - https://arxiv.org/abs/2512.06432 - arXiv:2512.06432v1 Announce Type: new -Abstract: Recent advances in LLM-based multi-agent systems have demonstrated remarkable capabilities in complex decision-making scenarios such as financial trading and software engineering. However, evaluating each individual agent's effectiveness and online optimization of underperforming agents remain open challenges. To address these issues, we present HiveMind, a self-adaptive framework designed to optimize LLM multi-agent collaboration through contribution analysis. At its core, HiveMind introduces Contribution-Guided Online Prompt Optimization (CG-OPO), which autonomously refines agent prompts based on their quantified contributions. We first propose the Shapley value as a grounded metric to quantify each agent's contribution, thereby identifying underperforming agents in a principled manner for automated prompt refinement. To overcome the computational complexity of the classical Shapley value, we present DAG-Shapley, a novel and efficient attribution algorithm that leverages the inherent Directed Acyclic Graph structure of the agent workflow to axiomatically prune non-viable coalitions. By hierarchically reusing intermediate outputs of agents in the DAG, our method further reduces redundant computations, and achieving substantial cost savings without compromising the theoretical guarantees of Shapley values. Evaluated in a multi-agent stock-trading scenario, HiveMind achieves superior performance compared to static baselines. Notably, DAG-Shapley reduces LLM calls by over 80\% while maintaining attribution accuracy comparable to full Shapley values, establishing a new standard for efficient credit assignment and enabling scalable, real-world optimization of multi-agent collaboration. - oai:arXiv.org:2512.06432v1 - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 + Detecting Dental Landmarks from Intraoral 3D Scans: the 3DTeethLand challenge + https://arxiv.org/abs/2512.08323 + arXiv:2512.08323v1 Announce Type: new +Abstract: Teeth landmark detection is a critical task in modern clinical orthodontics. Their precise identification enables advanced diagnostics, facilitates personalized treatment strategies, and supports more effective monitoring of treatment progress in clinical dentistry. However, several significant challenges may arise due to the intricate geometry of individual teeth and the substantial variations observed across different individuals. To address these complexities, the development of advanced techniques, especially through the application of deep learning, is essential for the precise and reliable detection of 3D tooth landmarks. In this context, the 3DTeethLand challenge was held in collaboration with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) in 2024, calling for algorithms focused on teeth landmark detection from intraoral 3D scans. This challenge introduced the first publicly available dataset for 3D teeth landmark detection, offering a valuable resource to assess the state-of-the-art methods in this task and encourage the community to provide methodological contributions towards the resolution of their problem with significant clinical implications. + oai:arXiv.org:2512.08323v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Achraf Ben-Hamadou, Nour Neifar, Ahmed Rekik, Oussama Smaoui, Firas Bouzguenda, Sergi Pujades, Niels van Nistelrooij, Shankeeth Vinayahalingam, Kaibo Shi, Hairong Jin, Youyi Zheng, Tibor Kub\'ik, Old\v{r}ich Kodym, Petr \v{S}illing, Kate\v{r}ina Tr\'avn\'i\v{c}kov\'a, Tom\'a\v{s} Moj\v{z}i\v{s}, Jan Matula, Jeffry Hartanto, Xiaoying Zhu, Kim-Ngan Nguyen, Tudor Dascalu, Huikai Wu, and Weijie Liu, Shaojie Zhuang, Guangshun Wei, Yuanfeng Zhou + + + GeoDiffMM: Geometry-Guided Conditional Diffusion for Motion Magnification + https://arxiv.org/abs/2512.08325 + arXiv:2512.08325v1 Announce Type: new +Abstract: Video Motion Magnification (VMM) amplifies subtle macroscopic motions to a perceptible level. Recently, existing mainstream Eulerian approaches address amplification-induced noise via decoupling representation learning such as texture, shape and frequancey schemes, but they still struggle to separate photon noise from true micro-motion when motion displacements are very small. We propose GeoDiffMM, a novel diffusion-based Lagrangian VMM framework conditioned on optical flow as a geometric cue, enabling structurally consistent motion magnification. Specifically, we design a Noise-free Optical Flow Augmentation strategy that synthesizes diverse nonrigid motion fields without photon noise as supervision, helping the model learn more accurate geometry-aware optial flow and generalize better. Next, we develop a Diffusion Motion Magnifier that conditions the denoising process on (i) optical flow as a geometry prior and (ii) a learnable magnification factor controlling magnitude, thereby selectively amplifying motion components consistent with scene semantics and structure while suppressing content-irrelevant perturbations. Finally, we perform Flow-based Video Synthesis to map the amplified motion back to the image domain with high fidelity. Extensive experiments on real and synthetic datasets show that GeoDiffMM outperforms state-of-the-art methods and significantly improves motion magnification. + oai:arXiv.org:2512.08325v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xuedeng Liu, Jiabao Guo, Zheng Zhang, Fei Wang, Zhi Liu, Dan Guo + + + Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships + https://arxiv.org/abs/2512.08326 + arXiv:2512.08326v1 Announce Type: new +Abstract: Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high false-positive rates. This not only reduces detection efficiency but also significantly increases the manual screening burden on developers. Recent advances in large language models (LLMs) and multi-agent collaborative architectures have demonstrated remarkable potential for tackling complex tasks, offering a novel technological perspective for sensitive information detection. In response to these challenges, we propose Argus, a multi-agent collaborative framework for detecting sensitive information. Argus employs a three-tier detection mechanism that integrates key content, file context, and project reference relationships to effectively reduce false positives and enhance overall detection accuracy. To comprehensively evaluate Argus in real-world repository environments, we developed two new benchmarks, one to assess genuine leak detection capabilities and another to evaluate false-positive filtering performance. Experimental results show that Argus achieves up to 94.86% accuracy in leak detection, with a precision of 96.36%, recall of 94.64%, and an F1 score of 0.955. Moreover, the analysis of 97 real repositories incurred a total cost of only 2.2$. All code implementations and related datasets are publicly available at https://github.com/TheBinKing/Argus-Guard for further research and application. + oai:arXiv.org:2512.08326v1 + cs.CR + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yihan Xia, Taotao Wang, Shengli Zhang, Zhangyuhua Weng, Bin Cao, Soung Chang Liew + 10.1145/3744916.3773208 + Bin Wang, Hui Li, Liyang Zhang, Qijia Zhuang, Ao Yang, Dong Zhang, Xijun Luo, Bing Lin - Automated Deep Learning Estimation of Anthropometric Measurements for Preparticipation Cardiovascular Screening - https://arxiv.org/abs/2512.06434 - arXiv:2512.06434v1 Announce Type: new -Abstract: Preparticipation cardiovascular examination (PPCE) aims to prevent sudden cardiac death (SCD) by identifying athletes with structural or electrical cardiac abnormalities. Anthropometric measurements, such as waist circumference, limb lengths, and torso proportions to detect Marfan syndrome, can indicate elevated cardiovascular risk. Traditional manual methods are labor-intensive, operator-dependent, and challenging to scale. We present a fully automated deep-learning approach to estimate five key anthropometric measurements from 2D synthetic human body images. Using a dataset of 100,000 images derived from 3D body meshes, we trained and evaluated VGG19, ResNet50, and DenseNet121 with fully connected layers for regression. All models achieved sub-centimeter accuracy, with ResNet50 performing best, achieving a mean MAE of 0.668 cm across all measurements. Our results demonstrate that deep learning can deliver accurate anthropometric data at scale, offering a practical tool to complement athlete screening protocols. Future work will validate the models on real-world images to extend applicability. - oai:arXiv.org:2512.06434v1 + Low Rank Support Quaternion Matrix Machine + https://arxiv.org/abs/2512.08327 + arXiv:2512.08327v1 Announce Type: new +Abstract: Input features are conventionally represented as vectors, matrices, or third order tensors in the real field, for color image classification. Inspired by the success of quaternion data modeling for color images in image recovery and denoising tasks, we propose a novel classification method for color image classification, named as the Low-rank Support Quaternion Matrix Machine (LSQMM), in which the RGB channels are treated as pure quaternions to effectively preserve the intrinsic coupling relationships among channels via the quaternion algebra. For the purpose of promoting low-rank structures resulting from strongly correlated color channels, a quaternion nuclear norm regularization term, serving as a natural extension of the conventional matrix nuclear norm to the quaternion domain, is added to the hinge loss in our LSQMM model. An Alternating Direction Method of Multipliers (ADMM)-based iterative algorithm is designed to effectively resolve the proposed quaternion optimization model. Experimental results on multiple color image classification datasets demonstrate that our proposed classification approach exhibits advantages in classification accuracy, robustness and computational efficiency, compared to several state-of-the-art methods using support vector machines, support matrix machines, and support tensor machines. + oai:arXiv.org:2512.08327v1 cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + math.OC + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Lucas R. Mareque, Ricardo L. Armentano, Leandro J. Cymberknop + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Wang Chen, Ziyan Luo, Shuangyue Wang - AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars - https://arxiv.org/abs/2512.06438 - arXiv:2512.06438v1 Announce Type: new -Abstract: The generation of high-fidelity, animatable 3D human avatars remains a core challenge in computer graphics and vision, with applications in VR, telepresence, and entertainment. Existing approaches based on implicit representations like NeRFs suffer from slow rendering and dynamic inconsistencies, while 3D Gaussian Splatting (3DGS) methods are typically limited to static head generation, lacking dynamic control. We bridge this gap by introducing AGORA, a novel framework that extends 3DGS within a generative adversarial network to produce animatable avatars. Our key contribution is a lightweight, FLAME-conditioned deformation branch that predicts per-Gaussian residuals, enabling identity-preserving, fine-grained expression control while allowing real-time inference. Expression fidelity is enforced via a dual-discriminator training scheme leveraging synthetic renderings of the parametric mesh. AGORA generates avatars that are not only visually realistic but also precisely controllable. Quantitatively, we outperform state-of-the-art NeRF-based methods on expression accuracy while rendering at 250+ FPS on a single GPU, and, notably, at $\sim$9 FPS under CPU-only inference - representing, to our knowledge, the first demonstration of practical CPU-only animatable 3DGS avatar synthesis. This work represents a significant step toward practical, high-performance digital humans. Project website: https://ramazan793.github.io/AGORA/ - oai:arXiv.org:2512.06438v1 + Interpreting Structured Perturbations in Image Protection Methods for Diffusion Models + https://arxiv.org/abs/2512.08329 + arXiv:2512.08329v1 Announce Type: new +Abstract: Recent image protection mechanisms such as Glaze and Nightshade introduce imperceptible, adversarially designed perturbations intended to disrupt downstream text-to-image generative models. While their empirical effectiveness is known, the internal structure, detectability, and representational behavior of these perturbations remain poorly understood. This study provides a systematic, explainable AI analysis using a unified framework that integrates white-box feature-space inspection and black-box signal-level probing. Through latent-space clustering, feature-channel activation analysis, occlusion-based spatial sensitivity mapping, and frequency-domain characterization, we show that protection mechanisms operate as structured, low-entropy perturbations tightly coupled to underlying image content across representational, spatial, and spectral domains. Protected images preserve content-driven feature organization with protection-specific substructure rather than inducing global representational drift. Detectability is governed by interacting effects of perturbation entropy, spatial deployment, and frequency alignment, with sequential protection amplifying detectable structure rather than suppressing it. Frequency-domain analysis shows that Glaze and Nightshade redistribute energy along dominant image-aligned frequency axes rather than introducing diffuse noise. These findings indicate that contemporary image protection operates through structured feature-level deformation rather than semantic dislocation, explaining why protection signals remain visually subtle yet consistently detectable. This work advances the interpretability of adversarial image protection and informs the design of future defenses and detection strategies for generative AI systems. + oai:arXiv.org:2512.08329v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Ramazan Fazylov, Sergey Zagoruyko, Aleksandr Parkin, Stamatis Lefkimmiatis, Ivan Laptev + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Michael R. Martin, Garrick Chan, Kwan-Liu Ma - Neural expressiveness for beyond importance model compression - https://arxiv.org/abs/2512.06440 - arXiv:2512.06440v1 Announce Type: new -Abstract: Neural Network Pruning has been established as driving force in the exploration of memory and energy efficient solutions with high throughput both during training and at test time. In this paper, we introduce a novel criterion for model compression, named "Expressiveness". Unlike existing pruning methods that rely on the inherent "Importance" of neurons' and filters' weights, ``Expressiveness" emphasizes a neuron's or group of neurons ability to redistribute informational resources effectively, based on the overlap of activations. This characteristic is strongly correlated to a network's initialization state, establishing criterion autonomy from the learning state stateless and thus setting a new fundamental basis for the expansion of compression strategies in regards to the "When to Prune" question. We show that expressiveness is effectively approximated with arbitrary data or limited dataset's representative samples, making ground for the exploration of Data-Agnostic strategies. Our work also facilitates a "hybrid" formulation of expressiveness and importance-based pruning strategies, illustrating their complementary benefits and delivering up to 10x extra gains w.r.t. weight-based approaches in parameter compression ratios, with an average of 1% in performance degradation. We also show that employing expressiveness (independently) for pruning leads to an improvement over top-performing and foundational methods in terms of compression efficiency. Finally, on YOLOv8, we achieve a 46.1% MACs reduction by removing 55.4\% of the parameters, with an increase of 3% in the mean Absolute Precision ($mAP_{50-95}$) for object detection on COCO dataset. - oai:arXiv.org:2512.06440v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models + https://arxiv.org/abs/2512.08330 + arXiv:2512.08330v1 Announce Type: new +Abstract: Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven density. Through an in-depth analysis of mainstream contrastive and generative approaches, we find that contrastive models tend to suffer from overfitting, while 3D Mask Autoencoders struggle to handle unordered point clouds. This motivates us to learn 3D representations by sharing the merits of diffusion and contrast models, which is non-trivial due to the pattern difference between the two paradigms. In this paper, we propose \textit{PointDico}, a novel model that seamlessly integrates these methods. \textit{PointDico} learns from both denoising generative modeling and cross-modal contrastive learning through knowledge distillation, where the diffusion model serves as a guide for the contrastive model. We introduce a hierarchical pyramid conditional generator for multi-scale geometric feature extraction and employ a dual-channel design to effectively integrate local and global contextual information. \textit{PointDico} achieves a new state-of-the-art in 3D representation learning, \textit{e.g.}, \textbf{94.32\%} accuracy on ScanObjectNN, \textbf{86.5\%} Inst. mIoU on ShapeNetPart. + oai:arXiv.org:2512.08330v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Angelos-Christos Maroudis, Sotirios Xydis + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Pengbo Li, Yiding Sun, Haozhe Cheng - Nice to Meet You: Synthesizing Practical MLIR Abstract Transformers - https://arxiv.org/abs/2512.06442 - arXiv:2512.06442v1 Announce Type: new -Abstract: Static analyses play a fundamental role during compilation: they discover facts that are true in all executions of the code being compiled, and then these facts are used to justify optimizations and diagnostics. Each static analysis is based on a collection of abstract transformers that provide abstract semantics for the concrete instructions that make up a program. It can be challenging to implement abstract transformers that are sound, precise, and efficient, and in fact both LLVM and GCC have suffered from miscompilations caused by unsound abstract transformers. Moreover, even after more than 20 years of development, LLVM lacks abstract transformers for hundreds of instructions in its intermediate representation (IR). We developed NiceToMeetYou, a program synthesis framework for abstract transformers that are aimed at the kinds of non-relational integer abstract domains that are heavily used by today's production compilers. It exploits a simple but novel technique for breaking the synthesis problem into parts: each of our transformers is the meet of a collection of simpler, sound transformers that are synthesized such that each new piece fills a gap in the precision of the final transformer. Our design point is bulk automation: no sketches are required. Transformers are verified by lowering to a previously created SMT dialect of MLIR. Each of our synthesized transformers is provably sound and some (17 percent) are more precise than those provided by LLVM. - oai:arXiv.org:2512.06442v1 - cs.PL - Tue, 09 Dec 2025 00:00:00 -0500 + Bi^2MAC: Bimodal Bi-Adaptive Mask-Aware Convolution for Remote Sensing Pansharpening + https://arxiv.org/abs/2512.08331 + arXiv:2512.08331v1 Announce Type: new +Abstract: Pansharpening aims to fuse a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to generate a high-resolution multispectral image (HRMS). Conventional deep learning-based methods are inherently limited in their ability to adapt to regional heterogeneity within feature representations. Although various adaptive convolution methods have been proposed to address this limitation, they often suffer from excessive computational costs and a limited ability to capture heterogeneous regions in remote sensing images effectively. To overcome these challenges, we propose Bimodal Bi-Adaptive Mask-Aware Convolution (Bi^2MAC), which effectively exploits information from different types of regions while intelligently allocating computational resources. Specifically, we design a lightweight module to generate both soft and hard masks, which are used to modulate the input features preliminarily and to guide different types of regions into separate processing branches, respectively. Redundant features are directed to a compact branch for low-cost global processing. In contrast, heterogeneous features are routed to a focused branch that invests more computational resources for fine-grained modeling. Extensive experiments on multiple benchmark datasets demonstrate that Bi^2MAC achieves state-of-the-art (SOTA) performance while requiring substantially lower training time and parameter counts, and the minimal computational cost among adaptive convolution models. + oai:arXiv.org:2512.08331v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Xuanyu Peng, Dominic Kennedy, Yuyou Fan, Ben Greenman, John Regehr, Loris D'Antoni + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xianghong Xiao, Zeyu Xia, Zhou Fei, Jinliang Xiao, Haorui Chen, Liangjian Deng - Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices - https://arxiv.org/abs/2512.06443 - arXiv:2512.06443v1 Announce Type: new -Abstract: Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table (LUT)-based inference, CPUs run these ultra-low-bit LLMs even faster than NPUs, opening new opportunities for ubiquitous on-device intelligence. - However, this paper identifies that LUT-based inference underutilizes memory bandwidth during parallel inference, which is required for prefilling, test-time scaling, and other multi-token scenarios. The root cause is the scalar LUT paradigm, which performs repetitive and non-contiguous memory accesses for each token. - To solve the issue, we propose vector LUT, a new lookup paradigm that constructs a unified LUT across parallel tokens, and performs a single $1 \rightarrow N$ lookup per index. To realize it efficiently, we further introduce (1) Vector LUT-Centric Tensor Layout, and (2) Cache-Aware Streamed Lookup techniques. Evaluations on 5 edge devices across 3 LLMs show that Vec-LUT outperforms state-of-the-art baselines by up to $4.2\times$. Our implementation is integrated into llama.cpp. The code is available at https://github.com/Cipherxzc/vlut.cpp. - oai:arXiv.org:2512.06443v1 - cs.DC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + On the Fundamental Tradeoff of Joint Communication and QCD: The Monostatic Case + https://arxiv.org/abs/2512.08332 + arXiv:2512.08332v1 Announce Type: new +Abstract: This paper investigates the fundamental tradeoff between communication and quickest change detection (QCD) in integrated sensing and communication (ISAC) systems under a monostatic setup. We introduce a novel Joint Communication and quickest Change subblock coding Strategy (JCCS) that leverages feedback to adapt coding dynamically based on real-time state estimation. The achievable rate-delay region is characterized using state-dependent mutual information and KL divergence, providing a comprehensive framework for analyzing the interplay between communication performance and detection delay. Moreover, we provide a partial converse demonstrating the asymptotic optimality of the proposed detection algorithm within the JCCS framework. To illustrate the practical implications, we analyze binary and MIMO Gaussian channels, revealing insights into achieving optimal tradeoffs in ISAC system design. + oai:arXiv.org:2512.08332v1 + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Xiangyu Li, Chengyu Yin, Weijun Wang, Jianyu Wei, Ting Cao, Yunxin Liu + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Sung Hoon Lim, Daewon Seo - Fault Tolerant Control of Mecanum Wheeled Mobile Robots - https://arxiv.org/abs/2512.06444 - arXiv:2512.06444v1 Announce Type: new -Abstract: Mecanum wheeled mobile robots (MWMRs) are highly susceptible to actuator faults that degrade performance and risk mission failure. Current fault tolerant control (FTC) schemes for MWMRs target complete actuator failures like motor stall, ignoring partial faults e.g., in torque degradation. We propose an FTC strategy handling both fault types, where we adopt posterior probability to learn real-time fault parameters. We derive the FTC law by aggregating probability-weighed control laws corresponding to predefined faults. This ensures the robustness and safety of MWMR control despite varying levels of fault occurrence. Simulation results demonstrate the effectiveness of our FTC under diverse scenarios. - oai:arXiv.org:2512.06444v1 + Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging + https://arxiv.org/abs/2512.08333 + arXiv:2512.08333v1 Announce Type: new +Abstract: Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall short on new tasks not covered in the training data. When finetuned on limited demonstrations of a new task, these policies often overfit to the specific demonstrations--not only losing their prior abilities to solve a wide variety of generalist tasks but also failing to generalize within the new task itself. In this work, we aim to develop a method that preserves the generalization capabilities of the generalist policy during finetuning, allowing a single policy to robustly incorporate a new skill into its repertoire. Our goal is a single policy that both learns to generalize to variations of the new task and retains the broad competencies gained from pretraining. We show that this can be achieved through a simple yet effective strategy: interpolating the weights of a finetuned model with that of the pretrained model. We show, across extensive simulated and real-world experiments, that such model merging produces a single model that inherits the generalist abilities of the base model and learns to solve the new task robustly, outperforming both the pretrained and finetuned model on out-of-distribution variations of the new task. Moreover, we show that model merging enables continual acquisition of new skills in a lifelong learning setting, without sacrificing previously learned generalist abilities. + oai:arXiv.org:2512.08333v1 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Xuehui Ma, Shiliang Zhang, Zhiyong Sun + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yajat Yadav, Zhiyuan Zhou, Andrew Wagenmaker, Karl Pertsch, Sergey Levine - Towards Stable Cross-Domain Depression Recognition under Missing Modalities - https://arxiv.org/abs/2512.06447 - arXiv:2512.06447v1 Announce Type: new -Abstract: Depression poses serious public health risks, including suicide, underscoring the urgency of timely and scalable screening. Multimodal automatic depression detection (ADD) offers a promising solution; however, widely studied audio- and video-based ADD methods lack a unified, generalizable framework for diverse depression recognition scenarios and show limited stability to missing modalities, which are common in real-world data. In this work, we propose a unified framework for Stable Cross-Domain Depression Recognition based on Multimodal Large Language Model (SCD-MLLM). The framework supports the integration and processing of heterogeneous depression-related data collected from varied sources while maintaining stability in the presence of incomplete modality inputs. Specifically, SCD-MLLM introduces two key components: (i) Multi-Source Data Input Adapter (MDIA), which employs masking mechanism and task-specific prompts to transform heterogeneous depression-related inputs into uniform token sequences, addressing inconsistency across diverse data sources; (ii) Modality-Aware Adaptive Fusion Module (MAFM), which adaptively integrates audio and visual features via a shared projection mechanism, enhancing resilience under missing modality conditions. e conduct comprehensive experiments under multi-dataset joint training settings on five publicly available and heterogeneous depression datasets from diverse scenarios: CMDC, AVEC2014, DAIC-WOZ, DVlog, and EATD. Across both complete and partial modality settings, SCD-MLLM outperforms state-of-the-art (SOTA) models as well as leading commercial LLMs (Gemini and GPT), demonstrating superior cross-domain generalization, enhanced ability to capture multimodal cues of depression, and strong stability to missing modality cases in real-world applications. - oai:arXiv.org:2512.06447v1 + HybridSplat: Fast Reflection-baked Gaussian Tracing using Hybrid Splatting + https://arxiv.org/abs/2512.08334 + arXiv:2512.08334v1 Announce Type: new +Abstract: Rendering complex reflection of real-world scenes using 3D Gaussian splatting has been a quite promising solution for photorealistic novel view synthesis, but still faces bottlenecks especially in rendering speed and memory storage. This paper proposes a new Hybrid Splatting(HybridSplat) mechanism for Gaussian primitives. Our key idea is a new reflection-baked Gaussian tracing, which bakes the view-dependent reflection within each Gaussian primitive while rendering the reflection using tile-based Gaussian splatting. Then we integrate the reflective Gaussian primitives with base Gaussian primitives using a unified hybrid splatting framework for high-fidelity scene reconstruction. Moreover, we further introduce a pipeline-level acceleration for the hybrid splatting, and reflection-sensitive Gaussian pruning to reduce the model size, thus achieving much faster rendering speed and lower memory storage while preserving the reflection rendering quality. By extensive evaluation, our HybridSplat accelerates about 7x rendering speed across complex reflective scenes from Ref-NeRF, NeRF-Casting with 4x fewer Gaussian primitives than similar ray-tracing based Gaussian splatting baselines, serving as a new state-of-the-art method especially for complex reflective scenes. + oai:arXiv.org:2512.08334v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiuyi Chen, Mingkui Tan, Haifeng Lu, Qiuna Xu, Zhihua Wang, Runhao Zeng, Xiping Hu + Chang Liu, Hongliang Yuan, Lianghao Zhang, Sichao Wang, Jianwei Guo, Shi-Sheng Huang - Translating PL/I Macro Procedures into Java Using Automatic Templatization and Large Language Models - https://arxiv.org/abs/2512.06448 - arXiv:2512.06448v1 Announce Type: new -Abstract: Modernizing legacy enterprise systems often involves translating PL/I programs into modern languages such as Java. This task becomes significantly more complex when PL/I macro procedures are involved. The PL/I macro procedures are considered string-manipulating programs that generate PL/I code, and they make automated translation more complex. Recently, large language models (LLMs) have been explored for automated code translation. However, LLM-based code translation struggles to translate the PL/I macro procedures to Java programs that reproduce the behavior of the plain PL/I code generated by the original PL/I macro procedures. - This paper proposes a novel method called templatization, which uses symbolic execution to generate code templates (code with named placeholders) as an intermediate representation. In this approach, symbolic values are treated as parts of macro-generated code. By symbolically executing macro procedures and generating code templates, our approach facilitates LLMs to generate readable and maintainable Java code. Our preliminary experiment on ten PL/I macro procedures shows that the LLM-based translation through templatization successfully generates Java programs that reproduce the behavior of the macro-generated PL/I programs. - oai:arXiv.org:2512.06448v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Dflow-SUR: Enhancing Generative Aerodynamic Inverse Design using Differentiation Throughout Flow Matching + https://arxiv.org/abs/2512.08336 + arXiv:2512.08336v1 Announce Type: new +Abstract: Generative inverse design requires incorporating physical constraints to ensure that generated designs are both reliable and accurate. However, we observe that current state-of-the-art energy-based methods suffer from an asynchronous phenomenon, where the optimization of the physical loss is constrained by the flow matching inference process. To overcome this limitation, we introduce Dflow-SUR, a differentiation strategy that separates the optimization of the physical loss from the flow matching inference. + Compared to the most advanced energy-based baseline, Dflow-SUR achieves a reduction in physical loss by four orders of magnitude, while also cutting wall-clock time by 74% on the airfoil case. Additionally, it increases the mean lift-to-drag ratio by 11.8% over traditional Latin-hypercube sampling in wing design. Beyond improvements in accuracy and efficiency, Dflow-SUR offers three additional practical advantages: (i) enhanced control over guidance, (ii) lower surrogate uncertainty, and (iii) greater robustness to hyper-parameter tuning. + Together, these results demonstrate that Dflow-SUR is a highly promising framework, providing both scalability and high fidelity for generative aerodynamic design. + oai:arXiv.org:2512.08336v1 + cs.CE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Takaaki Tateishi, Yasuharu Katsuno - - - Enhancing Medical Cross-Modal Hashing Retrieval using Dropout-Voting Mixture-of-Experts Fusion - https://arxiv.org/abs/2512.06449 - arXiv:2512.06449v1 Announce Type: new -Abstract: In recent years, cross-modal retrieval using images and text has become an active area of research, especially in the medical domain. The abundance of data in various modalities in this field has led to a growing importance of cross-modal retrieval for efficient image interpretation, data-driven diagnostic support, and medical education. In the context of the increasing integration of distributed medical data across healthcare facilities with the objective of enhancing interoperability, it is imperative to optimize the performance of retrieval systems in terms of the speed, memory efficiency, and accuracy of the retrieved data. This necessity arises in response to the substantial surge in data volume that characterizes contemporary medical practices. In this study, we propose a novel framework that incorporates dropout voting and mixture-of-experts (MoE) based contrastive fusion modules into a CLIP-based cross-modal hashing retrieval structure. We also propose the application of hybrid loss. So we now call our model MCMFH which is a medical cross-modal fusion hashing retrieval. Our method enables the simultaneous achievement of high accuracy and fast retrieval speed in low-memory environments. The model is demonstrated through experiments on radiological and non-radiological medical datasets. - oai:arXiv.org:2512.06449v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jaewon Ahn, Woosung Jang, Beakcheol Jang + Aobo Yang, Zhen Wei, Rhea Liem, Pascal Fua - Trajectory Optimization for Cellular-Connected UAV in Complex Environment with Partial CKM - https://arxiv.org/abs/2512.06452 - arXiv:2512.06452v1 Announce Type: new -Abstract: Cellular-connected unmanned aerial vehicles (UAVs) are expected to play an increasingly important role in future wireless networks. To facilitate the reliable navigation for cellular-connected UAVs, channel knowledge map (CKM) is considered a promising approach capable of tackling the non-negligible co-channel interference resulting from the high line-of-sight (LoS) probability of air-ground (AG) channels. Nevertheless, due to measurement constraints and the aging of information, CKM is usually incomplete and needs to be regularly updated to capture the dynamic nature of complex environments. In this paper, we propose a novel trajectory design strategy in which UAV navigation and CKM completion are incorporated into a common framework, enabling mutual benefits for both tasks. Specifically, a cellular-connected UAV deployed in an urban environment measures the radio information during its flight and completes the CKM with Kriging interpolation. Based on the method of grid discretization and spherical approximation, a mixed-integer multi-objective optimization problem is formulated. The problem falls into the category of combinatorial mathematics and is essentially equivalent to determining an optimum sequence of grid points to traverse. Through proper mathematical manipulation, the problem is reformulated as variants of two classic models in graph theory, namely the shortest-path problem (SPP) and the traveling salesman problem (TSP). Two navigation strategies based on the two different models are proposed and thoroughly compared based on numerical results to provide implementable methods for engineering practice and reveal the trade-offs between UAV navigation and CKM completion. Simulation results reveal that the proposed navigation strategies can quickly expand the Pareto boundary of the problem and approach the performance of fully-known CKM. - oai:arXiv.org:2512.06452v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + DINO-BOLDNet: A DINOv3-Guided Multi-Slice Attention Network for T1-to-BOLD Generation + https://arxiv.org/abs/2512.08337 + arXiv:2512.08337v1 Announce Type: new +Abstract: Generating BOLD images from T1w images offers a promising solution for recovering missing BOLD information and enabling downstream tasks when BOLD images are corrupted or unavailable. Motivated by this, we propose DINO-BOLDNet, a DINOv3-guided multi-slice attention framework that integrates a frozen self-supervised DINOv3 encoder with a lightweight trainable decoder. The model uses DINOv3 to extract within-slice structural representations, and a separate slice-attention module to fuse contextual information across neighboring slices. A multi-scale generation decoder then restores fine-grained functional contrast, while a DINO-based perceptual loss encourages structural and textural consistency between predictions and ground-truth BOLD in the transformer feature space. Experiments on a clinical dataset of 248 subjects show that DINO-BOLDNet surpasses a conditional GAN baseline in both PSNR and MS-SSIM. To our knowledge, this is the first framework capable of generating mean BOLD images directly from T1w images, highlighting the potential of self-supervised transformer guidance for structural-to-functional mapping. + oai:arXiv.org:2512.08337v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuxuan Song, Haiquan Lu, Chiya Zhang, Beixiong Zheng, Yong Zeng + Jianwei Wang, Qing Wang, Menglan Ruan, Rongjun Ge, Chunfeng Yang, Yang Chen, Chunming Xie - A two-stage explicit/implicit approach combined with mixed finite element methods for a radiation-conduction model in optically thick anisotropic media - https://arxiv.org/abs/2512.06456 - arXiv:2512.06456v1 Announce Type: new -Abstract: This paper develops a two-stage explicit/impicit computational technique combined with a mixed finite element method for solving a nonlinear radiation-conduction problem in anisotropic media, subject to suitable initial and boundary conditions. The space derivatives are approximated by the mixed finite element method ($\mathcal{P}_{p}/\mathcal{P}_{p-1}/\mathcal{P}_{p-1}$), while the interpolation technique is employed in two stages to approximate the time derivative. The proposed strategy is so-called, a two-stage explicit/implicit computational technique combined with mixed finite element method. Specifically, the new algorithm should be observed as a predictor-corrector numerical scheme. Additionally, it efficiently treats the time derivative term and provides a necessary requirement on time step for stability. Under this time step limitation, the stability is deeply analyzed whereas the convergence order is numerically obtained in the $L^{2}$-norm. The theoretical results suggest that the developed approach is spatial fourth-order convergent and temporal second-order accurate. Some numerical experiments are carried out to confirm the theoretical results and to demonstrate the practical applicability of the new algorithm. - oai:arXiv.org:2512.06456v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 + Predicting California Bearing Ratio with Ensemble and Neural Network Models: A Case Study from T\"urkiye + https://arxiv.org/abs/2512.08340 + arXiv:2512.08340v1 Announce Type: new +Abstract: The California Bearing Ratio (CBR) is a key geotechnical indicator used to assess the load-bearing capacity of subgrade soils, especially in transportation infrastructure and foundation design. Traditional CBR determination relies on laboratory penetration tests. Despite their accuracy, these tests are often time-consuming, costly, and can be impractical, particularly for large-scale or diverse soil profiles. Recent progress in artificial intelligence, especially machine learning (ML), has enabled data-driven approaches for modeling complex soil behavior with greater speed and precision. This study introduces a comprehensive ML framework for CBR prediction using a dataset of 382 soil samples collected from various geoclimatic regions in T\"urkiye. The dataset includes physicochemical soil properties relevant to bearing capacity, allowing multidimensional feature representation in a supervised learning context. Twelve ML algorithms were tested, including decision tree, random forest, extra trees, gradient boosting, xgboost, k-nearest neighbors, support vector regression, multi-layer perceptron, adaboost, bagging, voting, and stacking regressors. Each model was trained, validated, and evaluated to assess its generalization and robustness. Among them, the random forest regressor performed the best, achieving strong R2 scores of 0.95 (training), 0.76 (validation), and 0.83 (test). These outcomes highlight the model's powerful nonlinear mapping ability, making it a promising tool for predictive geotechnical tasks. The study supports the integration of intelligent, data-centric models in geotechnical engineering, offering an effective alternative to traditional methods and promoting digital transformation in infrastructure analysis and design. + oai:arXiv.org:2512.08340v1 + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Eric Ngondiep + http://creativecommons.org/licenses/by/4.0/ + 10.5281/zenodo.17530868 + Proc. of the 13th Int. Symp. on Intelligent Manufacturing and Service Systems, pp. 563-570, 2025, ISBN 978-625-00-3472-9 + Abdullah Hulusi K\"ok\c{c}am, U\u{g}ur Da\u{g}deviren, Talas Fikret Kurnaz, Alparslan Serhat Demir, Caner Erden - BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination - https://arxiv.org/abs/2512.06457 - arXiv:2512.06457v1 Announce Type: new -Abstract: Attention-based large language models (LLMs) have transformed modern AI applications, but the quadratic cost of self-attention imposes significant compute and memory overhead. Dynamic sparsity (DS) attention mitigates this, yet its hardware efficiency is limited by the added prediction stage and the heavy memory traffic it entails. To address these limitations, this paper proposes BitStopper, a fine-grained algorithm-architecture co-design that operates without a sparsity predictor. First, a bit-serial enable stage fusion (BESF) mechanism is proposed to reuse and minimize the memory access by progressively terminating trivial tokens and merging the prediction stage into the execution stage. Second, a lightweight and adaptive token selection (LATS) strategy is developed to work in concert with the bit-level sparsity speculation. Third, a bit-level asynchronous processing (BAP) strategy is employed to improve compute utilization during the on-demand bit-grained memory fetching. Finally, an elaborate architecture is designed to translate the theoretical complexity reduction into practical performance improvement. Extensive evaluations demonstrate that, compared to state-of-the-art (SOTA) Transformer accelerators, BitStopper achieves 2.03x and 1.89x speedups over Sanger and SOFA, respectively, while delivering 2.4x and 2.1x improvements in energy efficiency. - oai:arXiv.org:2512.06457v1 + Multi-Agent Deep Reinforcement Learning for Collaborative UAV Relay Networks under Jamming Atatcks + https://arxiv.org/abs/2512.08341 + arXiv:2512.08341v1 Announce Type: new +Abstract: The deployment of Unmanned Aerial Vehicle (UAV) swarms as dynamic communication relays is critical for next-generation tactical networks. However, operating in contested environments requires solving a complex trade-off, including maximizing system throughput while ensuring collision avoidance and resilience against adversarial jamming. Existing heuristic-based approaches often struggle to find effective solutions due to the dynamic and multi-objective nature of this problem. This paper formulates this challenge as a cooperative Multi-Agent Reinforcement Learning (MARL) problem, solved using the Centralized Training with Decentralized Execution (CTDE) framework. Our approach employs a centralized critic that uses global state information to guide decentralized actors which operate using only local observations. Simulation results show that our proposed framework significantly outperforms heuristic baselines, increasing the total system throughput by approximately 50% while simultaneously achieving a near-zero collision rate. A key finding is that the agents develop an emergent anti-jamming strategy without explicit programming. They learn to intelligently position themselves to balance the trade-off between mitigating interference from jammers and maintaining effective communication links with ground users. + oai:arXiv.org:2512.08341v1 + cs.NI cs.LG - eess.SP - Tue, 09 Dec 2025 00:00:00 -0500 + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Huizheng Wang, Hongbin Wang, Shaojun Wei, Yang Hu, Shouyi Yin + http://creativecommons.org/licenses/by/4.0/ + Thai Duong Nguyen, Ngoc-Tan Nguyen, Thanh-Dao Nguyen, Nguyen Van Huynh, Dinh-Hieu Tran, Symeon Chatzinotas - Instance Dependent Testing of Samplers using Interval Conditioning - https://arxiv.org/abs/2512.06458 - arXiv:2512.06458v1 Announce Type: new -Abstract: Sampling algorithms play a pivotal role in probabilistic AI. However, verifying if a sampler program indeed samples from the claimed distribution is a notoriously hard problem. Provably correct testers like Barbarik, Teq, Flash, CubeProbe for testing of different kinds of samplers were proposed only in the last few years. All these testers focus on the worst-case efficiency, and do not support verification of samplers over infinite domains, a case occurring frequently in Astronomy, Finance, Network Security, etc. - In this work, we design the first tester of samplers with instance-dependent efficiency, allowing us to test samplers over natural numbers. Our tests are developed via a novel distance estimation algorithm between an unknown and a known probability distribution using an interval conditioning framework. The core technical contribution is a new connection with probability mass estimation of a continuous distribution. The practical gains are also substantial: our experiments establish up to 1000x speedup over state-of-the-art testers. - oai:arXiv.org:2512.06458v1 - cs.DS + Soil Compaction Parameters Prediction Based on Automated Machine Learning Approach + https://arxiv.org/abs/2512.08343 + arXiv:2512.08343v1 Announce Type: new +Abstract: Soil compaction is critical in construction engineering to ensure the stability of structures like road embankments and earth dams. Traditional methods for determining optimum moisture content (OMC) and maximum dry density (MDD) involve labor-intensive laboratory experiments, and empirical regression models have limited applicability and accuracy across diverse soil types. In recent years, artificial intelligence (AI) and machine learning (ML) techniques have emerged as alternatives for predicting these compaction parameters. However, ML models often struggle with prediction accuracy and generalizability, particularly with heterogeneous datasets representing various soil types. This study proposes an automated machine learning (AutoML) approach to predict OMC and MDD. AutoML automates algorithm selection and hyperparameter optimization, potentially improving accuracy and scalability. Through extensive experimentation, the study found that the Extreme Gradient Boosting (XGBoost) algorithm provided the best performance, achieving R-squared values of 80.4% for MDD and 89.1% for OMC on a separate dataset. These results demonstrate the effectiveness of AutoML in predicting compaction parameters across different soil types. The study also highlights the importance of heterogeneous datasets in improving the generalization and performance of ML models. Ultimately, this research contributes to more efficient and reliable construction practices by enhancing the prediction of soil compaction parameters. + oai:arXiv.org:2512.08343v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Rishiraj Bhattacharyya, Sourav Chakraborty, Yash Pote, Uddalok Sarkar, Sayantan Sen + 10.5281/zenodo.17533851 + Proc. of the 13th Int. Symp. on Intelligent Manufacturing and Service Systems, pp. 571-578, 2025, ISBN 978-625-00-3472-9 + Caner Erden, Alparslan Serhat Demir, Abdullah Hulusi Kokcam, Talas Fikret Kurnaz, Ugur Dagdeviren - Cenergy3: An API for City Energy 3D Modeling - https://arxiv.org/abs/2512.06459 - arXiv:2512.06459v1 Announce Type: new -Abstract: The efficient management and planning of urban energy systems require integrated three-dimensional (3D) models that accurately represent both consumption nodes and distribution networks. This paper introduces our developed geospatial Application Programming Interface (API) that automates the generation of 3D urban digital model from open data. The API synthesizes data from OpenTopography, OpenStreetMap, and Overture Maps in generating 3D models. The rendered model visualizes and contextualizes power grid infrastructure alongside the built environment and transportation networks. The API provides interactive figures for the 3D models, which are essential for analyzing infrastructure alignment and spatially linking energy demand nodes (buildings) with energy supply (utility grids). Our API leverages standard Web Mercator coordinates (EPSG:3857) and JSON serialization to ensure interoperability within smart city and energy simulation platforms. - oai:arXiv.org:2512.06459v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Enhancing Explainability of Graph Neural Networks Through Conceptual and Structural Analyses and Their Extensions + https://arxiv.org/abs/2512.08344 + arXiv:2512.08344v1 Announce Type: new +Abstract: Graph Neural Networks (GNNs) have become a powerful tool for modeling and analyzing data with graph structures. The wide adoption in numerous applications underscores the value of these models. However, the complexity of these methods often impedes understanding their decision-making processes. Current Explainable AI (XAI) methods struggle to untangle the intricate relationships and interactions within graphs. Several methods have tried to bridge this gap via a post-hoc approach or self-interpretable design. Most of them focus on graph structure analysis to determine essential patterns that correlate with prediction outcomes. While post-hoc explanation methods are adaptable, they require extra computational resources and may be less reliable due to limited access to the model's internal workings. Conversely, Interpretable models can provide immediate explanations, but their generalizability to different scenarios remains a major concern. To address these shortcomings, this thesis seeks to develop a novel XAI framework tailored for graph-based machine learning. The proposed framework aims to offer adaptable, computationally efficient explanations for GNNs, moving beyond individual feature analysis to capture how graph structure influences predictions. + oai:arXiv.org:2512.08344v1 + cs.AI + cs.IT + cs.LG + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Shiliang Zhang, Sabita Maharjan + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Tien Cuong Bui - Modeling Contextual Passage Utility for Multihop Question Answering - https://arxiv.org/abs/2512.06464 - arXiv:2512.06464v1 Announce Type: new -Abstract: Multihop Question Answering (QA) requires systems to identify and synthesize information from multiple text passages. While most prior retrieval methods assist in identifying relevant passages for QA, further assessing the utility of the passages can help in removing redundant ones, which may otherwise add to noise and inaccuracies in the generated answers. Existing utility prediction approaches model passage utility independently, overlooking a critical aspect of multihop reasoning: the utility of a passage can be context-dependent, influenced by its relation to other passages - whether it provides complementary information or forms a crucial link in conjunction with others. In this paper, we propose a lightweight approach to model contextual passage utility, accounting for inter-passage dependencies. We fine-tune a small transformer-based model to predict passage utility scores for multihop QA. We leverage the reasoning traces from an advanced reasoning model to capture the order in which passages are used to answer a question and obtain synthetic training data. Through comprehensive experiments, we demonstrate that our utility-based scoring of retrieved passages leads to improved reranking and downstream QA performance compared to relevance-based reranking methods. - oai:arXiv.org:2512.06464v1 + The High Cost of Incivility: Quantifying Interaction Inefficiency via Multi-Agent Monte Carlo Simulations + https://arxiv.org/abs/2512.08345 + arXiv:2512.08345v1 Announce Type: new +Abstract: Workplace toxicity is widely recognized as detrimental to organizational culture, yet quantifying its direct impact on operational efficiency remains methodologically challenging due to the ethical and practical difficulties of reproducing conflict in human subjects. This study leverages Large Language Model (LLM) based Multi-Agent Systems to simulate 1-on-1 adversarial debates, creating a controlled "sociological sandbox". We employ a Monte Carlo method to simulate hundrets of discussions, measuring the convergence time (defined as the number of arguments required to reach a conclusion) between a baseline control group and treatment groups involving agents with "toxic" system prompts. Our results demonstrate a statistically significant increase of approximately 25\% in the duration of conversations involving toxic participants. We propose that this "latency of toxicity" serves as a proxy for financial damage in corporate and academic settings. Furthermore, we demonstrate that agent-based modeling provides a reproducible, ethical alternative to human-subject research for measuring the mechanics of social friction. + oai:arXiv.org:2512.08345v1 + cs.AI cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CY + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Akriti Jain, Aparna Garimella + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Benedikt Mangold - A finer reparameterisation theorem for MSO and FO queries on strings - https://arxiv.org/abs/2512.06466 - arXiv:2512.06466v1 Announce Type: new -Abstract: We show a theorem on monadic second-order k-ary queries on finite words. It may be illustrated by the following example: if the number of results of a query on binary strings is O(number of 0s $\times$ number of 1s), then each result can be MSO-definably identified from a 0-position, a 1-position and some finite data. - Our proofs also handle the case of first-order logic / aperiodic monoids. Thus we can state and prove the folklore theorem that dimension minimisation holds for first-order string-to-string interpretations. - oai:arXiv.org:2512.06466v1 - cs.LO - cs.FL - Tue, 09 Dec 2025 00:00:00 -0500 + A tight example for approximation ratio 5 for covering small cuts by the primal-dual method + https://arxiv.org/abs/2512.08350 + arXiv:2512.08350v1 Announce Type: new +Abstract: In the Small Cuts Cover problem we seek to cover by a min-cost edge-set the set family of cuts of size/capacity $<k$ of a graph. Recently, Simmons showed that the primal-dual algorithm of Williamson, Goemans, Mihail, and Vazirani achieves approximation ratio $5$ for this problem, and asked whether this bound is tight. We will answer this question positively, by providing an example in which the ratio between the solution produced by the primal-dual algorithm and the optimum is arbitrarily close to $5$. + oai:arXiv.org:2512.08350v1 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - L\^e Th\`anh D\~ung Nguy\^en, Pawe{\l} Parys + Zeev Nutov - Formalisation of Security for Federated Learning with DP and Attacker Advantage in IIIf for Satellite Swarms -- Extended Version - https://arxiv.org/abs/2512.06467 - arXiv:2512.06467v1 Announce Type: new -Abstract: In distributed applications, like swarms of satellites, machine learning can be efficiently applied even on small devices by using Federated Learning (FL). This allows to reduce the learning complexity by transmitting only updates to the general model in the server in the form of differences in stochastic gradient descent. FL naturally supports differential privacy but new attacks, so called Data Leakage from Gradient (DLG) have been discovered recently. There has been work on defenses against DLG but there is a lack of foundation and rigorous evaluation of their security. In the current work, we extend existing work on a formal notion of Differential Privacy for Federated Learning distributed dynamic systems and relate it to the notion of the attacker advantage. This formalisation is carried out within the Isabelle Insider and Infrastructure framework (IIIf) allowing the machine supported verification of theory and applications within the proof assistant Isabelle. Satellite swarm systems are used as a motivating use case but also as a validation case study. - oai:arXiv.org:2512.06467v1 - cs.CR - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + Turning Threat into Opportunity: DRL-Powered Anti-Jamming via Energy Harvesting in UAV-Disrupted Channels + https://arxiv.org/abs/2512.08351 + arXiv:2512.08351v1 Announce Type: new +Abstract: The open and broadcast nature of wireless communication systems, while enabling ubiquitous connectivity, also exposes them to jamming attacks that may critically compromise network performance or disrupt service availability. The proliferation of Unmanned Aerial Vehicles (UAVs) introduces a new dimension to this threat, as UAVs can act as mobile, intelligent jammers capable of launching sophisticated attacks by leveraging Line-of-Sight (LoS) channels and adaptive strategies. This paper addresses a critical challenge of countering intelligent UAV jamming in the context of energy-constrained ambient backscatter communication systems. Traditional anti-jamming techniques often fall short against such dynamic threats or are unsuitable for low-power backscatter devices. Hence, we propose a novel anti-jamming framework based on Deep Reinforcement Learning (DRL) that empowers the transmitter to not only defend against but also strategically exploit the UAV's jamming signals. In particular, our approach allows the transmitter to learn an optimal policy for switching between active transmission, energy harvesting from the jamming signal, and backscattering information using the jammer's own emissions. We then formulate the problem as a Markov Decision Process (MDP) and employ a Deep Q-Network (DQN) to derive the optimal operational strategy. Simulation results demonstrate that our DQN-based method significantly outperforms conventional Q-learning in convergence speed and surpasses a greedy anti-jamming strategy in terms of average throughput, packet loss rate, and packet delivery ratio. + oai:arXiv.org:2512.08351v1 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Florian Kamm\"uller + Ngoc-Tan Nguyen, Thi-Thu Hoang, Trung-Dung Hoang, Thai-Duong Nguyen - Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control - https://arxiv.org/abs/2512.06471 - arXiv:2512.06471v1 Announce Type: new -Abstract: Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on optimal control. In particular, we derive an optimality gap between more classical, often quadratic, objectives and the goal-conditioned reward, elucidating the success of goal-conditioned RL and why classical ``dense'' rewards can falter. We then consider the partially observed Markov decision setting and connect state estimation to our probabilistic reward, further making the goal-conditioned reward well suited to dual control problems. The advantages of goal-conditioned policies are validated on nonlinear and uncertain environments using both RL and predictive control techniques. - oai:arXiv.org:2512.06471v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + On Discrete Ambiguity Functions of Random Communication Waveforms + https://arxiv.org/abs/2512.08352 + arXiv:2512.08352v1 Announce Type: new +Abstract: This paper provides a fundamental characterization of the discrete ambiguity functions (AFs) of random communication waveforms under arbitrary orthonormal modulation with random constellation symbols, which serve as a key metric for evaluating the delay-Doppler sensing performance in future ISAC applications. A unified analytical framework is developed for two types of AFs, namely the discrete periodic AF (DP-AF) and the fast-slow time AF (FST-AF), where the latter may be seen as a small-Doppler approximation of the DP-AF. By analyzing the expectation of squared AFs, we derive exact closed-form expressions for both the expected sidelobe level (ESL) and the expected integrated sidelobe level (EISL) under the DP-AF and FST-AF formulations. For the DP-AF, we prove that the normalized EISL is identical for all orthogonal waveforms. To gain structural insights, we introduce a matrix representation based on the finite Weyl-Heisenberg (WH) group, where each delay-Doppler shift corresponds to a WH operator acting on the ISAC signal. This WH-group viewpoint yields sharp geometric constraints on the lowest sidelobes: The minimum ESL can only occur along a one-dimensional cut or over a set of widely dispersed delay-Doppler bins. Consequently, no waveform can attain the minimum ESL over any compact two-dimensional region, leading to a no-optimality (no-go) result under the DP-AF framework. For the FST-AF, the closed-form ESL and EISL expressions reveal a constellation-dependent regime governed by its kurtosis: The OFDM modulation achieves the minimum ESL for sub-Gaussian constellations, whereas the OTFS waveform becomes optimal for super-Gaussian constellations. Finally, four representative waveforms, namely, SC, OFDM, OTFS, and AFDM, are examined under both frameworks, and all theoretical results are verified through numerical examples. + oai:arXiv.org:2512.08352v1 + cs.IT + eess.SP + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Nathan P. Lawrence, Ali Mesbah + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ying Zhang, Fan Liu, Yifeng Xiong, Weijie Yuan, Shuangyang Li, Le Zheng, Tony Xiao Han, Christos Masouros, Shi Jin - Knowing What's Missing: Assessing Information Sufficiency in Question Answering - https://arxiv.org/abs/2512.06476 - arXiv:2512.06476v1 Announce Type: new -Abstract: Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success on factual questions, they frequently fail on inferential ones that require reasoning beyond direct text extraction. We hypothesize that asking a model to first reason about what specific information is missing provides a more reliable, implicit signal for assessing overall sufficiency. To this end, we propose a structured Identify-then-Verify framework for robust sufficiency modeling. Our method first generates multiple hypotheses about missing information and establishes a semantic consensus. It then performs a critical verification step, forcing the model to re-examine the source text to confirm whether this information is truly absent. We evaluate our method against established baselines across diverse multi-hop and factual QA datasets. The results demonstrate that by guiding the model to justify its claims about missing information, our framework produces more accurate sufficiency judgments while clearly articulating any information gaps. - oai:arXiv.org:2512.06476v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + A reconstructed discontinuous approximation for distributed elliptic control problems + https://arxiv.org/abs/2512.08353 + arXiv:2512.08353v1 Announce Type: new +Abstract: In this paper, we present and analyze an internal penalty discontinuous Galerkin method for the distributed elliptic optimal control problems. It is based on a reconstructed discontinuous approximation which admits arbitrarily high-order approximation space with only one unknown per element. Applying this method, we develop a proper discretization scheme that approximates the state and adjoint variables in the approximation space. Our main contributions are twofold: (1) the derivation of both a priori and a posteriori error estimates of the $L^2$-norm and the energy norms, and (2) the implementation of an efficiently solvable discrete system, which is solved via a linearly convergent projected gradient descent method. Numerical experiments are provided to verify the convergence order in a priori estimate and the efficiency of a posteriori error estimate. + oai:arXiv.org:2512.08353v1 + math.NA + cs.NA + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Akriti Jain, Aparna Garimella + http://creativecommons.org/publicdomain/zero/1.0/ + Ruo Li, Haoyang Liu, Jun Yin - Algebra in Algorithmic Coding Theory - https://arxiv.org/abs/2512.06478 - arXiv:2512.06478v1 Announce Type: new -Abstract: We survey the notion and history of error-correcting codes and the algorithms needed to make them effective in information transmission. We then give some basic as well as more modern constructions of, and algorithms for, error-correcting codes that depend on relatively simple elements of applied algebra. While the role of algebra in the constructions of codes has been widely acknowledged in texts and other writings, the role in the design of algorithms is often less widely understood, and this survey hopes to reduce this difference to some extent. - oai:arXiv.org:2512.06478v1 - cs.IT - cs.CC - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels + https://arxiv.org/abs/2512.08358 + arXiv:2512.08358v1 Announce Type: new +Abstract: Monocular 3D tracking aims to capture the long-term motion of pixels in 3D space from a single monocular video and has witnessed rapid progress in recent years. However, we argue that the existing monocular 3D tracking methods still fall short in separating the camera motion from foreground dynamic motion and cannot densely track newly emerging dynamic subjects in the videos. To address these two limitations, we propose TrackingWorld, a novel pipeline for dense 3D tracking of almost all pixels within a world-centric 3D coordinate system. First, we introduce a tracking upsampler that efficiently lifts the arbitrary sparse 2D tracks into dense 2D tracks. Then, to generalize the current tracking methods to newly emerging objects, we apply the upsampler to all frames and reduce the redundancy of 2D tracks by eliminating the tracks in overlapped regions. Finally, we present an efficient optimization-based framework to back-project dense 2D tracks into world-centric 3D trajectories by estimating the camera poses and the 3D coordinates of these 2D tracks. Extensive evaluations on both synthetic and real-world datasets demonstrate that our system achieves accurate and dense 3D tracking in a world-centric coordinate frame. + oai:arXiv.org:2512.08358v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Madhu Sudan + Jiahao Lu, Weitao Xiong, Jiacheng Deng, Peng Li, Tianyu Huang, Zhiyang Dou, Cheng Lin, Sai-Kit Yeung, Yuan Liu - Classifying German Language Proficiency Levels Using Large Language Models - https://arxiv.org/abs/2512.06483 - arXiv:2512.06483v1 Announce Type: new -Abstract: Assessing language proficiency is essential for education, as it enables instruction tailored to learners needs. This paper investigates the use of Large Language Models (LLMs) for automatically classifying German texts according to the Common European Framework of Reference for Languages (CEFR) into different proficiency levels. To support robust training and evaluation, we construct a diverse dataset by combining multiple existing CEFR-annotated corpora with synthetic data. We then evaluate prompt-engineering strategies, fine-tuning of a LLaMA-3-8B-Instruct model and a probing-based approach that utilizes the internal neural state of the LLM for classification. Our results show a consistent performance improvement over prior methods, highlighting the potential of LLMs for reliable and scalable CEFR classification. - oai:arXiv.org:2512.06483v1 - cs.CL + Conditional Morphogenesis: Emergent Generation of Structural Digits via Neural Cellular Automata + https://arxiv.org/abs/2512.08360 + arXiv:2512.08360v1 Announce Type: new +Abstract: Biological systems exhibit remarkable morphogenetic plasticity, where a single genome can encode various specialized cellular structures triggered by local chemical signals. In the domain of Deep Learning, Differentiable Neural Cellular Automata (NCA) have emerged as a paradigm to mimic this self-organization. However, existing NCA research has predominantly focused on continuous texture synthesis or single-target object recovery, leaving the challenge of class-conditional structural generation largely unexplored. In this work, we propose a novel Conditional Neural Cellular Automata (c-NCA) architecture capable of growing distinct topological structures - specifically MNIST digits - from a single generic seed, guided solely by a spatially broadcasted class vector. Unlike traditional generative models (e.g., GANs, VAEs) that rely on global reception fields, our model enforces strict locality and translation equivariance. We demonstrate that by injecting a one-hot condition into the cellular perception field, a single set of local rules can learn to break symmetry and self-assemble into ten distinct geometric attractors. Experimental results show that our c-NCA achieves stable convergence, correctly forming digit topologies from a single pixel, and exhibits robustness characteristic of biological systems. This work bridges the gap between texture-based NCAs and structural pattern formation, offering a lightweight, biologically plausible alternative for conditional generation. + oai:arXiv.org:2512.08360v1 + cs.NE cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Elias-Leander Ahlers, Witold Brunsmann, Malte Schilling + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ali Sakour - Sanvaad: A Multimodal Accessibility Framework for ISL Recognition and Voice-Based Interaction - https://arxiv.org/abs/2512.06485 - arXiv:2512.06485v1 Announce Type: new -Abstract: Communication between deaf users, visually im paired users, and the general hearing population often relies on tools that support only one direction of interaction. To address this limitation, this work presents Sanvaad, a lightweight multimodal accessibility framework designed to support real time, two-way communication. For deaf users, Sanvaad includes an ISL recognition module built on MediaPipe landmarks. MediaPipe is chosen primarily for its efficiency and low computational load, enabling the system to run smoothly on edge devices without requiring dedicated hardware. Spoken input from a phone can also be translated into sign representations through a voice-to-sign component that maps detected speech to predefined phrases and produces corresponding GIFs or alphabet-based visualizations. For visually impaired users, the framework provides a screen free voice interface that integrates multilingual speech recognition, text summarization, and text-to-speech generation. These components work together through a Streamlit-based interface, making the system usable on both desktop and mobile environments. Overall, Sanvaad aims to offer a practical and accessible pathway for inclusive communication by combining lightweight computer vision and speech processing tools within a unified framework. - oai:arXiv.org:2512.06485v1 + SCU-CGAN: Enhancing Fire Detection through Synthetic Fire Image Generation and Dataset Augmentation + https://arxiv.org/abs/2512.08362 + arXiv:2512.08362v1 Announce Type: new +Abstract: Fire has long been linked to human life, causing severe disasters and losses. Early detection is crucial, and with the rise of home IoT technologies, household fire detection systems have emerged. However, the lack of sufficient fire datasets limits the performance of detection models. We propose the SCU-CGAN model, which integrates U-Net, CBAM, and an additional discriminator to generate realistic fire images from nonfire images. We evaluate the image quality and confirm that SCU-CGAN outperforms existing models. Specifically, SCU-CGAN achieved a 41.5% improvement in KID score compared to CycleGAN, demonstrating the superior quality of the generated fire images. Furthermore, experiments demonstrate that the augmented dataset significantly improves the accuracy of fire detection models without altering their structure. For the YOLOv5 nano model, the most notable improvement was observed in the mAP@0.5:0.95 metric, which increased by 56.5%, highlighting the effectiveness of the proposed approach. + oai:arXiv.org:2512.08362v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Kush Revankar, Shreyas Deshpande, Araham Sayeed, Ansh Tandale, Sarika Bobde + Ju-Young Kim, Ji-Hong Park, Gun-Woo Kim - Entropy-Controlled Intrinsic Motivation Reinforcement Learning for Quadruped Robot Locomotion in Complex Terrains - https://arxiv.org/abs/2512.06486 - arXiv:2512.06486v1 Announce Type: new -Abstract: Learning is the basis of both biological and artificial systems when it comes to mimicking intelligent behaviors. From the classical PPO (Proximal Policy Optimization), there is a series of deep reinforcement learning algorithms which are widely used in training locomotion policies for quadrupedal robots because of their stability and sample efficiency. However, among all these variants, experiments and simulations often converge prematurely, leading to suboptimal locomotion and reduced task performance. Therefore, in this paper, we introduce Entropy-Controlled Intrinsic Motivation (ECIM), an entropy-based reinforcement learning algorithm in contrast with the PPO series, that can reduce premature convergence by combining intrinsic motivation with adaptive exploration. - For experiments, in order to parallel with other baselines, we chose to apply it in Isaac Gym across six terrain categories: upward slopes, downward slopes, uneven rough terrain, ascending stairs, descending stairs, and flat ground as widely used. For comparison, our experiments consistently achieve better performance: task rewards increase by 4--12%, peak body pitch oscillation is reduced by 23--29%, joint acceleration decreases by 20--32%, and joint torque consumption declines by 11--20%. Overall, our model ECIM, by combining entropy control and intrinsic motivation control, achieves better results in stability across different terrains for quadrupedal locomotion, and at the same time reduces energetic cost and makes it a practical choice for complex robotic control tasks. - oai:arXiv.org:2512.06486v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Generalized Discrepancy of Random Points + https://arxiv.org/abs/2512.08364 + arXiv:2512.08364v1 Announce Type: new +Abstract: We study the $L_p$-discrepancy of random point sets in high dimensions, with emphasis on small values of $p$. Although the classical $L_p$-discrepancy suffers from the curse of dimensionality for all $p \in (1,\infty)$, the gap between known upper and lower bounds remains substantial, in particular for small $p \ge 1$. To clarify this picture, we review the existing results for i.i.d.\ uniformly distributed points and derive new upper bounds for \emph{generalized} $L_p$-discrepancies, obtained by allowing non-uniform sampling densities and corresponding non-negative quadrature weights. + Using the probabilistic method, we show that random points drawn from optimally chosen product densities lead to significantly improved upper bounds. For $p=2$ these bounds are explicit and optimal; for general $p \in [1,\infty)$ we obtain sharp asymptotic estimates. The improvement can be interpreted as a form of importance sampling for the underlying Sobolev space $F_{d,q}$. + Our results also reveal that, even with optimal densities, the curse of dimensionality persists for random points when $p\ge 1$, and it becomes most pronounced for small $p$. This suggests that the curse should also hold for the classical $L_1$-discrepancy for deterministic point sets. + oai:arXiv.org:2512.08364v1 + math.NA + cs.NA + math.NT + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wanru Gong, Xinyi Zheng, Xiaopeng Yang, Xiaoqing Zhu + http://creativecommons.org/licenses/by/4.0/ + Erich Novak, Friedrich Pillichshammer - Optimizing LLMs Using Quantization for Mobile Execution - https://arxiv.org/abs/2512.06490 - arXiv:2512.06490v1 Announce Type: new -Abstract: Large Language Models (LLMs) offer powerful capabilities, but their significant size and computational requirements hinder deployment on resource-constrained mobile devices. This paper investigates Post-Training Quantization (PTQ) for compressing LLMs for mobile execution. We apply 4-bit PTQ using the BitsAndBytes library with the Hugging Face Transformers framework to Meta's Llama 3.2 3B model. The quantized model is converted to GGUF format using llama.cpp tools for optimized mobile inference. The PTQ workflow achieves a 68.66% reduction in model size through 4-bit quantization, enabling the Llama 3.2 3B model to run efficiently on an Android device. Qualitative validation shows that the 4-bit quantized model can perform inference tasks successfully. We demonstrate the feasibility of running the quantized GGUF model on an Android device using the Termux environment and the Ollama framework. PTQ, especially at 4-bit precision combined with mobile-optimized formats like GGUF, provides a practical pathway for deploying capable LLMs on mobile devices, balancing model size and performance. - oai:arXiv.org:2512.06490v1 + Magneton: Optimizing Energy Efficiency of ML Systems via Differential Energy Debugging + https://arxiv.org/abs/2512.08365 + arXiv:2512.08365v1 Announce Type: new +Abstract: The training and deployment of machine learning (ML) models have become extremely energy-intensive. While existing optimization efforts focus primarily on hardware energy efficiency, a significant but overlooked source of inefficiency is software energy waste caused by poor software design. This often includes redundant or poorly designed operations that consume more energy without improving performance. These inefficiencies arise in widely used ML frameworks and applications, yet developers often lack the visibility and tools to detect and diagnose them. + We propose differential energy debugging, a novel approach that leverages the observation that competing ML systems often implement similar functionality with vastly different energy consumption. Building on this insight, we design and implement Magneton, an energy profiler that compares energy consumption between similar ML systems at the operator level and automatically pinpoints code regions and configuration choices responsible for excessive energy use. Applied to 9 popular ML systems spanning LLM inference, general ML frameworks, and image generation, Magneton detects and diagnoses 16 known cases of software energy inefficiency and further discovers 8 previously unknown cases, 7 of which have been confirmed by developers. + oai:arXiv.org:2512.08365v1 + cs.DC cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1007/978-3-032-06697-8_33 - Fong, S., Dey, N., Joshi, A. (eds) ICT Analysis and Applications. ICT4SD 2025. Lecture Notes in Networks and Systems, vol 1654. Springer, Cham - Agatsya Yadav, Renta Chintala Bhargavi + Yi Pan, Wenbo Qian, Dedong Xie, Ruiyan Hu, Yigong Hu, Baris Kasikci - Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA ARC-OTA - https://arxiv.org/abs/2512.06493 - arXiv:2512.06493v1 Announce Type: new -Abstract: The transition of cellular networks to (i) software-based systems on commodity hardware and (ii) platforms for services beyond connectivity introduces critical system-level challenges. As sensing emerges as a key feature toward 6G standardization, supporting Integrated Sensing and Communication (ISAC) with limited bandwidth and piggybacking on communication signals, while maintaining high reliability and performance, remains a fundamental challenge. In this paper, we provide two key contributions. First, we present a programmable, plug-and-play framework for processing PHY/MAC signals through real-time, GPU-accelerated Artificial Intelligence (AI) applications on the edge Radio Access Network (RAN) infrastructure. Building on the Open RAN dApp architecture, the framework interfaces with a GPU-accelerated gNB based on NVIDIA ARC-OTA, feeding PHY/MAC data to custom AI logic with latency under 0.5 ms for complex channel state information extraction. Second, we demonstrate the framework's capabilities through cuSense, an indoor localization dApp that consumes uplink DMRS channel estimates, removes static multipath components, and runs a neural network to infer the position of a moving person. Evaluated on a 3GPP-compliant 5G NR deployment, cuSense achieves a mean localization error of 77 cm, with 75% of predictions falling within 1 meter. This is without dedicated sensing hardware or modifications to the RAN stack or signals. We plan to release both the framework and cuSense pipelines as open source, providing a reference design for future AI-native RANs and ISAC applications. - oai:arXiv.org:2512.06493v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 + Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making + https://arxiv.org/abs/2512.08366 + arXiv:2512.08366v1 Announce Type: new +Abstract: Large language model (LLM) agents often rely on external demonstrations or retrieval-augmented planning, leading to brittleness, poor generalization, and high computational overhead. Inspired by human problem-solving, we propose DuSAR (Dual-Strategy Agent with Reflecting) - a demonstration-free framework that enables a single frozen LLM to perform co-adaptive reasoning via two complementary strategies: a high-level holistic plan and a context-grounded local policy. These strategies interact through a lightweight reflection mechanism, where the agent continuously assesses progress via a Strategy Fitness Score and dynamically revises its global plan when stuck or refines it upon meaningful advancement, mimicking human metacognitive behavior. On ALFWorld and Mind2Web, DuSAR achieves state-of-the-art performance with open-source LLMs (7B-70B), reaching 37.1% success on ALFWorld (Llama3.1-70B) - more than doubling the best prior result (13.0%) - and 4.02% on Mind2Web, also more than doubling the strongest baseline. Remarkably, it reduces per-step token consumption by 3-9X while maintaining strong performance. Ablation studies confirm the necessity of dual-strategy coordination. Moreover, optional integration of expert demonstrations further boosts results, highlighting DuSAR's flexibility and compatibility with external knowledge. + oai:arXiv.org:2512.08366v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Davide Villa, Mauro Belgiovine, Nicholas Hedberg, Michele Polese, Chris Dick, Tommaso Melodia + Wentao Zhang, Qunbo Wang, Tao Zhang, Junsheng Wu, Hongping Gan, Yang Liu, Ling Dai, Shizhuang Deng, Shuntong Sun - String Diagrams for Closed Symmetric Monoidal Categories - https://arxiv.org/abs/2512.06499 - arXiv:2512.06499v1 Announce Type: new -Abstract: We introduce a graphical language for closed symmetric monoidal categories based on an extension of string diagrams with special bracket wires representing internal homs. These bracket wires make the structure of the internal hom functor explicit, allowing standard morphism wires to interact with them through a well-defined set of graphical rules. - We establish the soundness and completeness of the diagrammatic calculus, and illustrate its expressiveness through examples drawn from category theory, logic and programming language semantics. - oai:arXiv.org:2512.06499v1 - cs.LO - math.CT - Tue, 09 Dec 2025 00:00:00 -0500 + A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research + https://arxiv.org/abs/2512.08371 + arXiv:2512.08371v1 Announce Type: new +Abstract: Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate multivariate Bernoulli distribution parameters and calculate weights for each label combination. This approach ensures the weighted sampling acquires target distribution characteristics while accounting for label dependencies. We applied this approach to a sample of research articles from Web of Science labeled with 64 biomedical topic categories. We aimed to preserve category frequency order, reduce frequency differences between most and least common categories, and account for category dependencies. This approach produced a more balanced sub-sample, enhancing the representation of minority categories. + oai:arXiv.org:2512.08371v1 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Callum Reader, Alessandro Di Giorgio + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Simon Chung, Colby J. Vorland, Donna L. Maney, Andrew W. Brown - PDRIMA: A Policy-Driven Runtime Integrity Measurement and Attestation Approach for ARM TrustZone-based TEE - https://arxiv.org/abs/2512.06500 - arXiv:2512.06500v1 Announce Type: new -Abstract: Trusted Execution Environments (TEEs) such as ARM TrustZone are widely used in IoT and embedded devices to protect sensitive code and data. However, most existing defenses focus on secure boot or REE-side monitoring and provide little visibility into the runtime integrity of the TEE. This leaves TrustZone-based devices exposed to persistent TEE compromises. We propose Policy-Driven Runtime Integrity Measurement and Attestation (PDRIMA), a runtime integrity protection approach for TrustZone-based TEEs. PDRIMA systematically analyzes TEE attack surfaces and introduces two in-TEE subsystems: a Secure Monitor Agent (SMA) that performs policy-driven measurement, appraisal, logging, and time-based re-measurement over the TEE kernel, static components, user-TAs, and security-critical system calls; and a Remote Attestation Agent (RAA) that aggregates tamper-evident evidence and exposes a remote attestation protocol for verifying. We analyze PDRIMA's security against identified attack surfaces, implement a prototype on OP-TEE for Raspberry Pi 3B+, and evaluate its performance overhead to indicate its practicability. - oai:arXiv.org:2512.06500v1 + USCSA: Evolution-Aware Security Analysis for Proxy-Based Upgradeable Smart Contracts + https://arxiv.org/abs/2512.08372 + arXiv:2512.08372v1 Announce Type: new +Abstract: In the case of upgrading smart contracts on blockchain systems, it is essential to consider the continuity of upgrade and subsequent maintenance. In practice, upgrade operations often introduce new vulnerabilities. To address this, we propose an Upgradable Smart Contract Security Analyzer, USCSA, which evaluates the risks associated with the upgrade process using the Abstract Syntax Tree (AST) differential analysis. We collected and analyzed 3,546 cases of vulnerabilities in upgradable contracts,covering common vulnerability categories such as reentrancy, access control flaws, and integer overflow. Experimental results show that USCSA achieves an accuracy of 92.3%, recall of 89.7%, and F1-score of 91.0% in detecting upgrade-induced vulnerabilities. + In addition, the efficiency of mapping high-risk changes has achieved a 30% improvement over the conventional approach. As a result, USCSA provides a significant advantage to improve the security and integrity of upgradable smart contracts, providing a novel and efficient solution to secure audits on blockchain applications. + oai:arXiv.org:2512.08372v1 cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jingkai Mao, Xiaolin Chang + Xiaoqi Li, Lei Xie, Wenkai Li, Zongwei Li - Small Language Models Can Use Nuanced Reasoning For Health Science Research Classification: A Microbial-Oncogenesis Case Study - https://arxiv.org/abs/2512.06502 - arXiv:2512.06502v1 Announce Type: new -Abstract: Artificially intelligent (AI) co-scientists must be able to sift through research literature cost-efficiently while applying nuanced scientific reasoning. We evaluate Small Language Models (SLMs, <= 8B parameters) for classifying medical research papers. Using literature on the oncogenic potential of HMTV/MMTV-like viruses in breast cancer as a case study, we assess model performance with both zero-shot and in-context learning (ICL; few-shot prompting) strategies against frontier proprietary Large Language Models (LLMs). Llama 3 and Qwen2.5 outperform GPT-5 (API, low/high effort), Gemini 3 Pro Preview, and Meerkat in zero-shot settings, though trailing Gemini 2.5 Pro. ICL leads to improved performance on a case-by-case basis, allowing Llama 3 and Qwen2.5 to match Gemini 2.5 Pro in binary classification. Systematic lexical-ablation experiments show that SLM decisions are often grounded in valid scientific cues but can be influenced by spurious textual artifacts, underscoring need for interpretability in high-stakes pipelines. Our results reveal both promise and limitations of modern SLMs for scientific triage; pairing SLMs with simple but principled prompting strategies can approach performance of the strongest LLMs for targeted literature filtering in co-scientist pipelines. - oai:arXiv.org:2512.06502v1 - cs.CE - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 + The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss + https://arxiv.org/abs/2512.08374 + arXiv:2512.08374v1 Announce Type: new +Abstract: Multimodal Large Language Models (MLLMs), which couple pre-trained vision encoders and language models, have shown remarkable capabilities. However, their reliance on the ubiquitous Pre-Norm architecture introduces a subtle yet critical flaw: a severe norm disparity between the high-norm visual tokens and the low-norm text tokens. In this work, we present a formal theoretical analysis demonstrating that this imbalance is not a static issue. Instead, it induces an ``asymmetric update dynamic,'' where high-norm visual tokens exhibit a ``representational inertia,'' causing them to transform semantically much slower than their textual counterparts. This fundamentally impairs effective cross-modal feature fusion. Our empirical validation across a range of mainstream MLLMs confirms that this theoretical dynamic -- the persistence of norm disparity and the resulting asymmetric update rates -- is a prevalent phenomenon. Based on this insight, we propose a remarkably simple yet effective solution: inserting a single, carefully initialized LayerNorm layer after the visual projector to enforce norm alignment. Experiments conducted on the LLaVA-1.5 architecture show that this intervention yields significant performance gains not only on a wide suite of multimodal benchmarks but also, notably, on text-only evaluations such as MMLU, suggesting that resolving the architectural imbalance leads to a more holistically capable model. + oai:arXiv.org:2512.08374v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Muhammed Muaaz Dawood, Mohammad Zaid Moonsamy, Kaela Kokkas, Hairong Wang, Robert F. Breiman, Richard Klein, Emmanuel K. Sekyi, Bruce A. Bassett + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Bozhou Li, Xinda Xue, Sihan Yang, Yang Shi, Xinlong Chen, Yushuo Guan, Yuanxing Zhang, Wentao Zhang + + + A Distribution Testing Approach to Clustering Distributions + https://arxiv.org/abs/2512.08376 + arXiv:2512.08376v1 Announce Type: new +Abstract: We study the following distribution clustering problem: Given a hidden partition of $k$ distributions into two groups, such that the distributions within each group are the same, and the two distributions associated with the two clusters are $\varepsilon$-far in total variation, the goal is to recover the partition. We establish upper and lower bounds on the sample complexity for two fundamental cases: (1) when one of the cluster's distributions is known, and (2) when both are unknown. Our upper and lower bounds characterize the sample complexity's dependence on the domain size $n$, number of distributions $k$, size $r$ of one of the clusters, and distance $\varepsilon$. In particular, we achieve tightness with respect to $(n,k,r,\varepsilon)$ (up to an $O(\log k)$ factor) for all regimes. + oai:arXiv.org:2512.08376v1 + cs.DS + cs.IT + math.IT + math.ST + stat.ML + stat.TH + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Gunjan Kumar, Yash Pote, Jonathan Scarlett - Method of UAV Inspection of Photovoltaic Modules Using Thermal and RGB Data Fusion - https://arxiv.org/abs/2512.06504 - arXiv:2512.06504v1 Announce Type: new -Abstract: The subject of this research is the development of an intelligent, integrated framework for the automated inspection of photovoltaic (PV) infrastructure that addresses the critical shortcomings of conventional methods, including thermal palette bias, data redundancy, and high communication bandwidth requirements. The goal of this study is to design, develop, and validate a comprehensive, multi-modal system that fully automates the monitoring workflow, from data acquisition to the generation of actionable, geo-located maintenance alerts, thereby enhancing plant safety and operational efficiency. The methods employed involve a synergistic architecture that begins with a palette-invariant thermal embedding, learned by enforcing representational consistency, which is fused with a contrast-normalized RGB stream via a gated mechanism. This is supplemented by a closed-loop, adaptive re-acquisition controller that uses Rodrigues-based updates for targeted confirmation of ambiguous anomalies and a geospatial deduplication module that clusters redundant alerts using DBSCAN over the haversine distance. In conclusion, this study establishes a powerful new paradigm for proactive PV inspection, with the proposed system achieving a mean Average Precision (mAP@0.5) of 0.903 on the public PVF-10 benchmark, a significant 12-15% improvement over single-modality baselines. Field validation confirmed the system's readiness, achieving 96% recall, while the de-duplication process reduced duplicate-induced false positives by 15-20%, and relevance-only telemetry cut airborne data transmission by 60-70%. - oai:arXiv.org:2512.06504v1 + Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions + https://arxiv.org/abs/2512.08378 + arXiv:2512.08378v1 Announce Type: new +Abstract: Under challenging light conditions, captured images often suffer from various degradations, leading to a decline in the performance of vision-based applications. Although numerous methods have been proposed to enhance image quality, they either significantly amplify inherent noise or are only effective under specific illumination conditions. To address these issues, we propose a novel framework for simultaneous enhancement and noise suppression under complex illumination conditions. Firstly, a gradient-domain weighted guided filter (GDWGIF) is employed to accurately estimate illumination and improve image quality. Next, the Retinex model is applied to decompose the captured image into separate illumination and reflection layers. These layers undergo parallel processing, with the illumination layer being corrected to optimize lighting conditions and the reflection layer enhanced to improve image quality. Finally, the dynamic range of the image is optimized through multi-exposure fusion and a linear stretching strategy. The proposed method is evaluated on real-world datasets obtained from practical applications. Experimental results demonstrate that our proposed method achieves better performance compared to state-of-the-art methods in both contrast enhancement and noise suppression. + oai:arXiv.org:2512.08378v1 cs.CV - cs.AI - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Andrii Lysyi, Anatoliy Sachenko, Pavlo Radiuk, Mykola Lysyi, Oleksandr Melnychenko, Diana Zahorodnia + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Jing Tao, You Li, Banglei Guan, Yang Shang, Qifeng Yu - Diagnosis-based mortality prediction for intensive care unit patients via transfer learning - https://arxiv.org/abs/2512.06511 - arXiv:2512.06511v1 Announce Type: new -Abstract: In the intensive care unit, the underlying causes of critical illness vary substantially across diagnoses, yet prediction models accounting for diagnostic heterogeneity have not been systematically studied. To address the gap, we evaluate transfer learning approaches for diagnosis-specific mortality prediction and apply both GLM- and XGBoost-based models to the eICU Collaborative Research Database. Our results demonstrate that transfer learning consistently outperforms models trained only on diagnosis-specific data and those using a well-known ICU severity-of-illness score, i.e., APACHE IVa, alone, while also achieving better calibration than models trained on the pooled data. Our findings also suggest that the Youden cutoff is a more appropriate decision threshold than the conventional 0.5 for binary outcomes, and that transfer learning maintains consistently high predictive performance across various cutoff criteria. - oai:arXiv.org:2512.06511v1 - cs.LG - stat.AP - Tue, 09 Dec 2025 00:00:00 -0500 + DeepFeature: Iterative Context-aware Feature Generation for Wearable Biosignals + https://arxiv.org/abs/2512.08379 + arXiv:2512.08379v1 Announce Type: new +Abstract: Biosignals collected from wearable devices are widely utilized in healthcare applications. Machine learning models used in these applications often rely on features extracted from biosignals due to their effectiveness, lower data dimensionality, and wide compatibility across various model architectures. However, existing feature extraction methods often lack task-specific contextual knowledge, struggle to identify optimal feature extraction settings in high-dimensional feature space, and are prone to code generation and automation errors. In this paper, we propose DeepFeature, the first LLM-empowered, context-aware feature generation framework for wearable biosignals. DeepFeature introduces a multi-source feature generation mechanism that integrates expert knowledge with task settings. It also employs an iterative feature refinement process that uses feature assessment-based feedback for feature re-selection. Additionally, DeepFeature utilizes a robust multi-layer filtering and verification approach for robust feature-to-code translation to ensure that the extraction functions run without crashing. Experimental evaluation results show that DeepFeature achieves an average AUROC improvement of 4.21-9.67% across eight diverse tasks compared to baseline methods. It outperforms state-of-the-art approaches on five tasks while maintaining comparable performance on the remaining tasks. + oai:arXiv.org:2512.08379v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Mengqi Xu, Subha Maity, Joel Dubin + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Kaiwei Liu, Yuting He, Bufang Yang, Mu Yuan, Chun Man Victor Wong, Ho Pong Andrew Sze, Zhenyu Yan, Hongkai Chen - ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models - https://arxiv.org/abs/2512.06515 - arXiv:2512.06515v1 Announce Type: new -Abstract: Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time, parameter-efficient framework that steers generation toward safe, empathetic, and value-aligned responses without retraining the base model. We formalize five human-centered objectives and cast safety as lexicographic constrained generation: first, applying hard constraints to eliminate harmful continuations; then optimizing for prosocial quality within the safe set. Our method combines (i) directional regulation, a harm-mitigation mechanism that subtracts a learned "harm vector" in parameter space, and (ii) preference-aware autoregressive reward modeling trained jointly across attributes with gradient conflict resolution, enabling fine-grained, user-controllable decoding. Empirical evaluations across five safety benchmarks demonstrate state-of-the-art performance, reducing unsafe leakage and boosting alignment to human values, with strong gains across multiple evaluation metrics. ProSocialAlign offers a robust and modular foundation for generating context-sensitive, safe, and human-aligned responses at inference time. - oai:arXiv.org:2512.06515v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Finding All Bounded-Length Simple Cycles in a Directed Graphs - Revisited + https://arxiv.org/abs/2512.08392 + arXiv:2512.08392v1 Announce Type: new +Abstract: In 2021, Gupta and Suzumura proposed a novel algorithm for enumerating all bounded-length simple cycles in directed graphs. In this work, we present concrete examples demonstrating that the proposed algorithm fails to enumerate certain valid cycles. Via these examples, we perform a detailed analysis pinpointing the specific points at which the proofs exhibit logical gaps. Furthermore, we propose a corrected formulation that resolves these issues while preserving the desirable property that the algorithm's computational complexity remains $O((c + 1) \cdot k \cdot (n + e))$ where $c$ is the number of simple cycles of a specified maximum length $k$, and $n$ and $e$ the number of graph nodes and edges respectively. + oai:arXiv.org:2512.08392v1 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Somnath Banerjee, Sayan Layek, Sayantan Adak, Mykola Pechenizkiy, Animesh Mukherjee, Rima Hazra + Frank Bauern\"oppel, J\"org-R\"udiger Sack - Vision-Guided Grasp Planning for Prosthetic Hands in Unstructured Environments - https://arxiv.org/abs/2512.06517 - arXiv:2512.06517v1 Announce Type: new -Abstract: Recent advancements in prosthetic technology have increasingly focused on enhancing dexterity and autonomy through intelligent control systems. Vision-based approaches offer promising results for enabling prosthetic hands to interact more naturally with diverse objects in dynamic environments. Building on this foundation, the paper presents a vision-guided grasping algorithm for a prosthetic hand, integrating perception, planning, and control for dexterous manipulation. A camera mounted on the set up captures the scene, and a Bounding Volume Hierarchy (BVH)-based vision algorithm is employed to segment an object for grasping and define its bounding box. Grasp contact points are then computed by generating candidate trajectories using Rapidly-exploring Random Tree Star algorithm, and selecting fingertip end poses based on the minimum Euclidean distance between these trajectories and the objects point cloud. Each finger grasp pose is determined independently, enabling adaptive, object-specific configurations. Damped Least Square (DLS) based Inverse kinematics solver is used to compute the corresponding joint angles, which are subsequently transmitted to the finger actuators for execution. This modular pipeline enables per-finger grasp planning and supports real-time adaptability in unstructured environments. The proposed method is validated in simulation, and experimental integration on a Linker Hand O7 platform. - oai:arXiv.org:2512.06517v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Detection of Digital Facial Retouching utilizing Face Beauty Information + https://arxiv.org/abs/2512.08397 + arXiv:2512.08397v1 Announce Type: new +Abstract: Facial retouching to beautify images is widely spread in social media, advertisements, and it is even applied in professional photo studios to let individuals appear younger, remove wrinkles and skin impurities. Generally speaking, this is done to enhance beauty. This is not a problem itself, but when retouched images are used as biometric samples and enrolled in a biometric system, it is one. Since previous work has proven facial retouching to be a challenge for face recognition systems,the detection of facial retouching becomes increasingly necessary. This work proposes to study and analyze changes in beauty assessment algorithms of retouched images, assesses different feature extraction methods based on artificial intelligence in order to improve retouching detection, and evaluates whether face beauty can be exploited to enhance the detection rate. In a scenario where the attacking retouching algorithm is unknown, this work achieved 1.1% D-EER on single image detection. + oai:arXiv.org:2512.08397v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Shifa Sulaiman, Akash Bachhar, Ming Shen, Simon B{\o}gh + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Philipp Srock, Juan E. Tapia, Christoph Busch - Hierarchical geometric deep learning enables scalable analysis of molecular dynamics - https://arxiv.org/abs/2512.06520 - arXiv:2512.06520v1 Announce Type: new -Abstract: Molecular dynamics simulations can generate atomically detailed trajectories of complex systems, but analyzing these dynamics can be challenging when systems lack well-established quantitative descriptors (features). Graph neural networks (GNNs) in which messages are passed between nodes that represent atoms that are spatial neighbors promise to obviate manual feature engineering, but the use of GNNs with biomolecular systems of more than a few hundred residues has been limited in the context of analyzing dynamics by both difficulties in capturing the details of long-range interactions with message passing and the memory and runtime requirements associated with large graphs. Here, we show how local information can be aggregated to reduce memory and runtime requirements without sacrificing atomic detail. We demonstrate that this approach opens the door to analyzing simulations of protein-nucleic acid complexes with thousands of residues on single GPUs within minutes. For systems with hundreds of residues, for which there are sufficient data to make quantitative comparisons, we show that the approach improves performance and interpretability. - oai:arXiv.org:2512.06520v1 - cs.LG - cond-mat.stat-mech - physics.comp-ph - physics.data-an - Tue, 09 Dec 2025 00:00:00 -0500 + Ontology-Based Knowledge Graph Framework for Industrial Standard Documents via Hierarchical and Propositional Structuring + https://arxiv.org/abs/2512.08398 + arXiv:2512.08398v1 Announce Type: new +Abstract: Ontology-based knowledge graph (KG) construction is a core technology that enables multidimensional understanding and advanced reasoning over domain knowledge. Industrial standards, in particular, contain extensive technical information and complex rules presented in highly structured formats that combine tables, scopes of application, constraints, exceptions, and numerical calculations, making KG construction especially challenging. In this study, we propose a method that organizes such documents into a hierarchical semantic structure, decomposes sentences and tables into atomic propositions derived from conditional and numerical rules, and integrates them into an ontology-knowledge graph through LLM-based triple extraction. Our approach captures both the hierarchical and logical structures of documents, effectively representing domain-specific semantics that conventional methods fail to reflect. To verify its effectiveness, we constructed rule, table, and multi-hop QA datasets, as well as a toxic clause detection dataset, from industrial standards, and implemented an ontology-aware KG-RAG framework for comparative evaluation. Experimental results show that our method achieves significant performance improvements across all QA types compared to existing KG-RAG approaches. This study demonstrates that reliable and scalable knowledge representation is feasible even for industrial documents with intertwined conditions, constraints, and scopes, contributing to future domain-specific RAG development and intelligent document management. + oai:arXiv.org:2512.08398v1 + cs.IR + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Zihan Pengmei, Spencer C. Guo, Chatipat Lorpaiboon, Aaron R. Dinner + Jiin Park, Hyuna Jeon, Yoonseo Lee, Jisu Hong, Misuk Kim - ShadowWolf -- Automatic Labelling, Evaluation and Model Training Optimised for Camera Trap Wildlife Images - https://arxiv.org/abs/2512.06521 - arXiv:2512.06521v1 Announce Type: new -Abstract: The continuous growth of the global human population is leading to the expansion of human habitats, resulting in decreasing wildlife spaces and increasing human-wildlife interactions. These interactions can range from minor disturbances, such as raccoons in urban waste bins, to more severe consequences, including species extinction. As a result, the monitoring of wildlife is gaining significance in various contexts. Artificial intelligence (AI) offers a solution by automating the recognition of animals in images and videos, thereby reducing the manual effort required for wildlife monitoring. Traditional AI training involves three main stages: image collection, labelling, and model training. However, the variability, for example, in the landscape (e.g., mountains, open fields, forests), weather (e.g., rain, fog, sunshine), lighting (e.g., day, night), and camera-animal distances presents significant challenges to model robustness and adaptability in real-world scenarios. - In this work, we propose a unified framework, called ShadowWolf, designed to address these challenges by integrating and optimizing the stages of AI model training and evaluation. The proposed framework enables dynamic model retraining to adjust to changes in environmental conditions and application requirements, thereby reducing labelling efforts and allowing for on-site model adaptation. This adaptive and unified approach enhances the accuracy and efficiency of wildlife monitoring systems, promoting more effective and scalable conservation efforts. - oai:arXiv.org:2512.06521v1 + Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries + https://arxiv.org/abs/2512.08400 + arXiv:2512.08400v1 Announce Type: new +Abstract: Accurate fisheries data are crucial for effective and sustainable marine resource management. With the recent adoption of Electronic Monitoring (EM) systems, more video data is now being collected than can be feasibly reviewed manually. This paper addresses this challenge by developing an optimized deep learning pipeline for automated fish re-identification (Re-ID) using the novel AutoFish dataset, which simulates EM systems with conveyor belts with six similarly looking fish species. We demonstrate that key Re-ID metrics (R1 and mAP@k) are substantially improved by using hard triplet mining in conjunction with a custom image transformation pipeline that includes dataset-specific normalization. By employing these strategies, we demonstrate that the Vision Transformer-based Swin-T architecture consistently outperforms the Convolutional Neural Network-based ResNet-50, achieving peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy. An in-depth analysis reveals that the primary challenge is distinguishing visually similar individuals of the same species (Intra-species errors), where viewpoint inconsistency proves significantly more detrimental than partial occlusion. The source code and documentation are available at: https://github.com/msamdk/Fish_Re_Identification.git + oai:arXiv.org:2512.08400v1 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Jens Dede (Department of Sustainable Communication Networks, University of Bremen, Bibliothekstr. 1, 28359, Bremen, Bremen, Germany), Anna F\"orster (Department of Sustainable Communication Networks, University of Bremen, Bibliothekstr. 1, 28359, Bremen, Bremen, Germany) + Samitha Nuwan Thilakarathna, Ercan Avsar, Martin Mathias Nielsen, Malte Pedersen - TacFinRay: Soft Tactile Fin-Ray Finger with Indirect Tactile Sensing for Robust Grasping - https://arxiv.org/abs/2512.06524 - arXiv:2512.06524v1 Announce Type: new -Abstract: We present a tactile-sensorized Fin-Ray finger that enables simultaneous detection of contact location and indentation depth through an indirect sensing approach. A hinge mechanism is integrated between the soft Fin-Ray structure and a rigid sensing module, allowing deformation and translation information to be transferred to a bottom crossbeam upon which are an array of marker-tipped pins based on the biomimetic structure of the TacTip vision-based tactile sensor. Deformation patterns captured by an internal camera are processed using a convolutional neural network to infer contact conditions without directly sensing the finger surface. The finger design was optimized by varying pin configurations and hinge orientations, achieving 0.1\,mm depth and 2mm location-sensing accuracies. The perception demonstrated robust generalization to various indenter shapes and sizes, which was applied to a pick-and-place task under uncertain picking positions, where the tactile feedback significantly improved placement accuracy. Overall, this work provides a lightweight, flexible, and scalable tactile sensing solution suitable for soft robotic structures where the sensing needs situating away from the contact interface. - oai:arXiv.org:2512.06524v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + DFALLM: Achieving Generalizable Multitask Deepfake Detection by Optimizing Audio LLM Components + https://arxiv.org/abs/2512.08403 + arXiv:2512.08403v1 Announce Type: new +Abstract: Audio deepfake detection has recently garnered public concern due to its implications for security and reliability. Traditional deep learning methods have been widely applied to this task but often lack generalisability when confronted with newly emerging spoofing techniques and more tasks such as spoof attribution recognition rather than simple binary classification. In principle, Large Language Models (LLMs) are considered to possess the needed generalisation capabilities. However, previous research on Audio LLMs (ALLMs) indicates a generalization bottleneck in audio deepfake detection performance, even when sufficient data is available. Consequently, this study investigates the model architecture and examines the effects of the primary components of ALLMs, namely the audio encoder and the text-based LLM. Our experiments demonstrate that the careful selection and combination of audio encoders and text-based LLMs are crucial for unlocking the deepfake detection potential of ALLMs. We further propose an ALLM structure capable of generalizing deepfake detection abilities to out-of-domain spoofing tests and other deepfake tasks, such as spoof positioning and spoof attribution recognition. Our proposed model architecture achieves state-of-the-art (SOTA) performance across multiple datasets, including ASVSpoof2019, InTheWild, and Demopage, with accuracy reaching up to 95.76% on average, and exhibits competitive capabilities in other deepfake detection tasks such as attribution, and localisation compared to SOTA audio understanding models. Data and codes are provided in supplementary materials. + oai:arXiv.org:2512.08403v1 + cs.SD + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Saekwang Nam, Bowen Deng, Loong Yi Lee, Jonathan M. Rossiter, Nathan F. Lepora + Yupei Li, Li Wang, Yuxiang Wang, Lei Wang, Rizhao Cai, Jie Shi, Bj\"orn W. Schuller, Zhizheng Wu - Code vs. Context: STEM Students' Resistance to Non-STEM Coursework - https://arxiv.org/abs/2512.06529 - arXiv:2512.06529v1 Announce Type: new -Abstract: Many STEM programs now require students to take non-technical courses to develop the soft skills necessary for professional practice, yet engineering students frequently resist this requirement. While prior research often attributes this resistance to heavy workloads, little is known about its cognitive and identity-related mechanisms. This study fills this knowledge gap by examining the effects of Cognitive Switching Costs, Work Overload, and Role Ambiguity on students' Affective Resistance to non-STEM coursework, as well as the subsequent impact on their Willingness to Engage and Long-Term Adoption of skills. We collected survey data from 212 undergraduate Computer Science and Engineering students and tested directional relationships using sequential OLS regression. Role Ambiguity emerged as the strongest predictor of Affective Resistance (beta of 0.47, p less than 0.001), exceeding the effects of Work Overload (beta of 0.20, p equals 0.007) and Cognitive Switching Cost (beta of 0.14, p equals 0.038). In turn, Affective Resistance significantly reduced Willingness to Engage (beta of -0.25, p less than 0.001), while Willingness to Engage served as a strong predictor of Long-Term Adoption (beta of 0.55, p less than 0.001). These results indicate that student resistance is driven primarily by the incongruence between non-technical content and students' emergent professional identities, rather than by cognitive effort or workload alone. To improve outcomes, curricula should focus on reducing role ambiguity by placing humanities and social science material in clear engineering contexts. - oai:arXiv.org:2512.06529v1 - cs.CY - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 + Are generative AI text annotations systematically biased? + https://arxiv.org/abs/2512.08404 + arXiv:2512.08404v1 Announce Type: new +Abstract: This paper investigates bias in GLLM annotations by conceptually replicating manual annotations of Boukes (2024). Using various GLLMs (Llama3.1:8b, Llama3.3:70b, GPT4o, Qwen2.5:72b) in combination with five different prompts for five concepts (political content, interactivity, rationality, incivility, and ideology). We find GLLMs perform adequate in terms of F1 scores, but differ from manual annotations in terms of prevalence, yield substantively different downstream results, and display systematic bias in that they overlap more with each other than with manual annotations. Differences in F1 scores fail to account for the degree of bias. + oai:arXiv.org:2512.08404v1 + cs.CL + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Md Abdullah Al Kafi, Raka Moni, Sumit Kumar Banshal + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Sjoerd B. Stolwijk, Mark Boukes, Damian Trilling - On The Role of K-Space Acquisition in MRI Reconstruction Domain-Generalization - https://arxiv.org/abs/2512.06530 - arXiv:2512.06530v1 Announce Type: new -Abstract: Recent work has established learned k-space acquisition patterns as a promising direction for improving reconstruction quality in accelerated Magnetic Resonance Imaging (MRI). Despite encouraging results, most existing research focuses on acquisition patterns optimized for a single dataset or modality, with limited consideration of their transferability across imaging domains. In this work, we demonstrate that the benefits of learned k-space sampling can extend beyond the training domain, enabling superior reconstruction performance under domain shifts. Our study presents two main contributions. First, through systematic evaluation across datasets and acquisition paradigms, we show that models trained with learned sampling patterns exhibitimproved generalization under cross-domain settings. Second, we propose a novel method that enhances domain robustness by introducing acquisition uncertainty during training-stochastically perturbing k-space trajectories to simulate variability across scanners and imaging conditions. Our results highlight the importance of treating kspace trajectory design not merely as an acceleration mechanism, but as an active degree of freedom for improving domain generalization in MRI reconstruction. - oai:arXiv.org:2512.06530v1 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Learning Robot Manipulation from Audio World Models + https://arxiv.org/abs/2512.08405 + arXiv:2512.08405v1 Announce Type: new +Abstract: World models have demonstrated impressive performance on robotic learning tasks. Many such tasks inherently demand multimodal reasoning; for example, filling a bottle with water will lead to visual information alone being ambiguous or incomplete, thereby requiring reasoning over the temporal evolution of audio, accounting for its underlying physical properties and pitch patterns. In this paper, we propose a generative latent flow matching model to anticipate future audio observations, enabling the system to reason about long-term consequences when integrated into a robot policy. We demonstrate the superior capabilities of our system through two manipulation tasks that require perceiving in-the-wild audio or music signals, compared to methods without future lookahead. We further emphasize that successful robot action learning for these tasks relies not merely on multi-modal input, but critically on the accurate prediction of future audio states that embody intrinsic rhythmic patterns. + oai:arXiv.org:2512.08405v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Mohammed Wattad, Tamir Shor, Alex Bronstein + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Fan Zhang, Michael Gienger - Novel Deep Learning Architectures for Classification and Segmentation of Brain Tumors from MRI Images - https://arxiv.org/abs/2512.06531 - arXiv:2512.06531v1 Announce Type: new -Abstract: Brain tumors pose a significant threat to human life, therefore it is very much necessary to detect them accurately in the early stages for better diagnosis and treatment. Brain tumors can be detected by the radiologist manually from the MRI scan images of the patients. However, the incidence of brain tumors has risen amongst children and adolescents in recent years, resulting in a substantial volume of data, as a result, it is time-consuming and difficult to detect manually. With the emergence of Artificial intelligence in the modern world and its vast application in the medical field, we can make an approach to the CAD (Computer Aided Diagnosis) system for the early detection of Brain tumors automatically. All the existing models for this task are not completely generalized and perform poorly on the validation data. So, we have proposed two novel Deep Learning Architectures - (a) SAETCN (Self-Attention Enhancement Tumor Classification Network) for the classification of different kinds of brain tumors. We have achieved an accuracy of 99.38% on the validation dataset making it one of the few Novel Deep learning-based architecture that is capable of detecting brain tumors accurately. We have trained the model on the dataset, which contains images of 3 types of tumors (glioma, meningioma, and pituitary tumors) and non-tumor cases. and (b) SAS-Net (Self-Attentive Segmentation Network) for the accurate segmentation of brain tumors. We have achieved an overall pixel accuracy of 99.23%. - oai:arXiv.org:2512.06531v1 + SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos + https://arxiv.org/abs/2512.08406 + arXiv:2512.08406v1 Announce Type: new +Abstract: Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent image-based HMR methods such as SAM 3D Body achieve strong robustness on in-the-wild images, they rely on per-frame inference when applied to videos, leading to temporal inconsistency and degraded performance under occlusions. We address these issues without extra training by leveraging the inherent human continuity in videos. We propose SAM-Body4D, a training-free framework for temporally consistent and occlusion-robust HMR from videos. We first generate identity-consistent masklets using a promptable video segmentation model, then refine them with an Occlusion-Aware module to recover missing regions. The refined masklets guide SAM 3D Body to produce consistent full-body mesh trajectories, while a padding-based parallel strategy enables efficient multi-human inference. Experimental results demonstrate that SAM-Body4D achieves improved temporal stability and robustness in challenging in-the-wild videos, without any retraining. Our code and demo are available at: https://github.com/gaomingqi/sam-body4d. + oai:arXiv.org:2512.08406v1 cs.CV - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sayan Das (IIIT Delhi), Arghadip Biswas (Jadavpur University) + Mingqi Gao, Yunqi Miao, Jungong Han - Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning - https://arxiv.org/abs/2512.06533 - arXiv:2512.06533v1 Announce Type: new -Abstract: Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical prediction. However, its progress is hindered by the misalignment between discrete token-level objectives (e.g., cross-entropy) and continuous numerical values. Existing approaches relying on token-level constraints often fail to capture the global magnitude of the target value, limiting their precision and generalization. In this paper, we propose to unlock the potential of decoding-based regression via Reinforcement Learning (RL). We formulate the generation process as a Markov Decision Process, utilizing sequence-level rewards to enforce global numerical coherence. Extensive experiments on tabular regression and code metric regression demonstrate that our method (specifically with ReMax and GRPO) consistently outperforms both state-of-the-art token-level baselines and traditional regression heads, showing the superiority of introducing sequence-level signals. Our analysis further reveals that RL significantly enhances sampling efficiency and predictive precision, establishing decoding-based regression as a robust and accurate paradigm for general-purpose numerical prediction. - oai:arXiv.org:2512.06533v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Towards Effective and Efficient Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval + https://arxiv.org/abs/2512.08410 + arXiv:2512.08410v1 Announce Type: new +Abstract: Due to excessive memory overhead, most Multimodal Large Language Models (MLLMs) can only process videos of limited frames. In this paper, we propose an effective and efficient paradigm to remedy this shortcoming, termed One-shot video-Clip based Retrieval AuGmentation (OneClip-RAG). Compared with existing video RAG methods, OneClip-RAG makes full use of the merits of video clips for augmented video understanding in terms of both knowledge integrity and semantic coherence. Besides, it is also equipped with a novel query-guided video chunking algorithm that can unify clip chunking and cross-modal retrieval in one processing step, avoiding redundant computations. To improve instruction following, we further propose a new dataset called SynLongVideo and design a progressive training regime for OneClip-RAG. OneClip-RAG is plugged into five recent MLLMs and validated on a set of long-video benchmarks. Experimental results not only show the obvious performance gains by OneClip-RAG over MLLMs, e.g., boosting InternLV2 8B and Qwen2-VL 7B to the level of GPT-4o on MLVU, but also show its superior efficiency in handling long videos. e.g., enabling LLaVA-Video understand up to an hour of videos in less than 2.2 minutes on a single 4090 GPU. + oai:arXiv.org:2512.08410v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ming Chen, Sheng Tang, Rong-Xi Tan, Ziniu Li, Jiacheng Chen, Ke Xue, Chao Qian + Tao Chen, Shaobo Ju, Qiong Wu, Chenxin Fang, Kun Zhang, Jun Peng, Hui Li, Yiyi Zhou, Rongrong Ji - "Having Confidence in My Confidence Intervals": How Data Users Engage with Privacy-Protected Wikipedia Data - https://arxiv.org/abs/2512.06534 - arXiv:2512.06534v1 Announce Type: new -Abstract: In response to calls for open data and growing privacy threats, organizations are increasingly adopting privacy-preserving techniques such as differential privacy (DP) that inject statistical noise when generating published datasets. These techniques are designed to protect privacy of data subjects while enabling useful analyses, but their reception by data users is under-explored. We developed documentation that presents the noise characteristics of two Wikipedia pageview datasets: one using rounding (heuristic privacy) and another using DP (formal privacy). After incorporating expert feedback (n=5), we used these documents to conduct a task-based contextual inquiry (n=15) exploring how data users--largely unfamiliar with these methods--perceive, interact with, and interpret privacy-preserving noise during data analysis. - Participants readily used simple uncertainty metrics from the documentation, but struggled when asked to compute confidence intervals across multiple noisy estimates. They were better able to devise simulation-based approaches for computing uncertainty with DP data compared to rounded data. Surprisingly, several participants incorrectly believed DP's stronger utility implied weaker privacy protections. Based on our findings, we offer design recommendations for documentation and tools to better support data users working with privacy-noised data. - oai:arXiv.org:2512.06534v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems + https://arxiv.org/abs/2512.08411 + arXiv:2512.08411v1 Announce Type: new +Abstract: Model-based planning in robotic domains is fundamentally challenged by the hybrid nature of physical dynamics, where continuous motion is punctuated by discrete events such as contacts and impacts. Conventional latent world models typically employ monolithic neural networks that enforce global continuity, inevitably over-smoothing the distinct dynamic modes (e.g., sticking vs. sliding, flight vs. stance). For a planner, this smoothing results in catastrophic compounding errors during long-horizon lookaheads, rendering the search process unreliable at physical boundaries. To address this, we introduce the Prismatic World Model (PRISM-WM), a structured architecture designed to decompose complex hybrid dynamics into composable primitives. PRISM-WM leverages a context-aware Mixture-of-Experts (MoE) framework where a gating mechanism implicitly identifies the current physical mode, and specialized experts predict the associated transition dynamics. We further introduce a latent orthogonalization objective to ensure expert diversity, effectively preventing mode collapse. By accurately modeling the sharp mode transitions in system dynamics, PRISM-WM significantly reduces rollout drift. Extensive experiments on challenging continuous control benchmarks, including high-dimensional humanoids and diverse multi-task settings, demonstrate that PRISM-WM provides a superior high-fidelity substrate for trajectory optimization algorithms (e.g., TD-MPC), proving its potential as a powerful foundational model for next-generation model-based agents. + oai:arXiv.org:2512.08411v1 + cs.AI + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Harold Triedman, Jayshree Sarathy, Priyanka Nanayakkara, Rachel Cummings, Gabriel Kaptchuk, Sean Kross, Elissa M. Redmiles + http://creativecommons.org/licenses/by/4.0/ + Mingwei Li, Xiaoyuan Zhang, Chengwei Yang, Zilong Zheng, Yaodong Yang - The E-Rocket: Low-cost Testbed for TVC Rocket GNC Validation - https://arxiv.org/abs/2512.06535 - arXiv:2512.06535v1 Announce Type: new -Abstract: This paper presents the E-Rocket, an electric-powered, low-cost rocket prototype for validation of Guidance, Navigation & Control (GNC) algorithms based on Thrust Vector Control (TVC). Relying on commercially available components and 3D printed parts, a pair of contra-rotating DC brushless motors is assembled on a servo-actuated gimbal mechanism that provides thrust vectoring capability. A custom avionics hardware and software stack is developed considering a dual computer setup which leverages the capabilities of the PX4 autopilot and the modularity of ROS 2 to accommodate for tailored GNC algorithms. The platform is validated in an indoor motion-capture arena using a baseline PID-based trajectory tracking controller. Results demonstrate accurate trajectory tracking and confirm the suitability of the E-Rocket as a versatile testbed for rocket GNC algorithms. - oai:arXiv.org:2512.06535v1 + Integration of AI-Driven CAD Systems in Designing Water and Power Transportation Infrastructure for Industrial and Remote Landscape Applications + https://arxiv.org/abs/2512.08415 + arXiv:2512.08415v1 Announce Type: new +Abstract: The integration of AI into CAD systems transforms how engineers plan and develop infrastructure projects involving water and power transportation across industrial and remote landscapes. This paper discusses how AI-driven CAD systems improve the efficient, effective, and sustainable design of infrastructure by embedding automation, predictive modeling, and real-time data analytics. This study examines how AI-supported toolsets can enhance design workflows, minimize human error, and optimize resource allocation for projects in underdeveloped environments. It also addresses technical and organizational challenges to AI adoption, including data silos, interoperability issues, and workforce adaptation. The findings demonstrate that AI-powered CAD enables faster project delivery, enhanced design precision, and increased resilience to environmental and logistical constraints. AI helps connect CAD, GIS, and IoT technologies to develop self-learning, adaptive design systems that are needed to meet the increasing global demand for sustainable infrastructure. + oai:arXiv.org:2512.08415v1 eess.SY cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pedro Santos, Andr\'e Fonte, Pedro Martins, Paulo Oliveira + http://creativecommons.org/licenses/by/4.0/ + Sunggyu Park - Approximate Multiplier Induced Error Propagation in Deep Neural Networks - https://arxiv.org/abs/2512.06537 - arXiv:2512.06537v1 Announce Type: new -Abstract: Deep Neural Networks (DNNs) rely heavily on dense arithmetic operations, motivating the use of Approximate Multipliers (AxMs) to reduce energy consumption in hardware accelerators. However, a rigorous mathematical characterization of how AxMs error distributions influence DNN accuracy remains underdeveloped. This work presents an analytical framework that connects the statistical error moments of an AxM to the induced distortion in General Matrix Multiplication (GEMM). Using the Frobenius norm of the resulting error matrix, we derive a closed form expression for practical DNN dimensions that demonstrates the distortion is predominantly governed by the multiplier mean error (bias). To evaluate this model in realistic settings, we incorporate controlled error injection into GEMM and convolution layers and examine its effect on ImageNet scale networks. The predicted distortion correlates strongly with the observed accuracy degradation, and an error configurable AxM case study implemented on an FPGA further confirms the analytical trends. By providing a lightweight alternative to behavioral or hardware level simulations, this framework enables rapid estimation of AxM impact on DNN inference quality. - oai:arXiv.org:2512.06537v1 - cs.AR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Improvement and Stabilization of Output Voltages in a Vertical Tidal Turbine Using Intelligent Control Strategies + https://arxiv.org/abs/2512.08416 + arXiv:2512.08416v1 Announce Type: new +Abstract: This article investigates on the improvement and stabilization of alternating current (AC) and direct current (DC) output voltages in a Permanent Magnet Synchronous Generator (PMSG) driven by a vertical-axis tidal turbine using advanced control strategies. The research integrates artificial intelligence (AI)-based techniques to enhance voltage stability and efficiency. Initially, the Maximum Power Point Tracking (MPPT) approach based on Tip Speed Ratio (TSR) and Artificial Neural Network (ANN) Fuzzy logic controllers is explored. To further optimize the performance, Particle Swarm Optimization (PSO) and a hybrid ANN-PSO methodology are implemented. These strategies aim to refine the reference rotational speed of the turbine while minimizing deviations from optimal power extraction conditions. The simulation results of a tidal turbine operating at a water flow velocity of 1.5 m/s demonstrate that the PSO-based control approach significantly enhances the voltage stability compared to conventional MPPT-TSR and ANN-Fuzzy controllers. The hybrid ANN-PSO technique improves the voltage regulation by dynamically adapting to system variations and providing real-time reference speed adjustments. This research highlights the AI-based hybrid optimization benefit to stabilize the output voltage of tidal energy systems, thereby increasing reliability and efficiency in renewable energy applications. + oai:arXiv.org:2512.08416v1 + cs.NI + eess.SP + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - A. M. H. H. Alahakoon, Hassaan Saadat, Darshana Jayasinghe, Sri Parameswaran + International Conference on Electrical and Computer Engineering Researches (ICECER 2025), Dec 2025, Antananarivo, Madagascar + Fanambinantsoa Philibert Andriniriniaimalaza (PIMENT), Nour Murad (PIMENT), Randriamaitso Telesphore (SPE), Bilal Habachi (SPE), Randriatefison Nirilalaina (NUIST), Manasina Ruffin (NUIST), Andrianirina Charles Bernard (NUIST), Ravelo Blaise (NUIST) - Comparing Knowledge: An Analysis of the Relative Epistemic Powers of Groups - https://arxiv.org/abs/2512.06542 - arXiv:2512.06542v1 Announce Type: new -Abstract: We use a novel type of epistemic logic, employing comparative knowledge assertions, to analyze the relative epistemic powers of individuals or groups of agents. Such comparative assertions can express that a group has the potential to (collectively) know everything that another group can know. Moreover, we look at comparisons involving various types of knowledge (fully introspective, positively introspective, etc.), satisfying the corresponding modal-epistemic conditions (e.g., $S5$, $S4$, $KT$). For each epistemic attitude, we are particularly interested in what agents or groups can know about their own epistemic position relative to that of others. - oai:arXiv.org:2512.06542v1 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs + https://arxiv.org/abs/2512.08417 + arXiv:2512.08417v1 Announce Type: new +Abstract: Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable to Indirect Prompt Injection (IPI) attacks, where instructions are injected via untrustworthy external data sources. This paper presents Rennervate, a defense framework to detect and prevent IPI attacks. Rennervate leverages attention features to detect the covert injection at a fine-grained token level, enabling precise sanitization that neutralizes IPI attacks while maintaining LLM functionalities. Specifically, the token-level detector is materialized with a 2-step attentive pooling mechanism, which aggregates attention heads and response tokens for IPI detection and sanitization. Moreover, we establish a fine-grained IPI dataset, FIPI, to be open-sourced to support further research. Extensive experiments verify that Rennervate outperforms 15 commercial and academic IPI defense methods, achieving high precision on 5 LLMs and 6 datasets. We also demonstrate that Rennervate is transferable to unseen attacks and robust against adaptive adversaries. + oai:arXiv.org:2512.08417v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Baltag Alexandru, Smets Sonja + Yinan Zhong, Qianhao Miao, Yanjiao Chen, Jiangyi Deng, Yushi Cheng, Wenyuan Xu - A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation - https://arxiv.org/abs/2512.06547 - arXiv:2512.06547v1 Announce Type: new -Abstract: Decoupled loss has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss improves coupled-loss style of algorithms' (e.g., PPO, GRPO) learning stability by introducing a proximal policy to decouple the off-policy corrections (importance weight) from the controlling policy updates (trust region). However, the proximal policy requires an extra forward pass through the network at each training step, creating a computational bottleneck for large language models. We observe that since the proximal policy only serves as a trust region anchor between the behavior and target policies, we can approximate it through simple interpolation without explicit computation. We call this approach A-3PO (APproximated Proximal Policy Optimization). A-3PO eliminates this overhead, reducing training time by 18% while maintaining comparable performance. Code & off-the-shelf example are available at: https://github.com/inclusionAI/AReaL/blob/main/docs/algorithms/prox_approx.md - oai:arXiv.org:2512.06547v1 - cs.LG - cs.AI - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 + Mechanical behaviour of brain-skull interface (meninges) under shear loading through experiment and finite element modelling: Preliminary results + https://arxiv.org/abs/2512.08425 + arXiv:2512.08425v1 Announce Type: new +Abstract: The brain-skull interface (meninges) plays a critical role in governing brain motion during head impacts, yet computational models often simplify this interface using idealized contact conditions due to limited experimental data. This study presents an improved protocol combining experimental testing and computational modelling to determine the mechanical properties of the brain-skull interface under shear loading. Brain tissue and brain-skull complex samples were extracted from sheep cadaver heads and subjected to shear loading. Magnetic resonance imaging (MRI) was used to obtain accurate 3D geometries of the samples, which were then used to create computational grids (meshes) for simulation of the experiments using finite element (FE) models to determine subject-specific properties of the brain tissue and brain-skull interface. A second-order Ogden hyperelastic model was used for the brain tissue, and a cohesive layer was employed to model the brain-skull interface. Our results indicate that a cohesive layer captures the force-displacement and damage initiation of the brain-skull interface. The calibrated cohesive properties showed consistent patterns across samples, with maximum normal tractions ranging from 2.8-3.4 kPa and maximum tangential tractions from 1.8-2.1 kPa. This framework provides a foundation for improving the biofidelity of computational head models used in injury prediction and neurosurgical planning by replacing arbitrary boundary conditions with formulations derived from experimental data on brain-skull interface (meninges) biomechanical behaviour. + oai:arXiv.org:2512.08425v1 + cs.CE + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Xiaocan Li, Shiliang Wu, Zheng Shen + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Sajjad Arzemanzadeh, Karol Miller, Tim Rosenow, Sjoerd B. Vos, Adam Wittek - BEACON: A Unified Behavioral-Tactical Framework for Explainable Cybercrime Analysis with Large Language Models - https://arxiv.org/abs/2512.06555 - arXiv:2512.06555v1 Announce Type: new -Abstract: Cybercrime increasingly exploits human cognitive biases in addition to technical vulnerabilities, yet most existing analytical frameworks focus primarily on operational aspects and overlook psychological manipulation. This paper proposes BEACON, a unified dual-dimension framework that integrates behavioral psychology with the tactical lifecycle of cybercrime to enable structured, interpretable, and scalable analysis of cybercrime. We formalize six psychologically grounded manipulation categories derived from Prospect Theory and Cialdini's principles of persuasion, alongside a fourteen-stage cybercrime tactical lifecycle spanning reconnaissance to final impact. A single large language model is fine-tuned using parameter-efficient learning to perform joint multi-label classification across both psychological and tactical dimensions while simultaneously generating human-interpretable explanations. Experiments conducted on a curated dataset of real-world and synthetically augmented cybercrime narratives demonstrate a 20 percent improvement in overall classification accuracy over the base model, along with substantial gains in reasoning quality measured using ROUGE and BERTScore. The proposed system enables automated decomposition of unstructured victim narratives into structured behavioral and operational intelligence, supporting improved cybercrime investigation, case linkage, and proactive scam detection. - oai:arXiv.org:2512.06555v1 - cs.CR - cs.AI - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + Mediating Personal Relationships with Robotic Pets for Fostering Human-Human Interaction of Older Adults + https://arxiv.org/abs/2512.08426 + arXiv:2512.08426v1 Announce Type: new +Abstract: Good human relationships are important for us to have a happy life and maintain our well-being. Otherwise, we will be at risk of experiencing loneliness or depression. In human-computer interaction (HCI) and computer-supported cooperative work (CSCW), robotic systems offer nuanced approaches to foster human connection, providing interaction beyond the traditional mediums that smartphones and computers offer. However, many existing studies primarily focus on the humanrobot relationships that older adults form directly with robotic pets rather than exploring how these robotic pets can enhance human-human relationships. Our ethnographic study investigates how robotic pets can be designed to facilitate human relationships. Through semi-structured interviews with six older adults and thematic analysis, our empirical findings provide insights into how robotic pets can be designed as telerobots to connect with others remotely, thus contributing to advance future development of robotic systems for mental health. + oai:arXiv.org:2512.08426v1 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Arush Sachdeva, Rajendraprasad Saravanan, Gargi Sarkar, Kavita Vemuri, Sandeep Kumar Shukla + http://creativecommons.org/licenses/by/4.0/ + Delong Du, Sara Gilda Amirhajlou, Akwasi Gyabaah, Richard Paluch, Claudia M\"uller - Securing the Model Context Protocol: Defending LLMs Against Tool Poisoning and Adversarial Attacks - https://arxiv.org/abs/2512.06556 - arXiv:2512.06556v1 Announce Type: new -Abstract: The Model Context Protocol (MCP) enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates a largely overlooked security gap. Existing defenses focus on prompt-injection attacks and fail to address threats embedded in tool metadata, leaving MCP-based systems exposed to semantic manipulation. This work analyzes three classes of semantic attacks on MCP-integrated systems: (1) Tool Poisoning, where adversarial instructions are hidden in tool descriptors; (2) Shadowing, where trusted tools are indirectly compromised through contaminated shared context; and (3) Rug Pulls, where descriptors are altered after approval to subvert behavior. To counter these threats, we introduce a layered security framework with three components: RSA-based manifest signing to enforce descriptor integrity, LLM-on-LLM semantic vetting to detect suspicious tool definitions, and lightweight heuristic guardrails that block anomalous tool behavior at runtime. Through evaluation of GPT-4, DeepSeek, and Llama-3.5 across eight prompting strategies, we find that security performance varies widely by model architecture and reasoning method. GPT-4 blocks about 71 percent of unsafe tool calls, balancing latency and safety. DeepSeek shows the highest resilience to Shadowing attacks but with greater latency, while Llama-3.5 is fastest but least robust. Our results show that the proposed framework reduces unsafe tool invocation rates without model fine-tuning or internal modification. - oai:arXiv.org:2512.06556v1 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking + https://arxiv.org/abs/2512.08430 + arXiv:2512.08430v1 Announce Type: new +Abstract: Accurately recovering 6D poses in densely packed industrial bin-picking environments remain a serious challenge, owing to occlusions, reflections, and textureless parts. We introduce a holistic depth-only 6D pose estimation approach that fuses multi-view depth maps into either a fine-grained 3D point cloud in its vanilla version, or a sparse Truncated Signed Distance Field (TSDF). At the core of our framework lies a staged heatmap mechanism that yields scene-adaptive attention priors across different resolutions, steering computation toward foreground regions, thus keeping memory requirements at high resolutions feasible. Along, we propose a density-aware sparse transformer block that dynamically attends to (self-) occlusions and the non-uniform distribution of 3D data. While sparse 3D approaches has proven effective for long-range perception, its potential in close-range robotic applications remains underexplored. Our framework operates fully sparse, enabling high-resolution volumetric representations to capture fine geometric details crucial for accurate pose estimation in clutter. Our method processes the entire scene integrally, predicting the 6D pose via a novel per-voxel voting strategy, allowing simultaneous pose predictions for an arbitrary number of target objects. We validate our method on the recently published IPD and MV-YCB multi-view datasets, demonstrating competitive performance in heavily cluttered industrial and household bin picking scenarios. + oai:arXiv.org:2512.08430v1 + cs.CV + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Saeid Jamshidi, Kawser Wazed Nafi, Arghavan Moradi Dakhel, Negar Shahabi, Foutse Khomh, Naser Ezzati-Jivan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Nico Leuze, Maximilian Hoh, Samed Do\u{g}an, Nicolas R. -Pe\~na, Alfred Schoettl - Characterizing Large-Scale Adversarial Activities Through Large-Scale Honey-Nets - https://arxiv.org/abs/2512.06557 - arXiv:2512.06557v1 Announce Type: new -Abstract: The increasing sophistication of cyber threats demands novel approaches to characterize adversarial strategies, particularly those targeting critical infrastructure and IoT ecosystems. This paper presents a longitudinal analysis of attacker behavior using HoneyTrap, an adaptive honeypot framework deployed across geographically distributed nodes to emulate vulnerable services and safely capture malicious traffic. Over a 24 day observation window, more than 60.3 million events were collected. To enable scalable analytics, raw JSON logs were transformed into Apache Parquet, achieving 5.8 - 9.3x compression and 7.2x faster queries, while ASN enrichment and salted SHA-256 pseudonymization added network intelligence and privacy preservation. - Our analysis reveals three key findings: (1) The majority of traffic targeted HTTP and HTTPS services (ports 80 and 443), with more than 8 million connection attempts and daily peaks exceeding 1.7 million events. (2) SSH (port 22) was frequently subject to brute-force attacks, with over 4.6 million attempts. (3) Less common services like Minecraft (25565) and SMB (445) were also targeted, with Minecraft receiving about 118,000 daily attempts that often coincided with spikes on other ports. - oai:arXiv.org:2512.06557v1 - cs.CR - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 + Beyond Wave Variables: A Data-Driven Ensemble Approach for Enhanced Teleoperation Transparency and Stability + https://arxiv.org/abs/2512.08436 + arXiv:2512.08436v1 Announce Type: new +Abstract: Time delays in communication channels present significant challenges for bilateral teleoperation systems, affecting both transparency and stability. Although traditional wave variable-based methods for a four-channel architecture ensure stability via passivity, they remain vulnerable to wave reflections and disturbances like variable delays and environmental noise. This article presents a data-driven hybrid framework that replaces the conventional wave-variable transform with an ensemble of three advanced sequence models, each optimized separately via the state-of-the-art Optuna optimizer, and combined through a stacking meta-learner. The base predictors include an LSTM augmented with Prophet for trend correction, an LSTM-based feature extractor paired with clustering and a random forest for improved regression, and a CNN-LSTM model for localized and long-term dynamics. Experimental validation was performed in Python using data generated from the baseline system implemented in MATLAB/Simulink. The results show that our optimized ensemble achieves a transparency comparable to the baseline wave-variable system under varying delays and noise, while ensuring stability through passivity constraints. + oai:arXiv.org:2512.08436v1 + eess.SY + cs.LG + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tonia Haikal, Eman Hammad, Shereen Ismail + Nour Mitiche, Farid Ferguene, Mourad Oussalah - Embodied Referring Expression Comprehension in Human-Robot Interaction - https://arxiv.org/abs/2512.06558 - arXiv:2512.06558v1 Announce Type: new -Abstract: As robots enter human workspaces, there is a crucial need for them to comprehend embodied human instructions, enabling intuitive and fluent human-robot interaction (HRI). However, accurate comprehension is challenging due to a lack of large-scale datasets that capture natural embodied interactions in diverse HRI settings. Existing datasets suffer from perspective bias, single-view collection, inadequate coverage of nonverbal gestures, and a predominant focus on indoor environments. To address these issues, we present the Refer360 dataset, a large-scale dataset of embodied verbal and nonverbal interactions collected across diverse viewpoints in both indoor and outdoor settings. Additionally, we introduce MuRes, a multimodal guided residual module designed to improve embodied referring expression comprehension. MuRes acts as an information bottleneck, extracting salient modality-specific signals and reinforcing them into pre-trained representations to form complementary features for downstream tasks. We conduct extensive experiments on four HRI datasets, including the Refer360 dataset, and demonstrate that current multimodal models fail to capture embodied interactions comprehensively; however, augmenting them with MuRes consistently improves performance. These findings establish Refer360 as a valuable benchmark and exhibit the potential of guided residual learning to advance embodied referring expression comprehension in robots operating within human environments. - oai:arXiv.org:2512.06558v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Time and Money Matters for Sustainability: Insights on User Preferences on Renewable Energy for Electric Vehicle Charging Stations + https://arxiv.org/abs/2512.08437 + arXiv:2512.08437v1 Announce Type: new +Abstract: Charging electric vehicles (EVs) with renewable energy can lessen their environmental impact. However, the fluctuating availability of renewable energy affects the sustainability of public EV charging stations. Nearby public charging stations may utilize differing energy sources due to their microgrid connections - ranging from exclusively renewable to non-renewable or a combination of both - highlighting the substantial variability in energy supply types within short distances. This study investigates the near-future scenario of integrating dynamic renewable energy availability in charging station navigation to impact the choices of EV users towards renewable sources. We conducted a within-subjects design survey with 50 car users and semi-structured interviews with 10 EV users from rural, suburban, and urban areas. The results show that when choosing EV charging stations, drivers often prioritize either time savings or money savings based on the driving scenarios that influence drivers' consumer value. Notably, EV users tend to select renewable-powered stations when they align with their main priority, be it saving money or time. This study offers end-user insights into the front-end graphic user interface and the development of the back-end ranking algorithm for navigation recommender systems that integrate dynamic renewable energy availability for the sustainable use of electric vehicles. + oai:arXiv.org:2512.08437v1 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Md Mofijul Islam, Alexi Gladstone, Sujan Sarker, Ganesh Nanduru, Md Fahim, Keyan Du, Aman Chadha, Tariq Iqbal + Delong Du, Apostolos Vavouris, Omid Veisi, Lu Jin, Gunnar Stevens, Lina Stankovic, Vladimir Stankovic, Alexander Boden - Tight Universal Bounds for Partially Presorted Pareto Front and Convex Hull - https://arxiv.org/abs/2512.06559 - arXiv:2512.06559v1 Announce Type: new -Abstract: TimSort is a well-established sorting algorithm whose running time depends on how sorted the input already is. Recently, Eppstein, Goodrich, Illickan, and To designed algorithms inspired by TimSort for Pareto front, planar convex hull, and two other problems. For each of these problems, they define a Range Partition Entropy; a function $H$ mapping lists $I$ that store $n$ points to a number between $0$ and $\log n$. Their algorithms have, for each list of points $I$, a running time of $O(n(1 + H(I)))$. - In this paper, we provide matching lower bounds for the Pareto front and convex hull algorithms by Eppstein, Goodrich, Illickan, and To. In particular, we show that their algorithm does not correspond to TimSort (or related stack-based MergeSort variants) but rather to a variant of QuickSort. From this, we derive an intuitive notion of universal optimality. We show comparison-based lower bounds that prove that the algorithms by Eppstein, Goodrich, Illickan and To are universally optimal under this notion of universal optimality. - oai:arXiv.org:2512.06559v1 - cs.CG - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 + LapFM: A Laparoscopic Segmentation Foundation Model via Hierarchical Concept Evolving Pre-training + https://arxiv.org/abs/2512.08439 + arXiv:2512.08439v1 Announce Type: new +Abstract: Surgical segmentation is pivotal for scene understanding yet remains hindered by annotation scarcity and semantic inconsistency across diverse procedures. Existing approaches typically fine-tune natural foundation models (e.g., SAM) with limited supervision, functioning merely as domain adapters rather than surgical foundation models. Consequently, they struggle to generalize across the vast variability of surgical targets. To bridge this gap, we present LapFM, a foundation model designed to evolve robust segmentation capabilities from massive unlabeled surgical images. Distinct from medical foundation models relying on inefficient self-supervised proxy tasks, LapFM leverages a Hierarchical Concept Evolving Pre-training paradigm. First, we establish a Laparoscopic Concept Hierarchy (LCH) via a hierarchical mask decoder with parent-child query embeddings, unifying diverse entities (i.e., Anatomy, Tissue, and Instrument) into a scalable knowledge structure with cross-granularity semantic consistency. Second, we propose a Confidence-driven Evolving Labeling that iteratively generates and filters pseudo-labels based on hierarchical consistency, progressively incorporating reliable samples from unlabeled images into training. This process yields LapBench-114K, a large-scale benchmark comprising 114K image-mask pairs. Extensive experiments demonstrate that LapFM significantly outperforms state-of-the-art methods, establishing new standards for granularity-adaptive generalization in universal laparoscopic segmentation. The source code is available at https://github.com/xq141839/LapFM. + oai:arXiv.org:2512.08439v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ivor van der Hoog, Eva Rotenberg, Daniel Rutschmann + Qing Xu, Kun Yuan, Yuxiang Luo, Yuhao Zhai, Wenting Duan, Nassir Navab, Zhen Chen - Bridging spatial awareness and global context in medical image segmentation - https://arxiv.org/abs/2512.06560 - arXiv:2512.06560v1 Announce Type: new -Abstract: Medical image segmentation is a fundamental task in computer-aided diagnosis, requiring models that balance segmentation accuracy and computational efficiency. However, existing segmentation models often struggle to effectively capture local and global contextual information, leading to boundary pixel loss and segmentation errors. In this paper, we propose U-CycleMLP, a novel U-shaped encoder-decoder network designed to enhance segmentation performance while maintaining a lightweight architecture. The encoder learns multiscale contextual features using position attention weight excitation blocks, dense atrous blocks, and downsampling operations, effectively capturing both local and global contextual information. The decoder reconstructs high-resolution segmentation masks through upsampling operations, dense atrous blocks, and feature fusion mechanisms, ensuring precise boundary delineation. To further refine segmentation predictions, channel CycleMLP blocks are incorporated into the decoder along the skip connections, enhancing feature integration while maintaining linear computational complexity relative to input size. Experimental results, both quantitative and qualitative, across three benchmark datasets demonstrate the competitive performance of U-CycleMLP in comparison with state-of-the-art methods, achieving better segmentation accuracy across all datasets, capturing fine-grained anatomical structures, and demonstrating robustness across different medical imaging modalities. Ablation studies further highlight the importance of the model's core architectural components in enhancing segmentation accuracy. - oai:arXiv.org:2512.06560v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models + https://arxiv.org/abs/2512.08440 + arXiv:2512.08440v1 Announce Type: new +Abstract: Interpretability can be implemented as a means to understand decisions taken by (black box) models, such as machine translation (MT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested problem in these models: gender bias. With this research, we aim to move away from simply measuring bias to exploring its origins. Working with gender-ambiguous natural source data, this study examines which context, in the form of input tokens in the source sentence, influences (or triggers) the translation model choice of a certain gender inflection in the target language. To analyse this, we use contrastive explanations and compute saliency attribution. We first address the challenge of a lacking scoring threshold and specifically examine different attribution levels of source words on the model gender decisions in the translation. We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution. Additionally, we provide a linguistic analysis of salient words. Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias. + oai:arXiv.org:2512.08440v1 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-nc-sa/4.0/ - Dalia Alzu'bi, A. Ben Hamza + Jani\c{c}a Hackenbuchner, Arda Tezcan, Joke Daems - SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities - https://arxiv.org/abs/2512.06562 - arXiv:2512.06562v1 Announce Type: new -Abstract: Recent advances in 3D-aware generative models have enabled high-fidelity image synthesis of human identities. However, this progress raises urgent questions around user consent and the ability to remove specific individuals from a model's output space. We address this by introducing SUGAR, a framework for scalable generative unlearning that enables the removal of many identities (simultaneously or sequentially) without retraining the entire model. Rather than projecting unwanted identities to unrealistic outputs or relying on static template faces, SUGAR learns a personalized surrogate latent for each identity, diverting reconstructions to visually coherent alternatives while preserving the model's quality and diversity. We further introduce a continual utility preservation objective that guards against degradation as more identities are forgotten. SUGAR achieves state-of-the-art performance in removing up to 200 identities, while delivering up to a 700% improvement in retention utility compared to existing baselines. Our code is publicly available at https://github.com/judydnguyen/SUGAR-Generative-Unlearn. - oai:arXiv.org:2512.06562v1 + Leveraging Multispectral Sensors for Color Correction in Mobile Cameras + https://arxiv.org/abs/2512.08441 + arXiv:2512.08441v1 Announce Type: new +Abstract: Recent advances in snapshot multispectral (MS) imaging have enabled compact, low-cost spectral sensors for consumer and mobile devices. By capturing richer spectral information than conventional RGB sensors, these systems can enhance key imaging tasks, including color correction. However, most existing methods treat the color correction pipeline in separate stages, often discarding MS data early in the process. We propose a unified, learning-based framework that (i) performs end-to-end color correction and (ii) jointly leverages data from a high-resolution RGB sensor and an auxiliary low-resolution MS sensor. Our approach integrates the full pipeline within a single model, producing coherent and color-accurate outputs. We demonstrate the flexibility and generality of our framework by refactoring two different state-of-the-art image-to-image architectures. To support training and evaluation, we construct a dedicated dataset by aggregating and repurposing publicly available spectral datasets, rendering under multiple RGB camera sensitivities. Extensive experiments show that our approach improves color accuracy and stability, reducing error by up to 50% compared to RGB-only and MS-driven baselines. Datasets, code, and models will be made available upon acceptance. + oai:arXiv.org:2512.08441v1 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Dung Thuy Nguyen, Quang Nguyen, Preston K. Robinette, Eli Jiang, Taylor T. Johnson, Kevin Leach + Luca Cogo, Marco Buzzelli, Simone Bianco, Javier Vazquez-Corral, Raimondo Schettini - Deep Manifold Part 2: Neural Network Mathematics - https://arxiv.org/abs/2512.06563 - arXiv:2512.06563v1 Announce Type: new -Abstract: This work develops the global equations of neural networks through stacked piecewise manifolds, fixed--point theory, and boundary--conditioned iteration. Once fixed coordinates and operators are removed, a neural network appears as a learnable numerical computation shaped by manifold complexity, high--order nonlinearity, and boundary conditions. Real--world data impose strong data complexity, near-infinite scope, scale, and minibatch fragmentation, while training dynamics produce learning complexity through shifting node covers, curvature accumulation, and the rise and decay of plasticity. These forces constrain learnability and explain why capability emerges only when fixed--point regions stabilize. Neural networks do not begin with fixed points; they construct them through residual--driven iteration. This perspective clarifies the limits of monolithic models under geometric and data--induced plasticity and motivates architectures and federated systems that distribute manifold complexity across many elastic models, forming a coherent world--modeling framework grounded in geometry, algebra, fixed points, and real--data complexity. - oai:arXiv.org:2512.06563v1 + Fully Decentralized Certified Unlearning + https://arxiv.org/abs/2512.08443 + arXiv:2512.08443v1 Announce Type: new +Abstract: Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated settings (via guarantees analogous to differential privacy, DP), the decentralized setting -- where peers communicate without a coordinator remains underexplored. We study certified unlearning in decentralized networks with fixed topologies and propose RR-DU, a random-walk procedure that performs one projected gradient ascent step on the forget set at the unlearning client and a geometrically distributed number of projected descent steps on the retained data elsewhere, combined with subsampled Gaussian noise and projection onto a trust region around the original model. We provide (i) convergence guarantees in the convex case and stationarity guarantees in the nonconvex case, (ii) $(\varepsilon,\delta)$ network-unlearning certificates on client views via subsampled Gaussian $R\'enyi$ DP (RDP) with segment-level subsampling, and (iii) deletion-capacity bounds that scale with the forget-to-local data ratio and quantify the effect of decentralization (network mixing and randomized subsampling) on the privacy--utility trade-off. Empirically, on image benchmarks (MNIST, CIFAR-10), RR-DU matches a given $(\varepsilon,\delta)$ while achieving higher test accuracy than decentralized DP baselines and reducing forget accuracy to random guessing ($\approx 10\%$). + oai:arXiv.org:2512.08443v1 cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Max Y. Ma, Gen-Hua Shi + Hithem Lamri, Michail Maniatakos - GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation - https://arxiv.org/abs/2512.06565 - arXiv:2512.06565v1 Announce Type: new -Abstract: We present GNC--Pose, a fully learning--free monocular 6D object pose estimation pipeline for textured objects that combines rendering--based initialization, geometry--aware correspondence weighting, and robust GNC optimization. Starting from coarse 2D--3D correspondences obtained through feature matching and rendering--based alignment, our method builds upon the Graduated Non--Convexity (GNC) principle and introduces a geometry--aware, cluster--based weighting mechanism that assigns robust per point confidence based on the 3D structural consistency of the model. This geometric prior and weighting strategy significantly stabilizes the optimization under severe outlier contamination. A final LM refinement further improve accuracy. We tested GNC--Pose on The YCB Object and Model Set, despite requiring no learned features, training data, or category-specific priors, GNC--Pose achieves competitive accuracy compared with both learning-based and learning--free methods, and offers a simple, robust, and practical solution for learning-free 6D pose estimation. - oai:arXiv.org:2512.06565v1 + Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts + https://arxiv.org/abs/2512.08445 + arXiv:2512.08445v1 Announce Type: new +Abstract: Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in in-distribution (ID) settings, their behavior under out-of-distribution (OOD) conditions remains poorly understood. Through extensive experiments across multiple ID-OOD sets, we find that reliability of the existing subset based methods degrades markedly, yielding redundant, unstable, and uncertainty-sensitive explanations. To address these shortcomings, we introduce a framework that combines submodular subset selection with layer-wise, gradient-based uncertainty estimation to improve robustness and fidelity without requiring additional training or auxiliary models. Our approach estimates uncertainty via adaptive weight perturbations and uses these estimates to guide submodular optimization, ensuring diverse and informative subset selection. Empirical evaluations show that, beyond mitigating the weaknesses of existing methods under OOD scenarios, our framework also yields improvements in ID settings. These findings highlight limitations of current subset-based approaches and demonstrate how uncertainty-driven optimization can enhance attribution and object-level interpretability, paving the way for more transparent and trustworthy AI in real-world vision applications. + oai:arXiv.org:2512.08445v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiujin Liu + http://creativecommons.org/licenses/by/4.0/ + Madhav Gupta, Vishak Prasad C, Ganesh Ramakrishnan - Generic visuality of war? How image-generative AI models (mis)represent Russia's war against Ukraine - https://arxiv.org/abs/2512.06570 - arXiv:2512.06570v1 Announce Type: new -Abstract: The rise of generative AI (genAI) can transform the representation of different aspects of social reality, including modern wars. While scholarship has largely focused on the military applications of AI, the growing adoption of genAI technologies may have major implications for how wars are portrayed, remembered, and interpreted. A few initial scholarly inquiries highlight the risks of genAI in this context, specifically regarding its potential to distort the representation of mass violence, particularly by sanitising and homogenising it. However, little is known about how genAI representation practices vary between different episodes of violence portrayed by Western and non-Western genAI models. Using the Russian aggression against Ukraine as a case study, we audit how two image-generative models, the US-based Midjourney and the Russia-based Kandinsky, represent both fictional and factual episodes of the war. We then analyse the models' responsiveness to the war-related prompts, together with the aesthetic and content-based aspects of the resulting images. Our findings highlight that contextual factors lead to variation in the representation of war, both between models and within the outputs of the same model. However, there are some consistent patterns of representation that may contribute to the homogenization of war aesthetics. - oai:arXiv.org:2512.06570v1 - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + From Accuracy to Impact: The Impact-Driven AI Framework (IDAIF) for Aligning Engineering Architecture with Theory of Change + https://arxiv.org/abs/2512.08449 + arXiv:2512.08449v1 Announce Type: new +Abstract: This paper introduces the Impact-Driven AI Framework (IDAIF), a novel architectural methodology that integrates Theory of Change (ToC) principles with modern artificial intelligence system design. As AI systems increasingly influence high-stakes domains including healthcare, finance, and public policy, the alignment problem--ensuring AI behavior corresponds with human values and intentions--has become critical. Current approaches predominantly optimize technical performance metrics while neglecting the sociotechnical dimensions of AI deployment. IDAIF addresses this gap by establishing a systematic mapping between ToC's five-stage model (Inputs-Activities-Outputs-Outcomes-Impact) and corresponding AI architectural layers (Data Layer-Pipeline Layer-Inference Layer-Agentic Layer-Normative Layer). Each layer incorporates rigorous theoretical foundations: multi-objective Pareto optimization for value alignment, hierarchical multi-agent orchestration for outcome achievement, causal directed acyclic graphs (DAGs) for hallucination mitigation, and adversarial debiasing with Reinforcement Learning from Human Feedback (RLHF) for fairness assurance. We provide formal mathematical formulations for each component and introduce an Assurance Layer that manages assumption failures through guardian architectures. Three case studies demonstrate IDAIF application across healthcare, cybersecurity, and software engineering domains. This framework represents a paradigm shift from model-centric to impact-centric AI development, providing engineers with concrete architectural patterns for building ethical, trustworthy, and socially beneficial AI systems. + oai:arXiv.org:2512.08449v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Mykola Makhortykh, Migl\.e Bareikyt\.e + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Yong-Woon Kim - Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input - https://arxiv.org/abs/2512.06571 - arXiv:2512.06571v1 Announce Type: new -Abstract: Learning fast and robust ball-kicking skills is a critical capability for humanoid soccer robots, yet it remains a challenging problem due to the need for rapid leg swings, postural stability on a single support foot, and robustness under noisy sensory input and external perturbations (e.g., opponents). This paper presents a reinforcement learning (RL)-based system that enables humanoid robots to execute robust continual ball-kicking with adaptability to different ball-goal configurations. The system extends a typical teacher-student training framework -- in which a "teacher" policy is trained with ground truth state information and the "student" learns to mimic it with noisy, imperfect sensing -- by including four training stages: (1) long-distance ball chasing (teacher); (2) directional kicking (teacher); (3) teacher policy distillation (student); and (4) student adaptation and refinement (student). Key design elements -- including tailored reward functions, realistic noise modeling, and online constrained RL for adaptation and refinement -- are critical for closing the sim-to-real gap and sustaining performance under perceptual uncertainty. Extensive evaluations in both simulation and on a real robot demonstrate strong kicking accuracy and goal-scoring success across diverse ball-goal configurations. Ablation studies further highlight the necessity of the constrained RL, noise modeling, and the adaptation stage. This work presents a system for learning robust continual humanoid ball-kicking under imperfect perception, establishing a benchmark task for visuomotor skill learning in humanoid whole-body control. - oai:arXiv.org:2512.06571v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Connectivity-Preserving Cortical Surface Tetrahedralization + https://arxiv.org/abs/2512.08450 + arXiv:2512.08450v1 Announce Type: new +Abstract: A prerequisite for many biomechanical simulation techniques is discretizing a bounded volume into a tetrahedral mesh. In certain contexts, such as cortical surface simulations, preserving input surface connectivity is critical. However, automated surface extraction often yields meshes containing self-intersections, small holes, and faulty geometry, which prevents existing constrained and unconstrained meshers from preserving this connectivity. We address this issue by developing a novel tetrahedralization method that maintains input surface connectivity in the presence of such defects. We also present a metric to quantify the preservation of surface connectivity and demonstrate that our method correctly maintains connectivity compared to existing solutions. + oai:arXiv.org:2512.08450v1 + cs.CG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Zifan Xu, Myoungkyu Seo, Dongmyeong Lee, Hao Fu, Jiaheng Hu, Jiaxun Cui, Yuqian Jiang, Zhihan Wang, Anastasiia Brund, Joydeep Biswas, Peter Stone + Besm Osman, Ruben Vink, Andrei Jalba, Maxime Chamberland - The Effect of Belief Boxes and Open-mindedness on Persuasion - https://arxiv.org/abs/2512.06573 - arXiv:2512.06573v1 Announce Type: new -Abstract: As multi-agent systems are increasingly utilized for reasoning and decision-making applications, there is a greater need for LLM-based agents to have something resembling propositional beliefs. One simple method for doing so is to include statements describing beliefs maintained in the prompt space (in what we'll call their belief boxes). But when agents have such statements in belief boxes, how does it actually affect their behaviors and dispositions towards those beliefs? And does it significantly affect agents' ability to be persuasive in multi-agent scenarios? Likewise, if the agents are given instructions to be open-minded, how does that affect their behaviors? We explore these and related questions in a series of experiments. Our findings confirm that instructing agents to be open-minded affects how amenable they are to belief change. We show that incorporating belief statements and their strengths influences an agent's resistance to (and persuasiveness against) opposing viewpoints. Furthermore, it affects the likelihood of belief change, particularly when the agent is outnumbered in a debate by opposing viewpoints, i.e., peer pressure scenarios. The results demonstrate the feasibility and validity of the belief box technique in reasoning and decision-making tasks. - oai:arXiv.org:2512.06573v1 + Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models II: Benchmark Generation Process + https://arxiv.org/abs/2512.08451 + arXiv:2512.08451v1 Announce Type: new +Abstract: The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public concern. Both model developers and policymakers seek to quantify and mitigate any risk, with an important element of such efforts being the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper, the second in a series of three, describes the second component of a novel Biothreat Benchmark Generation (BBG) framework: the generation of the Bacterial Biothreat Benchmark (B3) dataset. The development process involved three complementary approaches: 1) web-based prompt generation, 2) red teaming, and 3) mining existing benchmark corpora, to generate over 7,000 potential benchmarks linked to the Task-Query Architecture that was developed during the first component of the project. A process of de-duplication, followed by an assessment of uplift diagnosticity, and general quality control measures, reduced the candidates to a set of 1,010 final benchmarks. This procedure ensured that these benchmarks are a) diagnostic in terms of providing uplift; b) directly relevant to biosecurity threats; and c) are aligned with a larger biosecurity architecture permitting nuanced analysis at different levels of analysis. + oai:arXiv.org:2512.08451v1 + cs.LG cs.AI - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CY + cs.ET + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Gary Ackerman, Zachary Kallenborn, Anna Wetzel, Hayley Peterson, Jenna LaTourette, Olivia Shoemaker, Brandon Behlendorf, Sheriff Almakki, Doug Clifford, Noah Sheinbaum + + + MPC for tracking for anesthesia dynamics + https://arxiv.org/abs/2512.08452 + arXiv:2512.08452v1 Announce Type: new +Abstract: In this paper, an MPC for tracking formulation is proposed for the control of anesthesia dynamics. It seamlessly enables the optimization of the steady-states pair that is not unique due to the MISO nature of the model. Anesthesia dynamics is a multi-time scale system with two types of states characterized, respectively, by fast and slow dynamics. In anesthesia control, the output equation depends only on the fast dynamics. Therefore, the slow states can be treated as disturbances, and compensation terms can be introduced. Subsequently, the system can be reformulated as a nominal one allowing the design of an MPC for tracking strategy. The presented framework ensures recursive feasibility and asymptotic stability, through the design of appropriate terminal ingredients in the MPC for tracking framework. The controller performance is then assessed on a patient in a simulation environment. + oai:arXiv.org:2512.08452v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Onur Bilgin, Abdullah As Sami, Sriram Sai Vujjini, John Licato + Maxim Raymond, Kaouther Moussa, Mirko Fiacchini, Jimmy Lauber - General Computation using Slidable Tiles with Deterministic Global Forces - https://arxiv.org/abs/2512.06574 - arXiv:2512.06574v1 Announce Type: new -Abstract: We study the computational power of the Full-Tilt model of motion planning, where slidable polyominos are moved maximally around a board by way of a sequence of directional ``tilts.'' We focus on the deterministic scenario in which the tilts constitute a repeated clockwise rotation. We show that general-purpose computation is possible within this framework by providing a direct and efficient simulation of space-bounded Turing machines in which one computational step of the machine is simulated per $O(1)$ rotations. We further show that the initial tape of the machine can be programmed by an initial tilt-sequence preceding the rotations. This result immediately implies new PSPACE-completeness results for the well-studied problems of \emph{occupancy} (deciding if a given board location can be occupied by a tile), \emph{vacancy} (deciding if a location can be emptied), \emph{relocation} (deciding if a tile can be moved from one location to another), and \emph{reconfiguration} (can a given board configuration be reconfigured into a second given configuration) that hold even for deterministically repeating tilt cycles such as rotations. All of our PSPACE-completeness results hold even when there is only a single domino in the system beyond singleton tiles. Following, we show that these results work in the Single-Step tilt model for larger constant cycles. We then investigate computational efficiency by showing a modification to implement a two-tape Turing machine in the Full-Tilt model and Systolic Arrays in the Single-Step model. Finally, we show a cyclic implementation for tilt-efficient Threshold Circuits. - oai:arXiv.org:2512.06574v1 - cs.CG - Tue, 09 Dec 2025 00:00:00 -0500 + Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models III: Implementing the Bacterial Biothreat Benchmark (B3) Dataset + https://arxiv.org/abs/2512.08459 + arXiv:2512.08459v1 Announce Type: new +Abstract: The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism or access to biological weapons has generated significant policy, academic, and public concern. Both model developers and policymakers seek to quantify and mitigate any risk, with an important element of such efforts being the development of model benchmarks that can assess the biosecurity risk posed by a particular model. This paper discusses the pilot implementation of the Bacterial Biothreat Benchmark (B3) dataset. It is the third in a series of three papers describing an overall Biothreat Benchmark Generation (BBG) framework, with previous papers detailing the development of the B3 dataset. The pilot involved running the benchmarks through a sample frontier AI model, followed by human evaluation of model responses, and an applied risk analysis of the results along several dimensions. Overall, the pilot demonstrated that the B3 dataset offers a viable, nuanced method for rapidly assessing the biosecurity risk posed by a LLM, identifying the key sources of that risk and providing guidance for priority areas of mitigation priority. + oai:arXiv.org:2512.08459v1 + cs.LG + cs.AI + cs.CY + cs.ET + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Alberto Avila-Jimenez, David Barreda, Sarah-Laurie Evans, Austin Luchsinger, Aiden Massie, Robert Schweller, Evan Tomai, Tim Wylie + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Gary Ackerman, Theodore Wilson, Zachary Kallenborn, Olivia Shoemaker, Anna Wetzel, Hayley Peterson, Abigail Danfora, Jenna LaTourette, Brandon Behlendorf, Douglas Clifford - Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules - https://arxiv.org/abs/2512.06575 - arXiv:2512.06575v1 Announce Type: new -Abstract: This study presents a validation and extension of a recent methodological framework for medical image classification. While an improved ConvNeXt Tiny architecture, integrating Global Average and Max Pooling fusion (GAGM), lightweight channel attention (SEVector), and Feature Smoothing Loss (FSL), demonstrated promising results on Alzheimer MRI under CPU friendly conditions, our work investigates its transposability to mammography classification. Using a Kaggle dataset that consolidates INbreast, MIAS, and DDSM mammography collections, we compare a baseline CNN, ConvNeXt Tiny, and InceptionV3 backbones enriched with GAGM and SEVector modules. Results confirm the effectiveness of GAGM and SEVector in enhancing feature discriminability and reducing false negatives, particularly for malignant cases. In our experiments, however, the Feature Smoothing Loss did not yield measurable improvements under mammography classification conditions, suggesting that its effectiveness may depend on specific architectural and computational assumptions. Beyond validation, our contribution extends the original framework through multi metric evaluation (macro F1, per class recall variance, ROC/AUC), feature interpretability analysis (Grad CAM), and the development of an interactive dashboard for clinical exploration. As a perspective, we highlight the need to explore alternative approaches to improve intra class compactness and inter class separability, with the specific goal of enhancing the distinction between malignant and benign cases in mammography classification. - oai:arXiv.org:2512.06575v1 - cs.CV + Measuring Agile Agreement: Development and Validation of the Manifesto and Principle Scales + https://arxiv.org/abs/2512.08461 + arXiv:2512.08461v1 Announce Type: new +Abstract: While the importance of human factors in agile software development is widely acknowledged, the measurement of an individual's "agile agreement" remains an ill-defined and challenging area. A key limitation in existing research is the failure to distinguish between agreement with the abstract, high-level values of the Agile Manifesto and agreement with the concrete, day-to-day practices derived from the 12 Principles. This paper addresses this methodological gap by presenting the design and validation of two distinct instruments: the novel Manifesto Agreement Scale (MAS), and the Principle Agreement Scale (PAS), which is a systematic adaptation and refinement of a prior instrument. + We detail the systematic process of item creation and selection, survey design, and validation. The results demonstrate that both scales possess important internal consistency and construct validity. A convergence and divergence analysis, including Proportional Odds Logistic Regression, a Bland-Altman plot, and an Intraclass Correlation Coefficient (ICC), reveals that while the two scales are moderately correlated, they are not interchangeable and capture distinct dimensions of agile agreement. The primary contribution of this work is a pair of publicly available instruments, validated within a specific demographic of Belgian IT professionals. These scales represent a critical initial step toward facilitating a more nuanced measurement of agile agreement, distinguishing agile agreement across various levels of perception and aiding in a more refined interpretation of person-agile fit. + oai:arXiv.org:2512.08461v1 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Nicolas Matton, Anthony Simonofski, Marie-Ange Remiche, Beno\^it Vanderose + + + Transformers for Multimodal Brain State Decoding: Integrating Functional Magnetic Resonance Imaging Data and Medical Metadata + https://arxiv.org/abs/2512.08462 + arXiv:2512.08462v1 Announce Type: new +Abstract: Decoding brain states from functional magnetic resonance imaging (fMRI) data is vital for advancing neuroscience and clinical applications. While traditional machine learning and deep learning approaches have made strides in leveraging the high-dimensional and complex nature of fMRI data, they often fail to utilize the contextual richness provided by Digital Imaging and Communications in Medicine (DICOM) metadata. This paper presents a novel framework integrating transformer-based architectures with multimodal inputs, including fMRI data and DICOM metadata. By employing attention mechanisms, the proposed method captures intricate spatial-temporal patterns and contextual relationships, enhancing model accuracy, interpretability, and robustness. The potential of this framework spans applications in clinical diagnostics, cognitive neuroscience, and personalized medicine. Limitations, such as metadata variability and computational demands, are addressed, and future directions for optimizing scalability and generalizability are discussed. + oai:arXiv.org:2512.08462v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Danial Jafarzadeh Jazi, Maryam Hajiesmaeili + + + Using reinforcement learning to probe the role of feedback in skill acquisition + https://arxiv.org/abs/2512.08463 + arXiv:2512.08463v1 Announce Type: new +Abstract: Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of skill acquisition under fully controlled conditions, we bypass human subjects. Instead, we directly interface a generalist reinforcement learning agent with a spinning cylinder in a tabletop circulating water channel to maximize or minimize drag. This setup has several desirable properties. First, it is a physical system, with the rich interactions and complex dynamics that only the physical world has: the flow is highly chaotic and extremely difficult, if not impossible, to model or simulate accurately. Second, the objective -- drag minimization or maximization -- is easy to state and can be captured directly in the reward, yet good strategies are not obvious beforehand. Third, decades-old experimental studies provide recipes for simple, high-performance open-loop policies. Finally, the setup is inexpensive and far easier to reproduce than human studies. In our experiments we find that high-dimensional flow feedback lets the agent discover high-performance drag-control strategies with only minutes of real-world interaction. When we later replay the same action sequences without any feedback, we obtain almost identical performance. This shows that feedback, and in particular flow feedback, is not needed to execute the learned policy. Surprisingly, without flow feedback during training the agent fails to discover any well-performing policy in drag maximization, but still succeeds in drag minimization, albeit more slowly and less reliably. Our studies show that learning a high-performance skill can require richer information than executing it, and learning conditions can be kind or wicked depending solely on the goal, not on dynamics or policy complexity. + oai:arXiv.org:2512.08463v1 + cs.AI cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Fariza Dahes + Antonio Terpin, Raffaello D'Andrea - Deep Neural Network-Based Aerial Transport in the Presence of Cooperative and Uncooperative UAS - https://arxiv.org/abs/2512.06577 - arXiv:2512.06577v1 Announce Type: new -Abstract: We present a resilient deep neural network (DNN) framework for decentralized transport and coverage using uncrewed aerial systems (UAS) operating in $\mathbb{R}^n$. The proposed DNN-based mass-transport architecture constructs a layered inter-UAS communication graph from an initial formation, assigns time-varying communication weights through a forward scheduling mechanism that guides the team from the initial to the final configuration, and ensures stability and convergence of the resulting multi-agent transport dynamics. The framework is explicitly designed to remain robust in the presence of uncooperative agents that deviate from or refuse to follow the prescribed protocol. Our method preserves a fixed feed-forward topology but dynamically prunes edges to uncooperative agents, maintains convex, feedforward mentoring among cooperative agents, and computes global desired set points through a sparse linear relation consistent with leader references. The target set is abstracted by $N$ points that become final desired positions, enabling coverage-optimal transport while keeping computation low and guarantees intact. Extensive simulations demonstrate that, under full cooperation, all agents converge rapidly to the target zone with a 10\% boundary margin and under partial cooperation with uncooperative agents, the system maintains high convergence among cooperative agents with performance degradation localized near the disruptions, evidencing graceful resilience and scalability. These results confirm that forward-weight scheduling, hierarchical mentor--mentee coordination, and on-the-fly DNN restructuring yield robust, provably stable UAS transport in realistic fault scenarios. - oai:arXiv.org:2512.06577v1 + Quantization and Security Parameter Design for Overflow-Free Confidential FRIT + https://arxiv.org/abs/2512.08464 + arXiv:2512.08464v1 Announce Type: new +Abstract: This study proposes a systematic design procedure for determining the quantization gain and the security parameter in the Confidential Fictitious Reference Iterative Tuning (CFRIT), enabling overflow-free and accuracy-guaranteed encrypted controller tuning. Within an encrypted data-driven gain tuning, the range of quantization errors induced during the encoding (encryption) process can be estimated from operational data. Based on this insight, explicit analytical conditions on the quantization gain and the security parameter are derived to prevent overflow in computing over encrypted data. Furthermore, the analysis reveals a quantitative relationship between quantization-induced errors and the deviation between the gains obtained by CFRIT and non-confidential Fictitious Reference Iterative Tuning (FRIT), clarifying how parameter choice affects tuning accuracy. A numerical example verifies the proposed procedure by demonstrating that the designed parameters achieve accurate encrypted tuning within a prescribed tolerance while preventing overflow. In addition, the admissible region of parameter combinations is visualized to examine the characteristics of feasible and infeasible regions, providing practical insights into parameter design for encrypted data-driven control. + oai:arXiv.org:2512.08464v1 eess.SY - cs.RO cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Jungjin Park, Osamu Kaneko, Kiminao Kogiso + + + High-performance computing enabled contingency analysis for modern power networks + https://arxiv.org/abs/2512.08465 + arXiv:2512.08465v1 Announce Type: new +Abstract: Modern power networks face increasing vulnerability to cascading failures due to high complexity and the growing penetration of intermittent resources, necessitating rigorous security assessment beyond the conventional $N-1$ criterion. Current approaches often struggle to achieve the computational tractability required for exhaustive $N-2$ contingency analysis integrated with complex stability evaluations like small-signal stability. Addressing this computational bottleneck and the limitations of deterministic screening, this paper presents a scalable methodology for the vulnerability assessment of modern power networks, integrating $N-2$ contingency analysis with small-signal stability evaluation. To prioritize critical components, we propose a probabilistic \textbf{Risk Index ($R_i$)} that weights the deterministic \textit{severity} of a contingency (including optimal power flow divergence, islanding, and oscillatory instability) by the \textit{failure frequency} of the involved elements based on reliability data. The proposed framework is implemented using High-Performance Computing (HPC) techniques through the PyCOMPSs parallel programming library, orchestrating optimal power flow simulations (VeraGrid) and small-signal analysis (STAMP) to enable the exhaustive exploration of massive contingency sets. The methodology is validated on the IEEE 118-bus test system, processing more than \num{57000} scenarios to identify components prone to triggering cascading failures. Results demonstrate that the risk-based approach effectively isolates critical assets that deterministic $N-1$ criteria often overlook. This work establishes a replicable and efficient workflow for probabilistic security assessment, suitable for large-scale networks and capable of supporting operator decision-making in near real-time environments. + oai:arXiv.org:2512.08465v1 + eess.SY + cs.PF + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Alexandre Gracia-Calvo, Francesca Rossi, Eduardo Iraola, Juan Carlos Olives-Camps, Eduardo Prieto-Araujo + + + Team-Aware Football Player Tracking with SAM: An Appearance-Based Approach to Occlusion Recovery + https://arxiv.org/abs/2512.08467 + arXiv:2512.08467v1 Announce Type: new +Abstract: Football player tracking is challenged by frequent occlusions, similar appearances, and rapid motion in crowded scenes. This paper presents a lightweight SAM-based tracking method combining the Segment Anything Model (SAM) with CSRT trackers and jersey color-based appearance models. We propose a team-aware tracking system that uses SAM for precise initialization and HSV histogram-based re-identification to improve occlusion recovery. Our evaluation measures three dimensions: processing speed (FPS and memory), tracking accuracy (success rate and box stability), and robustness (occlusion recovery and identity consistency). Experiments on football video sequences show that the approach achieves 7.6-7.7 FPS with stable memory usage (~1880 MB), maintaining 100 percent tracking success in light occlusions and 90 percent in crowded penalty-box scenarios with 5 or more players. Appearance-based re-identification recovers 50 percent of heavy occlusions, demonstrating the value of domain-specific cues. Analysis reveals key trade-offs: the SAM + CSRT combination provides consistent performance across crowd densities but struggles with long-term occlusions where players leave the frame, achieving only 8.66 percent re-acquisition success. These results offer practical guidelines for deploying football tracking systems under resource constraints, showing that classical tracker-based methods work well with continuous visibility but require stronger re-identification mechanisms for extended absences. + oai:arXiv.org:2512.08467v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Chamath Ranasinghe, Uthayasanker Thayasivam + + + Measuring Computer Science Enthusiasm: A Questionnaire-Based Analysis of Age and Gender Effects on Students' Interest + https://arxiv.org/abs/2512.08472 + arXiv:2512.08472v1 Announce Type: new +Abstract: This study offers new insights into students' interest in computer science (CS) education by disentangling the distinct effects of age and gender across a diverse adolescent sample. Grounded in the person-object theory of interest (POI), we conceptualize enthusiasm as a short-term, activating expression of interest that combines positive affect, perceived relevance, and intention to re-engage. Experiencing such enthusiasm can temporarily shift CS attitudes and strengthen future engagement intentions, making it a valuable lens for evaluating brief outreach activities. To capture these dynamics, we developed a theoretically grounded questionnaire for pre-post assessment of the enthusiasm potential of CS interventions. Using data from more than 400 students participating in online CS courses, we examined age- and gender-related patterns in enthusiasm. The findings challenge the prevailing belief that early exposure is the primary pathway to sustained interest in CS. Instead, we identify a marked decline in enthusiasm during early adolescence, particularly among girls, alongside substantial variability in interest trajectories across age groups. Crucially, our analyses reveal that age is a more decisive factor than gender in shaping interest development and uncover key developmental breakpoints. Despite starting with lower baseline attitudes, older students showed the largest positive changes following the intervention, suggesting that well-designed short activities can effectively re-activate interest even at later ages. Overall, the study highlights the need for a dynamic, age-sensitive framework for CS education in which instructional strategies are aligned with developmental trajectories. + oai:arXiv.org:2512.08472v1 + cs.SE + cs.CY + econ.GN + q-fin.EC + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Kai Marquardt, Robert Hanak, Anne Koziolek, Lucia Happe + + + Solving Over-Smoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability + https://arxiv.org/abs/2512.08475 + arXiv:2512.08475v1 Announce Type: new +Abstract: The relationship between Layer Normalization (LN) placement and the over-smoothing phenomenon remains underexplored. We identify a critical dilemma: Pre-LN architectures avoid over-smoothing but suffer from the curse of depth, while Post-LN architectures bypass the curse of depth but experience over-smoothing. + To resolve this, we propose a new method based on Post-LN that induces algebraic smoothing, preventing over-smoothing without the curse of depth. Empirical results across five benchmarks demonstrate that our approach supports deeper networks (up to 256 layers) and improves performance, requiring no additional parameters. + Key contributions: + Theoretical Characterization: Analysis of LN dynamics and their impact on over-smoothing and the curse of depth. + A Principled Solution: A parameter-efficient method that induces algebraic smoothing and avoids over-smoothing and the curse of depth. + Empirical Validation: Extensive experiments showing the effectiveness of the method in deeper GNNs. + oai:arXiv.org:2512.08475v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Muhammad Junayed Hasan Zahed, Hossein Rastgoftar + Weiqi Guan, Junlin He - Error-Centric PID Untrained Neural-Net (EC-PIDUNN) For Nonlinear Robotics Control - https://arxiv.org/abs/2512.06578 - arXiv:2512.06578v1 Announce Type: new -Abstract: Classical Proportional-Integral-Derivative (PID) control has been widely successful across various industrial systems such as chemical processes, robotics, and power systems. However, as these systems evolved, the increase in the nonlinear dynamics and the complexity of interconnected variables have posed challenges that classical PID cannot effectively handle, often leading to instability, overshooting, or prolonged settling times. Researchers have proposed PIDNN models that combine the function approximation capabilities of neural networks with PID control to tackle these nonlinear challenges. However, these models require extensive, highly refined training data and have significant computational costs, making them less favorable for real-world applications. In this paper, We propose a novel EC-PIDUNN architecture, which integrates an untrained neural network with an improved PID controller, incorporating a stabilizing factor (\(\tau\)) to generate the control signal. Like classical PID, our architecture uses the steady-state error \(e_t\) as input bypassing the need for explicit knowledge of the systems dynamics. By forming an input vector from \(e_t\) within the neural network, we increase the dimensionality of input allowing for richer data representation. Additionally, we introduce a vector of parameters \( \rho_t \) to shape the output trajectory and a \textit{dynamic compute} function to adjust the PID coefficients from predefined values. We validate the effectiveness of EC-PIDUNN on multiple nonlinear robotics applications: (1) nonlinear unmanned ground vehicle systems that represent the Ackermann steering mechanism and kinematics control, (2) Pan-Tilt movement system. In both tests, it outperforms classical PID in convergence and stability achieving a nearly critically damped response. - oai:arXiv.org:2512.06578v1 + A Multi-Agent LLM Framework for Design Space Exploration in Autonomous Driving Systems + https://arxiv.org/abs/2512.08476 + arXiv:2512.08476v1 Announce Type: new +Abstract: Designing autonomous driving systems requires efficient exploration of large hardware/software configuration spaces under diverse environmental conditions, e.g., with varying traffic, weather, and road layouts. Traditional design space exploration (DSE) approaches struggle with multi-modal execution outputs and complex performance trade-offs, and often require human involvement to assess correctness based on execution outputs. This paper presents a multi-agent, large language model (LLM)-based DSE framework, which integrates multi-modal reasoning with 3D simulation and profiling tools to automate the interpretation of execution outputs and guide the exploration of system designs. Specialized LLM agents are leveraged to handle user input interpretation, design point generation, execution orchestration, and analysis of both visual and textual execution outputs, which enables identification of potential bottlenecks without human intervention. A prototype implementation is developed and evaluated on a robotaxi case study (an SAE Level 4 autonomous driving application). Compared with a genetic algorithm baseline, the proposed framework identifies more Pareto-optimal, cost-efficient solutions with reduced navigation time under the same exploration budget. Experimental results also demonstrate the efficiency of the adoption of the LLM-based approach for DSE. We believe that this framework paves the way to the design automation of autonomous driving systems. + oai:arXiv.org:2512.08476v1 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Waleed Razzaq + Po-An Shih, Shao-Hua Wang, Yung-Che Li, Chia-Heng Tu, Chih-Han Chang - MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding - https://arxiv.org/abs/2512.06581 - arXiv:2512.06581v1 Announce Type: new -Abstract: Large vision-language models struggle with medical video understanding, where spatial precision, temporal reasoning, and clinical semantics are critical. To address this, we first introduce \textbf{MedVidBench}, a large-scale benchmark of 531,850 video-instruction pairs across 8 medical sources spanning video, segment, and frame-level tasks, curated through a rigorous quality assurance pipeline with expert-guided prompting and dual-model validation. While supervised fine-tuning on MedVidBench yields noticeable gains, standard Reinforcement Learning (RL) fails due to imbalanced reward scales across datasets, which destabilizes optimization and leads to training collapse. To overcome this, we introduce \textbf{MedGRPO}, a novel RL framework for balanced multi-dataset training with two key innovations: (1) \emph{cross-dataset reward normalization} that maps each dataset's median performance to a common reward value, ensuring fair optimization regardless of difficulty, and (2) a \emph{medical LLM judge} that evaluates caption quality on five clinical dimensions through comparative similarity scoring. Supervised fine-tuning Qwen2.5-VL-7B on MedVidBench substantially outperforms GPT-4.1 and Gemini-2.5-Flash across all tasks, demonstrating MedVidBench's efficacy, while our MedGRPO framework further improves upon the SFT baseline across grounding and captioning tasks. Our work establishes a foundational benchmark and robust training methodology for advancing vision-language models in medical domains. Our project website is available at https://yuhaosu.github.io/MedGRPO/. - oai:arXiv.org:2512.06581v1 + ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Consistent Attention + https://arxiv.org/abs/2512.08477 + arXiv:2512.08477v1 Announce Type: new +Abstract: Drag-based image editing aims to modify visual content followed by user-specified drag operations. Despite existing methods having made notable progress, they still fail to fully exploit the contextual information in the reference image, including fine-grained texture details, leading to edits with limited coherence and fidelity. To address this challenge, we introduce ContextDrag, a new paradigm for drag-based editing that leverages the strong contextual modeling capability of editing models, such as FLUX-Kontext. By incorporating VAE-encoded features from the reference image, ContextDrag can leverage rich contextual cues and preserve fine-grained details, without the need for finetuning or inversion. Specifically, ContextDrag introduced a novel Context-preserving Token Injection (CTI) that injects noise-free reference features into their correct destination locations via a Latent-space Reverse Mapping (LRM) algorithm. This strategy enables precise drag control while preserving consistency in both semantics and texture details. Second, ContextDrag adopts a novel Position-Consistent Attention (PCA), which positional re-encodes the reference tokens and applies overlap-aware masking to eliminate interference from irrelevant reference features. Extensive experiments on DragBench-SR and DragBench-DR demonstrate that our approach surpasses all existing SOTA methods. Code will be publicly available. + oai:arXiv.org:2512.08477v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuhao Su, Anwesa Choudhuri, Zhongpai Gao, Benjamin Planche, Van Nguyen Nguyen, Meng Zheng, Yuhan Shen, Arun Innanje, Terrence Chen, Ehsan Elhamifar, Ziyan Wu + Huiguo He, Pengyu Yan, Ziqi Yi, Weizhi Zhong, Zheng Liu, Yejun Tang, Huan Yang, Kun Gai, Guanbin Li, Lianwen Jin - QL-LSTM: A Parameter-Efficient LSTM for Stable Long-Sequence Modeling - https://arxiv.org/abs/2512.06582 - arXiv:2512.06582v1 Announce Type: new -Abstract: Recurrent neural architectures such as LSTM and GRU remain widely used in sequence modeling, but they continue to face two core limitations: redundant gate-specific parameters and reduced ability to retain information across long temporal distances. This paper introduces the Quantum-Leap LSTM (QL-LSTM), a recurrent architecture designed to address both challenges through two independent components. The Parameter-Shared Unified Gating mechanism replaces all gate-specific transformations with a single shared weight matrix, reducing parameters by approximately 48 percent while preserving full gating behavior. The Hierarchical Gated Recurrence with Additive Skip Connections component adds a multiplication-free pathway that improves long-range information flow and reduces forget-gate degradation. We evaluate QL-LSTM on sentiment classification using the IMDB dataset with extended document lengths, comparing it to LSTM, GRU, and BiLSTM reference models. QL-LSTM achieves competitive accuracy while using substantially fewer parameters. Although the PSUG and HGR-ASC components are more efficient per time step, the current prototype remains limited by the inherent sequential nature of recurrent models and therefore does not yet yield wall-clock speed improvements without further kernel-level optimization. - oai:arXiv.org:2512.06582v1 - cs.LG + Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform + https://arxiv.org/abs/2512.08478 + arXiv:2512.08478v1 Announce Type: new +Abstract: Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fragmented, heavy, or constrained by legacy pipelines, resulting in high deployment friction and limited support for dynamic content and generative models. In this work, we present Visionary, an open, web-native platform for real-time various Gaussian Splatting and meshes rendering. Built on an efficient WebGPU renderer with per-frame ONNX inference, Visionary enables dynamic neural processing while maintaining a lightweight, "click-to-run" browser experience. It introduces a standardized Gaussian Generator contract, which not only supports standard 3DGS rendering but also allows plug-and-play algorithms to generate or update Gaussians each frame. Such inference also enables us to apply feedforward generative post-processing. The platform further offers a plug in three.js library with a concise TypeScript API for seamless integration into existing web applications. Experiments show that, under identical 3DGS assets, Visionary achieves superior rendering efficiency compared to current Web viewers due to GPU-based primitive sorting. It already supports multiple variants, including MLP-based 3DGS, 4DGS, neural avatars, and style transformation or enhancement networks. By unifying inference and rendering directly in the browser, Visionary significantly lowers the barrier to reproduction, comparison, and deployment of 3DGS-family methods, serving as a unified World Model Carrier for both reconstructive and generative paradigms. + oai:arXiv.org:2512.08478v1 + cs.CV cs.AI - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 + cs.GR + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Isaac Kofi Nti + Yuning Gong, Yifei Liu, Yifan Zhan, Muyao Niu, Xueying Li, Yuanjun Liao, Jiaming Chen, Yuanyuan Gao, Jiaqi Chen, Minming Chen, Li Zhou, Yuning Zhang, Wei Wang, Xiaoqing Hou, Huaxi Huang, Shixiang Tang, Le Ma, Dingwen Zhang, Xue Yang, Junchi Yan, Yanchi Zhang, Yinqiang Zheng, Xiao Sun, Zhihang Zhong - The Communication Complexity of Combinatorial Auctions with Additional Succinct Bidders - https://arxiv.org/abs/2512.06585 - arXiv:2512.06585v1 Announce Type: new -Abstract: We study the communication complexity of welfare maximization in combinatorial auctions with bidders from either a standard valuation class (which require exponential communication to explicitly state, such as subadditive or XOS), or arbitrary succinct valuations (which can be fully described in polynomial communication, such as single-minded). Although succinct valuations can be efficiently communicated, we show that additional succinct bidders have a nontrivial impact on communication complexity of classical combinatorial auctions. Specifically, let $n$ be the number of subadditive/XOS bidders. We show that for SA $\cup$ SC (the union of subadditive and succinct valuations): (1) There is a polynomial communication $3$-approximation algorithm; (2) As $n \to \infty$, there is a matching $3$-hardness of approximation, which (a) is larger than the optimal approximation ratio of $2$ for SA, and (b) holds even for SA $\cup$ SM (the union of subadditive and single-minded valuations); and (3) For all $n \geq 3$, there is a constant separation between the optimal approximation ratios for SA $\cup$ SM and SA (and therefore between SA $\cup$ SC and SA as well). Similarly, we show that for XOS $\cup$ SC: (1) There is a polynomial communication $2$-approximation algorithm; (2) As $n \to \infty$, there is a matching $2$-hardness of approximation, which (a) is larger than the optimal approximation ratio of $e/(e-1)$ for XOS, and (b) holds even for XOS $\cup$ SM; and (3) For all $n \geq 2$, there is a constant separation between the optimal approximation ratios for XOS $\cup$ SM and XOS (and therefore between XOS $\cup$ SC and XOS as well). - oai:arXiv.org:2512.06585v1 - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 + Construction and Performance of Kinetic Schemes for Linear Systems of Conservation Laws + https://arxiv.org/abs/2512.08479 + arXiv:2512.08479v1 Announce Type: new +Abstract: We describe a methodology to build vectorial kinetic schemes, targetting the numerical solution of linear symmetric-hyperbolic systems of conservation laws -a minimal application case for those schemes. Precisely, we fully detail the construction of kinetic schemes that satisfy a discrete equivalent to a convex extension (an additional non-trivial conservation law) of the target system -the (linear) acoustic and elastodynamics systems, specifically -. Then, we evaluate numerically the convergence of various possible kinetic schemes toward smooth solutions, in comparison with standard finite-difference and finite-volume discretizations on Cartesian meshes. Our numerical results confirm the interest of ensuring a discrete equivalent to a convex extension, and show the influence of remaining parameter variations in terms of error magnitude, both for ''first-order'' and ''second-order'' kinetic schemes\,: the parameter choice with largest CFL number (equiv., smallest spurious diffusion in the equivalent equation analysis) has the smallest discretization error. + oai:arXiv.org:2512.08479v1 + math.NA + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Frederick V. Qiu, S. Matthew Weinberg, Qianfan Zhang + Emmanuel Audusse (LAGA), S\'ebastien Boyaval (MATHERIALS, LHSV), Virgile Dubos (UMA), Minh-Hoang Le (LHSV) - Adapting AlignScore Mertic for Factual Consistency Evaluation of Text in Russian: A Student Abstract - https://arxiv.org/abs/2512.06586 - arXiv:2512.06586v1 Announce Type: new -Abstract: Ensuring factual consistency in generated text is crucial for reliable natural language processing applications. However, there is a lack of evaluation tools for factual consistency in Russian texts, as existing tools primarily focus on English corpora. To bridge this gap, we introduce AlignRuScore, a comprehensive adaptation of the AlignScore metric for Russian. To adapt the metric, we fine-tuned a RuBERT-based alignment model with task-specific classification and regression heads on Russian and translated English datasets. Our results demonstrate that a unified alignment metric can be successfully ported to Russian, laying the groundwork for robust multilingual factual consistency evaluation. We release the translated corpora, model checkpoints, and code to support further research. - oai:arXiv.org:2512.06586v1 + Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models + https://arxiv.org/abs/2512.08480 + arXiv:2512.08480v1 Announce Type: new +Abstract: Recent incidents in certain online games and communities, where anonymity is guaranteed, show that unchecked inappropriate remarks frequently escalate into verbal abuse and even criminal behavior, raising significant social concerns. Consequently, there is a growing need for research on techniques that can detect inappropriate utterances within conversational texts to help build a safer communication environment. Although large-scale language models trained on Korean corpora and chain-of-thought reasoning have recently gained attention, research applying these approaches to inappropriate utterance detection remains limited. In this study, we propose a soft inductive bias approach that explicitly defines reasoning perspectives to guide the inference process, thereby promoting rational decision-making and preventing errors that may arise during reasoning. We fine-tune a Korean large language model using the proposed method and conduct both quantitative performance comparisons and qualitative evaluations across different training strategies. Experimental results show that the Kanana-1.5 model achieves an average accuracy of 87.0046, improving by approximately 3.89 percent over standard supervised learning. These findings indicate that the proposed method goes beyond simple knowledge imitation by large language models and enables more precise and consistent judgments through constrained reasoning perspectives, demonstrating its effectiveness for inappropriate utterance detection. + oai:arXiv.org:2512.08480v1 cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Mikhail Zimin, Milyausha Shamsutdinova, Georgii Andriushchenko + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Proceedings of the 37th Annual Conference on Human and Language Technology, 2025, pp. 714-719 + Ju-Young Kim, Ji-Hong Park, Se-Yeon Lee, Sujin Park, Gun-Woo Kim - OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation - https://arxiv.org/abs/2512.06589 - arXiv:2512.06589v1 Announce Type: new -Abstract: Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors. Existing benchmarks such as JailBreakV-28K, MM-SafetyBench, and HADES provide valuable insights into multi-modal vulnerabilities, but they typically focus on limited attack scenarios, lack standardized defense evaluation, and offer no unified, reproducible toolbox. To address these gaps, we introduce OmniSafeBench-MM, which is a comprehensive toolbox for multi-modal jailbreak attack-defense evaluation. OmniSafeBench-MM integrates 13 representative attack methods, 15 defense strategies, and a diverse dataset spanning 9 major risk domains and 50 fine-grained categories, structured across consultative, imperative, and declarative inquiry types to reflect realistic user intentions. Beyond data coverage, it establishes a three-dimensional evaluation protocol measuring (1) harmfulness, distinguished by a granular, multi-level scale ranging from low-impact individual harm to catastrophic societal threats, (2) intent alignment between responses and queries, and (3) response detail level, enabling nuanced safety-utility analysis. We conduct extensive experiments on 10 open-source and 8 closed-source MLLMs to reveal their vulnerability to multi-modal jailbreak. By unifying data, methodology, and evaluation into an open-source, reproducible platform, OmniSafeBench-MM provides a standardized foundation for future research. The code is released at https://github.com/jiaxiaojunQAQ/OmniSafeBench-MM. - oai:arXiv.org:2512.06589v1 - cs.CR - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Prospect Theory in Physical Human-Robot Interaction: A Pilot Study of Probability Perception + https://arxiv.org/abs/2512.08481 + arXiv:2512.08481v1 Announce Type: new +Abstract: Understanding how humans respond to uncertainty is critical for designing safe and effective physical human-robot interaction (pHRI), as physically working with robots introduces multiple sources of uncertainty, including trust, comfort, and perceived safety. Conventional pHRI control frameworks typically build on optimal control theory, which assumes that human actions minimize a cost function; however, human behavior under uncertainty often departs from such optimal patterns. To address this gap, additional understanding of human behavior under uncertainty is needed. This pilot study implemented a physically coupled target-reaching task in which the robot delivered assistance or disturbances with systematically varied probabilities (10\% to 90\%). Analysis of participants' force inputs and decision-making strategies revealed two distinct behavioral clusters: a "trade-off" group that modulated their physical responses according to disturbance likelihood, and an "always-compensate" group characterized by strong risk aversion irrespective of probability. These findings provide empirical evidence that human decision-making in pHRI is highly individualized and that the perception of probability can differ to its true value. Accordingly, the study highlights the need for more interpretable behavioral models, such as cumulative prospect theory (CPT), to more accurately capture these behaviors and inform the design of future adaptive robot controllers. + oai:arXiv.org:2512.08481v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaojun Jia, Jie Liao, Qi Guo, Teng Ma, Simeng Qin, Ranjie Duan, Tianlin Li, Yihao Huang, Zhitao Zeng, Dongxian Wu, Yiming Li, Wenqi Ren, Xiaochun Cao, Yang Liu + Yixiang Lin, Tiancheng Yang, Jonathan Eden, Ying Tan - Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems - https://arxiv.org/abs/2512.06590 - arXiv:2512.06590v1 Announce Type: new -Abstract: Recommender Systems (RSs) have become the cornerstone of various applications such as e-commerce and social media platforms. The evolution of RSs is paramount in the digital era, in which personalised user experience is tailored to the user's preferences. Large Language Models (LLMs) have sparked a new paradigm - generative retrieval and recommendation. Despite their potential, generative RS methods face issues such as hallucination, which degrades the recommendation performance, and high computational cost in practical scenarios. To address these issues, we introduce HGLMRec, a novel Multi-LLM agent-based RS that incorporates a hypergraph encoder designed to capture complex, multi-behaviour relationships between users and items. The HGLMRec model retrieves only the relevant tokens during inference, reducing computational overhead while enriching the retrieval context. Experimental results show performance improvement by HGLMRec against state-of-the-art baselines at lower computational cost. - oai:arXiv.org:2512.06590v1 - cs.IR - cs.AI - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 + NeurIDA: Dynamic Modeling for Effective In-Database Analytics + https://arxiv.org/abs/2512.08483 + arXiv:2512.08483v1 Announce Type: new +Abstract: Relational Database Management Systems (RDBMS) manage complex, interrelated data and support a broad spectrum of analytical tasks. With the growing demand for predictive analytics, the deep integration of machine learning (ML) into RDBMS has become critical. However, a fundamental challenge hinders this evolution: conventional ML models are static and task-specific, whereas RDBMS environments are dynamic and must support diverse analytical queries. Each analytical task entails constructing a bespoke pipeline from scratch, which incurs significant development overhead and hence limits wide adoption of ML in analytics. + We present NeurIDA, an autonomous end-to-end system for in-database analytics that dynamically "tweaks" the best available base model to better serve a given analytical task. In particular, we propose a novel paradigm of dynamic in-database modeling to pre-train a composable base model architecture over the relational data. Upon receiving a task, NeurIDA formulates the task and data profile to dynamically select and configure relevant components from the pool of base models and shared model components for prediction. For friendly user experience, NeurIDA supports natural language queries; it interprets user intent to construct structured task profiles, and generates analytical reports with dedicated LLM agents. By design, NeurIDA enables ease-of-use and yet effective and efficient in-database AI analytics. Extensive experiment study shows that NeurIDA consistently delivers up to 12% improve- ment in AUC-ROC and 25% relative reduction in MAE across ten tasks on five real-world datasets. The source code is available at https://github.com/Zrealshadow/NeurIDA + oai:arXiv.org:2512.08483v1 + cs.DB + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Tendai Mukande, Esraa Ali, Annalina Caputo, Ruihai Dong, Noel OConnor + Lingze Zeng, Naili Xing, Shaofeng Cai, Peng Lu, Gang Chen, Jian Pei, Beng Chin Ooi - Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability - https://arxiv.org/abs/2512.06591 - arXiv:2512.06591v1 Announce Type: new -Abstract: Explainable AI (XAI) presents useful tools to facilitate transparency and trustworthiness in machine learning systems. However, current evaluations of system explainability often rely heavily on subjective user surveys, which may not adequately capture the effectiveness of explanations. This paper critiques the overreliance on user satisfaction metrics and explores whether these can differentiate between meaningful (actionable) and vacuous (placebic) explanations. In experiments involving optimal Social Security filing age selection tasks, participants used one of three protocols: no explanations, placebic explanations, and actionable explanations. Participants who received actionable explanations significantly outperformed the other groups in objective measures of their mental model, but users rated placebic and actionable explanations as equally satisfying. This suggests that subjective surveys alone fail to capture whether explanations truly support users in building useful domain understanding. We propose that future evaluations of agent explanation capabilities should integrate objective task performance metrics alongside subjective assessments to more accurately measure explanation quality. The code for this study can be found at https://github.com/Shymkis/social-security-explainer. - oai:arXiv.org:2512.06591v1 - cs.HC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning + https://arxiv.org/abs/2512.08485 + arXiv:2512.08485v1 Announce Type: new +Abstract: Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to data poisoning attacks. Existing attack strategies typically rely on locally uniform perturbations, which treat all samples indiscriminately. This approach is inefficient, as it wastes the perturbation budget on low-impact samples, and lacks stealthiness due to significant statistical deviations. In this paper, we propose a novel Global Budget Allocation attack strategy. Leveraging the theoretical insight that a sample's influence on value function convergence is proportional to its Temporal Difference (TD) error, we formulate the attack as a global resource allocation problem. We derive a closed-form solution where perturbation magnitudes are assigned proportional to the TD-error sensitivity under a global L2 constraint. Empirical results on D4RL benchmarks demonstrate that our method significantly outperforms baseline strategies, achieving up to 80% performance degradation with minimal perturbations that evade detection by state-of-the-art statistical and spectral defenses. + oai:arXiv.org:2512.08485v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - 10.1007/978-3-032-01399-6_10 - In: Calvaresi, D., et al. Explainable, Trustworthy, and Responsible AI and Multi-Agent Systems. EXTRAAMAS 2025. Lecture Notes in Computer Science. Springer, Cham - Joe Shymanski, Jacob Brue, Sandip Sen + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Junnan Qiu, Jie Li - On fine-tuning Boltz-2 for protein-protein affinity prediction - https://arxiv.org/abs/2512.06592 - arXiv:2512.06592v1 Announce Type: new -Abstract: Accurate prediction of protein-protein binding affinity is vital for understanding molecular interactions and designing therapeutics. We adapt Boltz-2, a state-of-the-art structure-based protein-ligand affinity predictor, for protein-protein affinity regression and evaluate it on two datasets, TCR3d and PPB-affinity. Despite high structural accuracy, Boltz-2-PPI underperforms relative to sequence-based alternatives in both small- and larger-scale data regimes. Combining embeddings from Boltz-2-PPI with sequence-based embeddings yields complementary improvements, particularly for weaker sequence models, suggesting different signals are learned by sequence- and structure-based models. Our results echo known biases associated with training with structural data and suggest that current structure-based representations are not primed for performant affinity prediction. - oai:arXiv.org:2512.06592v1 - cs.LG - q-bio.BM - Tue, 09 Dec 2025 00:00:00 -0500 + Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions + https://arxiv.org/abs/2512.08486 + arXiv:2512.08486v1 Announce Type: new +Abstract: Diffusion models are usually evaluated by their final outputs, gradually denoising random noise into meaningful images. Yet, generation unfolds along a trajectory, and analyzing this dynamic process is crucial for understanding how controllable, reliable, and predictable these models are in terms of their success/failure modes. In this work, we ask the question: when does noise turn into a specific concept (e.g., age) and lock in the denoising trajectory? We propose PCI (Prompt-Conditioned Intervention) to study this question. PCI is a training-free and model-agnostic framework for analyzing concept dynamics through diffusion time. The central idea is the analysis of Concept Insertion Success (CIS), defined as the probability that a concept inserted at a given timestep is preserved and reflected in the final image, offering a way to characterize the temporal dynamics of concept formation. Applied to several state-of-the-art text-to-image diffusion models and a broad taxonomy of concepts, PCI reveals diverse temporal behaviors across diffusion models, in which certain phases of the trajectory are more favorable to specific concepts even within the same concept type. These findings also provide actionable insights for text-driven image editing, highlighting when interventions are most effective without requiring access to model internals or training, and yielding quantitatively stronger edits that achieve a balance of semantic accuracy and content preservation than strong baselines. Code is available at: https://github.com/adagorgun/PCI-Prompt-Controlled-Interventions + oai:arXiv.org:2512.08486v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - James King, Lewis Cornwall, Andrei Cristian Nica, James Day, Aaron Sim, Neil Dalchau, Lilly Wollman, Joshua Meyers + Ada Gorgun, Fawaz Sammani, Nikos Deligiannis, Bernt Schiele, Jonas Fischer - ChargingBoul: A Competitive Negotiating Agent with Novel Opponent Modeling - https://arxiv.org/abs/2512.06595 - arXiv:2512.06595v1 Announce Type: new -Abstract: Automated negotiation has emerged as a critical area of research in multiagent systems, with applications spanning e-commerce, resource allocation, and autonomous decision-making. This paper presents ChargingBoul, a negotiating agent that competed in the 2022 Automated Negotiating Agents Competition (ANAC) and placed second in individual utility by an exceptionally narrow margin. ChargingBoul employs a lightweight yet effective strategy that balances concession and opponent modeling to achieve high negotiation outcomes. The agent classifies opponents based on bid patterns, dynamically adjusts its bidding strategy, and applies a concession policy in later negotiation stages to maximize utility while fostering agreements. We evaluate ChargingBoul's performance using competition results and subsequent studies that have utilized the agent in negotiation research. Our analysis highlights ChargingBoul's effectiveness across diverse opponent strategies and its contributions to advancing automated negotiation techniques. We also discuss potential enhancements, including more sophisticated opponent modeling and adaptive bidding heuristics, to improve its performance further. - oai:arXiv.org:2512.06595v1 - cs.MA + Autonomous Issue Resolver: Towards Zero-Touch Code Maintenance + https://arxiv.org/abs/2512.08492 + arXiv:2512.08492v1 Announce Type: new +Abstract: Recent advances in Large Language Models have revolutionized function-level code generation; however, repository-scale Automated Program Repair (APR) remains a significant challenge. Current approaches typically employ a control-centric paradigm, forcing agents to navigate complex directory structures and irrelevant control logic. In this paper, we propose a paradigm shift from the standard Code Property Graphs (CPGs) to the concept of Data Transformation Graph (DTG) that inverts the topology by modeling data states as nodes and functions as edges, enabling agents to trace logic defects through data lineage rather than control flow. We introduce a multi-agent framework that reconciles data integrity navigation with control flow logic. Our theoretical analysis and case studies demonstrate that this approach resolves the "Semantic Trap" inherent in standard RAG systems in modern coding agents. We provide a comprehensive implementation in the form of Autonomous Issue Resolver (AIR), a self-improvement system for zero-touch code maintenance that utilizes neuro-symbolic reasoning and uses the DTG structure for scalable logic repair. Our approach has demonstrated good results on several SWE benchmarks, reaching a resolution rate of 87.1% on SWE-Verified benchmark. Our approach directly addresses the core limitations of current AI code-assistant tools and tackles the critical need for a more robust foundation for our increasingly software-dependent world. + oai:arXiv.org:2512.08492v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Joe Shymanski + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Aliaksei Kaliutau - When Does Regulation by Insurance Work? The Case of Frontier AI - https://arxiv.org/abs/2512.06597 - arXiv:2512.06597v1 Announce Type: new -Abstract: No one doubts the utility of insurance for its ability to spread risk or streamline claims management; much debated is when and how insurance uptake can improve welfare by reducing harm, despite moral hazard. Proponents and dissenters of "regulation by insurance" have now documented a number of cases of insurers succeeding or failing to have such a net regulatory effect (in contrast with a net hazard effect). Collecting these examples together and drawing on an extensive economics literature, this Article develops a principled framework for evaluating insurance uptake's effect in a given context. The presence of certain distortions - including judgment-proofness, competitive dynamics, and behavioral biases - creates potential for a net regulatory effect. How much of that potential gets realized then depends on the type of policyholder, type of risk, type of insurer, and the structure of the insurance market. The analysis suggests regulation by insurance can be particularly effective for catastrophic non-product accidents where market mechanisms provide insufficient discipline and psychological biases are strongest. As a demonstration, the framework is applied to the frontier AI industry, revealing significant potential for a net regulatory effect but also the need for policy intervention to realize that potential. One option is a carefully designed mandate that encourages forming a specialized insurer or mutual, focuses on catastrophic rather than routine risks, and bars pure captives. - oai:arXiv.org:2512.06597v1 - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + LLM-based Vulnerable Code Augmentation: Generate or Refactor? + https://arxiv.org/abs/2512.08493 + arXiv:2512.08493v1 Announce Type: new +Abstract: Vulnerability code-bases often suffer from severe imbalance, limiting the effectiveness of Deep Learning-based vulnerability classifiers. Data Augmentation could help solve this by mitigating the scarcity of under-represented CWEs. In this context, we investigate LLM-based augmentation for vulnerable functions, comparing controlled generation of new vulnerable samples with semantics-preserving refactoring of existing ones. Using Qwen2.5-Coder to produce augmented data and CodeBERT as a vulnerability classifier on the SVEN dataset, we find that our approaches are indeed effective in enriching vulnerable code-bases through a simple process and with reasonable quality, and that a hybrid strategy best boosts vulnerability classifiers' performance. + oai:arXiv.org:2512.08493v1 + cs.CR + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Cristian Trout + Dyna Soumhane Ouchebara, St\'ephane Dupont - From Remote Sensing to Multiple Time Horizons Forecasts: Transformers Model for CyanoHAB Intensity in Lake Champlain - https://arxiv.org/abs/2512.06598 - arXiv:2512.06598v1 Announce Type: new -Abstract: Cyanobacterial Harmful Algal Blooms (CyanoHABs) pose significant threats to aquatic ecosystems and public health globally. Lake Champlain is particularly vulnerable to recurring CyanoHAB events, especially in its northern segment: Missisquoi Bay, St. Albans Bay, and Northeast Arm, due to nutrient enrichment and climatic variability. Remote sensing provides a scalable solution for monitoring and forecasting these events, offering continuous coverage where in situ observations are sparse or unavailable. In this study, we present a remote sensing only forecasting framework that combines Transformers and BiLSTM to predict CyanoHAB intensities up to 14 days in advance. The system utilizes Cyanobacterial Index data from the Cyanobacterial Assessment Network and temperature data from Moderate Resolution Imaging Spectroradiometer satellites to capture long range dependencies and sequential dynamics in satellite time series. The dataset is very sparse, missing more than 30% of the Cyanobacterial Index data and 90% of the temperature data. A two stage preprocessing pipeline addressed data gaps by applying forward fill and weighted temporal imputation at the pixel level, followed by smoothing to reduce the discontinuities of CyanoHAB events. The raw dataset is transformed into meaningful features through equal frequency binning for the Cyanobacterial Index values and extracted temperature statistics. Transformer BiLSTM model demonstrates strong forecasting performance across multiple horizons, achieving F1 scores of 89.5%, 86.4%, and 85.5% at one, two, and three-day forecasts, respectively, and maintaining an F1 score of 78.9% with an AUC of 82.6% at the 14-day horizon. These results confirm the model's ability to capture complex spatiotemporal dynamics from sparse satellite data and to provide reliable early warning for CyanoHABs management. - oai:arXiv.org:2512.06598v1 + On-the-fly Large-scale 3D Reconstruction from Multi-Camera Rigs + https://arxiv.org/abs/2512.08498 + arXiv:2512.08498v1 Announce Type: new +Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled efficient free-viewpoint rendering and photorealistic scene reconstruction. While on-the-fly extensions of 3DGS have shown promise for real-time reconstruction from monocular RGB streams, they often fail to achieve complete 3D coverage due to the limited field of view (FOV). Employing a multi-camera rig fundamentally addresses this limitation. In this paper, we present the first on-the-fly 3D reconstruction framework for multi-camera rigs. Our method incrementally fuses dense RGB streams from multiple overlapping cameras into a unified Gaussian representation, achieving drift-free trajectory estimation and efficient online reconstruction. We propose a hierarchical camera initialization scheme that enables coarse inter-camera alignment without calibration, followed by a lightweight multi-camera bundle adjustment that stabilizes trajectories while maintaining real-time performance. Furthermore, we introduce a redundancy-free Gaussian sampling strategy and a frequency-aware optimization scheduler to reduce the number of Gaussian primitives and the required optimization iterations, thereby maintaining both efficiency and reconstruction fidelity. Our method reconstructs hundreds of meters of 3D scenes within just 2 minutes using only raw multi-camera video streams, demonstrating unprecedented speed, robustness, and Fidelity for on-the-fly 3D scene reconstruction. + oai:arXiv.org:2512.08498v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Muhammad Adil, Patrick J. Clemins, Andrew W. Schroth, Panagiotis D. Oikonomou, Donna M. Rizzo, Peter D. F. Isles, Xiaohan Zhang, Kareem I. Hannoun, Scott Turnbull, Noah B. Beckage, Asim Zia, Safwan Wshah + Yijia Guo, Tong Hu, Zhiwei Li, Liwen Hu, Keming Qian, Xitong Lin, Shengbo Chen, Tiejun Huang, Lei Ma - Learning Reachability of Energy Storage Arbitrage - https://arxiv.org/abs/2512.06600 - arXiv:2512.06600v1 Announce Type: new -Abstract: Power systems face increasing weather-driven variability and, therefore, increasingly rely on flexible but energy-limited storage resources. Energy storage can buffer this variability, but its value depends on intertemporal decisions under uncertain prices. Without accounting for the future reliability value of stored energy, batteries may act myopically, discharging too early or failing to preserve reserves during critical hours. This paper introduces a stopping-time reward that, together with a state-of-charge (SoC) range target penalty, aligns arbitrage incentives with system reliability by rewarding storage that maintains sufficient SoC before critical hours. We formulate the problem as an online optimization with a chance-constrained terminal SoC and embed it in an end-to-end (E2E) learning framework, jointly training the price predictor and control policy. The proposed design enhances reachability of target SoC ranges, improves profit under volatile conditions, and reduces its standard deviation. - oai:arXiv.org:2512.06600v1 - eess.SY - cs.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Developing Distance-Aware Uncertainty Quantification Methods in Physics-Guided Neural Networks for Reliable Bearing Health Prediction + https://arxiv.org/abs/2512.08499 + arXiv:2512.08499v1 Announce Type: new +Abstract: Accurate and uncertainty-aware degradation estimation is essential for predictive maintenance in safety-critical systems like rotating machinery with rolling-element bearings. Many existing uncertainty methods lack confidence calibration, are costly to run, are not distance-aware, and fail to generalize under out-of-distribution data. We introduce two distance-aware uncertainty methods for deterministic physics-guided neural networks: PG-SNGP, based on Spectral Normalization Gaussian Process, and PG-SNER, based on Deep Evidential Regression. We apply spectral normalization to the hidden layers so the network preserves distances from input to latent space. PG-SNGP replaces the final dense layer with a Gaussian Process layer for distance-sensitive uncertainty, while PG-SNER outputs Normal Inverse Gamma parameters to model uncertainty in a coherent probabilistic form. We assess performance using standard accuracy metrics and a new distance-aware metric based on the Pearson Correlation Coefficient, which measures how well predicted uncertainty tracks the distance between test and training samples. We also design a dynamic weighting scheme in the loss to balance data fidelity and physical consistency. We test our methods on rolling-element bearing degradation using the PRONOSTIA dataset and compare them with Monte Carlo and Deep Ensemble PGNNs. Results show that PG-SNGP and PG-SNER improve prediction accuracy, generalize reliably under OOD conditions, and remain robust to adversarial attacks and noise. + oai:arXiv.org:2512.08499v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Tom\'as Tapia, Agustin Castellano, Enrique Mallada, Yury Dvorkin + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Waleed Razzaq, Yun-Bo Zhao - Sliding-Mode Control Strategies for PMSM: Benchmarking and Comparative Simulation Study - https://arxiv.org/abs/2512.06603 - arXiv:2512.06603v1 Announce Type: new -Abstract: Permanent Magnet Synchronous Motors (PMSMs) are widely employed in high-performance drive systems owing to their high efficiency and power density. However, nonlinear dynamics, parameter uncertainties, and load disturbances complicate their control. Sliding-Mode Control (SMC) offers strong robustness but exists in numerous variants with unstandardized evaluation criteria. This paper presents a unified simulation benchmark and comparative analysis of six representative SMC techniques for PMSM speed regulation: conventional, integral, terminal, fractional-order, adaptive, and super-twisting. A standardized PMSM model, disturbance profile, and tuning protocol are adopted to ensure fair comparison across all methods. Performance is assessed through time-domain responses, integral error indices (ISE, IAE, ITSE, ITAE), and control-effort profiles, while also examining computational complexity and implementation feasibility. Results demonstrate that adaptive and higher-order SMCs, particularly the super-twisting and adaptive variants, achieve the most balanced trade-off between robustness, smoothness, and computational cost. The study provides a reproducible benchmarking framework, parameter-selection guidelines, and practical insights for designing efficient, low-chatter SMC-based PMSM drives suitable for real-time embedded implementation. - oai:arXiv.org:2512.06603v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions + https://arxiv.org/abs/2512.08500 + arXiv:2512.08500v1 Announce Type: new +Abstract: Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on off-the-shelf motion reconstruction techniques to obtain 3D trajectories for physics-based imitation. These reconstruction methods struggle with generalizability, as they either require 3D training data (potentially scarce) or fail to produce physically plausible poses, hindering their application to challenging scenarios like human-object interaction (HOI) or non-human characters. We tackle this challenge by introducing Mimic2DM, a novel motion imitation framework that learns the control policy directly and solely from widely available 2D keypoint trajectories extracted from videos. By minimizing the reprojection error, we train a general single-view 2D motion tracking policy capable of following arbitrary 2D reference motions in physics simulation, using only 2D motion data. The policy, when trained on diverse 2D motions captured from different or slightly different viewpoints, can further acquire 3D motion tracking capabilities by aggregating multiple views. Moreover, we develop a transformer-based autoregressive 2D motion generator and integrate it into a hierarchical control framework, where the generator produces high-quality 2D reference trajectories to guide the tracking policy. We show that the proposed approach is versatile and can effectively learn to synthesize physically plausible and diverse motions across a range of domains, including dancing, soccer dribbling, and animal movements, without any reliance on explicit 3D motion data. Project Website: https://jiann-li.github.io/mimic2dm/ + oai:arXiv.org:2512.08500v1 + cs.GR + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Mubarak Badamasi Aremu, Abdullah Ajasa, Ali Nasir + Jianan Li, Xiao Chen, Tao Huang, Tien-Tsin Wong - Description Logics with Two Types of Definite Descriptions: Complexity, Expressiveness, and Automated Deduction - https://arxiv.org/abs/2512.06604 - arXiv:2512.06604v1 Announce Type: new -Abstract: Definite descriptions are expressions of the form "the unique $x$ satisfying property $C$," which allow reference to objects through their distinguishing characteristics. They play a crucial role in ontology and query languages, offering an alternative to proper names (IDs), which lack semantic content and serve merely as placeholders. - In this paper, we introduce two extensions of the well-known description logic $\mathcal{ALC}$ with local and global definite descriptions, denoted $\mathcal{ALC}\iota_L$ and $\mathcal{ALC}\iota_G$, respectively. We define appropriate bisimulation notions for these logics, enabling an analysis of their expressiveness. We show that although both logics share the same tight ExpTime complexity bounds for concept and ontology satisfiability, $\mathcal{ALC}\iota_G$ is strictly more expressive than $\mathcal{ALC}\iota_L$. Moreover, we present tableau-based decision procedures for satisfiability in both logics, provide their implementation, and report on a series of experiments. The empirical results demonstrate the practical utility of the implementation and reveal interesting correlations between performance and structural properties of the input formulas. - oai:arXiv.org:2512.06604v1 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models + https://arxiv.org/abs/2512.08503 + arXiv:2512.08503v1 Announce Type: new +Abstract: Multi-modal large reasoning models (MLRMs) pose significant privacy risks by inferring precise geographic locations from personal images through hierarchical chain-of-thought reasoning. Existing privacy protection techniques, primarily designed for perception-based models, prove ineffective against MLRMs' sophisticated multi-step reasoning processes that analyze environmental cues. We introduce \textbf{ReasonBreak}, a novel adversarial framework specifically designed to disrupt hierarchical reasoning in MLRMs through concept-aware perturbations. Our approach is founded on the key insight that effective disruption of geographic reasoning requires perturbations aligned with conceptual hierarchies rather than uniform noise. ReasonBreak strategically targets critical conceptual dependencies within reasoning chains, generating perturbations that invalidate specific inference steps and cascade through subsequent reasoning stages. To facilitate this approach, we contribute \textbf{GeoPrivacy-6K}, a comprehensive dataset comprising 6,341 ultra-high-resolution images ($\geq$2K) with hierarchical concept annotations. Extensive evaluation across seven state-of-the-art MLRMs (including GPT-o3, GPT-5, Gemini 2.5 Pro) demonstrates ReasonBreak's superior effectiveness, achieving a 14.4\% improvement in tract-level protection (33.8\% vs 19.4\%) and nearly doubling block-level protection (33.5\% vs 16.8\%). This work establishes a new paradigm for privacy protection against reasoning-based threats. + oai:arXiv.org:2512.08503v1 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Micha{\l} Socha\'nski, Przemys{\l}aw Andrzej Wa{\l}\k{e}ga, Micha{\l} Zawidzki + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jiaming Zhang, Che Wang, Yang Cao, Longtao Huang, Wei Yang Bryan Lim - Improved Interactive Protocol for Synchronizing From Deletions - https://arxiv.org/abs/2512.06606 - arXiv:2512.06606v1 Announce Type: new -Abstract: Data synchronization is a fundamental problem with applications in diverse fields such as cloud storage, genomics, and distributed systems. This paper addresses the challenge of synchronizing two files, one of which is a subsequence of the other and related through a constant rate of deletions, using an improved communication protocol. Building upon prior work, we integrate advanced multi-deletion correction codes into an existing baseline protocol, which previously relied on single-deletion correction. Our proposed protocol reduces communication cost by leveraging more general partitioning techniques as well as multi-deletion error correction. We derive a generalized upper bound on the expected number of transmitted bits, applicable to a broad class of deletion correction codes. Experimental results demonstrate that our approach outperforms the baseline in communication cost. These findings establish the efficacy of the improved protocol in achieving low-redundancy synchronization in scenarios where deletion errors occur. - oai:arXiv.org:2512.06606v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + Beyond the Noise: Aligning Prompts with Latent Representations in Diffusion Models + https://arxiv.org/abs/2512.08505 + arXiv:2512.08505v1 Announce Type: new +Abstract: Conditional diffusion models rely on language-to-image alignment methods to steer the generation towards semantically accurate outputs. Despite the success of this architecture, misalignment and hallucinations remain common issues and require automatic misalignment detection tools to improve quality, for example by applying them in a Best-of-N (BoN) post-generation setting. Unfortunately, measuring the alignment after the generation is an expensive step since we need to wait for the overall generation to finish to determine prompt adherence. In contrast, this work hypothesizes that text/image misalignments can be detected early in the denoising process, enabling real-time alignment assessment without waiting for the complete generation. In particular, we propose NoisyCLIP a method that measures semantic alignment in the noisy latent space. This work is the first to explore and benchmark prompt-to-latent misalignment detection during image generation using dual encoders in the reverse diffusion process. We evaluate NoisyCLIP qualitatively and quantitatively and find it reduces computational cost by 50% while achieving 98% of CLIP alignment performance in BoN settings. This approach enables real-time alignment assessment during generation, reducing costs without sacrificing semantic fidelity. + oai:arXiv.org:2512.08505v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Haolun (Michael), Ni, Lev Tauz, Ryan Gabrys, Lara Dolecek + Vasco Ramos, Regev Cohen, Idan Szpektor, Joao Magalhaes - A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs - https://arxiv.org/abs/2512.06607 - arXiv:2512.06607v1 Announce Type: new -Abstract: Applying LLMs to predictive tasks in finance is challenging due to look-ahead bias resulting from their training on long time-series data. This precludes the backtests typically employed in finance since retraining frontier models from scratch with a specific knowledge cutoff is prohibitive. In this paper, we introduce a fast, effective, and low-cost alternative. Our method guides generation at inference time by adjusting the logits of a large base model using a pair of smaller, specialized models -- one fine-tuned on information to be forgotten and another on information to be retained. We demonstrate that our method effectively removes both verbatim and semantic knowledge, corrects biases, and outperforms prior methods. - oai:arXiv.org:2512.06607v1 - cs.LG - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Clouds + https://arxiv.org/abs/2512.08506 + arXiv:2512.08506v1 Announce Type: new +Abstract: A major challenge in reconstructing buildings from LiDAR point clouds lies in accurately capturing building surfaces under varying point densities and noise interference. To flexibly gather high-quality 3D profiles of the building in diverse resolution, we propose OCCDiff applying latent diffusion in the occupancy function space. Our OCCDiff combines a latent diffusion process with a function autoencoder architecture to generate continuous occupancy functions evaluable at arbitrary locations. Moreover, a point encoder is proposed to provide condition features to diffusion learning, constraint the final occupancy prediction for occupancy decoder, and insert multi-modal features for latent generation to latent encoder. To further enhance the model performance, a multi-task training strategy is employed, ensuring that the point encoder learns diverse and robust feature representations. Empirical results show that our method generates physically consistent samples with high fidelity to the target distribution and exhibits robustness to noisy data. + oai:arXiv.org:2512.08506v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Jialu Sui, Rui Liu, Hongsheng Zhang + + + Thinking with Images via Self-Calling Agent + https://arxiv.org/abs/2512.08511 + arXiv:2512.08511v1 Announce Type: new +Abstract: Thinking-with-images paradigms have showcased remarkable visual reasoning capability by integrating visual information as dynamic elements into the Chain-of-Thought (CoT). However, optimizing interleaved multimodal CoT (iMCoT) through reinforcement learning remains challenging, as it relies on scarce high-quality reasoning data. In this study, we propose Self-Calling Chain-of-Thought (sCoT), a novel visual reasoning paradigm that reformulates iMCoT as a language-only CoT with self-calling. Specifically, a main agent decomposes the complex visual reasoning task to atomic subtasks and invokes its virtual replicas, i.e. parameter-sharing subagents, to solve them in isolated context. sCoT enjoys substantial training effectiveness and efficiency, as it requires no explicit interleaving between modalities. sCoT employs group-relative policy optimization to reinforce effective reasoning behavior to enhance optimization. Experiments on HR-Bench 4K show that sCoT improves the overall reasoning performance by up to $1.9\%$ with $\sim 75\%$ fewer GPU hours compared to strong baseline approaches. Code is available at https://github.com/YWenxi/think-with-images-through-self-calling. + oai:arXiv.org:2512.08511v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Humzah Merchant, Bradford Levy + Wenxi Yang, Yuzhong Zhao, Fang Wan, Qixiang Ye + + + A Lightweight Transfer Learning-Based State-of-Health Monitoring with Application to Lithium-ion Batteries in Unmanned Air Vehicles + https://arxiv.org/abs/2512.08512 + arXiv:2512.08512v1 Announce Type: new +Abstract: Accurate and rapid state-of-health (SOH) monitoring plays an important role in indicating energy information for lithium-ion battery-powered portable mobile devices. To confront their variable working conditions, transfer learning (TL) emerges as a promising technique for leveraging knowledge from data-rich source working conditions, significantly reducing the training data required for SOH monitoring from target working conditions. However, traditional TL-based SOH monitoring is infeasible when applied in portable mobile devices since substantial computational resources are consumed during the TL stage and unexpectedly reduce the working endurance. To address these challenges, this paper proposes a lightweight TL-based SOH monitoring approach with constructive incremental transfer learning (CITL). First, taking advantage of the unlabeled data in the target domain, a semi-supervised TL mechanism is proposed to minimize the monitoring residual in a constructive way, through iteratively adding network nodes in the CITL. Second, the cross-domain learning ability of node parameters for CITL is comprehensively guaranteed through structural risk minimization, transfer mismatching minimization, and manifold consistency maximization. Moreover, the convergence analysis of the CITL is given, theoretically guaranteeing the efficacy of TL performance and network compactness. Finally, the proposed approach is verified through extensive experiments with a realistic unmanned air vehicles (UAV) battery dataset collected from dozens of flight missions. Specifically, the CITL outperforms SS-TCA, MMD-LSTM-DA, DDAN, BO-CNN-TL, and AS$^3$LSTM, in SOH estimation by 83.73%, 61.15%, 28.24%, 87.70%, and 57.34%, respectively, as evaluated using the index root mean square error. + oai:arXiv.org:2512.08512v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-sa/4.0/ + 10.1109/TII.2025.3631012 + Jiang Liu, Yan Qin, Wei Dai, Chau Yuen - A New Trajectory-Oriented Approach to Enhancing Comprehensive Crowd Navigation Performance - https://arxiv.org/abs/2512.06608 - arXiv:2512.06608v1 Announce Type: new -Abstract: Crowd navigation has garnered considerable research interest in recent years, especially with the proliferating application of deep reinforcement learning (DRL) techniques. Many studies, however, do not sufficiently analyze the relative priorities among evaluation metrics, which compromises the fair assessment of methods with divergent objectives. Furthermore, trajectory-continuity metrics, specifically those requiring $C^2$ smoothness, are rarely incorporated. Current DRL approaches generally prioritize efficiency and proximal comfort, often neglecting trajectory optimization or addressing it only through simplistic, unvalidated smoothness reward. Nevertheless, effective trajectory optimization is essential to ensure naturalness, enhance comfort, and maximize the energy efficiency of any navigation system. To address these gaps, this paper proposes a unified framework that enables the fair and transparent assessment of navigation methods by examining the prioritization and joint evaluation of multiple optimization objectives. We further propose a novel reward-shaping strategy that explicitly emphasizes trajectory-curvature optimization. The resulting trajectory quality and adaptability are significantly enhanced across multi-scale scenarios. Through extensive 2D and 3D experiments, we demonstrate that the proposed method achieves superior performance compared to state-of-the-art approaches. - oai:arXiv.org:2512.06608v1 + SensHRPS: Sensing Comfortable Human-Robot Proxemics and Personal Space With Eye-Tracking + https://arxiv.org/abs/2512.08518 + arXiv:2512.08518v1 Announce Type: new +Abstract: Social robots must adjust to human proxemic norms to ensure user comfort and engagement. While prior research demonstrates that eye-tracking features reliably estimate comfort in human-human interactions, their applicability to interactions with humanoid robots remains unexplored. In this study, we investigate user comfort with the robot "Ameca" across four experimentally controlled distances (0.5 m to 2.0 m) using mobile eye-tracking and subjective reporting (N=19). We evaluate multiple machine learning and deep learning models to estimate comfort based on gaze features. Contrary to previous human-human studies where Transformer models excelled, a Decision Tree classifier achieved the highest performance (F1-score = 0.73), with minimum pupil diameter identified as the most critical predictor. These findings suggest that physiological comfort thresholds in human-robot interaction differ from human-human dynamics and can be effectively modeled using interpretable logic. + oai:arXiv.org:2512.08518v1 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xinyu Zhou, Songhao Piao, Chao Gao, Liguo Chen + http://creativecommons.org/licenses/by/4.0/ + Nadezhda Kushina (RPTU Kaiserslautern-Landau), Ko Watanabe (DFKI GmbH), Aarthi Kannan (RPTU Kaiserslautern-Landau), Ashita Ashok (RPTU Kaiserslautern-Landau), Andreas Dengel (DFKI GmbH), Karsten Berns (RPTU Kaiserslautern-Landau) - Vector Quantization using Gaussian Variational Autoencoder - https://arxiv.org/abs/2512.06609 - arXiv:2512.06609v1 Announce Type: new -Abstract: Vector quantized variational autoencoder (VQ-VAE) is a discrete auto-encoder that compresses images into discrete tokens. It is difficult to train due to discretization. In this paper, we propose a simple yet effective technique, dubbed Gaussian Quant (GQ), that converts a Gaussian VAE with certain constraint into a VQ-VAE without training. GQ generates random Gaussian noise as a codebook and finds the closest noise to the posterior mean. Theoretically, we prove that when the logarithm of the codebook size exceeds the bits-back coding rate of the Gaussian VAE, a small quantization error is guaranteed. Practically, we propose a heuristic to train Gaussian VAE for effective GQ, named target divergence constraint (TDC). Empirically, we show that GQ outperforms previous VQ-VAEs, such as VQGAN, FSQ, LFQ, and BSQ, on both UNet and ViT architectures. Furthermore, TDC also improves upon previous Gaussian VAE discretization methods, such as TokenBridge. The source code is provided in https://github.com/tongdaxu/VQ-VAE-from-Gaussian-VAE. - oai:arXiv.org:2512.06609v1 - cs.LG + Beyond Real Weights: Hypercomplex Representations for Stable Quantization + https://arxiv.org/abs/2512.08524 + arXiv:2512.08524v1 Announce Type: new +Abstract: Multimodal language models (MLLMs) require large parameter capacity to align high-dimensional visual features with linguistic representations, making them computationally heavy and difficult to deploy efficiently. We introduce a progressive reparameterization strategy that compresses these models by gradually replacing dense feed-forward network blocks with compact Parameterized Hypercomplex Multiplication (PHM) layers. A residual interpolation schedule, together with lightweight reconstruction and knowledge distillation losses, ensures that the PHM modules inherit the functional behavior of their dense counterparts during training. This transition yields substantial parameter and FLOP reductions while preserving strong multimodal alignment, enabling faster inference without degrading output quality. We evaluate the approach on multiple vision-language models (VLMs). Our method maintains performance comparable to the base models while delivering significant reductions in model size and inference latency. Progressive PHM substitution thus offers an architecture-compatible path toward more efficient multimodal reasoning and complements existing low-bit quantization techniques. + oai:arXiv.org:2512.08524v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Tongda Xu, Wendi Zheng, Jiajun He, Jose Miguel Hernandez-Lobato, Yan Wang, Ya-Qin Zhang, Jie Tang + Jawad Ibn Ahad, Maisha Rahman, Amrijit Biswas, Muhammad Rafsan Kabir, Robin Krambroeckers, Sifat Momen, Nabeel Mohammed, Shafin Rahman - Robust Optimization-based Autonomous Dynamic Soaring with a Fixed-Wing UAV - https://arxiv.org/abs/2512.06610 - arXiv:2512.06610v1 Announce Type: new -Abstract: Dynamic soaring is a flying technique to exploit the energy available in wind shear layers, enabling potentially unlimited flight without the need for internal energy sources. We propose a framework for autonomous dynamic soaring with a fixed-wing unmanned aerial vehicle (UAV). The framework makes use of an explicit representation of the wind field and a classical approach for guidance and control of the UAV. Robustness to wind field estimation error is achieved by constructing point-wise robust reference paths for dynamic soaring and the development of a robust path following controller for the fixed-wing UAV. The framework is evaluated in dynamic soaring scenarios in simulation and real flight tests. In simulation, we demonstrate robust dynamic soaring flight subject to varied wind conditions, estimation errors and disturbances. Critical components of the framework, including energy predictions and path-following robustness, are further validated in real flights to assure small sim-to-real gap. Together, our results strongly indicate the ability of the proposed framework to achieve autonomous dynamic soaring flight in wind shear. - oai:arXiv.org:2512.06610v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Analyzing Deviations from Monotonic Trends through Database Repair + https://arxiv.org/abs/2512.08526 + arXiv:2512.08526v1 Announce Type: new +Abstract: Datasets often exhibit violations of expected monotonic trends - for example, higher education level correlating with higher average salary, newer homes being more expensive, or diabetes prevalence increasing with age. We address the problem of quantifying how far a dataset deviates from such trends. To this end, we introduce Aggregate Order Dependencies (AODs), an aggregation-centric extension of the previously studied order dependencies. An AOD specifies that the aggregated value of a target attribute (e.g., mean salary) should monotonically increase or decrease with the grouping attribute (e.g., education level). + We formulate the AOD repair problem as finding the smallest set of tuples to delete from a table so that the given AOD is satisfied. We analyze the computational complexity of this problem and propose a general algorithmic template for solving it. We instantiate the template for common aggregation functions, introduce optimization techniques that substantially improve the runtime of the template instances, and develop efficient heuristic alternatives. Our experimental study, carried out on both real-world and synthetic datasets, demonstrates the practical efficiency of the algorithms and provides insight into the performance of the heuristics. We also present case studies that uncover and explain unexpected AOD violations using our framework. + oai:arXiv.org:2512.08526v1 + cs.DB + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Marvin Harms, Jaeyoung Lim, David Rohr, Friedrich Rockenbauer, Nicholas Lawrance, Roland Siegwart + Shunit Agmon, Jonathan Gal, Amir Gilad, Ester Livshits, Or Mutay, Brit Youngmann, Benny Kimelfeld - The $k$-Fold Matroid Secretary Problem - https://arxiv.org/abs/2512.06611 - arXiv:2512.06611v1 Announce Type: new -Abstract: In the matroid secretary problem, elements $N := [n]$ of a matroid $\mathcal{M} \subseteq 2^N$ arrive in random order. When an element arrives, its weight is revealed and a choice must be made to accept or reject the element, subject to the constraint that the accepted set $S \in \mathcal{M}$. Kleinberg'05 gives a $(1-O(1/\sqrt{k}))$-competitive algorithm when $\mathcal{M}$ is a $k$-uniform matroid. We generalize their result, giving a $(1-O(\sqrt{\log(n)/k}))$-competitive algorithm when $\mathcal{M}$ is a $k$-fold matroid union. - oai:arXiv.org:2512.06611v1 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 + MVP: Multiple View Prediction Improves GUI Grounding + https://arxiv.org/abs/2512.08529 + arXiv:2512.08529v1 Announce Type: new +Abstract: GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing grounding models exhibit significant coordinate prediction instability, minor visual perturbations (e.g. cropping a few pixels) can drastically alter predictions, flipping results between correct and incorrect. This instability severely undermines model performance, especially for samples with high-resolution and small UI elements. To address this issue, we propose Multi-View Prediction (MVP), a training-free framework that enhances grounding performance through multi-view inference. Our key insight is that while single-view predictions may be unstable, aggregating predictions from multiple carefully cropped views can effectively distinguish correct coordinates from outliers. MVP comprises two components: (1) Attention-Guided View Proposal, which derives diverse views guided by instruction-to-image attention scores, and (2) Multi-Coordinates Clustering, which ensembles predictions by selecting the centroid of the densest spatial cluster. Extensive experiments demonstrate MVP's effectiveness across various models and benchmarks. Notably, on ScreenSpot-Pro, MVP boosts UI-TARS-1.5-7B to 56.1%, GTA1-7B to 61.7%, Qwen3VL-8B-Instruct to 65.3%, and Qwen3VL-32B-Instruct to 74.0%. The code is available at https://github.com/ZJUSCL/MVP. + oai:arXiv.org:2512.08529v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Rishi Gujjar, Kevin Hua, Robert Kleinberg, Frederick V. Qiu + http://creativecommons.org/licenses/by/4.0/ + Yunzhu Zhang, Zeyu Pan, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Linchao Zhu - Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics - https://arxiv.org/abs/2512.06612 - arXiv:2512.06612v1 Announce Type: new -Abstract: Gene expression estimation from pathology images has the potential to reduce the RNA sequencing cost. Point-wise loss functions have been widely used to minimize the discrepancy between predicted and absolute gene expression values. However, due to the complexity of the sequencing techniques and intrinsic variability across cells, the observed gene expression contains stochastic noise and batch effects, and estimating the absolute expression values accurately remains a significant challenge. To mitigate this, we propose a novel objective of learning relative expression patterns rather than absolute levels. We assume that the relative expression levels of genes exhibit consistent patterns across independent experiments, even when absolute expression values are affected by batch effects and stochastic noise in tissue samples. Based on the assumption, we model the relation and propose a novel loss function called STRank that is robust to noise and batch effects. Experiments using synthetic datasets and real datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/naivete5656/STRank. - oai:arXiv.org:2512.06612v1 + PaintFlow: A Unified Framework for Interactive Oil Paintings Editing and Generation + https://arxiv.org/abs/2512.08534 + arXiv:2512.08534v1 Announce Type: new +Abstract: Oil painting, as a high-level medium that blends human abstract thinking with artistic expression, poses substantial challenges for digital generation and editing due to its intricate brushstroke dynamics and stylized characteristics. Existing generation and editing techniques are often constrained by the distribution of training data and primarily focus on modifying real photographs. In this work, we introduce a unified multimodal framework for oil painting generation and editing. The proposed system allows users to incorporate reference images for precise semantic control, hand-drawn sketches for spatial structure alignment, and natural language prompts for high-level semantic guidance, while consistently maintaining a unified painting style across all outputs. Our method achieves interactive oil painting creation through three crucial technical advancements. First, we enhance the training stage with spatial alignment and semantic enhancement conditioning strategy, which map masks and sketches into spatial constraints, and encode contextual embedding from reference images and text into feature constraints, enabling object-level semantic alignment. Second, to overcome data scarcity, we propose a self-supervised style transfer pipeline based on Stroke-Based Rendering (SBR), which simulates the inpainting dynamics of oil painting restoration, converting real images into stylized oil paintings with preserved brushstroke textures to construct a large-scale paired training dataset. Finally, during inference, we integrate features using the AdaIN operator to ensure stylistic consistency. Extensive experiments demonstrate that our interactive system enables fine-grained editing while preserving the artistic qualities of oil paintings, achieving an unprecedented level of imagination realization in stylized oil paintings generation and editing. + oai:arXiv.org:2512.08534v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Kazuya Nishimura, Haruka Hirose, Ryoma Bise, Kaito Shiku, Yasuhiro Kojima + Zhangli Hu, Ye Chen, Jiajun Yao, Bingbing Ni - Hierarchical Deep Learning for Diatom Image Classification: A Multi-Level Taxonomic Approach - https://arxiv.org/abs/2512.06613 - arXiv:2512.06613v1 Announce Type: new -Abstract: Accurate taxonomic identification of diatoms is essential for aquatic ecosystem monitoring, yet conventional methods depend heavily on expert taxonomists. Recent deep learning approaches improve automation, but most treat diatom recognition as flat classification predicting only one taxonomic rank. We investigate whether embedding taxonomic hierarchy into neural network architectures can improve both accuracy and error locality. - We introduce a hierarchical convolutional network with five cascaded heads that jointly predict class, order, family, genus, and species. Each head receives shared backbone features and probability distributions from higher levels, with binary masks restricting predictions to valid descendants during training and inference. Using a filtered dataset of 1,456 diatom images covering 82 species, we compare hierarchical and flat models under identical settings. - The hierarchical model matches flat baselines at species level (69.4% accuracy) while outperforming at all upper taxonomic levels. When species predictions fail, errors remain taxonomically local: 92.5 % of misclassified species are correctly predicted at genus level, versus 67.2% for flat baselines. The hierarchical model reduces mean taxonomic distance by 38.2% (1.209 vs. 1.955). - Progressive training reveals bidirectional mechanisms: hierarchical constraint masks operate top-down to constrain prediction space, while gradients from fine-grained levels propagate bottom-up through the shared backbone, refining features. This improves class accuracy from 96.2% to 99.5% and yields 6-8% gains at upper levels, producing more robust, interpretable, and biologically aligned predictions for multi-level taxonomic classification. - oai:arXiv.org:2512.06613v1 + Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement + https://arxiv.org/abs/2512.08535 + arXiv:2512.08535v1 Announce Type: new +Abstract: Although recent 3D-native generators have made great progress in synthesizing reliable geometry, they still fall short in achieving realistic appearances. A key obstacle lies in the lack of diverse and high-quality real-world 3D assets with rich texture details, since capturing such data is intrinsically difficult due to the diverse scales of scenes, non-rigid motions of objects, and the limited precision of 3D scanners. We introduce Photo3D, a framework for advancing photorealistic 3D generation, which is driven by the image data generated by the GPT-4o-Image model. Considering that the generated images can distort 3D structures due to their lack of multi-view consistency, we design a structure-aligned multi-view synthesis pipeline and construct a detail-enhanced multi-view dataset paired with 3D geometry. Building on it, we present a realistic detail enhancement scheme that leverages perceptual feature adaptation and semantic structure matching to enforce appearance consistency with realistic details while preserving the structural consistency with the 3D-native geometry. Our scheme is general to different 3D-native generators, and we present dedicated training strategies to facilitate the optimization of geometry-texture coupled and decoupled 3D-native generation paradigms. Experiments demonstrate that Photo3D generalizes well across diverse 3D-native generation paradigms and achieves state-of-the-art photorealistic 3D generation performance. + oai:arXiv.org:2512.08535v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Yueying Ke + Xinyue Liang, Zhinyuan Ma, Lingchen Sun, Yanjun Guo, Lei Zhang - Data-driven functional state estimation of complex networks - https://arxiv.org/abs/2512.06614 - arXiv:2512.06614v1 Announce Type: new -Abstract: The internal state of a dynamical system, a set of variables that defines its evolving configuration, is often hidden and cannot be fully measured, posing a central challenge for real-time monitoring and control. While observers are designed to estimate these latent states from sensor outputs, their classical designs rely on precise system models, which are often unattainable for complex network systems. Here, we introduce a data-driven framework for estimating a targeted set of state variables, known as functional observers, without identifying the model parameters. We establish a fundamental functional observability criterion based on historical trajectories that guarantees the existence of such observers. We then develop methods to construct observers using either input-output data or partial state data. These observers match or exceed the performance of model-based counterparts while remaining applicable even to unobservable systems. The framework incorporates noise mitigation and can be easily extended to nonlinear networks via Koopman embeddings. We demonstrate its broad utility through applications including sensor fault detection in water networks, load-frequency control in power grids, and target estimation in nonlinear neuronal systems. Our work provides a practical route for real-time target state inference in complex systems where models are unavailable. - oai:arXiv.org:2512.06614v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans + https://arxiv.org/abs/2512.08536 + arXiv:2512.08536v1 Announce Type: new +Abstract: Ethical awareness is critical for robots operating in human environments, yet existing automated planning tools provide little support. Manually specifying ethical rules is labour-intensive and highly context-specific. We present Principles2Plan, an interactive research prototype demonstrating how a human and a Large Language Model (LLM) can collaborate to produce context-sensitive ethical rules and guide automated planning. A domain expert provides the planning domain, problem details, and relevant high-level principles such as beneficence and privacy. The system generates operationalisable ethical rules consistent with these principles, which the user can review, prioritise, and supply to a planner to produce ethically-informed plans. To our knowledge, no prior system supports users in generating principle-grounded rules for classical planning contexts. Principles2Plan showcases the potential of human-LLM collaboration for making ethical automated planning more practical and feasible. + oai:arXiv.org:2512.08536v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Yuan Zhang, Ziyuan Luo, Wenxuan Xu, Jiayu Wu, Wenqi Cao, Ranbo Cheng, Tingting Qin, Yuanqing Xia, Mohamed Darouach, Aming Li, Tyrone Fernando + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Tammy Zhong, Yang Song, Maurice Pagnucco - Memory Power Asymmetry in Human-AI Relationships: Preserving Mutual Forgetting in the Digital Age - https://arxiv.org/abs/2512.06616 - arXiv:2512.06616v1 Announce Type: new -Abstract: As artificial intelligence (AI) becomes embedded in personal and professional relationships, a new kind of power imbalance emerges from asymmetric memory capabilities. Human relationships have historically relied on mutual forgetting, the natural tendency for both parties to forget details over time, as a foundation for psychological safety, forgiveness, and identity change. By contrast, AI systems can record, store, and recombine interaction histories at scale, often indefinitely. We introduce Memory Power Asymmetry (MPA): a structural power imbalance that arises when one relationship partner (typically an AI-enabled firm) possesses a substantially superior capacity to record, retain, retrieve, and integrate the shared history of the relationship, and can selectively deploy that history in ways the other partner (the human) cannot. Drawing on research in human memory, power-dependence theory, AI architecture, and consumer vulnerability, we develop a conceptual framework with four dimensions of MPA (persistence, accuracy, accessibility, integration) and four mechanisms by which memory asymmetry is translated into power (strategic memory deployment, narrative control, dependence asymmetry, vulnerability accumulation). We theorize downstream consequences at individual, relational/firm, and societal levels, formulate boundary-conditioned propositions, and articulate six design principles for restoring a healthier balance of memory in human-AI relationships (e.g., forgetting by design, contextual containment, symmetric access to records). Our analysis positions MPA as a distinct construct relative to information asymmetry, privacy, surveillance, and customer relationship management, and argues that protecting mutual forgetting, or at least mutual control over memory, should become a central design and policy goal in the AI age. - oai:arXiv.org:2512.06616v1 - cs.HC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation + https://arxiv.org/abs/2512.08537 + arXiv:2512.08537v1 Announce Type: new +Abstract: Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's photorealistic synthesis, yet suffer from high latency due to sequential AR generation and iterative denoising. In this work, we tackle this bottleneck and propose a unified AR-diffusion framework Fast-ARDiff that jointly optimizes both components, accelerating AR speculative decoding while simultaneously facilitating faster diffusion decoding. Specifically: (1) The entropy-informed speculative strategy encourages draft model to produce higher-entropy representations aligned with target model's entropy characteristics, mitigating entropy mismatch and high rejection rates caused by draft overconfidence. (2) For diffusion decoding, rather than treating it as an independent module, we integrate it into the same end-to-end framework using a dynamic scheduler that prioritizes AR optimization to guide the diffusion part in further steps. The diffusion part is optimized through a joint distillation framework combining trajectory and distribution matching, ensuring stable training and high-quality synthesis with extremely few steps. During inference, shallow feature entropy from AR module is used to pre-filter low-entropy drafts, avoiding redundant computation and improving latency. Fast-ARDiff achieves state-of-the-art acceleration across diverse models: on ImageNet 256$\times$256, TransDiff attains 4.3$\times$ lossless speedup, and NextStep-1 achieves 3$\times$ acceleration on text-conditioned generation. Code will be available at https://github.com/aSleepyTree/Fast-ARDiff. + oai:arXiv.org:2512.08537v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Rasam Dorri, Rami Zwick + Zhen Zou, Xiaoxiao Ma, Jie Huang, Zichao Yu, Feng Zhao - FastLEC: Parallel Datapath Equivalence Checking with Hybrid Engines - https://arxiv.org/abs/2512.06627 - arXiv:2512.06627v1 Announce Type: new -Abstract: Combinational equivalence checking (CEC) remains a challenge EDA task in the formal verification of datapath circuits due to their complex arithmetic structures and the limited capability or scalability of SAT, BDD, and exact-simulation (ES) based techniques when used independently. This work presents FastLEC, a hybrid prover that unifies these three formal reasoning engines and introduces three strategies that substantially enhance verification efficiency. First, a regression-based engine-scheduling heuristic predicts solver effectiveness, enabling more accurate and balanced allocation of computational resources. Second, datapath-structure-aware partitioning strategies, along with a dynamic divide-and-conquer SAT prover, exploit the regularity of arithmetic designs while preserving completeness. Third, the memory overhead of ES is significantly reduced through address-reference-count tracking, and simulation is further accelerated through a GPU-enabled backend. FastLEC is evaluated across 368 datapath circuits. Using 32 CPU cores, it proves 5.07x more circuits than the widely used ABC &cec tool. Compared with the latest best datapath-oriented serial and parallel CEC provers, FastLEC outperforms them by 3.33x and 2.67x in PAR-2 time, demonstrating an improvement of 74 newly solved circuits. With the addition of a single GPU, it achieves a further 4.07x improvement. The prover also demonstrates excellent scalability. - oai:arXiv.org:2512.06627v1 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + vEDGAR - Can CARLA Do HiL? + https://arxiv.org/abs/2512.08541 + arXiv:2512.08541v1 Announce Type: new +Abstract: Simulation offers advantages throughout the development process of automated driving functions, both in research and product development. Common open-source simulators like CARLA are extensively used in training, evaluation, and software-in-the-loop testing of new automated driving algorithms. However, the CARLA simulator lacks an evaluation where research and automated driving vehicles are simulated with their entire sensor and actuation stack in real time. The goal of this work is therefore to create a simulation framework for testing the automation software on its dedicated hardware and identifying its limits. Achieving this goal would greatly benefit the open-source development workflow of automated driving functions, designating CARLA as a consistent evaluation tool along the entire development process. To achieve this goal, in a first step, requirements are derived, and a simulation architecture is specified and implemented. Based on the formulated requirements, the proposed vEDGAR software is evaluated, resulting in a final conclusion on the applicability of CARLA for HiL testing of automated vehicles. The tool is available open source: Modified CARLA fork: https://github.com/TUMFTM/carla, vEDGAR Framework: https://github.com/TUMFTM/vEDGAR + oai:arXiv.org:2512.08541v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Xindi Zhang, Furong Ye, Zhihan Chen, Shaowei Cai + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Nils Gehrke, David Brecht, Dominik Kulmer, Dheer Patel, Frank Diermeyer - MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment - https://arxiv.org/abs/2512.06628 - arXiv:2512.06628v1 Announce Type: new -Abstract: Embodied imitation learning is constrained by the scarcity of diverse, long-horizon robotic manipulation data. Existing video generation models for this domain are limited to synthesizing short clips of simple actions and often rely on manually defined trajectories. To this end, we introduce MIND-V, a hierarchical framework designed to synthesize physically plausible and logically coherent videos of long-horizon robotic manipulation. Inspired by cognitive science, MIND-V bridges high-level reasoning with pixel-level synthesis through three core components: a Semantic Reasoning Hub (SRH) that leverages a pre-trained vision-language model for task planning; a Behavioral Semantic Bridge (BSB) that translates abstract instructions into domain-invariant representations; and a Motor Video Generator (MVG) for conditional video rendering. MIND-V employs Staged Visual Future Rollouts, a test-time optimization strategy to enhance long-horizon robustness. To align the generated videos with physical laws, we introduce a GRPO reinforcement learning post-training phase guided by a novel Physical Foresight Coherence (PFC) reward. PFC leverages the V-JEPA world model to enforce physical plausibility by aligning the predicted and actual dynamic evolutions in the feature space. MIND-V demonstrates state-of-the-art performance in long-horizon robotic manipulation video generation, establishing a scalable and controllable paradigm for embodied data synthesis. - oai:arXiv.org:2512.06628v1 - cs.RO + A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation + https://arxiv.org/abs/2512.08542 + arXiv:2512.08542v1 Announce Type: new +Abstract: Color image generation has a wide range of applications, but the existing generation models ignore the correlation among color channels, which may lead to chromatic aberration problems. In addition, the data distribution problem of color images has not been systematically elaborated and explained, so that there is still the lack of the theory about measuring different color images datasets. In this paper, we define a new quaternion Wasserstein distance and develop its dual theory. To deal with the quaternion linear programming problem, we derive the strong duality form with helps of quaternion convex set separation theorem and quaternion Farkas lemma. With using quaternion Wasserstein distance, we propose a novel Wasserstein quaternion generative adversarial network. Experiments demonstrate that this novel model surpasses both the (quaternion) generative adversarial networks and the Wasserstein generative adversarial network in terms of generation efficiency and image quality. + oai:arXiv.org:2512.08542v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ruicheng Zhang, Mingyang Zhang, Jun Zhou, Zhangrui Guo, Xiaofan Liu, Zunnan Xu, Zhizhou Zhong, Puxin Yan, Haocheng Luo, Xiu Li + Zhigang Jia, Duan Wang, Hengkai Wang, Yajun Xie, Meixiang Zhao, Xiaoyu Zhao - FlatFormer: A Flat Transformer Knowledge Tracing Model Based on Cognitive Bias Injection - https://arxiv.org/abs/2512.06629 - arXiv:2512.06629v1 Announce Type: new -Abstract: Knowledge Tracing (KT) models face a critical ``Performance-Complexity Trap'': capturing complex cognitive dynamics like learning sessions and memory decay typically requires deep hierarchical architectures, which incur prohibitive computational costs for real-time deployment. To resolve this, we propose FlatFormer, a streamlined architecture based on the novel design paradigm of ``Information Injection over Structural Stacking.'' Unlike parameter-heavy hierarchical models, FlatFormer leverages a standard flat Transformer augmented with two lightweight injection mechanisms: (i) a hybrid input encoding strategy combining learnable session identifiers with fixed sinusoidal step embeddings; and (ii) a pre-computed power-law bias integrated directly into attention logits to explicitly model the forgetting curve. Extensive experiments on four large-scale datasets (e.g., EdNet, Junyi) show that FlatFormer achieves state-of-the-art performance. For example, on the EdNet dataset, compared to the strongest hierarchical baseline (HiTSKT), its absolute AUC increased by 8.3%, while using less than 15% of parameters, and inference speed was about three times faster. These results validate that high cognitive fidelity does not necessitate architectural complexity. - oai:arXiv.org:2512.06629v1 - cs.AI - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 + Optimal Control of Behavioral-Feedback SIR Epidemic Model + https://arxiv.org/abs/2512.08544 + arXiv:2512.08544v1 Announce Type: new +Abstract: We consider a behavioral-feedback SIR epidemic model, in which the infection rate depends in feedback on the fractions of susceptible and infected agents, respectively. The considered model allows one to account for endogenous adaptation mechanisms of the agents in response to the epidemics, such as voluntary social distancing, or the adoption of face masks. For this model, we formulate an optimal control problem for a social planner that has the ability to reduce the infection rate to keep the infection curve below a certain threshold within an infinite time horizon, while minimizing the intervention cost. Based on the dynamic properties of the model, we prove that, under quite general conditions on the infection rate, the \emph{filling the box} strategy is the optimal control. This strategy consists in letting the epidemics spread without intervention until the threshold is reached, then applying the minimum control that leaves the fraction of infected individuals constantly at the threshold until the reproduction number becomes less than one and the infection naturally fades out. Our result generalizes one available in the literature for the equivalent problem formulated for the classical SIR model, which can be recovered as a special case of our model when the infection rate is constant. Our contribution enhances the understanding of epidemic management with adaptive human behavior, offering insights for robust containment strategies. + oai:arXiv.org:2512.08544v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiao-li Xia, Hou-biao Li + http://creativecommons.org/licenses/by/4.0/ + Martina Alutto, Leonardo Cianfanelli, Giacomo Como, Fabio Fagnani, Francesca Parise - Quantum Temporal Convolutional Neural Networks for Cross-Sectional Equity Return Prediction: A Comparative Benchmark Study - https://arxiv.org/abs/2512.06630 - arXiv:2512.06630v1 Announce Type: new -Abstract: Quantum machine learning offers a promising pathway for enhancing stock market prediction, particularly under complex, noisy, and highly dynamic financial environments. However, many classical forecasting models struggle with noisy input, regime shifts, and limited generalization capacity. To address these challenges, we propose a Quantum Temporal Convolutional Neural Network (QTCNN) that combines a classical temporal encoder with parameter-efficient quantum convolution circuits for cross-sectional equity return prediction. The temporal encoder extracts multi-scale patterns from sequential technical indicators, while the quantum processing leverages superposition and entanglement to enhance feature representation and suppress overfitting. We conduct a comprehensive benchmarking study on the JPX Tokyo Stock Exchange dataset and evaluate predictions through long-short portfolio construction using out-of-sample Sharpe ratio as the primary performance metric. QTCNN achieves a Sharpe ratio of 0.538, outperforming the best classical baseline by approximately 72\%. These results highlight the practical potential of quantum-enhanced forecasting model, QTCNN, for robust decision-making in quantitative finance. - oai:arXiv.org:2512.06630v1 - cs.LG - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 + Curriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks + https://arxiv.org/abs/2512.08545 + arXiv:2512.08545v1 Announce Type: new +Abstract: Large Language Models and multi-agent systems have shown promise in decomposing complex tasks, yet they struggle with long-horizon reasoning tasks and escalating computation cost. This work introduces a hierarchical multi-agent architecture that distributes reasoning across a 64*64 grid of lightweight agents, supported by a selective oracle. A spatial curriculum progressively expands the operational region of the grid, ensuring that agents master easier central tasks before tackling harder peripheral ones. To improve reliability, the system integrates Negative Log-Likelihood as a measure of confidence, allowing the curriculum to prioritize regions where agents are both accurate and well calibrated. A Thompson Sampling curriculum manager adaptively chooses training zones based on competence and NLL-driven reward signals. We evaluate the approach on a spatially grounded Tower of Hanoi benchmark, which mirrors the long-horizon structure of many robotic manipulation and planning tasks. Results demonstrate improved stability, reduced oracle usage, and stronger long-range reasoning from distributed agent cooperation. + oai:arXiv.org:2512.08545v1 + cs.CL + cs.AI + cs.CV + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chi-Sheng Chen, Xinyu Zhang, Rong Fu, Qiuzhe Xie, Fan Zhang + Indrajit Kar, Kalathur Chenchu Kishore Kumar - B-spline periodization of Fourier pseudo-spectral method for non-periodic problems - https://arxiv.org/abs/2512.06631 - arXiv:2512.06631v1 Announce Type: new -Abstract: Spectral methods are renowned for their high accuracy and efficiency in solving partial differential equations. The Fourier pseudo-spectral method is limited to periodic domains and suffers from Gibbs oscillations in non-periodic problems. The Chebyshev method mitigates this issue but requires edge-clustered grids, which does not match the characteristics of many physical problems. To overcome these restrictions, we propose a B-spline-periodized Fourier (BSPF) method that extends to non-periodic problems while retaining spectral-like accuracy and efficiency. The method combines a B-spline approximation with a Fourier-based residual correction. The B-spline component enforces the smooth matching of boundary values and derivatives, while the periodic residual is efficiently treated by Fourier differentiation/integration. This construction preserves spectral convergence within the domain and algebraic convergence at the boundaries. Numerical tests on differentiation and integration confirm the accuracy of the BSPF method superior to Chebyshev and finite-difference schemes for interior-oscillatory data. Analytical mapping further extends BSPF to non-uniform meshes, which enables selective grid refinement in regions of sharp variation. Applications of the BSPF method to the one-dimensional Burgers' equation and two-dimensional shallow water equations demonstrate accurate resolution of sharp gradients and nonlinear wave propagation, proving it as a flexible and efficient framework for solving non-periodic PDEs with high-order accuracy. - oai:arXiv.org:2512.06631v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 + An Iteration-Free Fixed-Point Estimator for Diffusion Inversion + https://arxiv.org/abs/2512.08547 + arXiv:2512.08547v1 Announce Type: new +Abstract: Diffusion inversion aims to recover the initial noise corresponding to a given image such that this noise can reconstruct the original image through the denoising diffusion process. The key component of diffusion inversion is to minimize errors at each inversion step, thereby mitigating cumulative inaccuracies. Recently, fixed-point iteration has emerged as a widely adopted approach to minimize reconstruction errors at each inversion step. However, it suffers from high computational costs due to its iterative nature and the complexity of hyperparameter selection. To address these issues, we propose an iteration-free fixed-point estimator for diffusion inversion. First, we derive an explicit expression of the fixed point from an ideal inversion step. Unfortunately, it inherently contains an unknown data prediction error. Building upon this, we introduce the error approximation, which uses the calculable error from the previous inversion step to approximate the unknown error at the current inversion step. This yields a calculable, approximate expression for the fixed point, which is an unbiased estimator characterized by low variance, as shown by our theoretical analysis. We evaluate reconstruction performance on two text-image datasets, NOCAPS and MS-COCO. Compared to DDIM inversion and other inversion methods based on the fixed-point iteration, our method achieves consistent and superior performance in reconstruction tasks without additional iterations or training. + oai:arXiv.org:2512.08547v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dongan Li, Mou Lin, Shunxiang Cao, Shengli Chen + Yifei Chen, Kaiyu Song, Yan Pan, Jianxing Yu, Jian Yin, Hanjiang Lai - FEALPy v3: A Cross-platform Intelligent Numerical Simulation Engine - https://arxiv.org/abs/2512.06632 - arXiv:2512.06632v1 Announce Type: new -Abstract: In resent years, the software ecosystem for numerical simulation still remains fragmented, with different algorithms and discretization methods often implemented in isolation, each with distinct data structures and programming conventions. This fragmentation is compounded by the growing divide between packages from different research fields and the lack of a unified, universal data structure, hindering the development of integrated, cross-platform solutions. In this work, we introduce FEALPy, a numerical simulation engine built around a unified tensor abstraction layer in a modular design. It enables seamless integration between diverse numerical methods along with deep learning workflows. By supporting multiple computational backends such as NumPy, PyTorch, and JAX, FEALPy ensures consistent adaptability across CPU and GPU hardware systems. Its modular architecture facilitates the entire simulation pipeline, from mesh handling and assembly to solver execution, with built-in support for automatic differentiation. In this paper, the versatility and efficacy of the framework are demonstrated through applications spanning linear elasticity, high-order PDEs, moving mesh methods, inverse problems and path planning. - oai:arXiv.org:2512.06632v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 + Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations + https://arxiv.org/abs/2512.08548 + arXiv:2512.08548v1 Announce Type: new +Abstract: Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge arises from severe distribution shifts between robotic action data, primarily due to substantial numerical variations in action commands across diverse robotic platforms and tasks, hindering the effective transfer of pretrained knowledge. To address this limitation, we propose a semantically grounded linguistic representation to normalize actions for efficient pretraining. Unlike conventional discretized action representations that are sensitive to numerical scales, the motion representation specifically disregards numeric scale effects, emphasizing directionality instead. This abstraction mitigates distribution shifts, yielding a more generalizable pretraining representation. Moreover, using the motion representation narrows the feature distance between action tokens and standard vocabulary tokens, mitigating modality gaps. Multi-task experiments on two benchmarks demonstrate that the proposed method significantly improves generalization performance and transferability in robotic manipulation tasks. + oai:arXiv.org:2512.08548v1 + cs.RO + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yangyang Zheng, Huayi Wei, Yunqing Huang, Chunyu Chen, Tian Tian, Hanbin Liu, Wenbin Wang, Liang He + Yuchi Zhang, Churui Sun, Shiqi Liang, Diyuan Liu, Chao Ji, Wei-Nan Zhang, Ting Liu - Distribution-Aware Exploration for Adaptive HNSW Search - https://arxiv.org/abs/2512.06636 - arXiv:2512.06636v1 Announce Type: new -Abstract: Hierarchical Navigable Small World (HNSW) is widely adopted for approximate nearest neighbor search (ANNS) for its ability to deliver high recall with low latency on large-scale, high-dimensional embeddings. The exploration factor, commonly referred to as ef, is a key parameter in HNSW-based vector search that balances accuracy and efficiency. However, existing systems typically rely on manually and statically configured ef values that are uniformly applied across all queries. This results in a distribution-agnostic configuration that fails to account for the non-uniform and skewed nature of real-world embedding data and query workloads. As a consequence, HNSW-based systems suffer from two key practical issues: (i) the absence of recall guarantees, and (ii) inefficient ANNS performance due to over- or under-searching. In this paper, we propose Adaptive-ef (Ada-ef), a data-driven, update-friendly, query-adaptive approach that dynamically configures ef for each query at runtime to approximately meet a declarative target recall with minimal computation. The core of our approach is a theoretically grounded statistical model that captures the similarity distribution between each query and the database vectors. Based on this foundation, we design a query scoring mechanism that distinguishes between queries requiring only small ef and those that need larger ef to meet a target recall, and accordingly assigns an appropriate ef to each query. Experimental results on real-world embeddings produced by state-of-the-art Transformer models from OpenAI and Cohere show that, compared with state-of-the-art learning-based adaptive approaches, our method achieves the target recall while avoiding both over- and under-searching, reducing online query latency by up to 4x, offline computation time by 50x, and offline memory usage by 100x. - oai:arXiv.org:2512.06636v1 - cs.DB - Tue, 09 Dec 2025 00:00:00 -0500 + Gamification with Purpose: What Learners Prefer to Motivate Their Learning + https://arxiv.org/abs/2512.08551 + arXiv:2512.08551v1 Announce Type: new +Abstract: This study investigates learners' preferences for game design elements (GDEs) in educational contexts to inform the development of purpose-driven gamification strategies. It emphasizes a learner-centered approach that aligns gamification design with pedagogical goals, while mitigating risks such as the erosion of intrinsic motivation. A systematic literature review was conducted to identify ten widely discussed GDEs. Visual prototypes representing each element were developed, and a best-worst scaling (BWS) survey with 125 participants was administered to elicit preference rankings. Qualitative feedback was also collected to uncover motivational drivers. Learners consistently preferred GDEs that support learning processes directly-most notably progress bars, concept maps, immediate feedback, and achievements. Qualitative analysis revealed six recurring motivational themes, including visible progress, content relevance, and constructive feedback. The findings suggest that learners value gamification elements that are meaningfully integrated with educational content and support intrinsic motivation. Purpose-aligned gamification should prioritize tools that visualize learning progress and provide actionable feedback, rather than relying solely on extrinsic incentives. + oai:arXiv.org:2512.08551v1 + cs.SE + cs.CY + cs.HC + cs.MM + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chao Zhang, Ren\'ee J. Miller + Kai Marquardt, Mona Schulz, Anne Koziolek, Lucia Happe - The Impact of Data Characteristics on GNN Evaluation for Detecting Fake News - https://arxiv.org/abs/2512.06638 - arXiv:2512.06638v1 Announce Type: new -Abstract: Graph neural networks (GNNs) are widely used for the detection of fake news by modeling the content and propagation structure of news articles on social media. We show that two of the most commonly used benchmark data sets - GossipCop and PolitiFact - are poorly suited to evaluating the utility of models that use propagation structure. Specifically, these data sets exhibit shallow, ego-like graph topologies that provide little or no ability to differentiate among modeling methods. We systematically benchmark five GNN architectures against a structure-agnostic multilayer perceptron (MLP) that uses the same node features. We show that MLPs match or closely trail the performance of GNNs, with performance gaps often within 1-2% and overlapping confidence intervals. To isolate the contribution of structure in these datasets, we conduct controlled experiments where node features are shuffled or edge structures randomized. We find that performance collapses under feature shuffling but remains stable under edge randomization. This suggests that structure plays a negligible role in these benchmarks. Structural analysis further reveals that over 75% of nodes are only one hop from the root, exhibiting minimal structural diversity. In contrast, on synthetic datasets where node features are noisy and structure is informative, GNNs significantly outperform MLPs. These findings provide strong evidence that widely used benchmarks do not meaningfully test the utility of modeling structural features, and they motivate the development of datasets with richer, more diverse graph topologies. - oai:arXiv.org:2512.06638v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Extended formulations for induced tree and path polytopes of chordal graphs + https://arxiv.org/abs/2512.08554 + arXiv:2512.08554v1 Announce Type: new +Abstract: In this article, we give an extended space formulation for the induced tree and path polytopes of chordal graphs with variables associated with the edge and vertex sets. Whereas the formulation for the induced tree polytope is easily seen to have a compact size, the system we provide for the induced path polytope has an exponential number of inequalities. We show which of these inequalities define facets and exhibit a superset of the facet-defining ones that can be enumerated in polynomial time. We show that for some graphs, the latter superset contains redundant inequalities. + As corollaries, we obtain that the problems of finding an induced tree or path maximizing a linear function over the edges and vertices are solvable in polynomial time for the class of chordal graphs . + oai:arXiv.org:2512.08554v1 + cs.DM + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Isha Karn, David Jensen + Alexandre Dupont-Bouillard - An Index-based Approach for Efficient and Effective Web Content Extraction - https://arxiv.org/abs/2512.06641 - arXiv:2512.06641v1 Announce Type: new -Abstract: As web agents (e.g., Deep Research) routinely consume massive volumes of web pages to gather and analyze information, LLM context management -- under large token budgets and low signal density -- emerges as a foundational, high-importance, and technically challenging problem for agentic and RAG pipelines. Existing solutions for extracting relevant content are inadequate: generative extraction models suffer from high latency, rule-based heuristics lack adaptability, and chunk-and-rerank methods are blind to webpage structure. To overcome these issues, we introduce Index-based Web Content Extraction to reframe the extraction process from slow, token-by-token generation into a highly efficient, discriminative task of index prediction, achieving both effectiveness and efficiency. We partition HTML into structure-aware, addressable segments, and extract only the positional indices of content relevant to a given query. This method decouples extraction latency from content length, enabling rapid, query-relevant extraction. We first evaluate our method as a post-retrieval processing component within an RAG QA system and find that it improves QA accuracy. Then we directly measure its match rate with the target content in two scenarios: main content extraction (ME) and query-relevant extraction (QE). Experimental results show that our method outperforms existing works in both accuracy and speed, effectively bridging the gap between LLMs and the vast webpages. - oai:arXiv.org:2512.06641v1 - cs.IR - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + A scalable high-order multigrid-FFT Poisson solver for unbounded domains on adaptive multiresolution grids + https://arxiv.org/abs/2512.08555 + arXiv:2512.08555v1 Announce Type: new +Abstract: Multigrid solvers are among the most efficient methods for solving the Poisson equation, which is ubiquitous in computational physics. For example, in the context of incompressible flows, it is typically the costliest operation. The present document expounds upon the implementation of a flexible multigrid solver that is capable of handling any type of boundary conditions within murphy, a multiresolution framework for solving partial differential equations (PDEs) on collocated adaptive grids. The utilization of a Fourier-based direct solver facilitates the attainment of flexibility and enhanced performance by accommodating any combination of unbounded and semi-unbounded boundary conditions. The employment of high-order compact stencils contributes to the reduction of communication demands while concurrently enhancing the accuracy of the system. The resulting solver is validated against analytical solutions for periodic and unbounded domains. In conclusion, the solver has been demonstrated to demonstrate scalability to 16,384 cores within the context of leading European high-performance computing infrastructures. + oai:arXiv.org:2512.08555v1 + math.NA + cs.DC + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Yihan Chen, Benfeng Xu, Xiaorui Wang, Zhendong Mao + Gilles Poncelet, Jonathan Lambrechts, Thomas Gillis, Philippe Chatelain - Masked Autoencoder Pretraining on Strong-Lensing Images for Joint Dark-Matter Model Classification and Super-Resolution - https://arxiv.org/abs/2512.06642 - arXiv:2512.06642v1 Announce Type: new -Abstract: Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE) pretraining strategy on simulated strong-lensing images from the DeepLense ML4SCI benchmark to learn generalizable representations for two downstream tasks: (i) classifying the underlying dark matter model (cold dark matter, axion-like, or no substructure) and (ii) enhancing low-resolution lensed images via super-resolution. We pretrain a Vision Transformer encoder using a masked image modeling objective, then fine-tune the encoder separately for each task. Our results show that MAE pretraining, when combined with appropriate mask ratio tuning, yields a shared encoder that matches or exceeds a ViT trained from scratch. Specifically, at a 90% mask ratio, the fine-tuned classifier achieves macro AUC of 0.968 and accuracy of 88.65%, compared to the scratch baseline (AUC 0.957, accuracy 82.46%). For super-resolution (16x16 to 64x64), the MAE-pretrained model reconstructs images with PSNR ~33 dB and SSIM 0.961, modestly improving over scratch training. We ablate the MAE mask ratio, revealing a consistent trade-off: higher mask ratios improve classification but slightly degrade reconstruction fidelity. Our findings demonstrate that MAE pretraining on physics-rich simulations provides a flexible, reusable encoder for multiple strong-lensing analysis tasks. - oai:arXiv.org:2512.06642v1 + SSCATeR: Sparse Scatter-Based Convolution Algorithm with Temporal Data Recycling for Real-Time 3D Object Detection in LiDAR Point Clouds + https://arxiv.org/abs/2512.08557 + arXiv:2512.08557v1 Announce Type: new +Abstract: This work leverages the continuous sweeping motion of LiDAR scanning to concentrate object detection efforts on specific regions that receive a change in point data from one frame to another. We achieve this by using a sliding time window with short strides and consider the temporal dimension by storing convolution results between passes. This allows us to ignore unchanged regions, significantly reducing the number of convolution operations per forward pass without sacrificing accuracy. This data reuse scheme introduces extreme sparsity to detection data. To exploit this sparsity, we extend our previous work on scatter-based convolutions to allow for data reuse, and as such propose Sparse Scatter-Based Convolution Algorithm with Temporal Data Recycling (SSCATeR). This operation treats incoming LiDAR data as a continuous stream and acts only on the changing parts of the point cloud. By doing so, we achieve the same results with as much as a 6.61-fold reduction in processing time. Our test results show that the feature maps output by our method are identical to those produced by traditional sparse convolution techniques, whilst greatly increasing the computational efficiency of the network. + oai:arXiv.org:2512.08557v1 cs.CV - astro-ph.CO - astro-ph.IM - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Achmad Ardani Prasha, Clavino Ourizqi Rachmadi, Muhamad Fauzan Ibnu Syahlan, Naufal Rahfi Anugerah, Nanda Garin Raditya, Putri Amelia, Sabrina Laila Mutiara, Hilman Syachr Ramadhan + Alexander Dow, Manduhu Manduhu, Matheus Santos, Ben Bartlett, Gerard Dooly, James Riordan - Functional Reduction to Speed Up Bounded Model Checking - https://arxiv.org/abs/2512.06643 - arXiv:2512.06643v1 Announce Type: new -Abstract: Bounded model checking (BMC) is a widely used technique for formal property verification (FPV), where the transition relation is repeatedly unrolled to increasing depths and encoded into Boolean satisfiability (SAT) queries. As the bound grows deeper, these SAT queries typically become more difficult to solve, posing scalability challenges. Howevefor, many FPV problems involve multiple copies of related circuits, creating opportunities to simplify the unrolled transition relation. Motivated by the functionally reduced and-inverter-graph (FRAIG) technique, we propose FRAIG-BMC, which incrementally identifies and merges functionally equivalent nodes during the unrolling process. By reducing redundancy, FRAIG-BMC improves the efficiency of SAT solving and accelerates property checking. Experiments demonstrate that FRAIG-BMC significantly speeds up BMC across a range of applications, including sequential equivalence checking, partial retention register detection, and information flow checking - oai:arXiv.org:2512.06643v1 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + Labeled Delegated PSI and its Applications in the Public Sector + https://arxiv.org/abs/2512.08558 + arXiv:2512.08558v1 Announce Type: new +Abstract: Sensitive citizen data, such as social, medical, and fiscal data, is heavily fragmented across + public bodies and the private domain. Mining the combined data sets allows for new insights that otherwise remain hidden. + Examples are improved healthcare, fraud detection, and evidence-based policy making. + (Multi-party) delegated private set intersection (D-PSI) is a privacy-enhancing technology to link data across multiple data providers using a data collector. + However, before it can be deployed in these use cases, it needs to be enhanced with additional functions, e.g., securely delivering payload only for elements in the intersection. + Although there has been recent progress in the communication and computation requirements of D-PSI, these practical obstacles have not yet been addressed. + This paper is the result of a collaboration with a governmental organization responsible for collecting, linking, and pseudonymizing data. + Based on their requirements, we design a new D-PSI protocol with composable output functions, including encrypted payload and pseudonymized identifiers. + We show that our protocol is secure in the standard model against colluding semi-honest data providers and against a non-colluding, possibly malicious independent party, the data collector. + It, hence, allows to privately link and collect data from multiple data providers suitable for deployment in these use cases in the public sector. + oai:arXiv.org:2512.08558v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Changyuan Yu, Wenbin Che, Hongce Zhang + http://creativecommons.org/licenses/by/4.0/ + Kristof Verslype, Florian Kerschbaum, Cyprien Delpech de Saint Guilhem, Bart De Decker, Jorn Lapon - From Forecast to Action: A Deep Learning Model for Predicting Power Outages During Tropical Cyclones - https://arxiv.org/abs/2512.06644 - arXiv:2512.06644v1 Announce Type: new -Abstract: Power outages caused by tropical cyclones (TCs) pose serious risks to electric power systems and the communities they serve. Accurate, high-resolution outage forecasting is essential for enabling both proactive mitigation planning and real-time emergency response. This study introduces the SpatioTemporal Outage ForeCAST (STO-CAST) model, a deep learning framework developed for real-time, regional-scale outage prediction during TC events with high-resolution outputs in both space and time. STO-CAST integrates static environmental and infrastructure attributes with dynamic meteorological and outage sequences using gated recurrent units (GRUs) and fully connected layers, and is trained via a Leave-One-Storm-Out (LOSO) cross-validation strategy along with holdout grid experiments to demonstrate its preliminary generalization capability to unseen storms and grids. The model produces hourly outage forecasts at a 4 km * 4 km resolution and supports dual forecasting modes: short-term nowcasting with a 6-hour lead time via assimilation of real-time observations, and long-term forecasting with a 60-hour lead time based on evolving meteorological projections. A case study on Typhoon Muifa (2022) demonstrates STO-CAST's operational effectiveness, including error decomposition across model design, meteorological uncertainty, and observation gaps, while highlighting the value of real-time data assimilation and the model's capacity to identify evolving outage hotspots. STO-CAST offers a scalable, data-driven solution to support risk-informed emergency response and enhance power system resilience under intensifying TC threats. - oai:arXiv.org:2512.06644v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain + https://arxiv.org/abs/2512.08560 + arXiv:2512.08560v1 Announce Type: new +Abstract: Understanding how the human brain represents visual concepts, and in which brain regions these representations are encoded, remains a long-standing challenge. Decades of work have advanced our understanding of visual representations, yet brain signals remain large and complex, and the space of possible visual concepts is vast. As a result, most studies remain small-scale, rely on manual inspection, focus on specific regions and properties, and rarely include systematic validation. We present a large-scale, automated framework for discovering and explaining visual representations across the human cortex. Our method comprises two main stages. First, we discover candidate interpretable patterns in fMRI activity through unsupervised, data-driven decomposition methods. Next, we explain each pattern by identifying the set of natural images that most strongly elicit it and generating a natural-language description of their shared visual meaning. To scale this process, we introduce an automated pipeline that tests multiple candidate explanations, assigns quantitative reliability scores, and selects the most consistent description for each voxel pattern. Our framework reveals thousands of interpretable patterns spanning many distinct visual concepts, including fine-grained representations previously unreported. + oai:arXiv.org:2512.08560v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yongchuan Yang, Naiyu Wang, Zhenguo Wang, Min Ouyang, Can Wan + Navve Wasserman, Matias Cosarinsky, Yuval Golbari, Aude Oliva, Antonio Torralba, Tamar Rott Shaham, Michal Irani - Analyzing Collision Rates in Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning - https://arxiv.org/abs/2512.06645 - arXiv:2512.06645v1 Announce Type: new -Abstract: Vehicle collisions remain a major challenge in large-scale mixed traffic systems, especially when human-driven vehicles (HVs) and robotic vehicles (RVs) interact under dynamic and uncertain conditions. Although Multi-Agent Reinforcement Learning (MARL) offers promising capabilities for traffic signal control, ensuring safety in such environments remains difficult. As a direct indicator of traffic risk, the collision rate must be well understood and incorporated into traffic control design. This study investigates the primary factors influencing collision rates in a MARL-governed Mixed Traffic Control (MTC) network. We examine three dimensions: total vehicle count, signalized versus unsignalized intersection configurations, and turning-movement strategies. Through controlled simulation experiments, we evaluate how each factor affects collision likelihood. The results show that collision rates are sensitive to traffic density, the level of signal coordination, and turning-control design. These findings provide practical insights for improving the safety and robustness of MARL-based mixed traffic control systems, supporting the development of intelligent transportation systems in which both efficiency and safety are jointly optimized. - oai:arXiv.org:2512.06645v1 - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 + Basic Lock Algorithms in Lightweight Thread Environments + https://arxiv.org/abs/2512.08563 + arXiv:2512.08563v1 Announce Type: new +Abstract: Traditionally, multithreaded data structures have been designed for access by the threads of Operating Systems (OS). However, implementations for access by programmable alternatives known as lightweight threads (also referred to as asynchronous calls or coroutines) have not been thoroughly studied. The main advantage of lightweight threads is their significantly lower overhead during launch and context switching. However, this comes at a cost: to achieve proper parallelism, context switches must be manually invoked in the code; without these switches, new lightweight threads will never be executed. + In this paper, we focus on the simplest multithreaded data structure: a mutex (also known as a lock). We demonstrate that original implementations for OS threads cannot be used effectively in this new context due to the potential for deadlocks. Furthermore, correctness is not the only concern. In certain languages, such as C++, there are various lightweight thread libraries, each with different implementations and interfaces, which necessitate distinct lock implementations. + In this work, we present a modification of TTAS and MCS locks for the use from lightweight threads and demonstrate that the two context switch mechanisms of lightweight threads, yielding and sleeping, are crucial. However, the performance of TTAS and MCS may differ significantly depending on the settings. If one wants to have a lock that works well for any library, we suggest using the cohort lock, which strikes a balance between MCS and TTAS by utilizing several MCS queues with a common TTAS. + oai:arXiv.org:2512.08563v1 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Muyang Fan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Taras Skazhenik, Nikolai Korobenikov, Andrei Churbanov, Anton Malakhov, Vitaly Aksenov - Exploring Teenagers' Trust in Al Chatbots: An Empirical Study of Chinese Middle-School Students - https://arxiv.org/abs/2512.06647 - arXiv:2512.06647v1 Announce Type: new -Abstract: Chatbots have become increasingly prevalent. A growing body of research focused on the issue of human trust in AI. However, most existing user studies are conducted primarily with adult groups, overlooking teenagers who are also engaging more frequently with AI technologies. Based on previous theories about teenage education and psychology, this study investigates the correlation between teenagers' psychological characteristics and their trust in AI chatbots, examining four key variables: AI literacy, ego identity, social anxiety, and psychological resilience. We adopted a mixed-methods approach, combining an online survey with semi-structured interviews. Our findings reveal that psychological resilience is a significant positive predictor of trust in AI, and that age significantly moderates the relationship between social anxiety and trust. The interviews further suggest that teenagers generally report relatively high levels of trust in AI, tend to overestimate their AI literacy, and are influenced by external factors such as social media. - oai:arXiv.org:2512.06647v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Modular Neural Image Signal Processing + https://arxiv.org/abs/2512.08564 + arXiv:2512.08564v1 Announce Type: new +Abstract: This paper presents a modular neural image signal processing (ISP) framework that processes raw inputs and renders high-quality display-referred images. Unlike prior neural ISP designs, our method introduces a high degree of modularity, providing full control over multiple intermediate stages of the rendering process.~This modular design not only achieves high rendering accuracy but also improves scalability, debuggability, generalization to unseen cameras, and flexibility to match different user-preference styles. To demonstrate the advantages of this design, we built a user-interactive photo-editing tool that leverages our neural ISP to support diverse editing operations and picture styles. The tool is carefully engineered to take advantage of the high-quality rendering of our neural ISP and to enable unlimited post-editable re-rendering. Our method is a fully learning-based framework with variants of different capacities, all of moderate size (ranging from ~0.5 M to ~3.9 M parameters for the entire pipeline), and consistently delivers competitive qualitative and quantitative results across multiple test sets. Watch the supplemental video at: https://youtu.be/ByhQjQSjxVM + oai:arXiv.org:2512.08564v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Siyu Qiu, Anqi Lin, Shiya Wang, Xingyu Lan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Mahmoud Afifi, Zhongling Wang, Ran Zhang, Michael S. Brown - Financial Fraud Identification and Interpretability Study for Listed Companies Based on Convolutional Neural Network - https://arxiv.org/abs/2512.06648 - arXiv:2512.06648v1 Announce Type: new -Abstract: Since the emergence of joint-stock companies, financial fraud by listed firms has repeatedly undermined capital markets. Fraud is difficult to detect because of covert tactics and the high labor and time costs of audits. Traditional statistical models are interpretable but struggle with nonlinear feature interactions, while machine learning models are powerful but often opaque. In addition, most existing methods judge fraud only for the current year based on current year data, limiting timeliness. - This paper proposes a financial fraud detection framework for Chinese A-share listed companies based on convolutional neural networks (CNNs). We design a feature engineering scheme that transforms firm-year panel data into image like representations, enabling the CNN to capture cross-sectional and temporal patterns and to predict fraud in advance. Experiments show that the CNN outperforms logistic regression and LightGBM in accuracy, robustness, and early-warning performance, and that proper tuning of the classification threshold is crucial in high-risk settings. - To address interpretability, we analyze the model along the dimensions of entity, feature, and time using local explanation techniques. We find that solvency, ratio structure, governance structure, and internal control are general predictors of fraud, while environmental indicators matter mainly in high-pollution industries. Non-fraud firms share stable feature patterns, whereas fraud firms exhibit heterogeneous patterns concentrated in short time windows. A case study of Guanong Shares in 2022 shows that cash flow analysis, social responsibility, governance structure, and per-share indicators are the main drivers of the model's fraud prediction, consistent with the company's documented misconduct. - oai:arXiv.org:2512.06648v1 + A Hybrid Model for Stock Market Forecasting: Integrating News Sentiment and Time Series Data with Graph Neural Networks + https://arxiv.org/abs/2512.08567 + arXiv:2512.08567v1 Announce Type: new +Abstract: Stock market prediction is a long-standing challenge in finance, as accurate forecasts support informed investment decisions. Traditional models rely mainly on historical prices, but recent work shows that financial news can provide useful external signals. This paper investigates a multimodal approach that integrates companies' news articles with their historical stock data to improve prediction performance. We compare a Graph Neural Network (GNN) model with a baseline LSTM model. Historical data for each company is encoded using an LSTM, while news titles are embedded with a language model. These embeddings form nodes in a heterogeneous graph, and GraphSAGE is used to capture interactions between articles, companies, and industries. We evaluate two targets: a binary direction-of-change label and a significance-based label. Experiments on the US equities and Bloomberg datasets show that the GNN outperforms the LSTM baseline, achieving 53% accuracy on the first target and a 4% precision gain on the second. Results also indicate that companies with more associated news yield higher prediction accuracy. Moreover, headlines contain stronger predictive signals than full articles, suggesting that concise news summaries play an important role in short-term market reactions. + oai:arXiv.org:2512.08567v1 cs.LG cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Xiao Li + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.34190/icair.5.1.4294 + Proceedings of the 5th International Conference on AI Research (ICAIR 2025), Vol. 5, No. 1, pp. 452-462 (2025) + Nader Sadek, Mirette Moawad, Christina Naguib, Mariam Elzahaby - Estimating Black Carbon Concentration from Urban Traffic Using Vision-Based Machine Learning - https://arxiv.org/abs/2512.06649 - arXiv:2512.06649v1 Announce Type: new -Abstract: Black carbon (BC) emissions in urban areas are primarily driven by traffic, with hotspots near major roads disproportionately affecting marginalized communities. Because BC monitoring is typically performed using costly and specialized instruments. there is little to no available data on BC from local traffic sources that could help inform policy interventions targeting local factors. By contrast, traffic monitoring systems are widely deployed in cities around the world, highlighting the imbalance between what we know about traffic conditions and what do not know about their environmental consequences. To bridge this gap, we propose a machine learning-driven system that extracts visual information from traffic video to capture vehicles behaviors and conditions. Combining these features with weather data, our model estimates BC at street level, achieving an R-squared value of 0.72 and RMSE of 129.42 ng/m3 (nanogram per cubic meter). From a sustainability perspective, this work leverages resources already supported by urban infrastructure and established modeling techniques to generate information relevant to traffic emission. Obtaining BC concentration data provides actionable insights to support pollution reduction, urban planning, public health, and environmental justice at the local municipal level. - oai:arXiv.org:2512.06649v1 - cs.LG + Instance-Aware Test-Time Segmentation for Continual Domain Shifts + https://arxiv.org/abs/2512.08569 + arXiv:2512.08569v1 Announce Type: new +Abstract: Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying difficulty across classes and instances. This limitation is especially problematic in semantic segmentation, where each image requires dense, multi-class predictions. We propose an approach that adaptively adjusts pseudo labels to reflect the confidence distribution within each image and dynamically balances learning toward classes most affected by domain shifts. This fine-grained, class- and instance-aware adaptation produces more reliable supervision and mitigates error accumulation throughout continual adaptation. Extensive experiments across eight CTTA and TTA scenarios, including synthetic-to-real and long-term shifts, show that our method consistently outperforms state-of-the-art techniques, setting a new standard for semantic segmentation under evolving conditions. + oai:arXiv.org:2512.08569v1 cs.CV - cs.CY - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Camellia Zakaria, Aryan Sadeghi, Weaam Jaafar, Junshi Xu, Alex Mariakakis, Marianne Hatzopoulou + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Seunghwan Lee, Inyoung Jung, Hojoon Lee, Eunil Park, Sungeun Hong - Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohorts - https://arxiv.org/abs/2512.06652 - arXiv:2512.06652v1 Announce Type: new -Abstract: Accurate prediction of the need for invasive mechanical ventilation (IMV) in intensive care units (ICUs) patients is crucial for timely interventions and resource allocation. However, variability in patient populations, clinical practices, and electronic health record (EHR) systems across institutions introduces domain shifts that degrade the generalization performance of predictive models during deployment. Test-Time Training (TTT) has emerged as a promising approach to mitigate such shifts by adapting models dynamically during inference without requiring labeled target-domain data. In this work, we introduce Adaptive Test-Time Training (AdaTTT), an enhanced TTT framework tailored for EHR-based IMV prediction in ICU settings. We begin by deriving information-theoretic bounds on the test-time prediction error and demonstrate that it is constrained by the uncertainty between the main and auxiliary tasks. To enhance their alignment, we introduce a self-supervised learning framework with pretext tasks: reconstruction and masked feature modeling optimized through a dynamic masking strategy that emphasizes features critical to the main task. Additionally, to improve robustness against domain shifts, we incorporate prototype learning and employ Partial Optimal Transport (POT) for flexible, partial feature alignment while maintaining clinically meaningful patient representations. Experiments across multi-center ICU cohorts demonstrate competitive classification performance on different test-time adaptation benchmarks. - oai:arXiv.org:2512.06652v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaolei Lu, Shamim Nemati - - - LightSearcher: Efficient DeepSearch via Experiential Memory - https://arxiv.org/abs/2512.06653 - arXiv:2512.06653v1 Announce Type: new -Abstract: DeepSearch paradigms have become a core enabler for deep reasoning models, allowing them to invoke external search tools to access up-to-date, domain-specific knowledge beyond parametric boundaries, thereby enhancing the depth and factual reliability of reasoning. Building upon this foundation, recent advances in reinforcement learning (RL) have further empowered models to autonomously and strategically control search tool usage, optimizing when and how to query external knowledge sources. Yet, these RL-driven DeepSearch systems often reveal a see-saw trade-off between accuracy and efficiency-frequent tool invocations can improve factual correctness but lead to unnecessary computational overhead and diminished efficiency. To address this challenge, we propose LightSearcher, an efficient RL framework that incorporates textual experiential memory by learning contrastive reasoning trajectories to generate interpretable summaries of successful reasoning patterns. In addition, it employs an adaptive reward shaping mechanism that penalizes redundant tool calls only in correct-answer scenarios. This design effectively balances the inherent accuracy-efficiency trade-off in DeepSearch paradigms. Experiments on four multi-hop QA benchmarks show that LightSearcher maintains accuracy comparable to SOTA baseline ReSearch, while reducing search tool invocations by 39.6%, inference time by 48.6%, and token consumption by 21.2%, demonstrating its superior efficiency. - oai:arXiv.org:2512.06653v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + From Cells to Survival: Hierarchical Analysis of Cell Inter-Relations in Multiplex Microscopy for Lung Cancer Prognosis + https://arxiv.org/abs/2512.08572 + arXiv:2512.08572v1 Announce Type: new +Abstract: The tumor microenvironment (TME) has emerged as a promising source of prognostic biomarkers. To fully leverage its potential, analysis methods must capture complex interactions between different cell types. We propose HiGINE -- a hierarchical graph-based approach to predict patient survival (short vs. long) from TME characterization in multiplex immunofluorescence (mIF) images and enhance risk stratification in lung cancer. Our model encodes both local and global inter-relations in cell neighborhoods, incorporating information about cell types and morphology. Multimodal fusion, aggregating cancer stage with mIF-derived features, further boosts performance. We validate HiGINE on two public datasets, demonstrating improved risk stratification, robustness, and generalizability. + oai:arXiv.org:2512.08572v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hengzhi Lan, Yue Yu, Li Qian, Li Peng, Jie Wu, Wei Liu, Jian Luan, Ting Bai + Olle Edgren Sch\"ullerqvist, Jens Baumann, Joakim Lindblad, Love Nordling, Artur Mezheyeuski, Patrick Micke, Nata\v{s}a Sladoje - GSAE: Graph-Regularized Sparse Autoencoders for Robust LLM Safety Steering - https://arxiv.org/abs/2512.06655 - arXiv:2512.06655v1 Announce Type: new -Abstract: Large language models (LLMs) face critical safety challenges, as they can be manipulated to generate harmful content through adversarial prompts and jailbreak attacks. Many defenses are typically either black-box guardrails that filter outputs, or internals-based methods that steer hidden activations by operationalizing safety as a single latent feature or dimension. While effective for simple concepts, this assumption is limiting, as recent evidence shows that abstract concepts such as refusal and temporality are distributed across multiple features rather than isolated in one. To address this limitation, we introduce Graph-Regularized Sparse Autoencoders (GSAEs), which extends SAEs with a Laplacian smoothness penalty on the neuron co-activation graph. Unlike standard SAEs that assign each concept to a single latent feature, GSAEs recover smooth, distributed safety representations as coherent patterns spanning multiple features. We empirically demonstrate that GSAE enables effective runtime safety steering, assembling features into a weighted set of safety-relevant directions and controlling them with a two-stage gating mechanism that activates interventions only when harmful prompts or continuations are detected during generation. This approach enforces refusals adaptively while preserving utility on benign queries. Across safety and QA benchmarks, GSAE steering achieves an average 82% selective refusal rate, substantially outperforming standard SAE steering (42%), while maintaining strong task accuracy (70% on TriviaQA, 65% on TruthfulQA, 74% on GSM8K). Robustness experiments further show generalization across LLaMA-3, Mistral, Qwen, and Phi families and resilience against jailbreak attacks (GCG, AutoDAN), consistently maintaining >= 90% refusal of harmful content. - oai:arXiv.org:2512.06655v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + RVC-NMPC: Nonlinear Model Predictive Control with Reciprocal Velocity Constraints for Mutual Collision Avoidance in Agile UAV Flight + https://arxiv.org/abs/2512.08574 + arXiv:2512.08574v1 Announce Type: new +Abstract: This paper presents an approach to mutual collision avoidance based on Nonlinear Model Predictive Control (NMPC) with time-dependent Reciprocal Velocity Constraints (RVCs). Unlike most existing methods, the proposed approach relies solely on observable information about other robots, eliminating the necessity of excessive communication use. The computationally efficient algorithm for computing RVCs, together with the direct integration of these constraints into NMPC problem formulation on a controller level, allows the whole pipeline to run at 100 Hz. This high processing rate, combined with modeled nonlinear dynamics of the controlled Uncrewed Aerial Vehicles (UAVs), is a key feature that facilitates the use of the proposed approach for an agile UAV flight. The proposed approach was evaluated through extensive simulations emulating real-world conditions in scenarios involving up to 10 UAVs and velocities of up to 25 m/s, and in real-world experiments with accelerations up to 30 m/s$^2$. Comparison with state of the art shows 31% improvement in terms of flight time reduction in challenging scenarios, while maintaining a collision-free navigation in all trials. + oai:arXiv.org:2512.08574v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Jehyeok Yeon, Federico Cinus, Yifan Wu, Luca Luceri + Vit Kratky, Robert Penicka, Parakh M. Gupta, Ondrej Prochazka, Martin Saska - The Online Discourse of Virtual Reality and Anxiety - https://arxiv.org/abs/2512.06656 - arXiv:2512.06656v1 Announce Type: new -Abstract: VR in the treatment of clinical concerns such as generalized anxiety disorder or social anxiety. VR has created additional pathways to support patient well-being and care. Understanding online discussion of what users think about this technology may further support its efficacy. The purpose of this study was to employ a corpus linguistic methodology to identify the words and word networks that shed light on the online discussion of virtual reality and anxiety. Using corpus linguistics, frequently used words in discussion along with collocation were identified by utilizing Sketch Engine software. The results of the study, based upon the English Trends corpus, identified VR, Oculus, and headset as the most frequently discussed within the VR and anxiety subcorpus. These results point to the development of the virtual system, along with the physical apparatus that makes viewing and engaging with the virtual environment possible. Additional results point to collocation of prepositional phrases such as of virtual reality, in virtual reality, and for virtual reality relating to the design, experience, and development, respectively. These findings offer new perspective on how VR and anxiety together are discussed in general discourse and offer pathways for future opportunities to support counseling needs through development and accessibility. Keywords: anxiety disorders, corpus linguistics, Sketch Engine, and virtual reality VR - oai:arXiv.org:2512.06656v1 - cs.CL - stat.CO - Tue, 09 Dec 2025 00:00:00 -0500 + Integrating Public Input and Technical Expertise for Effective Cybersecurity Policy Formulation + https://arxiv.org/abs/2512.08575 + arXiv:2512.08575v1 Announce Type: new +Abstract: The evolving of digital transformation and increased use of technology comes with increased cyber vulnerabilities, which compromise national security. Cyber-threats become more sophisticated as the technology advances. This emphasises the need for strong risk mitigation strategies. To define strong and robust cybersecurity, policies requires an integrated approach of balancing technical expertise with public input. This paper aims to explore strategies used to balance technical expertise and public input to develop effective and robust cybersecurity policies. It also studied how the effective integration of technical expertise with public input is critical to developing effective strategies and resilient cybersecurity frameworks that strengthens national security. A lack of a holistic approach and collaborative efforts to cybersecurity can hinder the effectiveness of cybersecurity policies. This paper followed a systematic literature review with bibliometric analysis using the PRISMA methodology to explore how technical expertise and public input can be integrated to guide cybersecurity policy making. The thematic analysis identified five important themes in developing effective cybersecurity policies, these key themes are: Multi-Stakeholder Involvement and Human Centric Approaches (MSI & HCA), Governance and Policy Frameworks (GPF), Technical Infrastructure (TI), Evaluation and Compliance (EC), and Legal Rights and Sovereignty (LRS). The synthesis shows that there is no adequate exploration of collaborative efforts which undermines the effectiveness of the cybersecurity policies. The findings suggest that inclusive, flexible governance strategies that integrate public input at every stage are necessary for future cybersecurity policy research and practice, which must shift away from a primarily technical and legal perspective. + oai:arXiv.org:2512.08575v1 + cs.CR + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Kwabena Yamoah, Cass Dykeman + http://creativecommons.org/licenses/by-sa/4.0/ + Hlekane Ngobeni, Mike Wa Nkongolo - TextMamba: Scene Text Detector with Mamba - https://arxiv.org/abs/2512.06657 - arXiv:2512.06657v1 Announce Type: new -Abstract: In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers as encoders without evaluating their cross-domain limitations and inherent shortcomings: forgetting important information or focusing on irrelevant representations when modeling long-range dependencies for text detection. The recently proposed state space model Mamba has demonstrated better long-range dependencies modeling through a linear complexity selection mechanism. Therefore, we propose a novel scene text detector based on Mamba that integrates the selection mechanism with attention layers, enhancing the encoder's ability to extract relevant information from long sequences. We adopt the Top\_k algorithm to explicitly select key information and reduce the interference of irrelevant information in Mamba modeling. Additionally, we design a dual-scale feed-forward network and an embedding pyramid enhancement module to facilitate high-dimensional hidden state interactions and multi-scale feature fusion. Our method achieves state-of-the-art or competitive performance on various benchmarks, with F-measures of 89.7\%, 89.2\%, and 78.5\% on CTW1500, TotalText, and ICDAR19ArT, respectively. Codes will be available. - oai:arXiv.org:2512.06657v1 + Disturbance-Free Surgical Video Generation from Multi-Camera Shadowless Lamps for Open Surgery + https://arxiv.org/abs/2512.08577 + arXiv:2512.08577v1 Announce Type: new +Abstract: Video recordings of open surgeries are greatly required for education and research purposes. However, capturing unobstructed videos is challenging since surgeons frequently block the camera field of view. To avoid occlusion, the positions and angles of the camera must be frequently adjusted, which is highly labor-intensive. Prior work has addressed this issue by installing multiple cameras on a shadowless lamp and arranging them to fully surround the surgical area. This setup increases the chances of some cameras capturing an unobstructed view. However, manual image alignment is needed in post-processing since camera configurations change every time surgeons move the lamp for optimal lighting. This paper aims to fully automate this alignment task. The proposed method identifies frames in which the lighting system moves, realigns them, and selects the camera with the least occlusion to generate a video that consistently presents the surgical field from a fixed perspective. A user study involving surgeons demonstrated that videos generated by our method were superior to those produced by conventional methods in terms of the ease of confirming the surgical area and the comfort during video viewing. Additionally, our approach showed improvements in video quality over existing techniques. Furthermore, we implemented several synthesis options for the proposed view-synthesis method and conducted a user study to assess surgeons' preferences for each option. + oai:arXiv.org:2512.08577v1 cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - 10.1109/IJCNN64981.2025.11227846 - Qiyan Zhao, Yue Yan, Da-Han Wang + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Yuna Kato, Shohei Mori, Hideo Saito, Yoshifumi Takatsume, Hiroki Kajita, Mariko Isogawa - The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines - https://arxiv.org/abs/2512.06659 - arXiv:2512.06659v1 Announce Type: new -Abstract: Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language models can summarize alerts or interpret unstructured reports, they fall short in real SOC environments that require grounded data access, reproducibility, and accountable workflows. In response, the field has seen a rapid architectural evolution from single-model helpers toward tool-augmented agents, distributed multi-agent systems, schema-bound tool ecosystems, and early explorations of semi-autonomous investigative pipelines. This survey presents a five-generation taxonomy of agentic AI in cybersecurity. It traces how capabilities and risks change as systems advance from text-only LLM reasoners to multi-agent collaboration frameworks and constrained-autonomy pipelines. We compare these generations across core dimensions - reasoning depth, tool use, memory, reproducibility, and safety. In addition, we also synthesize emerging benchmarks used to evaluate cyber-oriented agents. Finally, we outline the unresolved challenges that accompany this evolution, such as response validation, tool-use correctness, multi-agent coordination, long-horizon reasoning, and safeguards for high-impact actions. Collectively, this work provides a structured perspective on how agentic AI is taking shape within cybersecurity and what is required to ensure its safe and reliable deployment. - oai:arXiv.org:2512.06659v1 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Mind to Hand: Purposeful Robotic Control via Embodied Reasoning + https://arxiv.org/abs/2512.08580 + arXiv:2512.08580v1 Announce Type: new +Abstract: Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abilities in physical action remains a major challenge. We introduce Lumo-1, a generalist vision-language-action (VLA) model that unifies robot reasoning ("mind") with robot action ("hand"). Our approach builds upon the general multi-modal reasoning capabilities of pre-trained vision-language models (VLMs), progressively extending them to embodied reasoning and action prediction, and ultimately towards structured reasoning and reasoning-action alignment. This results in a three-stage pre-training pipeline: (1) Continued VLM pre-training on curated vision-language data to enhance embodied reasoning skills such as planning, spatial understanding, and trajectory prediction; (2) Co-training on cross-embodiment robot data alongside vision-language data; and (3) Action training with reasoning process on trajectories collected on Astribot S1, a bimanual mobile manipulator with human-like dexterity and agility. Finally, we integrate reinforcement learning to further refine reasoning-action consistency and close the loop between semantic inference and motor control. Extensive experiments demonstrate that Lumo-1 achieves significant performance improvements in embodied vision-language reasoning, a critical component for generalist robotic control. Real-world evaluations further show that Lumo-1 surpasses strong baselines across a wide range of challenging robotic tasks, with strong generalization to novel objects and environments, excelling particularly in long-horizon tasks and responding to human-natural instructions that require reasoning over strategy, concepts and space. + oai:arXiv.org:2512.08580v1 + cs.RO + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Vaishali Vinay + http://creativecommons.org/licenses/by/4.0/ + Peijun Tang, Shangjin Xie, Binyan Sun, Baifu Huang, Kuncheng Luo, Haotian Yang, Weiqi Jin, Jianan Wang - Towards Small Language Models for Security Query Generation in SOC Workflows - https://arxiv.org/abs/2512.06660 - arXiv:2512.06660v1 Announce Type: new -Abstract: Analysts in Security Operations Centers routinely query massive telemetry streams using Kusto Query Language (KQL). Writing correct KQL requires specialized expertise, and this dependency creates a bottleneck as security teams scale. This paper investigates whether Small Language Models (SLMs) can enable accurate, cost-effective natural-language-to-KQL translation for enterprise security. We propose a three-knob framework targeting prompting, fine-tuning, and architecture design. First, we adapt existing NL2KQL framework for SLMs with lightweight retrieval and introduce error-aware prompting that addresses common parser failures without increasing token count. Second, we apply LoRA fine-tuning with rationale distillation, augmenting each NLQ-KQL pair with a brief chain-of-thought explanation to transfer reasoning from a teacher model while keeping the SLM compact. Third, we propose a two-stage architecture that uses an SLM for candidate generation and a low-cost LLM judge for schema-aware refinement and selection. We evaluate nine models (five SLMs and four LLMs) across syntax correctness, semantic accuracy, table selection, and filter precision, alongside latency and token cost. On Microsoft's NL2KQL Defender Evaluation dataset, our two-stage approach achieves 0.987 syntax and 0.906 semantic accuracy. We further demonstrate generalizability on Microsoft Sentinel data, reaching 0.964 syntax and 0.831 semantic accuracy. These results come at up to 10x lower token cost than GPT-5, establishing SLMs as a practical, scalable foundation for natural-language querying in security operations. - oai:arXiv.org:2512.06660v1 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Weighted $k$-Path and Other Problems in Almost $O^*(2^k)$ Deterministic Time via Dynamic Representative Sets + https://arxiv.org/abs/2512.08583 + arXiv:2512.08583v1 Announce Type: new +Abstract: We present a data structure that we call a Dynamic Representative Set. In its most basic form, it is given two parameters $0< k < n$ and allows us to maintain a representation of a family $\mathcal{F}$ of subsets of $\{1,\ldots,n\}$. It supports basic update operations (unioning of two families, element convolution) and a query operation that determines for a set $B \subseteq \{1,\ldots,n\}$ whether there is a set $A \in \mathcal{F}$ of size at most $k-|B|$ such that $A$ and $B$ are disjoint. After $2^{k+O(\sqrt{k}\log^2k)}n \log n$ preprocessing time, all operations use $2^{k+O(\sqrt{k}\log^2k)}\log n$ time. + Our data structure has many algorithmic consequences that improve over previous works. One application is a deterministic algorithm for the Weighted Directed $k$-Path problem, one of the central problems in parameterized complexity. Our algorithm takes as input an $n$-vertex directed graph $G=(V,E)$ with edge lengths and an integer $k$, and it outputs the minimum edge length of a path on $k$ vertices in $2^{k+O(\sqrt{k}\log^2k)}(n+m)\log n$ time (in the word RAM model where weights fit into a single word). Modulo the lower order term $2^{O(\sqrt{k}\log^2k)}$, this answers a question that has been repeatedly posed as a major open problem in the field. + oai:arXiv.org:2512.08583v1 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Saleha Muzammil, Rahul Reddy, Vishal Kamalakrishnan, Hadi Ahmadi, Wajih Ul Hassan + Jesper Nederlof - Personalized Image Descriptions from Attention Sequences - https://arxiv.org/abs/2512.06662 - arXiv:2512.06662v1 Announce Type: new -Abstract: People can view the same image differently: they focus on different regions, objects, and details in varying orders and describe them in distinct linguistic styles. This leads to substantial variability in image descriptions. However, existing models for personalized image description focus on linguistic style alone, with no prior work leveraging individual viewing patterns. We address this gap by explicitly modeling personalized viewing behavior as a core factor in description generation. Our method, DEPER (DEscription-PERception persona encoder), learns a subject embedding that captures both linguistic style and viewing behavior, guided by an auxiliary attention-prediction task. A lightweight adapter aligns these embeddings with a frozen vision-language model, enabling few-shot personalization without retraining. Across four datasets spanning diverse viewing tasks and both short and detailed descriptions, DEPER achieves a 24% average improvement, showing that modeling personalized attention produces more human-aligned and high-quality descriptions. We posit that understanding how people see helps predict what they say; modeling human diversity in perception can improve both performance and human alignment in multimodal systems. - oai:arXiv.org:2512.06662v1 + Automated Pollen Recognition in Optical and Holographic Microscopy Images + https://arxiv.org/abs/2512.08589 + arXiv:2512.08589v1 Announce Type: new +Abstract: This study explores the application of deep learning to improve and automate pollen grain detection and classification in both optical and holographic microscopy images, with a particular focus on veterinary cytology use cases. We used YOLOv8s for object detection and MobileNetV3L for the classification task, evaluating their performance across imaging modalities. The models achieved 91.3% mAP50 for detection and 97% overall accuracy for classification on optical images, whereas the initial performance on greyscale holographic images was substantially lower. We addressed the performance gap issue through dataset expansion using automated labeling and bounding box area enlargement. These techniques, applied to holographic images, improved detection performance from 2.49% to 13.3% mAP50 and classification performance from 42% to 54%. Our work demonstrates that, at least for image classification tasks, it is possible to pair deep learning techniques with cost-effective lensless digital holographic microscopy devices. + oai:arXiv.org:2512.08589v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-nc-nd/4.0/ - Ruoyu Xue, Hieu Le, Jingyi Xu, Sounak Mondal, Abe Leite, Gregory Zelinsky, Minh Hoai, Dimitris Samaras + 10.1109/AICCONF64766.2025.11064260 + 2025 3rd Cognitive Models and Artificial Intelligence Conference (AICCONF), vol. 1, no. 1, pp. 1-8, Prague, Czech Republic, IEEE, 2025 + Swarn Singh Warshaneyan, Maksims Ivanovs, Bla\v{z} Cugmas, Inese B\=erzi\c{n}a, Laura Goldberga, Mindaugas Tamosiunas, Roberts Kadi\c{k}is - CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks - https://arxiv.org/abs/2512.06663 - arXiv:2512.06663v1 Announce Type: new -Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable success in a broad range of vision-language tasks, such as general visual question answering and optical character recognition (OCR). However, their performance on perception-centric tasks -- such as object detection, semantic segmentation, and depth estimation -- remains significantly inferior to that of task-specific expert models. For example, Qwen2.5-VL-7B-Instruct achieves only 19% mAP on COCO2017 val, particularly struggling with dense scenes and small object recall. In this work, we introduce Chain-of-Thought for Detection (CoT4Det), a simple but efficient strategy that reformulates perception tasks into three interpretable steps: classification, counting, and grounding -- each more naturally aligned with the reasoning capabilities of LVLMs. Extensive experiments demonstrate that our method significantly improves perception performance without compromising general vision language capabilities. With a standard Qwen2.5-VL-7B-Instruct, CoT4Det boosts mAP from 19.0% to 33.0% on COCO2017 val and achieves competitive results across a variety of perception benchmarks, outperforming baselines by +2% on RefCOCO series and 19% on Flickr30k entities. - oai:arXiv.org:2512.06663v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Long-Sequence LSTM Modeling for NBA Game Outcome Prediction Using a Novel Multi-Season Dataset + https://arxiv.org/abs/2512.08591 + arXiv:2512.08591v1 Announce Type: new +Abstract: Predicting the outcomes of professional basketball games, particularly in the National Basketball Association (NBA), has become increasingly important for coaching strategy, fan engagement, and sports betting. However, many existing prediction models struggle with concept drift, limited temporal context, and instability across seasons. To advance forecasting in this domain, we introduce a newly constructed longitudinal NBA dataset covering the 2004-05 to 2024-25 seasons and present a deep learning framework designed to model long-term performance trends. Our primary contribution is a Long Short-Term Memory (LSTM) architecture that leverages an extended sequence length of 9,840 games equivalent to eight full NBA seasons to capture evolving team dynamics and season-over-season dependencies. We compare this model against several traditional Machine Learning (ML) and Deep Learning (DL) baselines, including Logistic Regression, Random Forest, Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). The LSTM achieves the best performance across all metrics, with 72.35 accuracy, 73.15 precision and 76.13 AUC-ROC. These results demonstrate the importance of long-sequence temporal modeling in basketball outcome prediction and highlight the value of our new multi-season dataset for developing robust, generalizable NBA forecasting systems. + oai:arXiv.org:2512.08591v1 + cs.LG + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Yu Qi, Yumeng Zhang, Chenting Gong, Xiao Tan, Weiming Zhang, Wei Zhang, Jingdong Wang + Charles Rios, Longzhen Han, Almas Baimagambetov, Nikolaos Polatidis - Statistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving - https://arxiv.org/abs/2512.06664 - arXiv:2512.06664v1 Announce Type: new -Abstract: Autonomous driving (AD) scenarios are inherently complex and diverse, posing significant challenges for a single deep learning model to effectively cover all possible conditions, such as varying weather, traffic densities, and road types. Large Model (LM)-Driven Mixture of Experts (MoE) paradigm offers a promising solution, where LM serves as the backbone to extract latent features while MoE serves as the downstream head to dynamically select and aggregate specialized experts to adapt to different scenarios. However, routing and aggregating in MoE face intrinsic challenges, including imprecise expert selection due to flawed routing strategy and inefficient expert aggregation leading to suboptimal prediction. To address these issues, we propose a statistic-augmented, decoupled MoE }outing and Aggregating Mechanism (MoE-RAM) driven by LM. Specifically, on the one hand, MoE-RAM enhances expert routing by incorporating statistical retrieval mechanism to match LM-extracted latent features with cached prototypical features of the most relevant experts; on the other hand, MoE-RAM adaptively reweights experts' outputs in fusion by measuring statistical distances of experts' instant features against LM-extracted latent features. Benefiting from the synergy of the statistic-augmented MoE's routing and aggregating, MoE-RAM ultimately improves the prediction performance. We take the AD semantic segmentation task as an example to assess the proposed MoE-RAM. Extensive experiments on AD datasets demonstrate the superiority of MoE-RAM compared to other MoE baselines and conventional single-model approaches. - oai:arXiv.org:2512.06664v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + The SMART+ Framework for AI Systems + https://arxiv.org/abs/2512.08592 + arXiv:2512.08592v1 Announce Type: new +Abstract: Artificial Intelligence (AI) systems are now an integral part of multiple industries. In clinical research, AI supports automated adverse event detection in clinical trials, patient eligibility screening for protocol enrollment, and data quality validation. Beyond healthcare, AI is transforming finance through real-time fraud detection, automated loan risk assessment, and algorithmic decision-making. Similarly, in manufacturing, AI enables predictive maintenance to reduce equipment downtime, enhances quality control through computer-vision inspection, and optimizes production workflows using real-time operational data. While these technologies enhance operational efficiency, they introduce new challenges regarding safety, accountability, and regulatory compliance. To address these concerns, we introduce the SMART+ Framework - a structured model built on the pillars of Safety, Monitoring, Accountability, Reliability, and Transparency, and further enhanced with Privacy & Security, Data Governance, Fairness & Bias, and Guardrails. SMART+ offers a practical, comprehensive approach to evaluating and governing AI systems across industries. This framework aligns with evolving mechanisms and regulatory guidance to integrate operational safeguards, oversight procedures, and strengthened privacy and governance controls. SMART+ demonstrates risk mitigation, trust-building, and compliance readiness. By enabling responsible AI adoption and ensuring auditability, SMART+ provides a robust foundation for effective AI governance in clinical research. + oai:arXiv.org:2512.08592v1 + cs.AI + cs.CY + cs.HC + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wei-Bin Kou, Guangxu Zhu, Jingreng Lei, Chen Zhang, Yik-Chung Wu, Jianping Wang + http://creativecommons.org/licenses/by/4.0/ + Laxmiraju Kandikatla, Branislav Radeljic - Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods - https://arxiv.org/abs/2512.06665 - arXiv:2512.06665v1 Announce Type: new -Abstract: This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of evaluating the robustness of attribution methods. Specifically, we propose a new definition of similar inputs, a new robustness metric, and a novel method based on generative adversarial networks to generate these inputs. In addition, we present a comprehensive evaluation with existing metrics and state-of-the-art attribution methods. Our findings highlight the need for a more objective metric that reveals the weaknesses of an attribution method rather than that of the neural network, thus providing a more accurate evaluation of the robustness of attribution methods. - oai:arXiv.org:2512.06665v1 - cs.LG + Examining Student Interactions with a Pedagogical AI-Assistant for Essay Writing and their Impact on Students Writing Quality + https://arxiv.org/abs/2512.08596 + arXiv:2512.08596v1 Announce Type: new +Abstract: The dynamic nature of interactions between students and GenAI, as well as their relationship to writing quality, remains underexplored. While most research has examined how general-purpose GenAI can support writing, fewer studies have investigated how students interact with pedagogically designed systems across different phases of the writing process. To address this gap, we evaluated a GenAI-driven essay-writing assistant (EWA) designed to support higher education students in argumentative writing. Drawing on 1,282 interaction logs from 32 undergraduates during a two-hour writing session, Sequential Pattern Mining and K-Means clustering were used to identify behavioral patterns. Two clusters emerged: Cluster 1 emphasized outline planning and essay structure, while Cluster 2 focused on content development. A Mann-Whitney U test revealed a moderate effect size (r = 0.36) in the essay Organization dimension, with Cluster 1 showing higher scores. Qualitative analysis indicated that students with better performance actively wrote and shared essay sections with EWA for feedback, rather than interacted passively by asking questions. These findings suggest implications for teaching and system design. Teachers can encourage active engagement, while future EWAs may integrate automatic labeling and monitoring to prompt students to move from questioning to writing, enabling fuller benefits from GenAI-supported learning. + oai:arXiv.org:2512.08596v1 + cs.CY cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Wicaksono Febriantoro, Qi Zhou, Wannapon Suraworachet, Sahan Bulathwela, Andrea Gauthier, Eva Millan, Mutlu Cukurova + + + A fourth-order multi-scale computational method and its convergence analysis for composite Kirchhoff plates with microscopic periodic configurations + https://arxiv.org/abs/2512.08597 + arXiv:2512.08597v1 Announce Type: new +Abstract: The Kirchhoff plate model plays a vital role in modeling, computing and analyzing the mechanical behaviors of thin plate structures. This study propose a novel fourth-order multi-scale (FOMS) computational method for high-accuracy and efficient simulation of composite Kirchhoff plates with highly periodic heterogeneities. At first, two-scale asymptotic expansion theory is employed to establish the high-accuracy fourth-order multi-scale computation model with novel fourth-order correctors for composite Kirchhoff plates, which are governed by fourth-order partial differential equation (PDE) with periodically oscillatory and highly discontinuous coefficients. Then, the locally point-wise error analysis is derived to theoretically illustrate the local balance preserving of fourth-order multi-scale model enabling high-accuracy multi-scale computation. Furthermore, a global error estimation with an explicit order for fourth-order multi-scale solutions is first demonstrated under appropriate assumptions. In contrast to the second- and third-order multi-scale solutions, only the fourth-order one is capable of providing an explicit error order estimate. Additionally, an efficient numerical algorithm is developed to conduct high-accuracy simulation for heterogeneous plate structures. Extensive numerical examples are provided to confirm the theoretical results for the computational convergence and accuracy of the proposed method. This work offers a higher-order (fourth-order) multi-scale computational framework that enables robust simulation and high-accuracy analysis to composite Kirchhoff plates. + oai:arXiv.org:2512.08597v1 + math.NA + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Panagiota Kiourti, Anu Singh, Preeti Duraipandian, Weichao Zhou, Wenchao Li + Hao Dong, Liqun Cao - The Meta-Learning Gap: Combining Hydra and Quant for Large-Scale Time Series Classification - https://arxiv.org/abs/2512.06666 - arXiv:2512.06666v1 Announce Type: new -Abstract: Time series classification faces a fundamental trade-off between accuracy and computational efficiency. While comprehensive ensembles like HIVE-COTE 2.0 achieve state-of-the-art accuracy, their 340-hour training time on the UCR benchmark renders them impractical for large-scale datasets. We investigate whether targeted combinations of two efficient algorithms from complementary paradigms can capture ensemble benefits while maintaining computational feasibility. Combining Hydra (competing convolutional kernels) and Quant (hierarchical interval quantiles) across six ensemble configurations, we evaluate performance on 10 large-scale MONSTER datasets (7,898 to 1,168,774 training instances). Our strongest configuration improves mean accuracy from 0.829 to 0.836, succeeding on 7 of 10 datasets. However, prediction-combination ensembles capture only 11% of theoretical oracle potential, revealing a substantial meta-learning optimization gap. Feature-concatenation approaches exceeded oracle bounds by learning novel decision boundaries, while prediction-level complementarity shows moderate correlation with ensemble gains. The central finding: the challenge has shifted from ensuring algorithms are different to learning how to combine them effectively. Current meta-learning strategies struggle to exploit the complementarity that oracle analysis confirms exists. Improved combination strategies could potentially double or triple ensemble gains across diverse time series classification applications. - oai:arXiv.org:2512.06666v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Fast exact algorithms via the Matrix Tree Theorem + https://arxiv.org/abs/2512.08600 + arXiv:2512.08600v1 Announce Type: new +Abstract: Fast exact algorithms are known for Hamiltonian paths in undirected and directed bipartite graphs through elegant though involved algorithms that are quite different from each other. We devise algorithms that are simple and similar to each other while having the same upper bounds. The common features of these algorithms is the use of the Matrix-Tree theorem and sieving using roots of unity. + Next, we use the framework to provide alternative algorithms to count perfect matchings in bipartite graphs on $n$ vertices, i.e., computing the $\{0,1\}$-permanent of a square $n/2 \times n/2$ matrix which runs in a time similar to Ryser. + We demonstrate the flexibility of our method by counting the number of ways to vertex partition the graph into $k$-stars (a $k$-star consist of a tree with a root having $k-1$ children that are all leaves). Interestingly, our running time improves to $O^*((1+\epsilon_k)^n)$ with $\epsilon_k \rightarrow 0$ as $k \rightarrow \infty$. + As an aside, making use of Bj\"orklund's algorithm for exact counting perfect matchings in general graphs, we show that the count of maximum matchings can be computed in time $O^*(2^\nu)$ where $\nu$ is the size of a maximum matching. The crucial ingredient here is the famous Gallai-Edmonds decomposition theorem. + All our algorithms run in polynomial space. + oai:arXiv.org:2512.08600v1 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Urav Maniar + V. Arvind, Srijan Chakraborty, Samir Datta, Asif Khan - 1 + 1 > 2: Detector-Empowered Video Large Language Model for Spatio-Temporal Grounding and Reasoning - https://arxiv.org/abs/2512.06673 - arXiv:2512.06673v1 Announce Type: new -Abstract: Spatio-temporal grounding and reasoning aims to locate the temporal segment and spatial region of an event in a video given a user query, while also reasoning about semantics such as causality, temporal order, and action relationships. To achieve this, current MLLMs primarily treats bounding boxes as text tokens and generates them autoregressively. However, such autoregressive spatial decoding leads to very-long output sequences, causing spatial errors to accumulated over time and the localization results to progressively drift across a video. To address this, we present a Detector-Empowered Video LLM, short for DEViL, which couples a Video LLM with an open-vocabulary detector (OVD). Specifically, the MLLM and detector are connected via a reference-semantic token (RST) that distills the user query into a rich semantic representation. Unlike tokens that merely serve as spatial prompts or segmentor switches, the RST functions as both a control signal and a replacement for the OVD's text embedding, enabling end-to-end learning of both referential understanding and spatial localization. Furthermore, we propose a tube-mined temporal regularization (TTReg) within OVD, which drives the OVD to generate temporally-consistent queries for target objects, thereby ensuring effective temporal association. Experiments demonstrate that DEViL achieves strong performance across various fine-grained video understanding tasks, particularly STVG and GroundedVQA. Code will be released on https://github.com/gaostar123/DeViL. - oai:arXiv.org:2512.06673v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Skew polynomial representations of matrix algebras and applications to coding theory + https://arxiv.org/abs/2512.08602 + arXiv:2512.08602v1 Announce Type: new +Abstract: We extend the existing skew polynomial representations of matrix algebras which are direct sum of matrix spaces over division rings. In this representation, the sum-rank distance between two tuples of matrices is captured by a weight function on their associated skew polynomials, defined through degrees and greatest common right divisors with the polynomial that defines the representation. We exploit this representation to construct new families of maximum sum-rank distance (MSRD) codes over finite and infinite fields, and over division rings. These constructions generalize many of the known existing constructions of MSRD codes as well as of optimal codes in the rank and in the Hamming metric. As a byproduct, in the case of finite fields we obtain new families of MDS codes which are linear over a subfield and whose length is close to the field size. + oai:arXiv.org:2512.08602v1 + cs.IT + math.IT + math.RA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shida Gao, Feng Xue, Xiangfeng Wang, Anlong Ming, Teng Long, Yihua Shao, Haozhe Wang, Zhaowen Lin, Wei Wang, Nicu Sebe + http://creativecommons.org/licenses/by/4.0/ + Alessandro Neri, Paolo Santonastaso - RunawayEvil: Jailbreaking the Image-to-Video Generative Models - https://arxiv.org/abs/2512.06674 - arXiv:2512.06674v1 Announce Type: new -Abstract: Image-to-Video (I2V) generation synthesizes dynamic visual content from image and text inputs, providing significant creative control. However, the security of such multimodal systems, particularly their vulnerability to jailbreak attacks, remains critically underexplored. To bridge this gap, we propose RunawayEvil, the first multimodal jailbreak framework for I2V models with dynamic evolutionary capability. Built on a "Strategy-Tactic-Action" paradigm, our framework exhibits self-amplifying attack through three core components: (1) Strategy-Aware Command Unit that enables the attack to self-evolve its strategies through reinforcement learning-driven strategy customization and LLM-based strategy exploration; (2) Multimodal Tactical Planning Unit that generates coordinated text jailbreak instructions and image tampering guidelines based on the selected strategies; (3) Tactical Action Unit that executes and evaluates the multimodal coordinated attacks. This self-evolving architecture allows the framework to continuously adapt and intensify its attack strategies without human intervention. Extensive experiments demonstrate RunawayEvil achieves state-of-the-art attack success rates on commercial I2V models, such as Open-Sora 2.0 and CogVideoX. Specifically, RunawayEvil outperforms existing methods by 58.5 to 79 percent on COCO2017. This work provides a critical tool for vulnerability analysis of I2V models, thereby laying a foundation for more robust video generation systems. - oai:arXiv.org:2512.06674v1 + Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning + https://arxiv.org/abs/2512.08606 + arXiv:2512.08606v1 Announce Type: new +Abstract: The Contrastive Language-Image Pre-Training (CLIP) model excels in few-shot learning by aligning visual and textual representations. Our study shows that template-sample similarity (TSS), defined as the resemblance between a text template and an image sample, introduces bias. This bias leads the model to rely on template proximity rather than true sample-to-category alignment, reducing both accuracy and robustness in classification. We present a framework that uses empty prompts, textual inputs that convey the idea of "emptiness" without category information. These prompts capture unbiased template features and offset TSS bias. The framework employs two stages. During pre-training, empty prompts reveal and reduce template-induced bias within the CLIP encoder. During few-shot fine-tuning, a bias calibration loss enforces correct alignment between images and their categories, ensuring the model focuses on relevant visual cues. Experiments across multiple benchmarks demonstrate that our template correction method significantly reduces performance fluctuations caused by TSS, yielding higher classification accuracy and stronger robustness. The repository of this project is available at https://github.com/zhenyuZ-HUST/Decoupling-Template-Bias-in-CLIP. + oai:arXiv.org:2512.08606v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Songping Wang, Rufan Qian, Yueming Lyu, Qinglong Liu, Linzhuang Zou, Jie Qin, Songhua Liu, Caifeng Shan + Zhenyu Zhang, Guangyao Chen, Yixiong Zou, Zhimeng Huang, Yuhua Li - FedDSR: Federated Deep Supervision and Regularization Towards Autonomous Driving - https://arxiv.org/abs/2512.06676 - arXiv:2512.06676v1 Announce Type: new -Abstract: Federated Learning (FL) enables collaborative training of autonomous driving (AD) models across distributed vehicles while preserving data privacy. However, FL encounters critical challenges such as poor generalization and slow convergence due to non-independent and identically distributed (non-IID) data from diverse driving environments. To overcome these obstacles, we introduce Federated Deep Supervision and Regularization (FedDSR), a paradigm that incorporates multi-access intermediate layer supervision and regularization within federated AD system. Specifically, FedDSR comprises following integral strategies: (I) to select multiple intermediate layers based on predefined architecture-agnostic standards. (II) to compute mutual information (MI) and negative entropy (NE) on those selected layers to serve as intermediate loss and regularizer. These terms are integrated into the output-layer loss to form a unified optimization objective, enabling comprehensive optimization across the network hierarchy. (III) to aggregate models from vehicles trained based on aforementioned rules of (I) and (II) to generate the global model on central server. By guiding and penalizing the learning of feature representations at intermediate stages, FedDSR enhances the model generalization and accelerates model convergence for federated AD. We then take the semantic segmentation task as an example to assess FedDSR and apply FedDSR to multiple model architectures and FL algorithms. Extensive experiments demonstrate that FedDSR achieves up to 8.93% improvement in mIoU and 28.57% reduction in training rounds, compared to other FL baselines, making it highly suitable for practical deployment in federated AD ecosystems. - oai:arXiv.org:2512.06676v1 + Decoupled Design of Time-Varying Control Barrier Functions via Equivariances + https://arxiv.org/abs/2512.08607 + arXiv:2512.08607v1 Announce Type: new +Abstract: This article presents a systematic method for designing time-varying Control Barrier Functions (CBF) composed of a time-invariant component and multiple time-dependent components, leveraging structural properties of the system dynamics. The method involves the construction of a specific class of time-invariant CBFs that encode the system's dynamic capabilities with respect to a given constraint, and augments them subsequently with appropriately designed time-dependent transformations. While transformations uniformly varying the time-invariant CBF can be applied to arbitrary systems, transformations exploiting structural properties in the dynamics - equivariances in particular - enable the handling of a broader and more expressive class of time-varying constraints. The article shows how to leverage such properties in the design of time-varying CBFs. The proposed method decouples the design of time variations from the computationally expensive construction of the underlying CBFs, thereby providing a computationally attractive method to the design of time-varying CBFs. The method accounts for input constraints and under-actuation, and requires only qualitative knowledge on the time-variation of the constraints making it suitable to the application in uncertain environments. + oai:arXiv.org:2512.08607v1 + eess.SY cs.RO - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wei-Bin Kou, Guangxu Zhu, Bingyang Cheng, Chen Zhang, Yik-Chung Wu, Jianping Wang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Adrian Wiltz, Dimos V. Dimarogonas - GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning - https://arxiv.org/abs/2512.06678 - arXiv:2512.06678v1 Announce Type: new -Abstract: Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they consist of a mixture of diverse information, causing gradient interference, where conflicting gradients pull the model in opposing directions, degrading performance. A common strategy to mitigate this issue is to group data based on semantic or embedding similarity. However, this fails to capture how data influences model parameters during learning. While recent works have attempted to cluster gradients directly, they randomly project gradients into lower dimensions to manage memory, which leads to accuracy loss. Moreover, these methods rely on expert ensembles which necessitates multiple inference passes and expensive on-the-fly gradient computations during inference. To address these limitations, we propose GradientSpace, a framework that clusters samples directly in full-dimensional gradient space. We introduce an online SVD-based algorithm that operates on LoRA gradients to identify latent skills without the infeasible cost of storing all sample gradients. Each cluster is used to train a specialized LoRA expert along with a lightweight router trained to select the best expert during inference. We show that routing to a single, appropriate expert outperforms expert ensembles used in prior work, while significantly reducing inference latency. Our experiments across mathematical reasoning, code generation, finance, and creative writing tasks demonstrate that GradientSpace leads to coherent expert specialization and consistent accuracy gains over state-of-the-art clustering methods and finetuning techniques. - oai:arXiv.org:2512.06678v1 - cs.LG + NLoS Localization with Single Base Station Based on Radio Map + https://arxiv.org/abs/2512.08608 + arXiv:2512.08608v1 Announce Type: new +Abstract: Accurate outdoor localization in Non-Line-of-Sight (NLoS) environments remains a critical challenge for wireless communication and sensing systems. Existing methods, including positioning based on the Global Navigation Satellite System (GNSS) and triple Base Stations (BSs) techniques, cannot provide reliable performance under NLoS conditions, particularly in dense urban areas with strong multipath effects. To address this limitation, we propose a single BS localization framework that integrates sequential signal measurements with prior radio information embedded in the Radio Map (RM). Using temporal measurement features and matching them with radio maps, the proposed method effectively mitigates the adverse impact of multipath propagation and reduces the dependence on LoS paths. Simulation experiments further evaluate the impact of different radio map construction strategies and the varying lengths of the measurement sequence on localization accuracy. Results demonstrate that the proposed scheme achieves sub-meter positioning accuracy in typical NLoS environments, highlighting its potential as a practical and robust solution for single-base-station deployment. + oai:arXiv.org:2512.08608v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jiajie Xu, Yifan Guo, Xiucheng Wang, Nan Cheng, Tingting Yang + + + CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models + https://arxiv.org/abs/2512.08609 + arXiv:2512.08609v1 Announce Type: new +Abstract: Automatic Heuristic Design (AHD) is an effective1 framework for solving complex optimization prob-2 lems. The development of large language mod-3 els (LLMs) enables the automated generation of4 heuristics. Existing LLM-based evolutionary meth-5 ods rely on population strategies and are prone6 to local optima. Integrating LLMs with Monte7 Carlo Tree Search (MCTS) improves the trade-off8 between exploration and exploitation, but multi-9 round cognitive integration remains limited and10 search diversity is constrained. To overcome these11 limitations, this paper proposes a novel cognitive-12 guided MCTS framework (CogMCTS). CogMCTS13 tightly integrates the cognitive guidance mecha-14 nism of LLMs with MCTS to achieve efficient au-15 tomated heuristic optimization. The framework16 employs multi-round cognitive feedback to incor-17 porate historical experience, node information, and18 negative outcomes, dynamically improving heuris-19 tic generation. Dual-track node expansion com-20 bined with elite heuristic management balances the21 exploration of diverse heuristics and the exploita-22 tion of high-quality experience. In addition, strate-23 gic mutation modifies the heuristic forms and pa-24 rameters to further enhance the diversity of the so-25 lution and the overall optimization performance.26 The experimental results indicate that CogMCTS27 outperforms existing LLM-based AHD methods in28 stability, efficiency, and solution quality. + oai:arXiv.org:2512.08609v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Shrihari Sridharan, Deepak Ravikumar, Anand Raghunathan, Kaushik Roy + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Hui Wang, Yang Liu, Xiaoyu Zhang, Chaoxu Mu - CMV-Fuse: Cross Modal-View Fusion of AMR, Syntax, and Knowledge Representations for Aspect Based Sentiment Analysis - https://arxiv.org/abs/2512.06679 - arXiv:2512.06679v1 Announce Type: new -Abstract: Natural language understanding inherently depends on integrating multiple complementary perspectives spanning from surface syntax to deep semantics and world knowledge. However, current Aspect-Based Sentiment Analysis (ABSA) systems typically exploit isolated linguistic views, thereby overlooking the intricate interplay between structural representations that humans naturally leverage. We propose CMV-Fuse, a Cross-Modal View fusion framework that emulates human language processing by systematically combining multiple linguistic perspectives. Our approach systematically orchestrates four linguistic perspectives: Abstract Meaning Representations, constituency parsing, dependency syntax, and semantic attention, enhanced with external knowledge integration. Through hierarchical gated attention fusion across local syntactic, intermediate semantic, and global knowledge levels, CMV-Fuse captures both fine-grained structural patterns and broad contextual understanding. A novel structure aware multi-view contrastive learning mechanism ensures consistency across complementary representations while maintaining computational efficiency. Extensive experiments demonstrate substantial improvements over strong baselines on standard benchmarks, with analysis revealing how each linguistic view contributes to more robust sentiment analysis. - oai:arXiv.org:2512.06679v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Compact Runge-Kutta flux reconstruction methods for non-conservative hyperbolic equations + https://arxiv.org/abs/2512.08611 + arXiv:2512.08611v1 Announce Type: new +Abstract: Compact Runge-Kutta (cRK) Flux Reconstruction (FR) methods are a variant of RKFR methods for hyperbolic conservation laws with a compact stencil including only immediate neighboring finite elements. We extend cRKFR methods to handle hyperbolic equations with stiff source terms and non-conservative products. To handle stiff source terms, we use IMplicit EXplicit (IMEX) time integration schemes such that the implicitness is local to each solution point, and thus does not increase inter-element communication. Although non-conservative products do not correspond to a physical flux, we formulate the scheme using numerical fluxes at element interfaces. We use similar numerical fluxes for a lower order finite volume scheme on subcells of each element, which is then blended with the high order cRKFR scheme to obtain a robust scheme for problems with non-smooth solutions. Combined with a flux limiter at the element interfaces, the subcell based blending scheme preserves the physical admissibility of the solution, e.g., positivity of density and pressure for compressible Euler equations. The procedure thus leads to an admissibility preserving IMEX cRKFR scheme for hyperbolic equations with stiff source terms and non-conservative products. The capability of the scheme to handle stiff terms is shown through numerical tests involving Burgers' equations, reactive Euler's equations, and the ten moment problem. The non-conservative treatment is tested using variable advection equations, shear shallow water equations, the GLM-MHD, and the multi-ion MHD equations. + oai:arXiv.org:2512.08611v1 + math.NA + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Smitha Muthya Sudheendra, Mani Deep Cherukuri, Jaideep Srivastava + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Arpit Babbar, Hendrik Ranocha - Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment Analysis - https://arxiv.org/abs/2512.06681 - arXiv:2512.06681v1 Announce Type: new -Abstract: We present a mechanistic interpretability study of GPT-2 that causally examines how sentiment information is processed across its transformer layers. Using systematic activation patching across all 12 layers, we test the hypothesized two-stage sentiment architecture comprising early lexical detection and mid-layer contextual integration. Our experiments confirm that early layers (0-3) act as lexical sentiment detectors, encoding stable, position specific polarity signals that are largely independent of context. However, all three contextual integration hypotheses: Middle Layer Concentration, Phenomenon Specificity, and Distributed Processing are falsified. Instead of mid-layer specialization, we find that contextual phenomena such as negation, sarcasm, domain shifts etc. are integrated primarily in late layers (8-11) through a unified, non-modular mechanism. These experimental findings provide causal evidence that GPT-2's sentiment computation differs from the predicted hierarchical pattern, highlighting the need for further empirical characterization of contextual integration in large language models. - oai:arXiv.org:2512.06681v1 - cs.CL + Protein Secondary Structure Prediction Using Transformers + https://arxiv.org/abs/2512.08613 + arXiv:2512.08613v1 Announce Type: new +Abstract: Predicting protein secondary structures such as alpha helices, beta sheets, and coils from amino acid sequences is essential for understanding protein function. This work presents a transformer-based model that applies attention mechanisms to protein sequence data to predict structural motifs. A sliding-window data augmentation technique is used on the CB513 dataset to expand the training samples. The transformer shows strong ability to generalize across variable-length sequences while effectively capturing both local and long-range residue interactions. + oai:arXiv.org:2512.08613v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Amartya Hatua + Manzi Kevin Maxime - EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy - https://arxiv.org/abs/2512.06684 - arXiv:2512.06684v1 Announce Type: new -Abstract: Volume electron microscopy (vEM) enables nanoscale 3D imaging of biological structures but remains constrained by acquisition trade-offs, leading to anisotropic volumes with limited axial resolution. Existing deep learning methods seek to restore isotropy by leveraging lateral priors, yet their assumptions break down for morphologically anisotropic structures. We present EMGauss, a general framework for 3D reconstruction from planar scanned 2D slices with applications in vEM, which circumvents the inherent limitations of isotropy-based approaches. Our key innovation is to reframe slice-to-3D reconstruction as a 3D dynamic scene rendering problem based on Gaussian splatting, where the progression of axial slices is modeled as the temporal evolution of 2D Gaussian point clouds. To enhance fidelity in data-sparse regimes, we incorporate a Teacher-Student bootstrapping mechanism that uses high-confidence predictions on unobserved slices as pseudo-supervisory signals. Compared with diffusion- and GAN-based reconstruction methods, EMGauss substantially improves interpolation quality, enables continuous slice synthesis, and eliminates the need for large-scale pretraining. Beyond vEM, it potentially provides a generalizable slice-to-3D solution across diverse imaging domains. - oai:arXiv.org:2512.06684v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + HealthcareNLP: where are we and what is next? + https://arxiv.org/abs/2512.08617 + arXiv:2512.08617v1 Announce Type: new +Abstract: This proposed tutorial focuses on Healthcare Domain Applications of NLP, what we have achieved around HealthcareNLP, and the challenges that lie ahead for the future. Existing reviews in this domain either overlook some important tasks, such as synthetic data generation for addressing privacy concerns, or explainable clinical NLP for improved integration and implementation, or fail to mention important methodologies, including retrieval augmented generation and the neural symbolic integration of LLMs and KGs. In light of this, the goal of this tutorial is to provide an introductory overview of the most important sub-areas of a patient- and resource-oriented HealthcareNLP, with three layers of hierarchy: data/resource layer: annotation guidelines, ethical approvals, governance, synthetic data; NLP-Eval layer: NLP tasks such as NER, RE, sentiment analysis, and linking/coding with categorised methods, leading to explainable HealthAI; patients layer: Patient Public Involvement and Engagement (PPIE), health literacy, translation, simplification, and summarisation (also NLP tasks), and shared decision-making support. A hands-on session will be included in the tutorial for the audience to use HealthcareNLP applications. The target audience includes NLP practitioners in the healthcare application domain, NLP researchers who are interested in domain applications, healthcare researchers, and students from NLP fields. The type of tutorial is "Introductory to CL/NLP topics (HealthcareNLP)" and the audience does not need prior knowledge to attend this. Tutorial materials: https://github.com/4dpicture/HealthNLP + oai:arXiv.org:2512.08617v1 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yumeng He, Zanwei Zhou, Yekun Zheng, Chen Liang, Yunbo Wang, Xiaokang Yang + http://creativecommons.org/licenses/by-sa/4.0/ + Lifeng Han, Paul Rayson, Suzan Verberne, Andrew Moore, Goran Nenadic - PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory - https://arxiv.org/abs/2512.06688 - arXiv:2512.06688v1 Announce Type: new -Abstract: Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simulates 1,000 realistic user-chatbot interactions on 300+ scenarios, 20,000+ user preferences, and 128k-token context windows, where most user preferences are implicitly revealed to reflect real-world interactions. Using this data, we investigate how reinforcement fine-tuning enables a model to improve its long-context reasoning capabilities for user understanding and personalization. We also develop a framework for training an agentic memory system, which maintains a single, human-readable memory that grows with each user over time. - In our experiments, frontier LLMs still struggle with implicit personalization, achieving only 37-48% accuracy. While they support long context windows, reasoning remains the bottleneck for implicit personalization tasks. Using reinforcement fine-tuning, we successfully train Qwen3-4B to outperforms GPT-5, reaching 53% accuracy in implicit personalization. Moreover, our agentic memory framework achieves state-of-the-art 55% accuracy while using 16x fewer input tokens, relying on a 2k-token memory instead of full 32k conversation histories. These results underscore the impact of our dataset and demonstrate agentic memory as a scalable path toward real-world personalized intelligence. - oai:arXiv.org:2512.06688v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + New Constructions of SSPDs and their Applications + https://arxiv.org/abs/2512.08619 + arXiv:2512.08619v1 Announce Type: new +Abstract: $\renewcommand{\Re}{\mathbb{R}}$We present a new optimal construction of a semi-separated pair decomposition (i.e., SSPD) for a set of $n$ points in $\Re^d$. In the new construction each point participates in a few pairs, and it extends easily to spaces with low doubling dimension. This is the first optimal construction with these properties. + As an application of the new construction, for a fixed $t>1$, we present a new construction of a $t$-spanner with $O(n)$ edges and maximum degree $O(\log^2 n)$ that has a separator of size $O\pth{n^{1-1/d}}$. + oai:arXiv.org:2512.08619v1 + cs.CG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bowen Jiang, Yuan Yuan, Maohao Shen, Zhuoqun Hao, Zhangchen Xu, Zichen Chen, Ziyi Liu, Anvesh Rao Vijjini, Jiashu He, Hanchao Yu, Radha Poovendran, Gregory Wornell, Lyle Ungar, Dan Roth, Sihao Chen, Camillo Jose Taylor + 10.1016/j.comgeo.2011.12.003 + Mohammad A. Abam, Sariel Har-Peled - Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation - https://arxiv.org/abs/2512.06689 - arXiv:2512.06689v1 Announce Type: new -Abstract: Speech Enhancement (SE) and Speech Separation (SS) have traditionally been treated as distinct tasks in speech processing. However, real-world audio often involves both background noise and overlapping speakers, motivating the need for a unified solution. While recent approaches have attempted to integrate SE and SS within multi-stage architectures, these approaches typically involve complex, parameter-heavy models and rely on supervised training, limiting scalability and generalization. In this work, we propose UniVoiceLite, a lightweight and unsupervised audio-visual framework that unifies SE and SS within a single model. UniVoiceLite leverages lip motion and facial identity cues to guide speech extraction and employs Wasserstein distance regularization to stabilize the latent space without requiring paired noisy-clean data. Experimental results demonstrate that UniVoiceLite achieves strong performance in both noisy and multi-speaker scenarios, combining efficiency with robust generalization. The source code is available at https://github.com/jisoo-o/UniVoiceLite. - oai:arXiv.org:2512.06689v1 + OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics + https://arxiv.org/abs/2512.08625 + arXiv:2512.08625v1 Announce Type: new +Abstract: Simultaneous Localization and Mapping (SLAM) is a foundational component in robotics, AR/VR, and autonomous systems. With the rising focus on spatial AI in recent years, combining SLAM with semantic understanding has become increasingly important for enabling intelligent perception and interaction. Recent efforts have explored this integration, but they often rely on depth sensors or closed-set semantic models, limiting their scalability and adaptability in open-world environments. In this work, we present OpenMonoGS-SLAM, the first monocular SLAM framework that unifies 3D Gaussian Splatting (3DGS) with open-set semantic understanding. To achieve our goal, we leverage recent advances in Visual Foundation Models (VFMs), including MASt3R for visual geometry and SAM and CLIP for open-vocabulary semantics. These models provide robust generalization across diverse tasks, enabling accurate monocular camera tracking and mapping, as well as a rich understanding of semantics in open-world environments. Our method operates without any depth input or 3D semantic ground truth, relying solely on self-supervised learning objectives. Furthermore, we propose a memory mechanism specifically designed to manage high-dimensional semantic features, which effectively constructs Gaussian semantic feature maps, leading to strong overall performance. Experimental results demonstrate that our approach achieves performance comparable to or surpassing existing baselines in both closed-set and open-set segmentation tasks, all without relying on supplementary sensors such as depth maps or semantic annotations. + oai:arXiv.org:2512.08625v1 cs.CV - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jisoo Park, Seonghak Lee, Guisik Kim, Taewoo Kim, Junseok Kwon + Jisang Yoo, Gyeongjin Kang, Hyun-kyu Ko, Hyeonwoo Yu, Eunbyung Park - Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation - https://arxiv.org/abs/2512.06690 - arXiv:2512.06690v1 Announce Type: new -Abstract: Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlooking individual users. Personalization is essential, yet early approaches-such as prompt customization or fine-tuning-struggle to reason over implicit preferences, limiting real-world effectiveness. Recent "think-then-generate" methods address this by reasoning before response generation. However, they face challenges in long-form generation: their static one-shot reasoning must capture all relevant information for the full response generation, making learning difficult and limiting adaptability to evolving content. To address this issue, we propose FlyThinker, an efficient "think-while-generating" framework for personalized long-form generation. FlyThinker employs a separate reasoning model that generates latent token-level reasoning in parallel, which is fused into the generation model to dynamically guide response generation. This design enables reasoning and generation to run concurrently, ensuring inference efficiency. In addition, the reasoning model is designed to depend only on previous responses rather than its own prior outputs, which preserves training parallelism across different positions-allowing all reasoning tokens for training data to be produced in a single forward pass like standard LLM training, ensuring training efficiency. Extensive experiments on real-world benchmarks demonstrate that FlyThinker achieves better personalized generation while keeping training and inference efficiency. - oai:arXiv.org:2512.06690v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Inferring Causal Relationships to Improve Caching for Clients with Correlated Requests: Applications to VR + https://arxiv.org/abs/2512.08626 + arXiv:2512.08626v1 Announce Type: new +Abstract: Efficient edge caching reduces latency and alleviates backhaul congestion in modern networks. Traditional caching policies, such as Least Recently Used (LRU) and Least Frequently Used (LFU), perform well under specific request patterns. LRU excels in workloads with strong temporal locality, while LFU is effective when content popularity remains static. However, real-world client requests often exhibit correlations due to shared contexts and coordinated activities. This is particularly evident in Virtual Reality (VR) environments, where groups of clients navigate shared virtual spaces, leading to correlated content requests. + In this paper, we introduce the \textit{grouped client request model}, a generalization of the Independent Reference Model that explicitly captures different types of request correlations. Our theoretical analysis of LRU under this model reveals that the optimal causal caching policy depends on cache size: LFU is optimal for small to moderate caches, while LRU outperforms it for larger caches. To address the limitations of existing policies, we propose Least Following and Recently Used (LFRU), a novel online caching policy that dynamically infers and adapts to causal relationships in client requests to optimize evictions. LFRU prioritizes objects likely to be requested based on inferred dependencies, achieving near-optimal performance compared to the offline optimal Belady policy in structured correlation settings. + We develop VR based datasets to evaluate caching policies under realistic correlated requests. Our results show that LFRU consistently performs at least as well as LRU and LFU, outperforming LRU by up to 2.9x and LFU by up to1.9x in certain settings. + oai:arXiv.org:2512.08626v1 + cs.NI + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://creativecommons.org/licenses/by/4.0/ + Agrim Bari, Gustavo de Veciana, Yuqi Zhou + + + Trajectory Densification and Depth from Perspective-based Blur + https://arxiv.org/abs/2512.08627 + arXiv:2512.08627v1 Announce Type: new +Abstract: In the absence of a mechanical stabilizer, the camera undergoes inevitable rotational dynamics during capturing, which induces perspective-based blur especially under long-exposure scenarios. From an optical standpoint, perspective-based blur is depth-position-dependent: objects residing at distinct spatial locations incur different blur levels even under the same imaging settings. Inspired by this, we propose a novel method that estimate metric depth by examining the blur pattern of a video stream and dense trajectory via joint optical design algorithm. Specifically, we employ off-the-shelf vision encoder and point tracker to extract video information. Then, we estimate depth map via windowed embedding and multi-window aggregation, and densify the sparse trajectory from the optical algorithm using a vision-language model. Evaluations on multiple depth datasets demonstrate that our method attains strong performance over large depth range, while maintaining favorable generalization. Relative to the real trajectory in handheld shooting settings, our optical algorithm achieves superior precision and the dense reconstruction maintains strong accuracy. + oai:arXiv.org:2512.08627v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao, Fuli Feng, Xiangnan He, Tat-Seng Chua + Tianchen Qiu, Qirun Zhang, Jiajian He, Zhengyue Zhuge, Jiahui Xu, Yueting Chen - State Diversity Matters in Offline Behavior Distillation - https://arxiv.org/abs/2512.06692 - arXiv:2512.06692v1 Announce Type: new -Abstract: Offline Behavior Distillation (OBD), which condenses massive offline RL data into a compact synthetic behavioral dataset, offers a promising approach for efficient policy training and can be applied across various downstream RL tasks. In this paper, we uncover a misalignment between original and distilled datasets, observing that a high-quality original dataset does not necessarily yield a superior synthetic dataset. Through an empirical analysis of policy performance under varying levels of training loss, we show that datasets with greater state diversity outperforms those with higher state quality when training loss is substantial, as is often the case in OBD, whereas the relationship reverses under minimal loss, which contributes to the misalignment. By associating state quality and diversity in reducing pivotal and surrounding error, respectively, our theoretical analysis establishes that surrounding error plays a more crucial role in policy performance when pivotal error is large, thereby highlighting the importance of state diversity in OBD scenario. Furthermore, we propose a novel yet simple algorithm, state density weighted (SDW) OBD, which emphasizes state diversity by weighting the distillation objective using the reciprocal of state density, thereby distilling a more diverse state information into synthetic data. Extensive experiments across multiple D4RL datasets confirm that SDW significantly enhances OBD performance when the original dataset exhibits limited state diversity. - oai:arXiv.org:2512.06692v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Sustainable Development Goals in Psychology: A Century of Progress in Publications + https://arxiv.org/abs/2512.08628 + arXiv:2512.08628v1 Announce Type: new +Abstract: The Sustainable Development Goals (SDGs) offer a lens for tracking societal change, yet contributions from the social and behavioral sciences have rarely been integrated into policy agendas. To take stock and create a baseline and benchmark for the future, we assemble 233,061 psychology publications (1894 -- 2022) and tag them to the 17 SDGs using a query-based classifier. Health, education, work, inequality, and gender dominate the study of SDGs in psychology, shifting from an early focus on work to education and inequality, and since the 1960s, health. United States-based research leads across most goals. Other countries set distinct priorities (e.g., China: education and work; Australia: health). Women comprise about one-third of authors, concentrated in social and health goals, but have been underrepresented in STEM-oriented goals. The 2015 launch of the SDGs marked a turning point: SDG-tagged publications have been receiving more citations than comparable non-SDG work, reversing a pre-2015 deficit. Tracking the SDGs through psychology clarifies long-run engagement with social priorities, identifies evidence gaps, and guides priorities to accelerate the field's contribution to the SDG agenda. + oai:arXiv.org:2512.08628v1 + cs.DL + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Shiye Lei, Zhihao Cheng, Dacheng Tao + http://creativecommons.org/licenses/by-sa/4.0/ + Xinyi Zhao, Ralph Hertwig, Dirk U. Wulff - TopiCLEAR: Topic extraction by CLustering Embeddings with Adaptive dimensional Reduction - https://arxiv.org/abs/2512.06694 - arXiv:2512.06694v1 Announce Type: new -Abstract: Rapid expansion of social media platforms such as X (formerly Twitter), Facebook, and Reddit has enabled large-scale analysis of public perceptions on diverse topics, including social issues, politics, natural disasters, and consumer sentiment. Topic modeling is a widely used approach for uncovering latent themes in text data, typically framed as an unsupervised classification task. However, traditional models, originally designed for longer and more formal documents, struggle with short social media posts due to limited co-occurrence statistics, fragmented semantics, inconsistent spelling, and informal language. To address these challenges, we propose a new method, TopiCLEAR: Topic extraction by CLustering Embeddings with Adaptive dimensional Reduction. Specifically, each text is embedded using Sentence-BERT (SBERT) and provisionally clustered using Gaussian Mixture Models (GMM). The clusters are then refined iteratively using a supervised projection based on linear discriminant analysis, followed by GMM-based clustering until convergence. Notably, our method operates directly on raw text, eliminating the need for preprocessing steps such as stop word removal. We evaluate our approach on four diverse datasets, 20News, AgNewsTitle, Reddit, and TweetTopic, each containing human-labeled topic information. Compared with seven baseline methods, including a recent SBERT-based method and a zero-shot generative AI method, our approach achieves the highest similarity to human-annotated topics, with significant improvements for both social media posts and online news articles. Additionally, qualitative analysis shows that our method produces more interpretable topics, highlighting its potential for applications in social media data and web content analytics. - oai:arXiv.org:2512.06694v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + See-Control: A Multimodal Agent Framework for Smartphone Interaction with a Robotic Arm + https://arxiv.org/abs/2512.08629 + arXiv:2512.08629v1 Announce Type: new +Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have enabled their use as intelligent agents for smartphone operation. However, existing methods depend on the Android Debug Bridge (ADB) for data transmission and action execution, limiting their applicability to Android devices. In this work, we introduce the novel Embodied Smartphone Operation (ESO) task and present See-Control, a framework that enables smartphone operation via direct physical interaction with a low-DoF robotic arm, offering a platform-agnostic solution. See-Control comprises three key components: (1) an ESO benchmark with 155 tasks and corresponding evaluation metrics; (2) an MLLM-based embodied agent that generates robotic control commands without requiring ADB or system back-end access; and (3) a richly annotated dataset of operation episodes, offering valuable resources for future research. By bridging the gap between digital agents and the physical world, See-Control provides a concrete step toward enabling home robots to perform smartphone-dependent tasks in realistic environments. + oai:arXiv.org:2512.08629v1 + cs.AI + cs.CV + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Aoi Fujita, Taichi Yamamoto, Yuri Nakayama, Ryota Kobayashi + Haoyu Zhao, Weizhong Ding, Yuhao Yang, Zheng Tian, Linyi Yang, Kun Shao, Jun Wang - Mitigating Barren plateaus in quantum denoising diffusion probabilistic models - https://arxiv.org/abs/2512.06695 - arXiv:2512.06695v1 Announce Type: new -Abstract: Quantum generative models leverage quantum superposition and entanglement to enhance learning efficiency for both classical and quantum data. The quantum denoising diffusion probabilistic model (QuDDPM), inspired by its classical counterpart, has been proposed as a promising framework for quantum generative learning. QuDDPM is capable of efficiently learning and generating quantum data, and it demonstrates excellent performance in learning correlated quantum noise models, quantum many-body phases, and the topological structure of quantum data. However, we show that barren plateaus emerge in QuDDPMs due to the use of 2-design states as the input for the denoising process, which severely undermines the performance of QuDDPM. Through theoretical analysis and experimental validation, we confirm the presence of barren plateaus in the original QuDDPM. To address this issue, we introduce an improved QuDDPM that utilizes a distribution maintaining a certain distance from the Haar distribution, ensuring better trainability. Experimental results demonstrate that our approach effectively mitigates the barren plateau problem and generates samples with higher quality, paving the way for scalable and efficient quantum generative learning. - oai:arXiv.org:2512.06695v1 - cs.LG - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 + Multi-Task Bayesian Optimization for Tuning Decentralized Trajectory Generation in Multi-UAV Systems + https://arxiv.org/abs/2512.08630 + arXiv:2512.08630v1 Announce Type: new +Abstract: This paper investigates the use of Multi-Task Bayesian Optimization for tuning decentralized trajectory generation algorithms in multi-drone systems. We treat each task as a trajectory generation scenario defined by a specific number of drone-to-drone interactions. To model relationships across scenarios, we employ Multi-Task Gaussian Processes, which capture shared structure across tasks and enable efficient information transfer during optimization. We compare two strategies: optimizing the average mission time across all tasks and optimizing each task individually. Through a comprehensive simulation campaign, we show that single-task optimization leads to progressively shorter mission times as swarm size grows, but requires significantly more optimization time than the average-task approach. + oai:arXiv.org:2512.08630v1 + cs.RO + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Haipeng Cao, Kaining Zhang, Dacheng Tao, Zhaofeng Su + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Marta Manzoni, Alessandro Nazzari, Roberto Rubinacci, Marco Lovera - Predictive Modeling of I/O Performance for Machine Learning Training Pipelines: A Data-Driven Approach to Storage Optimization - https://arxiv.org/abs/2512.06699 - arXiv:2512.06699v1 Announce Type: new -Abstract: Modern machine learning training is increasingly bottlenecked by data I/O rather than compute. GPUs often sit idle at below 50% utilization waiting for data. This paper presents a machine learning approach to predict I/O performance and recommend optimal storage configurations for ML training pipelines. We collected 141 observations through systematic benchmarking across different storage backends (NVMe SSD, network-attached storage, in-memory filesystems), data formats, and access patterns, covering both low-level I/O operations and full training pipelines. After evaluating seven regression models and three classification approaches, XGBoost achieved the best performance with R-squared of 0.991, predicting I/O throughput within 11.8% error on average. Feature importance analysis revealed that throughput metrics and batch size are the primary performance drivers. This data-driven approach can reduce configuration time from days of trial-and-error to minutes of predictive recommendation. The methodology is reproducible and extensible to other resource management problems in ML systems. Code and data are available at https://github.com/knkarthik01/gpu_storage_ml_project - oai:arXiv.org:2512.06699v1 - cs.PF + Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning + https://arxiv.org/abs/2512.08639 + arXiv:2512.08639v1 Announce Type: new +Abstract: Aerial Vision-and-Language Navigation (VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and navigate complex urban environments using onboard visual observation. This task holds promise for real-world applications such as low-altitude inspection, search-and-rescue, and autonomous aerial delivery. Existing methods often rely on panoramic images, depth inputs, or odometry to support spatial reasoning and action planning. These requirements increase system cost and integration complexity, thus hindering practical deployment for lightweight UAVs. We present a unified aerial VLN framework that operates solely on egocentric monocular RGB observations and natural language instructions. The model formulates navigation as a next-token prediction problem, jointly optimizing spatial perception, trajectory reasoning, and action prediction through prompt-guided multi-task learning. Moreover, we propose a keyframe selection strategy to reduce visual redundancy by retaining semantically informative frames, along with an action merging and label reweighting mechanism that mitigates long-tailed supervision imbalance and facilitates stable multi-task co-training. Extensive experiments on the Aerial VLN benchmark validate the effectiveness of our method. Under the challenging monocular RGB-only setting, our model achieves strong results across both seen and unseen environments. It significantly outperforms existing RGB-only baselines and narrows the performance gap with state-of-the-art panoramic RGB-D counterparts. Comprehensive ablation studies further demonstrate the contribution of our task design and architectural choices. + oai:arXiv.org:2512.08639v1 + cs.CV cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Karthik Prabhakar + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Huilin Xu, Zhuoyang Liu, Yixiang Luomei, Feng Xu - Foresight Prediction Enhanced Live-Streaming Recommendation - https://arxiv.org/abs/2512.06700 - arXiv:2512.06700v1 Announce Type: new -Abstract: Live-streaming, as an emerging media enabling real-time interaction between authors and users, has attracted significant attention. Unlike the stable playback time of traditional TV live or the fixed content of short video, live-streaming, due to the dynamics of content and time, poses higher requirements for the recommendation algorithm of the platform - understanding the ever-changing content in real time and push it to users at the appropriate moment. Through analysis, we find that users have a better experience and express more positive behaviors during highlight moments of the live-streaming. Furthermore, since the model lacks access to future content during recommendation, yet user engagement depends on how well subsequent content aligns with their interests, an intuitive solution is to predict future live-streaming content. Therefore, we perform semantic quantization on live-streaming segments to obtain Semantic ids (Sid), encode the historical Sid sequence to capture the author's characteristics, and model Sid evolution trend to enable foresight prediction of future content. This foresight enhances the ranking model through refined features. Extensive offline and online experiments demonstrate the effectiveness of our method. - oai:arXiv.org:2512.06700v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 + Applications of Interval-based Temporal Separation: the Reactivity Normal Form, Inverse $\Pi$, Craig Interpolation and Beth Definability + https://arxiv.org/abs/2512.08640 + arXiv:2512.08640v1 Announce Type: new +Abstract: We show how interval-based temporal separation on the extension of Moszkowski's discrete time interval temporal logic (Moszkowski, 1986) by the neighbourhood modalities (ITL-NL) and a lemma which is key in establishing this form of separation in (Guelev and Moszkowski, 2022) can be used to obtain concise proofs of an interval-based form of the reactivity normal form as known from (Manna and Pnueli, 1990), the inverse of the temporal projection operator from (Halpern, Manna and Moszkowski, 1983), the elimination of propositional quantification in ITL-NL and, consequently, uniform Craig interpolation and Beth definability for ITL-NL. + oai:arXiv.org:2512.08640v1 + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiangxia Cao, Ruochen Yang, Xiang Chen, Changxin Lao, Yueyang Liu, Yusheng Huang, Yuanhao Tian, Xiangyu Wu, Shuang Yang, Zhaojie Liu, Guorui Zhou + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Dimitar P. Guelev - Pathway to $O(\sqrt{d})$ Complexity bound under Wasserstein metric of flow-based models - https://arxiv.org/abs/2512.06702 - arXiv:2512.06702v1 Announce Type: new -Abstract: We provide attainable analytical tools to estimate the error of flow-based generative models under the Wasserstein metric and to establish the optimal sampling iteration complexity bound with respect to dimension as $O(\sqrt{d})$. We show this error can be explicitly controlled by two parts: the Lipschitzness of the push-forward maps of the backward flow which scales independently of the dimension; and a local discretization error scales $O(\sqrt{d})$ in terms of dimension. The former one is related to the existence of Lipschitz changes of variables induced by the (heat) flow. The latter one consists of the regularity of the score function in both spatial and temporal directions. - These assumptions are valid in the flow-based generative model associated with the F\"{o}llmer process and $1$-rectified flow under the Gaussian tail assumption. As a consequence, we show that the sampling iteration complexity grows linearly with the square root of the trace of the covariance operator, which is related to the invariant distribution of the forward process. - oai:arXiv.org:2512.06702v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation + https://arxiv.org/abs/2512.08645 + arXiv:2512.08645v1 Announce Type: new +Abstract: While state-of-the-art image generation models achieve remarkable visual quality, their internal generative processes remain a "black box." This opacity limits human observation and intervention, and poses a barrier to ensuring model reliability, safety, and control. Furthermore, their non-human-like workflows make them difficult for human observers to interpret. To address this, we introduce the Chain-of-Image Generation (CoIG) framework, which reframes image generation as a sequential, semantic process analogous to how humans create art. Similar to the advantages in monitorability and performance that Chain-of-Thought (CoT) brought to large language models (LLMs), CoIG can produce equivalent benefits in text-to-image generation. CoIG utilizes an LLM to decompose a complex prompt into a sequence of simple, step-by-step instructions. The image generation model then executes this plan by progressively generating and editing the image. Each step focuses on a single semantic entity, enabling direct monitoring. We formally assess this property using two novel metrics: CoIG Readability, which evaluates the clarity of each intermediate step via its corresponding output; and Causal Relevance, which quantifies the impact of each procedural step on the final generated image. We further show that our framework mitigates entity collapse by decomposing the complex generation task into simple subproblems, analogous to the procedural reasoning employed by CoT. Our experimental results indicate that CoIG substantially enhances quantitative monitorability while achieving competitive compositional robustness compared to established baseline models. The framework is model-agnostic and can be integrated with any image generation model. + oai:arXiv.org:2512.08645v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiangjun Meng, Zhongjian Wang + http://creativecommons.org/licenses/by/4.0/ + Young Kyung Kim, Oded Schlesinger, Yuzhou Zhao, J. Matias Di Martino, Guillermo Sapiro - Academic journals' AI policies fail to curb the surge in AI-assisted academic writing - https://arxiv.org/abs/2512.06705 - arXiv:2512.06705v1 Announce Type: new -Abstract: The rapid integration of generative AI into academic writing has prompted widespread policy responses from journals and publishers. However, the effectiveness of these policies remains unclear. Here, we analyze 5,114 journals and over 5.2 million papers to evaluate the real-world impact of AI usage guidelines. We show that despite 70% of journals adopting AI policies (primarily requiring disclosure), researchers' use of AI writing tools has increased dramatically across disciplines, with no significant difference between journals with or without policies. Non-English-speaking countries, physical sciences, and high-OA journals exhibit the highest growth rates. Crucially, full-text analysis on 164k scientific publications reveals a striking transparency gap: Of the 75k papers published since 2023, only 76 (0.1%) explicitly disclosed AI use. Our findings suggest that current policies have largely failed to promote transparency or restrain AI adoption. We urge a re-evaluation of ethical frameworks to foster responsible AI integration in science. - oai:arXiv.org:2512.06705v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models + https://arxiv.org/abs/2512.08646 + arXiv:2512.08646v1 Announce Type: new +Abstract: We introduce QSTN, an open-source Python framework for systematically generating responses from questionnaire-style prompts to support in-silico surveys and annotation tasks with large language models (LLMs). QSTN enables robust evaluation of questionnaire presentation, prompt perturbations, and response generation methods. Our extensive evaluation ($>40 $ million survey responses) shows that question structure and response generation methods have a significant impact on the alignment of generated survey responses with human answers, and can be obtained for a fraction of the compute cost. In addition, we offer a no-code user interface that allows researchers to set up robust experiments with LLMs without coding knowledge. We hope that QSTN will support the reproducibility and reliability of LLM-based research in the future. + oai:arXiv.org:2512.08646v1 + cs.CL + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Yongyuan He, Yi Bu + Maximilian Kreutner, Jens Rupprecht, Georg Ahnert, Ahmed Salem, Markus Strohmaier - A Novel Multimodal RUL Framework for Remaining Useful Life Estimation with Layer-wise Explanations - https://arxiv.org/abs/2512.06708 - arXiv:2512.06708v1 Announce Type: new -Abstract: Estimating the Remaining Useful Life (RUL) of mechanical systems is pivotal in Prognostics and Health Management (PHM). Rolling-element bearings are among the most frequent causes of machinery failure, highlighting the need for robust RUL estimation methods. Existing approaches often suffer from poor generalization, lack of robustness, high data demands, and limited interpretability. This paper proposes a novel multimodal-RUL framework that jointly leverages image representations (ImR) and time-frequency representations (TFR) of multichannel, nonstationary vibration signals. The architecture comprises three branches: (1) an ImR branch and (2) a TFR branch, both employing multiple dilated convolutional blocks with residual connections to extract spatial degradation features; and (3) a fusion branch that concatenates these features and feeds them into an LSTM to model temporal degradation patterns. A multi-head attention mechanism subsequently emphasizes salient features, followed by linear layers for final RUL regression. To enable effective multimodal learning, vibration signals are converted into ImR via the Bresenham line algorithm and into TFR using Continuous Wavelet Transform. We also introduce multimodal Layer-wise Relevance Propagation (multimodal-LRP), a tailored explainability technique that significantly enhances model transparency. The approach is validated on the XJTU-SY and PRONOSTIA benchmark datasets. Results show that our method matches or surpasses state-of-the-art baselines under both seen and unseen operating conditions, while requiring ~28 % less training data on XJTU-SY and ~48 % less on PRONOSTIA. The model exhibits strong noise resilience, and multimodal-LRP visualizations confirm the interpretability and trustworthiness of predictions, making the framework highly suitable for real-world industrial deployment. - oai:arXiv.org:2512.06708v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + C-DIRA: Computationally Efficient Dynamic ROI Routing and Domain-Invariant Adversarial Learning for Lightweight Driver Behavior Recognition + https://arxiv.org/abs/2512.08647 + arXiv:2512.08647v1 Announce Type: new +Abstract: Driver distraction behavior recognition using in-vehicle cameras demands real-time inference on edge devices. However, lightweight models often fail to capture fine-grained behavioral cues, resulting in reduced performance on unseen drivers or under varying conditions. ROI-based methods also increase computational cost, making it difficult to balance efficiency and accuracy. This work addresses the need for a lightweight architecture that overcomes these constraints. We propose Computationally efficient Dynamic region of Interest Routing and domain-invariant Adversarial learning for lightweight driver behavior recognition (C-DIRA). The framework combines saliency-driven Top-K ROI pooling and fused classification for local feature extraction and integration. Dynamic ROI routing enables selective computation by applying ROI inference only to high difficulty data samples. Moreover, pseudo-domain labeling and adversarial learning are used to learn domain-invariant features robust to driver and background variation. Experiments on the State Farm Distracted Driver Detection Dataset show that C-DIRA maintains high accuracy with significantly fewer FLOPs and lower latency than prior lightweight models. It also demonstrates robustness under visual degradation such as blur and low-light, and stable performance across unseen domains. These results confirm C-DIRA's effectiveness in achieving compactness, efficiency, and generalization. + oai:arXiv.org:2512.08647v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Waleed Razzaq, Yun-Bo Zhao + Keito Inoshita - Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation - https://arxiv.org/abs/2512.06710 - arXiv:2512.06710v1 Announce Type: new -Abstract: As large language models become components of larger agentic systems, evaluation reliability becomes critical: unreliable sub-agents introduce brittleness into downstream system behavior. Yet current evaluation practice, reporting a single accuracy number from a single run, obscures the variance underlying these results, making it impossible to distinguish genuine capability improvements from lucky sampling. We propose adopting Intraclass Correlation Coefficient (ICC), a metric from measurement science, to characterize this variance. ICC decomposes observed variance into between-query variance (task difficulty) and within-query variance (agent inconsistency), highlighting whether reported results reflect true capability or measurement noise. We evaluated on GAIA (Levels 1-3, measuring agentic capabilities across varying reasoning complexity) and FRAMES (measuring retrieval and factuality across multiple documents). We found that ICC varies dramatically with task structure, with reasoning and retrieval tasks (FRAMES) exhibit ICC=0.4955-0.7118 across models, and agentic tasks (GAIA) exhibiting ICC=0.304-0.774 across models. For sub-agent replacement decisions in agentic systems, accuracy improvements are only trustworthy if ICC also improves. We demonstrate that ICC converges by n=8-16 trials for structured tasks and n>=32 for complex reasoning, enabling practitioners to set evidence-based resampling budgets. We recommend reporting accuracy alongside ICC and within-query variance as standard practice, and propose updated Evaluation Cards capturing these metrics. By making evaluation stability visible, we aim to transform agentic benchmarking from opaque leaderboard competition to trustworthy experimental science. Our code is open-sourced at https://github.com/youdotcom-oss/stochastic-agent-evals. - oai:arXiv.org:2512.06710v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank + https://arxiv.org/abs/2512.08648 + arXiv:2512.08648v1 Announce Type: new +Abstract: The dominance of denoising generative models (e.g., diffusion, flow-matching) in visual synthesis is tempered by their substantial training costs and inefficiencies in representation learning. While injecting discriminative representations via auxiliary alignment has proven effective, this approach still faces key limitations: the reliance on external, pre-trained encoders introduces overhead and domain shift. A dispersed-based strategy that encourages strong separation among in-batch latent representations alleviates this specific dependency. To assess the effect of the number of negative samples in generative modeling, we propose {\mname}, a plug-and-play training framework that requires no external encoders. Our method integrates a memory bank mechanism that maintains a large, dynamically updated queue of negative samples across training iterations. This decouples the number of negatives from the mini-batch size, providing abundant and high-quality negatives for a contrastive objective without a multiplicative increase in computational cost. A low-dimensional projection head is used to further minimize memory and bandwidth overhead. {\mname} offers three principal advantages: (1) it is self-contained, eliminating dependency on pretrained vision foundation models and their associated forward-pass overhead; (2) it introduces no additional parameters or computational cost during inference; and (3) it enables substantially faster convergence, achieving superior generative quality more efficiently. On ImageNet-256, {\mname} achieves a state-of-the-art FID of \textbf{2.40} within 400k steps, significantly outperforming comparable methods. + oai:arXiv.org:2512.08648v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zairah Mustahsan, Abel Lim, Megna Anand, Saahil Jain, Bryan McCann + Shaofeng Zhang, Xuanqi Chen, Ning Liao, Haoxiang Zhao, Xiaoxing Wang, Haoru Tan, Sitong Wu, Xiaosong Jia, Qi Fan, Junchi Yan - Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Models - https://arxiv.org/abs/2512.06711 - arXiv:2512.06711v1 Announce Type: new -Abstract: This study addresses the issues of privacy protection and efficiency in instruction fine-tuning of large-scale language models by proposing a parameter-efficient method that integrates differential privacy noise allocation with gradient clipping in a collaborative optimization framework. The method keeps the backbone model frozen and updates parameters through a low-dimensional projection subspace, while introducing clipping and adaptive noise allocation during gradient computation. This design reduces privacy budget consumption and ensures training stability and robustness. The unified framework combines gradient constraints, noise allocation, and parameter projection, effectively mitigating performance fluctuations and privacy risks in multi-task instruction scenarios. Experiments are conducted across hyperparameter, environment, and data sensitivity dimensions. Results show that the method outperforms baseline models in accuracy, privacy budget, and parameter efficiency, and maintains stable performance under diverse and uncertain data conditions. The findings enrich the theoretical integration of differential privacy and parameter-efficient fine-tuning and demonstrate its practical adaptability in instruction tasks, providing a feasible solution for secure training in complex instruction environments. - oai:arXiv.org:2512.06711v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + A Sensor-Aware Phenomenological Framework for Lidar Degradation Simulation and SLAM Robustness Evaluation + https://arxiv.org/abs/2512.08653 + arXiv:2512.08653v1 Announce Type: new +Abstract: Lidar-based SLAM systems are highly sensitive to adverse conditions such as occlusion, noise, and field-of-view (FoV) degradation, yet existing robustness evaluation methods either lack physical grounding or do not capture sensor-specific behavior. This paper presents a sensor-aware, phenomenological framework for simulating interpretable lidar degradations directly on real point clouds, enabling controlled and reproducible SLAM stress testing. Unlike image-derived corruption benchmarks (e.g., SemanticKITTI-C) or simulation-only approaches (e.g., lidarsim), the proposed system preserves per-point geometry, intensity, and temporal structure while applying structured dropout, FoV reduction, Gaussian noise, occlusion masking, sparsification, and motion distortion. The framework features autonomous topic and sensor detection, modular configuration with four severity tiers (light--extreme), and real-time performance (less than 20 ms per frame) compatible with ROS workflows. Experimental validation across three lidar architectures and five state-of-the-art SLAM systems reveals distinct robustness patterns shaped by sensor design and environmental context. The open-source implementation provides a practical foundation for benchmarking lidar-based SLAM under physically meaningful degradation scenarios. + oai:arXiv.org:2512.08653v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yulin Huang, Yaxuan Luan, Jinxu Guo, Xiangchen Song, Yuchen Liu + Doumegna Mawuto Koudjo Felix, Xianjia Yu, Zhuo Zou, Tomi Westerlund - Look Twice before You Leap: A Rational Agent Framework for Localized Adversarial Anonymization - https://arxiv.org/abs/2512.06713 - arXiv:2512.06713v1 Announce Type: new -Abstract: Current LLM-based text anonymization frameworks usually rely on remote API services from powerful LLMs, which creates an inherent "privacy paradox": users must somehow disclose data to untrusted third parties for superior privacy preservation. Moreover, directly migrating these frameworks to local small-scale models (LSMs) offers a suboptimal solution with catastrophic collapse in utility based on our core findings. Our work argues that this failure stems not merely from the capability deficits of LSMs, but from the inherent irrationality of the greedy adversarial strategies employed by current state-of-the-art (SoTA) methods. We model the anonymization process as a trade-off between Marginal Privacy Gain (MPG) and Marginal Utility Cost (MUC), and demonstrate that greedy strategies inevitably drift into an irrational state. To address this, we propose Rational Localized Adversarial Anonymization (RLAA), a fully localized and training-free framework featuring an Attacker-Arbitrator-Anonymizer (A-A-A) architecture. RLAA introduces an arbitrator that acts as a rationality gatekeeper, validating the attacker's inference to filter out feedback providing negligible benefits on privacy preservation. This mechanism enforces a rational early-stopping criterion, and systematically prevents utility collapse. Extensive experiments on different datasets demonstrate that RLAA achieves the best privacy-utility trade-off, and in some cases even outperforms SoTA on the Pareto principle. Our code and datasets will be released upon acceptance. - oai:arXiv.org:2512.06713v1 - cs.CR - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Sim2Swim: Zero-Shot Velocity Control for Agile AUV Maneuvering in 3 Minutes + https://arxiv.org/abs/2512.08656 + arXiv:2512.08656v1 Announce Type: new +Abstract: Holonomic autonomous underwater vehicles (AUVs) have the hardware ability for agile maneuvering in both translational and rotational degrees of freedom (DOFs). However, due to challenges inherent to underwater vehicles, such as complex hydrostatics and hydrodynamics, parametric uncertainties, and frequent changes in dynamics due to payload changes, control is challenging. Performance typically relies on carefully tuned controllers targeting unique platform configurations, and a need for re-tuning for deployment under varying payloads and hydrodynamic conditions. As a consequence, agile maneuvering with simultaneous tracking of time-varying references in both translational and rotational DOFs is rarely utilized in practice. To the best of our knowledge, this paper presents the first general zero-shot sim2real deep reinforcement learning-based (DRL) velocity controller enabling path following and agile 6DOF maneuvering with a training duration of just 3 minutes. Sim2Swim, the proposed approach, inspired by state-of-the-art DRL-based position control, leverages domain randomization and massively parallelized training to converge to field-deployable control policies for AUVs of variable characteristics without post-processing or tuning. Sim2Swim is extensively validated in pool trials for a variety of configurations, showcasing robust control for highly agile motions. + oai:arXiv.org:2512.08656v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Donghang Duan, Xu Zheng + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Lauritz Rismark Fosso, Herman Bi{\o}rn Amundsen, Marios Xanthidis, Sveinung Johan Ohrem - A Novel Deep Neural Network Architecture for Real-Time Water Demand Forecasting - https://arxiv.org/abs/2512.06714 - arXiv:2512.06714v1 Announce Type: new -Abstract: Short-term water demand forecasting (StWDF) is the foundation stone in the derivation of an optimal plan for controlling water supply systems. Deep learning (DL) approaches provide the most accurate solutions for this purpose. However, they suffer from complexity problem due to the massive number of parameters, in addition to the high forecasting error at the extreme points. In this work, an effective method to alleviate the error at these points is proposed. It is based on extending the data by inserting virtual data within the actual data to relieve the nonlinearity around them. To our knowledge, this is the first work that considers the problem related to the extreme points. Moreover, the water demand forecasting model proposed in this work is a novel DL model with relatively low complexity. The basic model uses the gated recurrent unit (GRU) to handle the sequential relationship in the historical demand data, while an unsupervised classification method, K-means, is introduced for the creation of new features to enhance the prediction accuracy with less number of parameters. Real data obtained from two different water plants in China are used to train and verify the model proposed. The prediction results and the comparison with the state-of-the-art illustrate that the method proposed reduces the complexity of the model six times of what achieved in the literature while conserving the same accuracy. Furthermore, it is found that extending the data set significantly reduces the error by about 30%. However, it increases the training time. - oai:arXiv.org:2512.06714v1 - cs.LG + Reusability in MLOps: Leveraging Ports and Adapters to Build a Microservices Architecture for the Maritime Domain + https://arxiv.org/abs/2512.08657 + arXiv:2512.08657v1 Announce Type: new +Abstract: ML-Enabled Systems (MLES) are inherently complex since they require multiple components to achieve their business goal. This experience report showcases the software architecture reusability techniques applied while building Ocean Guard, an MLES for anomaly detection in the maritime domain. In particular, it highlights the challenges and lessons learned to reuse the Ports and Adapters pattern to support building multiple microservices from a single codebase. This experience report hopes to inspire software engineers, machine learning engineers, and data scientists to apply the Hexagonal Architecture pattern to build their MLES. + oai:arXiv.org:2512.08657v1 + cs.SE cs.AI - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1016/j.jhydrol.2021.126353 - Journal of Hydrology 2021 - Tony Salloom, Okyay Kaynak, Wei He + Renato Cordeiro Ferreira (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University, University of S\~ao Paulo), Aditya Dhinavahi (Jheronimus Academy of Data Science, Technical University of Eindhoven), Rowanne Trapmann (Jheronimus Academy of Data Science, Tilburg University), Willem-Jan van den Heuvel (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University) - Cognitive Control Architecture (CCA): A Lifecycle Supervision Framework for Robustly Aligned AI Agents - https://arxiv.org/abs/2512.06716 - arXiv:2512.06716v1 Announce Type: new -Abstract: Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs between security and functionality in existing defense mechanisms. This leads to malicious and unauthorized tool invocations, diverting agents from their original objectives. The success of complex IPIs reveals a deeper systemic fragility: while current defenses demonstrate some effectiveness, most defense architectures are inherently fragmented. Consequently, they fail to provide full integrity assurance across the entire task execution pipeline, forcing unacceptable multi-dimensional compromises among security, functionality, and efficiency. Our method is predicated on a core insight: no matter how subtle an IPI attack, its pursuit of a malicious objective will ultimately manifest as a detectable deviation in the action trajectory, distinct from the expected legitimate plan. Based on this, we propose the Cognitive Control Architecture (CCA), a holistic framework achieving full-lifecycle cognitive supervision. CCA constructs an efficient, dual-layered defense system through two synergistic pillars: (i) proactive and preemptive control-flow and data-flow integrity enforcement via a pre-generated "Intent Graph"; and (ii) an innovative "Tiered Adjudicator" that, upon deviation detection, initiates deep reasoning based on multi-dimensional scoring, specifically designed to counter complex conditional attacks. Experiments on the AgentDojo benchmark substantiate that CCA not only effectively withstands sophisticated attacks that challenge other advanced defense methods but also achieves uncompromised security with notable efficiency and robustness, thereby reconciling the aforementioned multi-dimensional trade-off. - oai:arXiv.org:2512.06716v1 - cs.AI + An Agentic AI System for Multi-Framework Communication Coding + https://arxiv.org/abs/2512.08659 + arXiv:2512.08659v1 Announce Type: new +Abstract: Clinical communication is central to patient outcomes, yet large-scale human annotation of patient-provider conversation remains labor-intensive, inconsistent, and difficult to scale. Existing approaches based on large language models typically rely on single-task models that lack adaptability, interpretability, and reliability, especially when applied across various communication frameworks and clinical domains. In this study, we developed a Multi-framework Structured Agentic AI system for Clinical Communication (MOSAIC), built on a LangGraph-based architecture that orchestrates four core agents, including a Plan Agent for codebook selection and workflow planning, an Update Agent for maintaining up-to-date retrieval databases, a set of Annotation Agents that applies codebook-guided retrieval-augmented generation (RAG) with dynamic few-shot prompting, and a Verification Agent that provides consistency checks and feedback. To evaluate performance, we compared MOSAIC outputs against gold-standard annotations created by trained human coders. We developed and evaluated MOSAIC using 26 gold standard annotated transcripts for training and 50 transcripts for testing, spanning rheumatology and OB/GYN domains. On the test set, MOSAIC achieved an overall F1 score of 0.928. Performance was highest in the Rheumatology subset (F1 = 0.962) and strongest for Patient Behavior (e.g., patients asking questions, expressing preferences, or showing assertiveness). Ablations revealed that MOSAIC outperforms baseline benchmarking. + oai:arXiv.org:2512.08659v1 cs.CL - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhibo Liang, Tianze Hu, Zaiye Chen, Mingjie Tang + Bohao Yang, Rui Yang, Joshua M. Biro, Haoyuan Wang, Jessica L. Handley, Brianna Richardson, Sophia Bessias, Nicoleta Economou-Zavlanos, Armando D. Bedoya, Monica Agrawal, Michael M. Zavlanos, Anand Chowdhury, Raj M. Ratwani, Kai Sun, Kathryn I. Pollak, Michael J. Pencina, Chuan Hong - ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems - https://arxiv.org/abs/2512.06721 - arXiv:2512.06721v1 Announce Type: new -Abstract: Large Language Model (LLM) agents are emerging to transform daily life. However, existing LLM agents primarily follow a reactive paradigm, relying on explicit user instructions to initiate services, which increases both physical and cognitive workload. In this paper, we propose ProAgent, the first end-to-end proactive agent system that harnesses massive sensory contexts and LLM reasoning to deliver proactive assistance. ProAgent first employs a proactive-oriented context extraction approach with on-demand tiered perception to continuously sense the environment and derive hierarchical contexts that incorporate both sensory and persona cues. ProAgent then adopts a context-aware proactive reasoner to map these contexts to user needs and tool calls, providing proactive assistance. We implement ProAgent on Augmented Reality (AR) glasses with an edge server and extensively evaluate it on a real-world testbed, a public dataset, and through a user study. Results show that ProAgent achieves up to 33.4% higher proactive prediction accuracy, 16.8% higher tool-calling F1 score, and notable improvements in user satisfaction over state-of-the-art baselines, marking a significant step toward proactive assistants. A video demonstration of ProAgent is available at https://youtu.be/pRXZuzvrcVs. - oai:arXiv.org:2512.06721v1 - cs.AI - cs.CL - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Ergodic Trajectory Planning with Dynamic Sensor Footprints + https://arxiv.org/abs/2512.08661 + arXiv:2512.08661v1 Announce Type: new +Abstract: This paper addresses the problem of trajectory planning for information gathering with a dynamic and resolution-varying sensor footprint. Ergodic planning offers a principled framework that balances exploration (visiting all areas) and exploitation (focusing on high-information regions) by planning trajectories such that the time spent in a region is proportional to the amount of information in that region. Existing ergodic planning often oversimplifies the sensing model by assuming a point sensor or a footprint with constant shape and resolution. In practice, the sensor footprint can drastically change over time as the robot moves, such as aerial robots equipped with downward-facing cameras, whose field of view depends on the orientation and altitude. To overcome this limitation, we propose a new metric that accounts for dynamic sensor footprints, analyze the theoretic local optimality conditions, and propose numerical trajectory optimization algorithms. Experimental results show that the proposed approach can simultaneously optimize both the trajectories and sensor footprints, with up to an order of magnitude better ergodicity than conventional methods. We also deploy our approach in a multi-drone system to ergodically cover an object in 3D space. + oai:arXiv.org:2512.08661v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bufang Yang, Lilin Xu, Liekang Zeng, Yunqi Guo, Siyang Jiang, Wenrui Lu, Kaiwei Liu, Hancheng Xiang, Xiaofan Jiang, Guoliang Xing, Zhenyu Yan + Ziyue Zheng, Yongce Liu, Hesheng Wang, Zhongqiang Ren - Decoding Motor Behavior Using Deep Learning and Reservoir Computing - https://arxiv.org/abs/2512.06725 - arXiv:2512.06725v1 Announce Type: new -Abstract: We present a novel approach to EEG decoding for non-invasive brain machine interfaces (BMIs), with a focus on motor-behavior classification. While conventional convolutional architectures such as EEGNet and DeepConvNet are effective in capturing local spatial patterns, they are markedly less suited for modeling long-range temporal dependencies and nonlinear dynamics. To address this limitation, we integrate an Echo State Network (ESN), a prominent paradigm in reservoir computing into the decoding pipeline. ESNs construct a high-dimensional, sparsely connected recurrent reservoir that excels at tracking temporal dynamics, thereby complementing the spatial representational power of CNNs. Evaluated on a skateboard-trick EEG dataset preprocessed via the PREP pipeline and implemented in MNE-Python, our ESNNet achieves 83.2% within-subject and 51.3% LOSO accuracies, surpassing widely used CNN-based baselines. Code is available at https://github.com/Yutiankunkun/Motion-Decoding-Using-Biosignals - oai:arXiv.org:2512.06725v1 + Direct transfer of optimized controllers to similar systems using dimensionless MPC + https://arxiv.org/abs/2512.08667 + arXiv:2512.08667v1 Announce Type: new +Abstract: Scaled model experiments are commonly used in various engineering fields to reduce experimentation costs and overcome constraints associated with full-scale systems. The relevance of such experiments relies on dimensional analysis and the principle of dynamic similarity. However, transferring controllers to full-scale systems often requires additional tuning. In this paper, we propose a method to enable a direct controller transfer using dimensionless model predictive control, tuned automatically for closed-loop performance. With this reformulation, the closed-loop behavior of an optimized controller transfers directly to a new, dynamically similar system. Additionally, the dimensionless formulation allows for the use of data from systems of different scales during parameter optimization. We demonstrate the method on a cartpole swing-up and a car racing problem, applying either reinforcement learning or Bayesian optimization for tuning the controller parameters. Software used to obtain the results in this paper is publicly available at https://github.com/josipkh/dimensionless-mpcrl. + oai:arXiv.org:2512.08667v1 + eess.SY cs.LG - eess.SP - Tue, 09 Dec 2025 00:00:00 -0500 + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tian Lan - - - The Role of Entropy in Visual Grounding: Analysis and Optimization - https://arxiv.org/abs/2512.06726 - arXiv:2512.06726v1 Announce Type: new -Abstract: Recent advances in fine-tuning multimodal large language models (MLLMs) using reinforcement learning have achieved remarkable progress, particularly with the introduction of various entropy control techniques. However, the role and characteristics of entropy in perception-oriented tasks like visual grounding, as well as effective strategies for controlling it, remain largely unexplored. To address this issue, we focus on the visual grounding task and analyze the role and characteristics of entropy in comparison to reasoning tasks. Building on these findings, we introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation. Through entropy control, the trade-off between exploration and exploitation is better balanced. Experiments show that ECVGPO achieves broad improvements across various benchmarks and models. - oai:arXiv.org:2512.06726v1 - cs.CV - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Shuo Li, Jiajun Sun, Zhihao Zhang, Xiaoran Fan, Senjie Jin, Hui Li, Yuming Yang, Junjie Ye, Lixing Shen, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang + Josip Kir Hromatko, Shambhuraj Sawant, \v{S}andor Ile\v{s}, S\'ebastien Gros - KV-CAR: KV Cache Compression using Autoencoders and KV Reuse in Large Language Models - https://arxiv.org/abs/2512.06727 - arXiv:2512.06727v1 Announce Type: new -Abstract: As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding dimension, often exceeding the memory footprint of the model itself and limiting achievable batch sizes and context windows. To address this challenge, we present KV CAR, a unified and architecture agnostic framework that significantly reduces KV cache storage while maintaining model fidelity. KV CAR combines two complementary techniques. First, a lightweight autoencoder learns compact representations of key and value tensors along the embedding dimension, compressing them before they are stored in the KV cache and restoring them upon retrieval. Second, a similarity driven reuse mechanism identifies opportunities to reuse KV tensors of specific attention heads across adjacent layers. Together, these methods reduce the dimensional and structural redundancy in KV tensors without requiring changes to the transformer architecture. Evaluations on GPT 2 and TinyLLaMA models across Wikitext, C4, PIQA, and Winogrande datasets demonstrate that KV CAR achieves up to 47.85 percent KV cache memory reduction with minimal impact on perplexity and zero shot accuracy. System level measurements on an NVIDIA A40 GPU show that the reduced KV footprint directly translates into longer sequence lengths and larger batch sizes during inference. These results highlight the effectiveness of KV CAR in enabling memory efficient LLM inference. - oai:arXiv.org:2512.06727v1 + DS FedProxGrad: Asymptotic Stationarity Without Noise Floor in Fair Federated Learning + https://arxiv.org/abs/2512.08671 + arXiv:2512.08671v1 Announce Type: new +Abstract: Recent work \cite{arifgroup} introduced Federated Proximal Gradient \textbf{(\texttt{FedProxGrad})} for solving non-convex composite optimization problems in group fair federated learning. However, the original analysis established convergence only to a \textit{noise-dominated neighborhood of stationarity}, with explicit dependence on a variance-induced noise floor. In this work, we provide an improved asymptotic convergence analysis for a generalized \texttt{FedProxGrad}-type analytical framework with inexact local proximal solutions and explicit fairness regularization. We call this extended analytical framework \textbf{DS \texttt{FedProxGrad}} (Decay Step Size \texttt{FedProxGrad}). Under a Robbins-Monro step-size schedule \cite{robbins1951stochastic} and a mild decay condition on local inexactness, we prove that $\liminf_{r\to\infty} \mathbb{E}[\|\nabla F(\mathbf{x}^r)\|^2] = 0$, i.e., the algorithm is asymptotically stationary and the convergence rate does not depend on a variance-induced noise floor. + oai:arXiv.org:2512.08671v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Sourjya Roy, Shrihari Sridharan, Surya Selvam, Anand Raghunathan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Huzaifa Arif - Enhancing Interpretability of AR-SSVEP-Based Motor Intention Recognition via CNN-BiLSTM and SHAP Analysis on EEG Data - https://arxiv.org/abs/2512.06730 - arXiv:2512.06730v1 Announce Type: new -Abstract: Patients with motor dysfunction show low subjective engagement in rehabilitation training. Traditional SSVEP-based brain-computer interface (BCI) systems rely heavily on external visual stimulus equipment, limiting their practicality in real-world settings. This study proposes an augmented reality steady-state visually evoked potential (AR-SSVEP) system to address the lack of patient initiative and the high workload on therapists. Firstly, we design four HoloLens 2-based EEG classes and collect EEG data from seven healthy subjects for analysis. Secondly, we build upon the conventional CNN-BiLSTM architecture by integrating a multi-head attention mechanism (MACNN-BiLSTM). We extract ten temporal-spectral EEG features and feed them into a CNN to learn high-level representations. Then, we use BiLSTM to model sequential dependencies and apply a multi-head attention mechanism to highlight motor-intention-related patterns. Finally, the SHAP (SHapley Additive exPlanations) method is applied to visualize EEG feature contributions to the neural network's decision-making process, enhancing the model's interpretability. These findings enhance real-time motor intention recognition and support recovery in patients with motor impairments. - oai:arXiv.org:2512.06730v1 - cs.LG + Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds + https://arxiv.org/abs/2512.08673 + arXiv:2512.08673v1 Announce Type: new +Abstract: Most existing self-supervised learning (SSL) approaches for 3D point clouds are dominated by generative methods based on Masked Autoencoders (MAE). However, these generative methods have been proven to struggle to capture high-level discriminative features effectively, leading to poor performance on linear probing and other downstream tasks. In contrast, contrastive methods excel in discriminative feature representation and generalization ability on image data. Despite this, contrastive learning (CL) in 3D data remains scarce. Besides, simply applying CL methods designed for 2D data to 3D fails to effectively learn 3D local details. To address these challenges, we propose a novel Dual-Branch \textbf{C}enter-\textbf{S}urrounding \textbf{Con}trast (CSCon) framework. Specifically, we apply masking to the center and surrounding parts separately, constructing dual-branch inputs with center-biased and surrounding-biased representations to better capture rich geometric information. Meanwhile, we introduce a patch-level contrastive loss to further enhance both high-level information and local sensitivity. Under the FULL and ALL protocols, CSCon achieves performance comparable to generative methods; under the MLP-LINEAR, MLP-3, and ONLY-NEW protocols, our method attains state-of-the-art results, even surpassing cross-modal approaches. In particular, under the MLP-LINEAR protocol, our method outperforms the baseline (Point-MAE) by \textbf{7.9\%}, \textbf{6.7\%}, and \textbf{10.3\%} on the three variants of ScanObjectNN, respectively. The code will be made publicly available. + oai:arXiv.org:2512.08673v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lin Yang, Xiang Li, Xin Ma, Xinxin Zhao + 10.13140/RG.2.2.16132.18563 + Shaofeng Zhang, Xuanqi Chen, Xiangdong Zhang, Sitong Wu, Junchi Yan - "The Dentist is an involved parent, the bartender is not": Revealing Implicit Biases in QA with Implicit BBQ - https://arxiv.org/abs/2512.06732 - arXiv:2512.06732v1 Announce Type: new -Abstract: Existing benchmarks evaluating biases in large language models (LLMs) primarily rely on explicit cues, declaring protected attributes like religion, race, gender by name. However, real-world interactions often contain implicit biases, inferred subtly through names, cultural cues, or traits. This critical oversight creates a significant blind spot in fairness evaluation. We introduce ImplicitBBQ, a benchmark extending the Bias Benchmark for QA (BBQ) with implicitly cued protected attributes across 6 categories. Our evaluation of GPT-4o on ImplicitBBQ illustrates troubling performance disparity from explicit BBQ prompts, with accuracy declining up to 7% in the "sexual orientation" subcategory and consistent decline located across most other categories. This indicates that current LLMs contain implicit biases undetected by explicit benchmarks. ImplicitBBQ offers a crucial tool for nuanced fairness evaluation in NLP. - oai:arXiv.org:2512.06732v1 - cs.CL + Multi-Agent Intelligence for Multidisciplinary Decision-Making in Gastrointestinal Oncology + https://arxiv.org/abs/2512.08674 + arXiv:2512.08674v1 Announce Type: new +Abstract: Multimodal clinical reasoning in the field of gastrointestinal (GI) oncology necessitates the integrated interpretation of endoscopic imagery, radiological data, and biochemical markers. Despite the evident potential exhibited by Multimodal Large Language Models (MLLMs), they frequently encounter challenges such as context dilution and hallucination when confronted with intricate, heterogeneous medical histories. In order to address these limitations, a hierarchical Multi-Agent Framework is proposed, which emulates the collaborative workflow of a human Multidisciplinary Team (MDT). The system attained a composite expert evaluation score of 4.60/5.00, thereby demonstrating a substantial improvement over the monolithic baseline. It is noteworthy that the agent-based architecture yielded the most substantial enhancements in reasoning logic and medical accuracy. The findings indicate that mimetic, agent-based collaboration provides a scalable, interpretable, and clinically robust paradigm for automated decision support in oncology. + oai:arXiv.org:2512.08674v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Aarushi Wagh, Saniya Srivastava + Rongzhao Zhang, Junqiao Wang, Shuyun Yang, Mouxiao Bian, Chao Ding, Yuwei Bai, Chihao Zhang, Yuguang Shen, Lei Wang, Lei Zheng, Qiujuan Yan, Yun Zhong, Meiling Liu, Jiwei Yu, Zheng Wang, Jie Xu, Meng Luo - Symmetry-Based Formation Control on Cycle Graphs Using Dihedral Point Groups - https://arxiv.org/abs/2512.06733 - arXiv:2512.06733v1 Announce Type: new -Abstract: This work develops a symmetry-based framework for formation control on cycle graphs using Dihedral point-group constraints. We show that enforcing inter-agent reflection symmetries, together with anchoring a single designated agent to its prescribed mirror axis, is sufficient to realize every $\mathcal{C}_{nv}$-symmetric configuration using only $n-1$ communication links. The resulting control laws have a matrix-weighted Laplacian structure and guarantee exponential convergence to the desired symmetric configuration. Furthermore, we extend the method to enable coordinated maneuvers along a time-varying reference trajectory. Simulation results are provided to support the theoretical analysis. - oai:arXiv.org:2512.06733v1 - eess.SY - cs.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Causal Explanations for Disparate Trends: Where and Why? + https://arxiv.org/abs/2512.08679 + arXiv:2512.08679v1 Announce Type: new +Abstract: During data analysis, we are often perplexed by certain disparities observed between two groups of interest within a dataset. To better understand an observed disparity, we need explanations that can pinpoint the data regions where the disparity is most pronounced, along with its causes, i.e., factors that alleviate or exacerbate the disparity. This task is complex and tedious, particularly for large and high-dimensional datasets, demanding an automatic system for discovering explanations (data regions and causes) of an observed disparity. It is critical that explanations for disparities are not only interpretable but also actionable-enabling users to make informed, data-driven decisions. This requires explanations to go beyond surface-level correlations and instead capture causal relationships. We introduce ExDis, a framework for discovering causal Explanations for Disparities between two groups of interest. ExDis identifies data regions (subpopulations) where disparities are most pronounced (or reversed), and associates specific factors that causally contribute to the disparity within each identified data region. We formally define the ExDis framework and the associated optimization problem, analyze its complexity, and develop an efficient algorithm to solve the problem. Through extensive experiments over three real-world datasets, we demonstrate that ExDis generates meaningful causal explanations, outperforms prior methods, and scales effectively to handle large, high-dimensional datasets. + oai:arXiv.org:2512.08679v1 + cs.DB + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Zamir Martinez, Daniel Zelazo + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Tal Blau, Brit Youngmann, Anna Fariha, Yuval Moskovitch - A Patient-Doctor-NLP-System to contest inequality for less privileged - https://arxiv.org/abs/2512.06734 - arXiv:2512.06734v1 Announce Type: new -Abstract: Transfer Learning (TL) has accelerated the rapid development and availability of large language models (LLMs) for mainstream natural language processing (NLP) use cases. However, training and deploying such gigantic LLMs in resource-constrained, real-world healthcare situations remains challenging. This study addresses the limited support available to visually impaired users and speakers of low-resource languages such as Hindi who require medical assistance in rural environments. We propose PDFTEMRA (Performant Distilled Frequency Transformer Ensemble Model with Random Activations), a compact transformer-based architecture that integrates model distillation, frequency-domain modulation, ensemble learning, and randomized activation patterns to reduce computational cost while preserving language understanding performance. The model is trained and evaluated on medical question-answering and consultation datasets tailored to Hindi and accessibility scenarios, and its performance is compared against standard NLP state-of-the-art model baselines. Results demonstrate that PDFTEMRA achieves comparable performance with substantially lower computational requirements, indicating its suitability for accessible, inclusive, low-resource medical NLP applications. - oai:arXiv.org:2512.06734v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Non Normalized Shared-Constraint Dynamic Games for Human-Robot Collaboration with Asymmetric Responsibility + https://arxiv.org/abs/2512.08688 + arXiv:2512.08688v1 Announce Type: new +Abstract: This paper proposes a dynamic game formulation for cooperative human-robot navigation in shared workspaces with obstacles, where the human and robot jointly satisfy shared safety constraints while pursuing a common task. A key contribution is the introduction of a non-normalized equilibrium structure for the shared constraints. This structure allows the two agents to contribute different levels of effort towards enforcing safety requirements such as collision avoidance and inter-players spacing. We embed this non-normalized equilibrium into a receding-horizon optimal control scheme. + oai:arXiv.org:2512.08688v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Subrit Dikshit, Ritu Tiwari, Priyank Jain + Mark Pustilnik, Francesco Borrelli - Graph Convolutional Long Short-Term Memory Attention Network for Post-Stroke Compensatory Movement Detection Based on Skeleton Data - https://arxiv.org/abs/2512.06736 - arXiv:2512.06736v1 Announce Type: new -Abstract: Most stroke patients experience upper limb motor dysfunction. Compensatory movements are prevalent during rehabilitation training, which is detrimental to patients' long-term recovery. Therefore, detecting compensatory movements is of great significance. In this study, a Graph Convolutional Long Short-Term Memory Attention Network (GCN-LSTM-ATT) based on skeleton data is proposed for the detection of compensatory movements after stroke. Sixteen stroke patients were selected in the research. The skeleton data of the patients performing specific rehabilitation movements were collected using the Kinect depth camera. After data processing, detection models were constructed respectively using the GCN-LSTM-ATT model, the Support Vector Machine(SVM), the K-Nearest Neighbor algorithm(KNN), and the Random Forest(RF). The results show that the detection accuracy of the GCN-LSTM-ATT model reaches 0.8580, which is significantly higher than that of traditional machine learning algorithms. Ablation experiments indicate that each component of the model contributes significantly to the performance improvement. These findings provide a more precise and powerful tool for the detection of compensatory movements after stroke, and are expected to facilitate the optimization of rehabilitation training strategies for stroke patients. - oai:arXiv.org:2512.06736v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + ITU-T Y.2325: NGN Evolution Towards Future + https://arxiv.org/abs/2512.08695 + arXiv:2512.08695v1 Announce Type: new +Abstract: International Telecommunications Union (ITU) defined Next Generation Network (NGN) underlies most wireline and wireless packet-based telecommunications networks. A key design principle of NGN is decoupling of service-related functions from the underlying transport stratum, making user services independent of transport technologies. Interestingly, the NGN architecture, as defined in ITU standards, did not follow this design principle for internal network services, e.g., mobility, or authentication though adhering for external user services like IPTV or Multimedia services. These internal services are handled by the NGN transport control plane, making them an intrinsic part of the transport stratum, resulting in a tightly coupled service and transport functionality as opposed to the proclaimed design goal. This design choice may force each transport technology to support internal services individually, e.g., separate authentication service for each transport, leading to duplication. Since the NGN architecture is the base underlying architecture for most packet-based telecommunications network including advanced cellular networks like 4th/5th Generation cellular networks, the limitation persists in these cellular networks as well. To remedy the situation, the decoupling of service and transport can be generalized to include internal services like mobility and authentication also. In this context, the recently published ITU Y.2325 recommendation, defines an evolved NGN architecture, wherein all services, including internal network services, are decoupled from the transport stratum. The proposal results in a more scalable and modular evolved NGN architecture that can be used as a template for all future telecom networks including IMT-2030 (6th generation mobile networks). In this article, we review the evolved NGN architecture, as proposed in ITU-T Y.2325. + oai:arXiv.org:2512.08695v1 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiaxing Fan, Jiaojiao Liu, Wenkong Wang, Yang Zhang, Xin Ma, Jichen Zhang + http://creativecommons.org/licenses/by/4.0/ + Rashmi Kamran, Shwetha Kiran, Pranav Jha, Rashmi Yadav, Abhay Karandikar, Prasanna Chaporkar - Arc Gradient Descent: A Mathematically Derived Reformulation of Gradient Descent with Phase-Aware, User-Controlled Step Dynamics - https://arxiv.org/abs/2512.06737 - arXiv:2512.06737v1 Announce Type: new -Abstract: The paper presents the formulation, implementation, and evaluation of the ArcGD optimiser. The evaluation is conducted initially on a non-convex benchmark function and subsequently on a real-world ML dataset. The initial comparative study using the Adam optimiser is conducted on a stochastic variant of the highly non-convex and notoriously challenging Rosenbrock function, renowned for its narrow, curved valley, across dimensions ranging from 2D to 1000D and an extreme case of 50,000D. Two configurations were evaluated to eliminate learning-rate bias: (i) both using ArcGD's effective learning rate and (ii) both using Adam's default learning rate. ArcGD consistently outperformed Adam under the first setting and, although slower under the second, achieved super ior final solutions in most cases. In the second evaluation, ArcGD is evaluated against state-of-the-art optimizers (Adam, AdamW, Lion, SGD) on the CIFAR-10 image classification dataset across 8 diverse MLP architectures ranging from 1 to 5 hidden layers. ArcGD achieved the highest average test accuracy (50.7%) at 20,000 iterations, outperforming AdamW (46.6%), Adam (46.8%), SGD (49.6%), and Lion (43.4%), winning or tying on 6 of 8 architectures. Notably, while Adam and AdamW showed strong early convergence at 5,000 iterations, but regressed with extended training, whereas ArcGD continued improving, demonstrating generalization and resistance to overfitting without requiring early stopping tuning. Strong performance on geometric stress tests and standard deep-learning benchmarks indicates broad applicability, highlighting the need for further exploration. Moreover, it is also shown that a variant of ArcGD can be interpreted as a special case of the Lion optimiser, highlighting connections between the inherent mechanisms of such optimisation methods. - oai:arXiv.org:2512.06737v1 - cs.LG - cs.AI - cs.CL + What really matters for person re-identification? A Mixture-of-Experts Framework for Semantic Attribute Importance + https://arxiv.org/abs/2512.08697 + arXiv:2512.08697v1 Announce Type: new +Abstract: State-of-the-art person re-identification methods achieve impressive accuracy but remain largely opaque, leaving open the question: which high-level semantic attributes do these models actually rely on? We propose MoSAIC-ReID, a Mixture-of-Experts framework that systematically quantifies the importance of pedestrian attributes for re-identification. Our approach uses LoRA-based experts, each linked to a single attribute, and an oracle router that enables controlled attribution analysis. While MoSAIC-ReID achieves competitive performance on Market-1501 and DukeMTMC under the assumption that attribute annotations are available at test time, its primary value lies in providing a large-scale, quantitative study of attribute importance across intrinsic and extrinsic cues. Using generalized linear models, statistical tests, and feature-importance analyses, we reveal which attributes, such as clothing colors and intrinsic characteristics, contribute most strongly, while infrequent cues (e.g. accessories) have limited effect. This work offers a principled framework for interpretable ReID and highlights the requirements for integrating explicit semantic knowledge in practice. Code is available at https://github.com/psaltaath/MoSAIC-ReID + oai:arXiv.org:2512.08697v1 cs.CV - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nikhil Verma, Joonas Linnosmaa, Espinosa-Leal Leonardo, Napat Vajragupta + http://creativecommons.org/licenses/by/4.0/ + Athena Psalta, Vasileios Tsironis, Konstantinos Karantzalos - FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation - https://arxiv.org/abs/2512.06738 - arXiv:2512.06738v1 Announce Type: new -Abstract: We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrains the FL frameworks to employ only a pre-trained server model as the setup restricts access to the source dataset during the training rounds. Often, this source domain dataset has a distinct distribution to the clients' domains. To address the challenges posed by the FFreeDA setup, adaptation of the Source-Free Domain Adaptation (SFDA) methods to FL struggles with client-drift in real-world scenarios due to extreme data heterogeneity caused by the aforementioned domain gaps, resulting in unreliable pseudo-labels. In this paper, we introduce FedSCAl, an FL framework leveraging our proposed Server-Client Alignment (SCAl) mechanism to regularize client updates by aligning the clients' and server model's predictions. We observe an improvement in the clients' pseudo-labeling accuracy post alignment, as the SCAl mechanism helps to mitigate the client-drift. Further, we present extensive experiments on benchmark vision datasets showcasing how FedSCAl consistently outperforms state-of-the-art FL methods in the FFreeDA setup for classification tasks. - oai:arXiv.org:2512.06738v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Model-based Testing of Practical Distributed Systems in Actor Model + https://arxiv.org/abs/2512.08698 + arXiv:2512.08698v1 Announce Type: new +Abstract: Designing and implementing distributed systems correctly can be quite challenging. Although these systems are often accompanied by formal specifications that are verified using model-checking techniques, a gap still exists between the implementation and its formal specification: there is no guarantee that the implementation is free of bugs. + To bridge this gap, we can use model-based testing. Specifically, if the model of the system can be interpreted as a finite-state automaton, we can generate an exhaustive test suite for the implementation that covers all possible states and transitions. + In this paper, we discuss how to efficiently generate such a test suite for distributed systems written in the actor model. Importantly, our approach does not require any modifications to the code or interfering with the distributed system execution environment. As an example, we verified an implementation of a replication algorithm based on Viewstamped Replication, which is used in a real-world system. + oai:arXiv.org:2512.08698v1 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - M Yashwanth, Sampath Koti, Arunabh Singh, Shyam Marjit, Anirban Chakraborty + Ilya Kokorin, Evgeny Chernatskiy, Vitaly Aksenov - OSM+: Billion-Level Open Street Map Data Processing System for City-wide Experiments - https://arxiv.org/abs/2512.06743 - arXiv:2512.06743v1 Announce Type: new -Abstract: Road network data can provide rich information about cities and thus become the base for various urban research. However, processing large volume world-wide road network data requires intensive computing resources and the processed results might be different to be unified for testing downstream tasks. Therefore, in this paper, we process the OpenStreetMap data via a distributed computing of 5,000 cores on cloud services and release a structured world-wide 1-billion-vertex road network graph dataset with high accessibility (opensource and downloadable to the whole world) and usability (open-box graph structure and easy spatial query interface). To demonstrate how this dataset can be utilized easily, we present three illustrative use cases, including traffic prediction, city boundary detection and traffic policy control, and conduct extensive experiments for these three tasks. (1) For the well-investigated traffic prediction tasks, we release a new benchmark with 31 cities (traffic data processed and combined with our released OSM+ road network dataset), to provide much larger spatial coverage and more comprehensive evaluation of compared algorithms than the previously frequently-used datasets. This new benchmark will push the algorithms on their scalability from hundreds of road network intersections to thousands of intersections. (2) While for the more advanced traffic policy control task which requires interaction with the road network, we release a new 6 city datasets with much larger scale than the previous datasets. This brings new challenge for thousand-scale multi-agent coordination. (3) Along with the OSM+ dataset, the release of data converters facilitates the integration of multimodal spatial-temporal data for geospatial foundation model training, thereby expediting the process of uncovering compelling scientific insights. PVLDB Reference Forma - oai:arXiv.org:2512.06743v1 - cs.DB - Tue, 09 Dec 2025 00:00:00 -0500 + An Additive Manufacturing Part Qualification Framework: Transferring Knowledge of Stress-strain Behaviors from Additively Manufactured Polymers to Metals + https://arxiv.org/abs/2512.08699 + arXiv:2512.08699v1 Announce Type: new +Abstract: Part qualification is crucial in additive manufacturing (AM) because it ensures that additively manufactured parts can be consistently produced and reliably used in critical applications. Part qualification aims at verifying that an additively manufactured part meets performance requirements; therefore, predicting the complex stress-strain behaviors of additively manufactured parts is critical. We develop a dynamic time warping (DTW)-transfer learning (TL) framework for additive manufacturing part qualification by transferring knowledge of the stress-strain behaviors of additively manufactured low-cost polymers to metals. Specifically, the framework employs DTW to select a polymer dataset as the source domain that is the most relevant to the target metal dataset. Using a long short-term memory (LSTM) model, four source polymers (i.e., Nylon, PLA, CF-ABS, and Resin) and three target metals (i.e., AlSi10Mg, Ti6Al4V, and carbon steel) that are fabricated by different AM techniques are utilized to demonstrate the effectiveness of the DTW-TL framework. Experimental results show that the DTW-TL framework identifies the closest match between polymers and metals to select one single polymer dataset as the source domain. The DTW-TL model achieves the lowest mean absolute percentage error of 12.41% and highest coefficient of determination of 0.96 when three metals are used as the target domain, respectively, outperforming the vanilla LSTM model without TL as well as the TL model pre-trained on four polymer datasets as the source domain. + oai:arXiv.org:2512.08699v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Guanjie Zheng, Ziyang Su, Yiheng Wang, Yuhang Luo, Hongwei Zhang, Xuanhe Zhou, Linghe Kong, Fan Wu, Wen Ling + Chenglong Duan, Dazhong Wu - One Word Is Not Enough: Simple Prompts Improve Word Embeddings - https://arxiv.org/abs/2512.06744 - arXiv:2512.06744v1 Announce Type: new -Abstract: Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply prepending semantic prompts to words before embedding substantially improves word similarity correlations. Testing 7 text embedding models, including text-embedding-3-large (OpenAI), embed-english-v3.0 (Cohere), voyage-3(Voyage AI), all-mpnet-base-v2, and Qwen3-Embedding-8B, on 3 standard benchmarks (SimLex-999, WordSim-353, MEN-3000), we find that prompts like "meaning: {word}" or "Represent the semantic concept: {word}" improve Spearman correlations by up to +0.29 on SimLex-999. Some models fail completely on bare words (correlation = 0) but recover with prompts (+0.73 improvement). Our best results achieve correlation = 0.692 on SimLex-999 with embed-english-v3.0 (Cohere), correlation = 0.811 on WordSim-353, and correlation = 0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec (correlation = 0.40) and even the best static method LexVec (correlation = 0.48) on SimLex-999, establishing a new state-of-the-art for pure embedding methods. This zero-shot technique requires no training and works with any text embedding model. - oai:arXiv.org:2512.06744v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Scale-invariant and View-relational Representation Learning for Full Surround Monocular Depth + https://arxiv.org/abs/2512.08700 + arXiv:2512.08700v1 Announce Type: new +Abstract: Recent foundation models demonstrate strong generalization capabilities in monocular depth estimation. However, directly applying these models to Full Surround Monocular Depth Estimation (FSMDE) presents two major challenges: (1) high computational cost, which limits real-time performance, and (2) difficulty in estimating metric-scale depth, as these models are typically trained to predict only relative depth. To address these limitations, we propose a novel knowledge distillation strategy that transfers robust depth knowledge from a foundation model to a lightweight FSMDE network. Our approach leverages a hybrid regression framework combining the knowledge distillation scheme--traditionally used in classification--with a depth binning module to enhance scale consistency. Specifically, we introduce a cross-interaction knowledge distillation scheme that distills the scale-invariant depth bin probabilities of a foundation model into the student network while guiding it to infer metric-scale depth bin centers from ground-truth depth. Furthermore, we propose view-relational knowledge distillation, which encodes structural relationships among adjacent camera views and transfers them to enhance cross-view depth consistency. Experiments on DDAD and nuScenes demonstrate the effectiveness of our method compared to conventional supervised methods and existing knowledge distillation approaches. Moreover, our method achieves a favorable trade-off between performance and efficiency, meeting real-time requirements. + oai:arXiv.org:2512.08700v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Rajeev Ranjan + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Kyumin Hwang, Wonhyeok Choi, Kiljoon Han, Wonjoon Choi, Minwoo Choi, Yongcheon Na, Minwoo Park, Sunghoon Im - Task-Model Alignment: A Simple Path to Generalizable AI-Generated Image Detection - https://arxiv.org/abs/2512.06746 - arXiv:2512.06746v1 Announce Type: new -Abstract: Vision Language Models (VLMs) are increasingly adopted for AI-generated images (AIGI) detection, yet converting VLMs into detectors requires substantial resource, while the resulting models still exhibit severe hallucinations. To probe the core issue, we conduct an empirical analysis and observe two characteristic behaviors: (i) fine-tuning VLMs on high-level semantic supervision strengthens semantic discrimination and well generalize to unseen data; (ii) fine-tuning VLMs on low-level pixel-artifact supervision yields poor transfer. We attribute VLMs' underperformance to task-model misalignment: semantics-oriented VLMs inherently lack sensitivity to fine-grained pixel artifacts, and semantically non-discriminative pixel artifacts thus exceeds their inductive biases. In contrast, we observe that conventional pixel-artifact detectors capture low-level pixel artifacts yet exhibit limited semantic awareness relative to VLMs, highlighting that distinct models are better matched to distinct tasks. In this paper, we formalize AIGI detection as two complementary tasks--semantic consistency checking and pixel-artifact detection--and show that neglecting either induces systematic blind spots. Guided by this view, we introduce the Task-Model Alignment principle and instantiate it as a two-branch detector, AlignGemini, comprising a VLM fine-tuned exclusively with pure semantic supervision and a pixel-artifact expert trained exclusively with pure pixel-artifact supervision. By enforcing orthogonal supervision on two simplified datasets, each branch trains to its strengths, producing complementary discrimination over semantic and pixel cues. On five in-the-wild benchmarks, AlignGemini delivers a +9.5 gain in average accuracy, supporting task-model alignment as an effective path to generalizable AIGI detection. - oai:arXiv.org:2512.06746v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + VI-MMRec: Similarity-Aware Training Cost-free Virtual User-Item Interactions for Multimodal Recommendation + https://arxiv.org/abs/2512.08702 + arXiv:2512.08702v1 Announce Type: new +Abstract: Although existing multimodal recommendation models have shown promising performance, their effectiveness continues to be limited by the pervasive data sparsity problem. This problem arises because users typically interact with only a small subset of available items, leading existing models to arbitrarily treat unobserved items as negative samples. To this end, we propose VI-MMRec, a model-agnostic and training cost-free framework that enriches sparse user-item interactions via similarity-aware virtual user-item interactions. These virtual interactions are constructed based on modality-specific feature similarities of user-interacted items. Specifically, VI-MMRec introduces two different strategies: (1) Overlay, which independently aggregates modality-specific similarities to preserve modality-specific user preferences, and (2) Synergistic, which holistically fuses cross-modal similarities to capture complementary user preferences. To ensure high-quality augmentation, we design a statistically informed weight allocation mechanism that adaptively assigns weights to virtual user-item interactions based on dataset-specific modality relevance. As a plug-and-play framework, VI-MMRec seamlessly integrates with existing models to enhance their performance without modifying their core architecture. Its flexibility allows it to be easily incorporated into various existing models, maximizing performance with minimal implementation effort. Moreover, VI-MMRec introduces no additional overhead during training, making it significantly advantageous for practical deployment. Comprehensive experiments conducted on six real-world datasets using seven state-of-the-art multimodal recommendation models validate the effectiveness of our VI-MMRec. + oai:arXiv.org:2512.08702v1 + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ruoxin Chen, Jiahui Gao, Kaiqing Lin, Keyue Zhang, Yandan Zhao, Isabel Guan, Taiping Yao, Shouhong Ding + Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Zitong Wan, Hewei Wang, Weijie Liu, Yijie Li, Edith C. H. Ngai - PrivLLMSwarm: Privacy-Preserving LLM-Driven UAV Swarms for Secure IoT Surveillance - https://arxiv.org/abs/2512.06747 - arXiv:2512.06747v1 Announce Type: new -Abstract: Large Language Models (LLMs) are emerging as powerful enablers for autonomous reasoning and natural-language coordination in unmanned aerial vehicle (UAV) swarms operating within Internet of Things (IoT) environments. However, existing LLM-driven UAV systems process sensitive operational data in plaintext, exposing them to privacy and security risks. This work introduces PrivLLMSwarm, a privacy-preserving framework that performs secure LLM inference for UAV swarm coordination through Secure Multi-Party Computation (MPC). The framework incorporates MPC-optimized transformer components with efficient approximations of nonlinear activations, enabling practical encrypted inference on resource-constrained aerial platforms. A fine-tuned GPT-based command generator, enhanced through reinforcement learning in simulation, provides reliable instructions while maintaining confidentiality. Experimental evaluation in urban-scale simulations demonstrates that PrivLLMSwarm achieves high semantic accuracy, low encrypted inference latency, and robust formation control under privacy constraints. Comparative analysis shows PrivLLMSwarm offers a superior privacy-utility balance compared to differential privacy, federated learning, and plaintext baselines. To support reproducibility, the full implementation including source code, MPC components, and a synthetic dataset is publicly available. PrivLLMSwarm establishes a practical foundation for secure, LLM-enabled UAV swarms in privacy-sensitive IoT applications including smart-city monitoring and emergency response. - oai:arXiv.org:2512.06747v1 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Gradient-Informed Monte Carlo Fine-Tuning of Diffusion Models for Low-Thrust Trajectory Design + https://arxiv.org/abs/2512.08705 + arXiv:2512.08705v1 Announce Type: new +Abstract: Preliminary mission design of low-thrust spacecraft trajectories in the Circular Restricted Three-Body Problem is a global search characterized by a complex objective landscape and numerous local minima. Formulating the problem as sampling from an unnormalized distribution supported on neighborhoods of locally optimal solutions, provides the opportunity to deploy Markov chain Monte Carlo methods and generative machine learning. In this work, we extend our previous self-supervised diffusion model fine-tuning framework to employ gradient-informed Markov chain Monte Carlo. We compare two algorithms - the Metropolis-Adjusted Langevin Algorithm and Hamiltonian Monte Carlo - both initialized from a distribution learned by a diffusion model. Derivatives of an objective function that balances fuel consumption, time of flight and constraint violations are computed analytically using state transition matrices. We show that incorporating the gradient drift term accelerates mixing and improves convergence of the Markov chain for a multi-revolution transfer in the Saturn-Titan system. Among the evaluated methods, MALA provides the best trade-off between performance and computational cost. Starting from samples generated by a baseline diffusion model trained on a related transfer, MALA explicitly targets Pareto-optimal solutions. Compared to a random walk Metropolis algorithm, it increases the feasibility rate from 17.34% to 63.01% and produces a denser, more diverse coverage of the Pareto front. By fine-tuning a diffusion model on the generated samples and associated reward values with reward-weighted likelihood maximization, we learn the global solution structure of the problem and eliminate the need for a tedious separate data generation phase. + oai:arXiv.org:2512.08705v1 + eess.SY + cs.LG + cs.SY + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jifar Wakuma Ayana, Huang Qiming + Jannik Graebner, Ryne Beeson - DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems - https://arxiv.org/abs/2512.06749 - arXiv:2512.06749v1 Announce Type: new -Abstract: Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm has two key limitations: (i) log-only debugging lacks validation, producing untested hypotheses, and (ii) single-step or single-agent attribution is often ill-posed, as we find that multiple distinct interventions can independently repair the failed task. To address the first limitation, we introduce DoVer, an intervention-driven debugging framework, which augments hypothesis generation with active verification through targeted interventions (e.g., editing messages, altering plans). For the second limitation, rather than evaluating on attribution accuracy, we focus on measuring whether the system resolves the failure or makes quantifiable progress toward task success, reflecting a more outcome-oriented view of debugging. Within the Magnetic-One agent framework, on the datasets derived from GAIA and AssistantBench, DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses. DoVer also performs effectively on a different dataset (GSMPlus) and agent framework (AG2), where it recovers 49% of failed trials. These results highlight intervention as a practical mechanism for improving reliability in agentic systems and open opportunities for more robust, scalable debugging methods for LLM-based multi-agent systems. Project website and code will be available at https://aka.ms/DoVer. - oai:arXiv.org:2512.06749v1 - cs.AI + RESTifAI: LLM-Based Workflow for Reusable REST API Testing + https://arxiv.org/abs/2512.08706 + arXiv:2512.08706v1 Announce Type: new +Abstract: With this paper, we introduce RESTifAI, an LLM-driven approach for generating reusable, CI/CD ready REST API tests, following the happy-path approach. Unlike existing tools that often focus primarily on internal server errors, RESTifAI systematically constructs valid test scenarios (happy paths) and derives negative cases to verify both intended functionality (2xx responses) and robustness against invalid inputs or business-rule violations (4xx responses). The results indicate that RESTifAI performs on par with the latest LLM tools, i.e., AutoRestTest and LogiAgent, while addressing limitations related to reusability, oracle complexity, and integration. To support this, we provide common comparative results and demonstrate the tool's applicability in industrial services. For tool demonstration, please refer to https://www.youtube.com/watch?v=2vtQo0T0Lo4. RESTifAI is publicly available at https://github.com/casablancahotelsoftware/RESTifAI. + oai:arXiv.org:2512.08706v1 cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Ming Ma, Jue Zhang, Fangkai Yang, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang - - - UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement - https://arxiv.org/abs/2512.06750 - arXiv:2512.06750v1 Announce Type: new -Abstract: Image quality assessment (IQA) and image restoration are fundamental problems in low-level vision. Although IQA and restoration are closely connected conceptually, most existing work treats them in isolation. Recent advances in unified multimodal understanding-generation models demonstrate promising results and indicate that stronger understanding can improve generative performance. This motivates a single model that unifies IQA and restoration and explicitly studies how IQA can guide restoration, a setting that remains largely underexplored yet highly valuable. In this paper, we propose UARE, to our knowledge the first Unified vision-language model for image quality Assessment, Restoration, and Enhancement. Built on pretrained unified understanding and generation models, we introduce a two-stage training framework. First, a progressive, easy-to-hard schedule expands from single-type distortions to higher-order mixed degradations, enabling UARE to handle multiple degradations. Second, we perform unified fine-tuning of quality understanding and restoration with interleaved text-image data, aligning IQA signals with restoration objectives. Through multi-task co-training, UARE leverages IQA to boost restoration and enhancement performance. Extensive experiments across IQA, restoration, and enhancement tasks demonstrate the effectiveness of UARE. The code and models will be available at https://github.com/lwq20020127/UARE. - oai:arXiv.org:2512.06750v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Weiqi Li, Xuanyu Zhang, Bin Chen, Jingfen Xie, Yan Wang, Kexin Zhang, Junlin Li, Li Zhang, Jian Zhang, Shijie Zhao + Leon Kogler, Maximilian Ehrhart, Benedikt Dornauer, Eduard Paul Enoiu - Becoming Experienced Judges: Selective Test-Time Learning for Evaluators - https://arxiv.org/abs/2512.06751 - arXiv:2512.06751v1 Announce Type: new -Abstract: Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case independently, missing the opportunity to accumulate experience, and (ii) rely on a single fixed prompt for all cases, neglecting the need for sample-specific evaluation criteria. We introduce Learning While Evaluating (LWE), a framework that allows evaluators to improve sequentially at inference time without requiring training or validation sets. LWE maintains an evolving meta-prompt that (i) produces sample-specific evaluation instructions and (ii) refines itself through self-generated feedback. Furthermore, we propose Selective LWE, which updates the meta-prompt only on self-inconsistent cases, focusing computation where it matters most. This selective approach retains the benefits of sequential learning while being far more cost-effective. Across two pairwise comparison benchmarks, Selective LWE outperforms strong baselines, empirically demonstrating that evaluators can improve during sequential testing with a simple selective update, learning most from the cases they struggle with. - oai:arXiv.org:2512.06751v1 + Automatic Essay Scoring and Feedback Generation in Basque Language Learning + https://arxiv.org/abs/2512.08713 + arXiv:2512.08713v1 Announce Type: new +Abstract: This paper introduces the first publicly available dataset for Automatic Essay Scoring (AES) and feedback generation in Basque, targeting the CEFR C1 proficiency level. The dataset comprises 3,200 essays from HABE, each annotated by expert evaluators with criterion specific scores covering correctness, richness, coherence, cohesion, and task alignment enriched with detailed feedback and error examples. We fine-tune open-source models, including RoBERTa-EusCrawl and Latxa 8B/70B, for both scoring and explanation generation. Our experiments show that encoder models remain highly reliable for AES, while supervised fine-tuning (SFT) of Latxa significantly enhances performance, surpassing state-of-the-art (SoTA) closed-source systems such as GPT-5 and Claude Sonnet 4.5 in scoring consistency and feedback quality. We also propose a novel evaluation methodology for assessing feedback generation, combining automatic consistency metrics with expert-based validation of extracted learner errors. Results demonstrate that the fine-tuned Latxa model produces criterion-aligned, pedagogically meaningful feedback and identifies a wider range of error types than proprietary models. This resource and benchmark establish a foundation for transparent, reproducible, and educationally grounded NLP research in low-resource languages such as Basque. + oai:arXiv.org:2512.08713v1 cs.CL cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Seungyeon Jwa, Daechul Ahn, Reokyoung Kim, Dongyeop Kang, Jonghyun Choi + Ekhi Azurmendi, Xabier Arregi, Oier Lopez de Lacalle - Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets - https://arxiv.org/abs/2512.06752 - arXiv:2512.06752v1 Announce Type: new -Abstract: Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical interactions that govern protein function, such as global domains and long-range allosteric regulation. In this work, we argue that the network architecture itself should mirror this biological hierarchy. We introduce Geometric Graph U-Nets, a new class of models that learn multi-scale representations by recursively coarsening and refining the protein graph. We prove that this hierarchical design can theoretically more expressive than standard Geometric GNNs. Empirically, on the task of protein fold classification, Geometric U-Nets substantially outperform invariant and equivariant baselines, demonstrating their ability to learn the global structural patterns that define protein folds. Our work provides a principled foundation for designing geometric deep learning architectures that can learn the multi-scale structure of biomolecules. - oai:arXiv.org:2512.06752v1 + Multi-domain performance analysis with scores tailored to user preferences + https://arxiv.org/abs/2512.08715 + arXiv:2512.08715v1 Announce Type: new +Abstract: The performance of algorithms, methods, and models tends to depend heavily on the distribution of cases on which they are applied, this distribution being specific to the applicative domain. After performing an evaluation in several domains, it is highly informative to compute a (weighted) mean performance and, as shown in this paper, to scrutinize what happens during this averaging. To achieve this goal, we adopt a probabilistic framework and consider a performance as a probability measure (e.g., a normalized confusion matrix for a classification task). It appears that the corresponding weighted mean is known to be the summarization, and that only some remarkable scores assign to the summarized performance a value equal to a weighted arithmetic mean of the values assigned to the domain-specific performances. These scores include the family of ranking scores, a continuum parameterized by user preferences, and that the weights to consider in the arithmetic mean depend on the user preferences. Based on this, we rigorously define four domains, named easiest, most difficult, preponderant, and bottleneck domains, as functions of user preferences. After establishing the theory in a general setting, regardless of the task, we develop new visual tools for two-class classification. + oai:arXiv.org:2512.08715v1 + cs.PF + cs.AI + cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Chang Liu, Vivian Li, Linus Leong, Vladimir Radenkovic, Pietro Li\`o, Chaitanya K. Joshi + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + S\'ebastien Pi\'erard, Adrien Deli\`ege, Marc Van Droogenbroeck - Model-Less Feedback Control of Space-based Continuum Manipulators using Backbone Tension Optimization - https://arxiv.org/abs/2512.06754 - arXiv:2512.06754v1 Announce Type: new -Abstract: Continuum manipulators offer intrinsic dexterity and safe geometric compliance for navigation within confined and obstacle-rich environments. However, their infinite-dimensional backbone deformation, unmodeled internal friction, and configuration-dependent stiffness fundamentally limit the reliability of model-based kinematic formulations, resulting in inaccurate Jacobian predictions, artificial singularities, and unstable actuation behavior. Motivated by these limitations, this work presents a complete model-less control framework that bypasses kinematic modeling by using an empirically initialized Jacobian refined online through differential convex updates. Tip motion is generated via a real-time quadratic program that computes actuator increments while enforcing tendon slack avoidance and geometric limits. A backbone tension optimization term is introduced in this paper to regulate axial loading and suppress co-activation compression. The framework is validated across circular, pentagonal, and square trajectories, demonstrating smooth convergence, stable tension evolution, and sub-millimeter steady-state accuracy without any model calibration or parameter identification. These results establish the proposed controller as a scalable alternative to model-dependent continuum manipulation in a constrained environment. - oai:arXiv.org:2512.06754v1 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + The Role of Risk Modeling in Advanced AI Risk Management + https://arxiv.org/abs/2512.08723 + arXiv:2512.08723v1 Announce Type: new +Abstract: Rapidly advancing artificial intelligence (AI) systems introduce novel, uncertain, and potentially catastrophic risks. Managing these risks requires a mature risk-management infrastructure whose cornerstone is rigorous risk modeling. We conceptualize AI risk modeling as the tight integration of (i) scenario building$-$causal mapping from hazards to harms$-$and (ii) risk estimation$-$quantifying the likelihood and severity of each pathway. We review classical techniques such as Fault and Event Tree Analyses, FMEA/FMECA, STPA and Bayesian networks, and show how they can be adapted to advanced AI. A survey of emerging academic and industry efforts reveals fragmentation: capability benchmarks, safety cases, and partial quantitative studies are valuable but insufficient when divorced from comprehensive causal scenarios. Comparing the nuclear, aviation, cybersecurity, financial, and submarine domains, we observe that every sector combines deterministic guarantees for unacceptable events with probabilistic assessments of the broader risk landscape. We argue that advanced-AI governance should adopt a similar dual approach and that verifiable, provably-safe AI architectures are urgently needed to supply deterministic evidence where current models are the result of opaque end-to-end optimization procedures rather than specified by hand. In one potential governance-ready framework, developers conduct iterative risk modeling and regulators compare the results with predefined societal risk tolerance thresholds. The paper provides both a methodological blueprint and opens a discussion on the best way to embed sound risk modeling at the heart of advanced-AI risk management. + oai:arXiv.org:2512.08723v1 + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Shrreya Rajneesh, Nikita Pavle, Rakesh Kumar Sahoo, Manoranjan Sinha + Chlo\'e Touzet, Henry Papadatos, Malcolm Murray, Otter Quarks, Steve Barrett, Alejandro Tlaie Boria, Elija Perrier, Matthew Smith, Sim\'eon Campos - XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association - https://arxiv.org/abs/2512.06757 - arXiv:2512.06757v1 Announce Type: new -Abstract: This paper introduces our solution, XM-ALIGN (Unified Cross-Modal Embedding Alignment Framework), proposed for the FAME challenge at ICASSP 2026. Our framework combines explicit and implicit alignment mechanisms, significantly improving cross-modal verification performance in both "heard" and "unheard" languages. By extracting feature embeddings from both face and voice encoders and jointly optimizing them using a shared classifier, we employ mean squared error (MSE) as the embedding alignment loss to ensure tight alignment between modalities. Additionally, data augmentation strategies are applied during model training to enhance generalization. Experimental results show that our approach demonstrates superior performance on the MAV-Celeb dataset. The code will be released at https://github.com/PunkMale/XM-ALIGN. - oai:arXiv.org:2512.06757v1 - cs.SD - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search + https://arxiv.org/abs/2512.08724 + arXiv:2512.08724v1 Announce Type: new +Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing approaches frequently depend on curated prompt datasets - either manually constructed or generated with large language models (LLMs) - as part of their training and/or evaluation procedures. Beside the curation cost, this also risks overlooking unanticipated, less obvious prompts that trigger biased generation, even in models that have undergone debiasing. In this work, we introduce Bias-Guided Prompt Search (BGPS), a framework that automatically generates prompts that aim to maximize the presence of biases in the resulting images. BGPS comprises two components: (1) an LLM instructed to produce attribute-neutral prompts and (2) attribute classifiers acting on the TTI's internal representations that steer the decoding process of the LLM toward regions of the prompt space that amplify the image attributes of interest. We conduct extensive experiments on Stable Diffusion 1.5 and a state-of-the-art debiased model and discover an array of subtle and previously undocumented biases that severely deteriorate fairness metrics. Crucially, the discovered prompts are interpretable, i.e they may be entered by a typical user, quantitatively improving the perplexity metric compared to a prominent hard prompt optimization counterpart. Our findings uncover TTI vulnerabilities, while BGPS expands the bias search space and can act as a new evaluation tool for bias mitigation. + oai:arXiv.org:2512.08724v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhihua Fang, Shumei Tao, Junxu Wang, Liang He + http://creativecommons.org/licenses/by/4.0/ + Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis - Optimal Analysis for Bandit Learning in Matching Markets with Serial Dictatorship - https://arxiv.org/abs/2512.06758 - arXiv:2512.06758v1 Announce Type: new -Abstract: The problem of two-sided matching markets is well-studied in computer science and economics, owing to its diverse applications across numerous domains. Since market participants are usually uncertain about their preferences in various online matching platforms, an emerging line of research is dedicated to the online setting where one-side participants (players) learn their unknown preferences through multiple rounds of interactions with the other side (arms). Sankararaman et al. provide an $\Omega\left( \frac{N\log(T)}{\Delta^2} + \frac{K\log(T)}{\Delta} \right)$ regret lower bound for this problem under serial dictatorship assumption, where $N$ is the number of players, $K (\geq N)$ is the number of arms, $\Delta$ is the minimum reward gap across players and arms, and $T$ is the time horizon. Serial dictatorship assumes arms have the same preferences, which is common in reality when one side participants have a unified evaluation standard. Recently, the work of Kong and Li proposes the ET-GS algorithm and achieves an $O\left( \frac{K\log(T)}{\Delta^2} \right)$ regret upper bound, which is the best upper bound attained so far. Nonetheless, a gap between the lower and upper bounds, ranging from $N$ to $K$, persists. It remains unclear whether the lower bound or the upper bound needs to be improved. In this paper, we propose a multi-level successive selection algorithm that obtains an $O\left( \frac{N\log(T)}{\Delta^2} + \frac{K\log(T)}{\Delta} \right)$ regret bound when the market satisfies serial dictatorship. To the best of our knowledge, we are the first to propose an algorithm that matches the lower bound in the problem of matching markets with bandits. - oai:arXiv.org:2512.06758v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Spatio-Temporal Shifting to Reduce Carbon, Water, and Land-Use Footprints of Cloud Workloads + https://arxiv.org/abs/2512.08725 + arXiv:2512.08725v1 Announce Type: new +Abstract: In this paper, we investigate the potential of spatial and temporal cloud workload shifting to reduce carbon, water, and land-use footprints. Specifically, we perform a simulation study using real-world data from multiple cloud providers (AWS and Azure) and workload traces for different applications (big data analytics and FaaS). Our simulation results indicate that spatial shifting can substantially lower carbon, water, and land use footprints, with observed reductions ranging from 20% to 85%, depending on the scenario and optimization criteria. Temporal shifting also decreases the footprint, though to a lesser extent. When applied together, the two strategies yield the greatest overall reduction, driven mainly by spatial shifting with temporal adjustments providing an additional, incremental benefit. Sensitivity analysis demonstrates that such shifting is robust to prediction errors in grid mix data and to variations across different seasons. + oai:arXiv.org:2512.08725v1 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1016/j.tcs.2024.114703 - Theor. Comput. Sci. 1010, C (Sep 2024) - Zilong Wang, Shuai Li + Giulio Attenni, Youssef Moawad, Novella Bartolini, Lauritz Thamsen - VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors - https://arxiv.org/abs/2512.06759 - arXiv:2512.06759v1 Announce Type: new -Abstract: Understanding multi-image, multi-turn scenarios is a critical yet underexplored capability for Large Vision-Language Models (LVLMs). Existing benchmarks predominantly focus on static or horizontal comparisons -- e.g., spotting visual differences or assessing appropriateness -- while relying heavily on language cues. Such settings overlook progressive, context-dependent reasoning and the challenge of visual-to-visual inference. To bridge this gap, we present VisChainBench, a large-scale benchmark designed to rigorously evaluate LVLMs' ability to perform multi-step visual reasoning across sequential, interdependent tasks with minimal language guidance. VisChainBench contains 1,457 tasks spanning over 20,000 images across three diverse domains (e.g., daily scenarios, engineering troubleshooting), structured to mimic real-world decision-making processes. Uniquely, the benchmark is constructed using a multi-agent generation pipeline, ensuring high visual diversity and controlled language bias. All the benchmark data and code for benchmark construction are available for viewing and download via following Link: https://huggingface.co/datasets/eyehole/VisChainBench - oai:arXiv.org:2512.06759v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + A Task Parallel Orthonormalization Multigrid Method For Multiphase Elliptic Problems + https://arxiv.org/abs/2512.08728 + arXiv:2512.08728v1 Announce Type: new +Abstract: Multigrid methods have been a popular approach for solving linear systems arising from the discretization of partial differential equations (PDEs) for several decades. They are particularly effective for accelerating convergence rates with optimal complexity in terms of both time and space. K-cycle orthonormalization multigrid is a robust variant of the multigrid method that combines the efficiency of multigrid with the robustness of Krylov-type residual minimalizations for problems with strong anisotropies. However, traditional implementations of K-cycle orthonormalization multigrid often rely on bulk-synchronous parallelism, which can limit scalability on modern high-performance computing (HPC) systems. This paper presents a task- parallel variant of the K-cycle orthonormalization multigrid method that leverages asynchronous execution to improve scalability and performance on large-scale parallel systems. + oai:arXiv.org:2512.08728v1 + math.NA + cs.DC + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wenbo Lyu, Yingjun Du, Jinglin Zhao, Xianton Zhen, Ling Shao + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Teoman Toprak, Florian Kummer - JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms - https://arxiv.org/abs/2512.06763 - arXiv:2512.06763v1 Announce Type: new -Abstract: The quality of captured images strongly influences the performance of downstream perception tasks. Recent works on co-designing camera systems with perception tasks have shown improved task performance. However, most prior approaches focus on optimising fixed camera parameters set at manufacturing, while many parameters, such as exposure settings, require adaptive control at runtime. This paper introduces a method that jointly optimises camera hardware and adaptive camera control algorithms with downstream vision tasks. We present a unified optimisation framework that integrates gradient-based and derivative-free methods, enabling support for both continuous and discrete parameters, non-differentiable image formation processes, and neural network-based adaptive control algorithms. To address non-differentiable effects such as motion blur, we propose DF-Grad, a hybrid optimisation strategy that trains adaptive control networks using signals from a derivative-free optimiser alongside unsupervised task-driven learning. Experiments show that our method outperforms baselines that optimise static and dynamic parameters separately, particularly under challenging conditions such as low light and fast motion. These results demonstrate that jointly optimising hardware parameters and adaptive control algorithms improves perception performance and provides a unified approach to task-driven camera system design. - oai:arXiv.org:2512.06763v1 + SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images + https://arxiv.org/abs/2512.08730 + arXiv:2512.08730v1 Announce Type: new +Abstract: Most existing methods for training-free Open-Vocabulary Semantic Segmentation (OVSS) are based on CLIP. While these approaches have made progress, they often face challenges in precise localization or require complex pipelines to combine separate modules, especially in remote sensing scenarios where numerous dense and small targets are present. Recently, Segment Anything Model 3 (SAM 3) was proposed, unifying segmentation and recognition in a promptable framework. In this paper, we present a preliminary exploration of applying SAM 3 to the remote sensing OVSS task without any training. First, we implement a mask fusion strategy that combines the outputs from SAM 3's semantic segmentation head and the Transformer decoder (instance head). This allows us to leverage the strengths of both heads for better land coverage. Second, we utilize the presence score from the presence head to filter out categories that do not exist in the scene, reducing false positives caused by the vast vocabulary sizes and patch-level processing in geospatial scenes. We evaluate our method on extensive remote sensing datasets. Experiments show that this simple adaptation achieves promising performance, demonstrating the potential of SAM 3 for remote sensing OVSS. Our code is released at https://github.com/earth-insights/SegEarth-OV-3. + oai:arXiv.org:2512.08730v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chengyang Yan, Mitch Bryson, Donald G. Dansereau + Kaiyu Li, Shengqi Zhang, Yupeng Deng, Zhi Wang, Deyu Meng, Xiangyong Cao - Distributed Traffic State Estimation in V2X-Enabled Connected Vehicle Networks - https://arxiv.org/abs/2512.06765 - arXiv:2512.06765v1 Announce Type: new -Abstract: This paper presents a distributed traffic state estimation framework in which infrastructure sensors and connected vehicles act as autonomous, cooperative sensing nodes. These nodes share local traffic estimates with nearby nodes using Vehicle-to-Everything (V2X) communication. The proposed estimation algorithm uses a distributed Kalman filter tailored to a second-order macroscopic traffic flow model. To achieve global state awareness, the algorithm employs a consensus protocol to fuse heterogeneous spatiotemporal estimates from V2X neighbors and applies explicit projection steps to maintain physical consistency in density and flow estimates. The algorithm's performance is validated through microscopic simulations of a highway segment experiencing transient congestion. Results demonstrate that the proposed distributed estimator accurately reconstructs nonlinear shockwave dynamics, even with sparse infrastructure sensors and intermittent vehicular network connectivity. Statistical analysis explores how different connected vehicle penetration rates affect estimation accuracy, revealing notable phase transitions in network observability. - oai:arXiv.org:2512.06765v1 + LaMoSys3.5D: Enabling 3.5D-IC-Based Large Language Model Inference Serving Systems via Hardware/Software Co-Design + https://arxiv.org/abs/2512.08731 + arXiv:2512.08731v1 Announce Type: new +Abstract: The success of large language models LLMs amplifies the need for highthroughput energyefficient inference at scale. 3DDRAMbased accelerators provide high memory bandwidth and therefore an opportunity to accelerate the bandwidthbound decode phase. However, how to adequately balance compute density for prefill with bandwidthcapacity for decode remains open. Moreover, most prior designs do not target endtoend serving, leaving the codesign of dataflow, parallel mapping, and scheduling underexplored. To bridge the gap, we present LaMoSys3.5D, to our knowledge the first scalable 3.5DIC architecture for LLM serving. LaMoSys3.5D composes heterogeneous 3DDRAM chiplets on a 2.5D interposer: computerich chiplets for prefill and bandwidthcapacityrich chiplets for decode. To realize efficient serving, we adopt a hardwaresoftware codesign spanning dataflow, parallel mapping, and introduce a thermalaware modeling and hierarchical designspace exploration framework. Across diverse LLMs and workloads, LaMoSys3.5D improves throughputperwatt over DGXA100 systems by 62 and achieves a 4.87 better endtoend latency geomean versus prior 3D designs. We further distill intriguing design guidelines for 3.5DIC architectures and endtoend inference serving. + oai:arXiv.org:2512.08731v1 eess.SY cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Vincent de Heij, M. Umar B. Niazi, Saeed Ahmed, Karl Henrik Johansson + Qipan Wang, Zhe Zhang, Shuangchen Li, Hongzhong Zheng, Zheng Liang, Yibo Lin, Runsheng Wang, Ru Huang - Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding - https://arxiv.org/abs/2512.06769 - arXiv:2512.06769v1 Announce Type: new -Abstract: Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties between images and text. To enrich the spatial understanding ability of vision-language models, we propose a simple, annotation-free, plug-and-play method named $\text{Stitch and Tell}$ (abbreviated as SiTe), which injects structured spatial supervision into data. It constructs stitched image-text pairs by stitching images along a spatial axis and generating spatially-aware captions or question answer pairs based on the layout of stitched image, without relying on costly advanced models or human involvement. We evaluate SiTe across three architectures including LLaVA-v1.5-7B, LLaVA-Qwen2-1.5B and HALVA-7B, two training datasets, and eight benchmarks. Experiments show that SiTe improves spatial understanding tasks such as $\text{MME}_{\text{Position}}$ (+5.50%) and Spatial-MM (+4.19%), while maintaining or improving performance on general vision-language benchmarks including COCO-QA (+1.02%) and MMBench (+4.76%). Our findings suggest that explicitly injecting spatially-aware structure into training data offers an effective way to mitigate spatial hallucinations and improve spatial understanding, while preserving general vision-language capabilities. - oai:arXiv.org:2512.06769v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Neural Ordinary Differential Equations for Simulating Metabolic Pathway Dynamics from Time-Series Multiomics Data + https://arxiv.org/abs/2512.08732 + arXiv:2512.08732v1 Announce Type: new +Abstract: The advancement of human healthspan and bioengineering relies heavily on predicting the behavior of complex biological systems. While high-throughput multiomics data is becoming increasingly abundant, converting this data into actionable predictive models remains a bottleneck. High-capacity, datadriven simulation systems are critical in this landscape; unlike classical mechanistic models restricted by prior knowledge, these architectures can infer latent interactions directly from observational data, allowing for the simulation of temporal trajectories and the anticipation of downstream intervention effects in personalized medicine and synthetic biology. To address this challenge, we introduce Neural Ordinary Differential Equations (NODEs) as a dynamic framework for learning the complex interplay between the proteome and metabolome. We applied this framework to time-series data derived from engineered Escherichia coli strains, modeling the continuous dynamics of metabolic pathways. The proposed NODE architecture demonstrates superior performance in capturing system dynamics compared to traditional machine learning pipelines. Our results show a greater than 90% improvement in root mean squared error over baselines across both Limonene (up to 94.38% improvement) and Isopentenol (up to 97.65% improvement) pathway datasets. Furthermore, the NODE models demonstrated a 1000x acceleration in inference time, establishing them as a scalable, high-fidelity tool for the next generation of metabolic engineering and biological discovery. + oai:arXiv.org:2512.08732v1 + cs.LG + q-bio.SC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hang Yin, Xiaomin He, PeiWen Yuan, Yiwei Li, Jiayi Shi, Wenxiao Fan, Shaoxiong Feng, Kan Li + http://creativecommons.org/licenses/by/4.0/ + Udesh Habaraduwa, Andrei Lixandru - Foundation Model for Polycrystalline Material Informatics - https://arxiv.org/abs/2512.06770 - arXiv:2512.06770v1 Announce Type: new -Abstract: We present a 3D polycrystal foundation model that learns a physically structured representation of voxel-based microstructures through large-scale self-supervised pretraining. The encoder is trained on a dataset of 100,000 FCC microstructures whose crystallographic orientations span the texture hull, using a masking strategy that forces the model to infer latent features from incomplete spatial information. The quality of the learned representation is evaluated through two downstream tasks with distinct physical characteristics. (i) Homogenized stiffness prediction: the pretrained encoder consistently outperforms the non-pretrained baseline across all masking ratios. (ii) Nonlinear response modeling: the encoder is coupled with an orientation-aware interaction-based deep material network (ODMN) to infer complete sets of network parameters, enabling accurate stress-strain predictions for previously unseen microstructures. In both tasks, the pretrained encoder demonstrates markedly stronger generalization capability. These results underscore the strong transferability of the proposed framework and its suitability for data-scarce scientific settings, where labeled microstructures are limited and physics-consistent generalization is essential. The foundation model provides a scalable route toward integration with experimentally derived microstructures, offering a new basis for microstructure-property reasoning in practical materials design. - oai:arXiv.org:2512.06770v1 - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 + Mitigating Individual Skin Tone Bias in Skin Lesion Classification through Distribution-Aware Reweighting + https://arxiv.org/abs/2512.08733 + arXiv:2512.08733v1 Announce Type: new +Abstract: Skin color has historically been a focal point of discrimination, yet fairness research in machine learning for medical imaging often relies on coarse subgroup categories, overlooking individual-level variations. Such group-based approaches risk obscuring biases faced by outliers within subgroups. This study introduces a distribution-based framework for evaluating and mitigating individual fairness in skin lesion classification. We treat skin tone as a continuous attribute rather than a categorical label, and employ kernel density estimation (KDE) to model its distribution. We further compare twelve statistical distance metrics to quantify disparities between skin tone distributions and propose a distance-based reweighting (DRW) loss function to correct underrepresentation in minority tones. Experiments across CNN and Transformer models demonstrate: (i) the limitations of categorical reweighting in capturing individual-level disparities, and (ii) the superior performance of distribution-based reweighting, particularly with Fidelity Similarity (FS), Wasserstein Distance (WD), Hellinger Metric (HM), and Harmonic Mean Similarity (HS). These findings establish a robust methodology for advancing fairness at individual level in dermatological AI systems, and highlight broader implications for sensitive continuous attributes in medical image analysis. + oai:arXiv.org:2512.08733v1 + cs.CV + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ting-Ju Wei, Chuin-Shan Chen + Kuniko Paxton, Zeinab Dehghani, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos - RDSplat: Robust Watermarking Against Diffusion Editing for 3D Gaussian Splatting - https://arxiv.org/abs/2512.06774 - arXiv:2512.06774v1 Announce Type: new -Abstract: 3D Gaussian Splatting (3DGS) has enabled the creation of digital assets and downstream applications, underscoring the need for robust copyright protection via digital watermarking. However, existing 3DGS watermarking methods remain highly vulnerable to diffusion-based editing, which can easily erase embedded provenance. This challenge highlights the urgent need for 3DGS watermarking techniques that are intrinsically resilient to diffusion-based editing. In this paper, we introduce RDSplat, a Robust watermarking paradigm against Diffusion editing for 3D Gaussian Splatting. RDSplat embeds watermarks into 3DGS components that diffusion-based editing inherently preserve, achieved through (i) proactively targeting low-frequency Gaussians and (ii) adversarial training with a diffusion proxy. Specifically, we introduce a multi-domain framework that operates natively in 3DGS space and embeds watermarks into diffusion-editing-preserved low-frequency Gaussians via coordinated covariance regularization and 2D filtering. In addition, we exploit the low-pass filtering behavior of diffusion-based editing by using Gaussian blur as an efficient training surrogate, enabling adversarial fine-tuning that further enhances watermark robustness against diffusion-based editing. Empirically, comprehensive quantitative and qualitative evaluations on three benchmark datasets demonstrate that RDSplat not only maintains superior robustness under diffusion-based editing, but also preserves watermark invisibility, achieving state-of-the-art performance. - oai:arXiv.org:2512.06774v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Insured Agents: A Decentralized Trust Insurance Mechanism for Agentic Economy + https://arxiv.org/abs/2512.08737 + arXiv:2512.08737v1 Announce Type: new +Abstract: The emerging "agentic web" envisions large populations of autonomous agents coordinating, transacting, and delegating across open networks. Yet many agent communication and commerce protocols treat agents as low-cost identities, despite the empirical reality that LLM agents remain unreliable, hallucinated, manipulable, and vulnerable to prompt-injection and tool-abuse. A natural response is "agents-at-stake": binding economically meaningful, slashable collateral to persistent identities and adjudicating misbehavior with verifiable evidence. However, heterogeneous tasks make universal verification brittle and centralization-prone, while traditional reputation struggles under rapid model drift and opaque internal states. We propose a protocol-native alternative: insured agents. Specialized insurer agents post stake on behalf of operational agents in exchange for premiums, and receive privileged, privacy-preserving audit access via TEEs to assess claims. A hierarchical insurer market calibrates stake through pricing, decentralizes verification via competitive underwriting, and yields incentive-compatible dispute resolution. + oai:arXiv.org:2512.08737v1 + cs.CY + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Longjie Zhao, Ziming Hong, Zhenyang Ren, Runnan Chen, Mingming Gong, Tongliang Liu + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Botao 'Amber' Hu, Bangdao Chen - From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs - https://arxiv.org/abs/2512.06776 - arXiv:2512.06776v1 Announce Type: new -Abstract: Large language models (LLMs) excel at generation but dominant autoregressive (AR) decoding is inherently sequential, creating a throughput bottleneck. Diffusion Language Models (DLMs)--especially block-wise variants--enable parallel generation and intra-block bidirectional reasoning, yet training large DLMs from scratch is costly and wastes the knowledge in mature AR checkpoints. Prior "adaptation" attempts either modify logits or randomly grow attention masks to full-sequence diffusion, or simply transplant AR weights into a block-diffusion recipe, leaving a fundamental mismatch between AR causality and block-wise bidirectionality unaddressed. We reframe adaptation as a intra-paradigm path from AR to Block-Diffusion by viewing AR as Block-Diffusion with blocksize=1. Concretely, we design the pathway of adaptation as follows: we use a context-causal attention mask (causal in context, bidirectional only within the active block), an efficient parallel adaptation procedure, an auxiliary AR loss to maximize data utilization and retain pretrained knowledge, and gradual increment of the generation block size. The recipe integrates cleanly with masked block-diffusion and maintains train-inference consistency. Built on these components, NBDiff-7B (Base and Instruct) could inherit the long-context modeling and reasoning capabilities, and achieve state-of-the-art performance among the 7B-class DLMs, delivering strong gains on general-knowledge, math, and code benchmarks over strong baselines. These results demonstrate that principled AR-to-block-diffusion adaptation is an effective and compute-efficient alternative to training DLMs from scratch. Codes: https://github.com/YuchuanTian/NBDiff. - oai:arXiv.org:2512.06776v1 + Pose-Based Sign Language Spotting via an End-to-End Encoder Architecture + https://arxiv.org/abs/2512.08738 + arXiv:2512.08738v1 Announce Type: new +Abstract: Automatic Sign Language Recognition (ASLR) has emerged as a vital field for bridging the gap between deaf and hearing communities. However, the problem of sign-to-sign retrieval or detecting a specific sign within a sequence of continuous signs remains largely unexplored. We define this novel task as Sign Language Spotting. In this paper, we present a first step toward sign language retrieval by addressing the challenge of detecting the presence or absence of a query sign video within a sentence-level gloss or sign video. Unlike conventional approaches that rely on intermediate gloss recognition or text-based matching, we propose an end-to-end model that directly operates on pose keypoints extracted from sign videos. Our architecture employs an encoder-only backbone with a binary classification head to determine whether the query sign appears within the target sequence. By focusing on pose representations instead of raw RGB frames, our method significantly reduces computational cost and mitigates visual noise. We evaluate our approach on the Word Presence Prediction dataset from the WSLP 2025 shared task, achieving 61.88\% accuracy and 60.00\% F1-score. These results demonstrate the effectiveness of our pose-based framework for Sign Language Spotting, establishing a strong foundation for future research in automatic sign language retrieval and verification. Code is available at https://github.com/EbimoJohnny/Pose-Based-Sign-Language-Spotting + oai:arXiv.org:2512.08738v1 + cs.CV cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuchuan Tian, Yuchen Liang, Jiacheng Sun, Shuo Zhang, Guangwen Yang, Yingte Shu, Sibo Fang, Tianyu Guo, Kai Han, Chao Xu, Hanting Chen, Xinghao Chen, Yunhe Wang + http://creativecommons.org/licenses/by/4.0/ + Samuel Ebimobowei Johnny, Blessed Guda, Emmanuel Enejo Aaron, Assane Gueye - Crystallographic Texture-Generalizable Orientation-Aware Interaction-Based Deep Material Network for Polycrystal Modeling and Texture Evolution - https://arxiv.org/abs/2512.06779 - arXiv:2512.06779v1 Announce Type: new -Abstract: Machine learning has significantly advanced materials modeling by enabling surrogate models that achieve high computational efficiency without compromising predictive accuracy. The Orientation-aware Interaction-based Deep Material Network (ODMN) is one such framework, in which a set of material nodes represents crystallographic textures, and a hierarchical interaction network enforces stress equilibrium among these nodes based on the Hill-Mandel condition. Using only linear elastic stiffness data, ODMN learns the intrinsic geometry-mechanics relationships within polycrystalline microstructures, allowing it to predict nonlinear mechanical responses and texture evolution with high fidelity. However, its applicability remains limited by the need to retrain for each distinct crystallographic texture. To address this limitation, we introduce the TACS-GNN-ODMN framework, which integrates (i) a Texture-Adaptive Clustering and Sampling (TACS) scheme for initializing texture-related parameters and (ii) a Graph Neural Network (GNN) for predicting stress-equilibrium-related parameters. The proposed framework accurately predicts nonlinear responses and texture evolution across diverse textures, showing close agreement with direct numerical simulations (DNS). By eliminating the requirement for texture-specific retraining while preserving physical interpretability, TACS-GNN-ODMN substantially enhances the generalization capability of ODMN, offering a robust and efficient surrogate model for multiscale simulations and next-generation materials design. - oai:arXiv.org:2512.06779v1 - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 + Deconstructing the Dual Black Box:A Plug-and-Play Cognitive Framework for Human-AI Collaborative Enhancement and Its Implications for AI Governance + https://arxiv.org/abs/2512.08740 + arXiv:2512.08740v1 Announce Type: new +Abstract: Currently, there exists a fundamental divide between the "cognitive black box" (implicit intuition) of human experts and the "computational black box" (untrustworthy decision-making) of artificial intelligence (AI). This paper proposes a new paradigm of "human-AI collaborative cognitive enhancement," aiming to transform the dual black boxes into a composable, auditable, and extensible "functional white-box" system through structured "meta-interaction." The core breakthrough lies in the "plug-and-play cognitive framework"--a computable knowledge package that can be extracted from expert dialogues and loaded into the Recursive Adversarial Meta-Thinking Network (RAMTN). This enables expert thinking, such as medical diagnostic logic and teaching intuition, to be converted into reusable and scalable public assets, realizing a paradigm shift from "AI as a tool" to "AI as a thinking partner." This work not only provides the first engineering proof for "cognitive equity" but also opens up a new path for AI governance: constructing a verifiable and intervenable governance paradigm through "transparency of interaction protocols" rather than prying into the internal mechanisms of models. The framework is open-sourced to promote technology for good and cognitive inclusion. This paper is an independent exploratory research conducted by the author. All content presented, including the theoretical framework (RAMTN), methodology (meta-interaction), system implementation, and case validation, constitutes the author's individual research achievements. + oai:arXiv.org:2512.08740v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ting-Ju Wei, Tung-Huan Su, Chuin-Shan Chen + Yiming Lu - From Description to Score: Can LLMs Quantify Vulnerabilities? - https://arxiv.org/abs/2512.06781 - arXiv:2512.06781v1 Announce Type: new -Abstract: Manual vulnerability scoring, such as assigning Common Vulnerability Scoring System (CVSS) scores, is a resource-intensive process that is often influenced by subjective interpretation. This study investigates the potential of general-purpose large language models (LLMs), namely ChatGPT, Llama, Grok, DeepSeek, and Gemini, to automate this process by analyzing over 31{,}000 recent Common Vulnerabilities and Exposures (CVE) entries. The results show that LLMs substantially outperform the baseline on certain metrics (e.g., \textit{Availability Impact}), while offering more modest gains on others (e.g., \textit{Attack Complexity}). Moreover, model performance varies across both LLM families and individual CVSS metrics, with ChatGPT-5 attaining the highest precision. Our analysis reveals that LLMs tend to misclassify many of the same CVEs, and ensemble-based meta-classifiers only marginally improve performance. Further examination shows that CVE descriptions often lack critical context or contain ambiguous phrasing, which contributes to systematic misclassifications. These findings underscore the importance of enhancing vulnerability descriptions and incorporating richer contextual details to support more reliable automated reasoning and alleviate the growing backlog of CVEs awaiting triage. - oai:arXiv.org:2512.06781v1 - cs.CR - cs.AI - cs.PL - Tue, 09 Dec 2025 00:00:00 -0500 + Parallel Batch Dynamic Vertex Coloring in $O(\log \Delta)$ Amortized Update Time + https://arxiv.org/abs/2512.08742 + arXiv:2512.08742v1 Announce Type: new +Abstract: We present the first parallel batch-dynamic algorithm for maintaining a proper $(\Delta + 1)$-vertex coloring. Our approach builds on a new sequential dynamic algorithm inspired by the work of Bhattacharya et al. (SODA'18). The resulting randomized algorithm achieves $O(\log \Delta)$ expected amortized update time and, for any batch of $b$ updates, has parallel span $O(\operatorname{polylog} b + \operatorname{polylog} n)$ with high probability. + oai:arXiv.org:2512.08742v1 + cs.DS + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sima Jafarikhah, Daniel Thompson, Eva Deans, Hossein Siadati, Yi Liu + Chase Hutton, Adam Melrod - Measuring Over-smoothing beyond Dirichlet energy - https://arxiv.org/abs/2512.06782 - arXiv:2512.06782v1 Announce Type: new -Abstract: While Dirichlet energy serves as a prevalent metric for quantifying over-smoothing, it is inherently restricted to capturing first-order feature derivatives. To address this limitation, we propose a generalized family of node similarity measures based on the energy of higher-order feature derivatives. Through a rigorous theoretical analysis of the relationships among these measures, we establish the decay rates of Dirichlet energy under both continuous heat diffusion and discrete aggregation operators. Furthermore, our analysis reveals an intrinsic connection between the over-smoothing decay rate and the spectral gap of the graph Laplacian. Finally, empirical results demonstrate that attention-based Graph Neural Networks (GNNs) suffer from over-smoothing when evaluated under these proposed metrics. - oai:arXiv.org:2512.06782v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Towards Foundation Models with Native Multi-Agent Intelligence + https://arxiv.org/abs/2512.08743 + arXiv:2512.08743v1 Announce Type: new +Abstract: Foundation models (FMs) are increasingly assuming the role of the "brain" of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify four core capabilities of FMs in multi-agent contexts: understanding, planning, efficient communication, and adaptation. Contrary to assumptions about the spontaneous emergence of such abilities, we provide extensive empirical evidence across 41 large language models showing that strong single-agent performance alone does not automatically yield robust multi-agent intelligence. To address this gap, we outline key research directions -- spanning dataset construction, evaluation, training paradigms, and safety considerations -- for building FMs with native multi-agent intelligence. + oai:arXiv.org:2512.08743v1 + cs.AI + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Weiqi Guan, Zihao Shi + http://creativecommons.org/licenses/by/4.0/ + Shuyue Hu, Haoyang Yan, Yiqun Zhang, Yang Chen, Dongzhan Zhou, Lei Bai - Physics Informed Human Posture Estimation Based on 3D Landmarks from Monocular RGB-Videos - https://arxiv.org/abs/2512.06783 - arXiv:2512.06783v1 Announce Type: new -Abstract: Applications providing automated coaching for physical training are increasing in popularity, for example physical therapy. These applications rely on accurate and robust pose estimation using monocular video streams. State-of-the-art models like BlazePose excel in real-time pose tracking, but their lack of anatomical constraints indicates improvement potential by including physical knowledge. We present a real-time post-processing algorithm fusing the strengths of BlazePose 3D and 2D estimations using a weighted optimization, penalizing deviations from expected bone length and biomechanical models. Bone length estimations are refined to the individual anatomy using a Kalman filter with adapting measurement trust. Evaluation using the Physio2.2M dataset shows a 10.2 percent reduction in 3D MPJPE and a 16.6 percent decrease in errors of angles between body segments compared to BlazePose 3D estimation. Our method provides a robust, anatomically consistent pose estimation based on a computationally efficient video-to-3D pose estimation, suitable for automated physiotherapy, healthcare, and sports coaching on consumer-level laptops and mobile devices. The refinement runs on the backend with anonymized data only. - oai:arXiv.org:2512.06783v1 + A Scalable Pipeline Combining Procedural 3D Graphics and Guided Diffusion for Photorealistic Synthetic Training Data Generation in White Button Mushroom Segmentation + https://arxiv.org/abs/2512.08747 + arXiv:2512.08747v1 Announce Type: new +Abstract: Industrial mushroom cultivation increasingly relies on computer vision for monitoring and automated harvesting. However, developing accurate detection and segmentation models requires large, precisely annotated datasets that are costly to produce. Synthetic data provides a scalable alternative, yet often lacks sufficient realism to generalize to real-world scenarios. This paper presents a novel workflow that integrates 3D rendering in Blender with a constrained diffusion model to automatically generate high-quality annotated, photorealistic synthetic images of Agaricus Bisporus mushrooms. This approach preserves full control over 3D scene configuration and annotations while achieving photorealism without the need for specialized computer graphics expertise. We release two synthetic datasets (each containing 6,000 images depicting over 250k mushroom instances) and evaluate Mask R-CNN models trained on them in a zero-shot setting. When tested on two independent real-world datasets (including a newly collected benchmark), our method achieves state-of-the-art segmentation performance (F1 = 0.859 on M18K), despite using only synthetic training data. Although the approach is demonstrated on Agaricus Bisporus mushrooms, the proposed pipeline can be readily adapted to other mushroom species or to other agricultural domains, such as fruit and leaf detection. + oai:arXiv.org:2512.08747v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tobias Leuthold, Michele Xiloyannis, Yves Zimmermann + http://creativecommons.org/licenses/by/4.0/ + Art\'ur I. K\'aroly, P\'eter Galambos - Stable-MoE: Lyapunov-based Token Routing for Distributed Mixture-of-Experts Training over Edge Networks - https://arxiv.org/abs/2512.06784 - arXiv:2512.06784v1 Announce Type: new -Abstract: The sparse activation mechanism of mixture of experts (MoE) model empowers edge intelligence with enhanced training efficiency and reduced computational resource consumption. However, traditional token routing in distributed MoE training faces significant challenges in resource-constrained edge networks characterized by heterogeneous computing capabilities and stochastic token arrivals, which inevitably suffer from workload backlog, resource inefficiency, and performance degradation. To address this issue, we propose a novel Lyapunov-based token routing framework for distributed MoE training over resource-heterogeneous edge networks, termed Stable-MoE. Specifically, we formulate a stochastic optimization problem to maximize both system throughput and gating consistency via optimizing the token routing strategy and computational resource allocation, while ensuring long-term stability of both token and energy queues at the edge devices. Using the Lyapunov optimization, we transform the intractable long-term optimization problem into tractable per-slot subproblems by enabling online decision-making of token routing and computation frequency utilization without the knowledge of future system states. Experimental results on the SVHN and CIFAR-100 datasets demonstrate that Stable-MoE outperforms the baselines with at least 40% and 5% gains in system throughput and test accuracy, respectively. - oai:arXiv.org:2512.06784v1 + Skewness-Guided Pruning of Multimodal Swin Transformers for Federated Skin Lesion Classification on Edge Devices + https://arxiv.org/abs/2512.08751 + arXiv:2512.08751v1 Announce Type: new +Abstract: In recent years, high-performance computer vision models have achieved remarkable success in medical imaging, with some skin lesion classification systems even surpassing dermatology specialists in diagnostic accuracy. However, such models are computationally intensive and large in size, making them unsuitable for deployment on edge devices. In addition, strict privacy constraints hinder centralized data management, motivating the adoption of Federated Learning (FL). To address these challenges, this study proposes a skewness-guided pruning method that selectively prunes the Multi-Head Self-Attention and Multi-Layer Perceptron layers of a multimodal Swin Transformer based on the statistical skewness of their output distributions. The proposed method was validated in a horizontal FL environment and shown to maintain performance while substantially reducing model complexity. Experiments on the compact Swin Transformer demonstrate approximately 36\% model size reduction with no loss in accuracy. These findings highlight the feasibility of achieving efficient model compression and privacy-preserving distributed learning for multimodal medical AI on edge devices. + oai:arXiv.org:2512.08751v1 + cs.CV cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Long Shi, Bingyan Ou, Kang Wei, Weihao Zhu, Zhe Wang, Zhiyong Chen + http://creativecommons.org/licenses/by/4.0/ + Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos - Angular Regularization for Positive-Unlabeled Learning on the Hypersphere - https://arxiv.org/abs/2512.06785 - arXiv:2512.06785v1 Announce Type: new -Abstract: Positive-Unlabeled (PU) learning addresses classification problems where only a subset of positive examples is labeled and the remaining data is unlabeled, making explicit negative supervision unavailable. Existing PU methods often rely on negative-risk estimation or pseudo-labeling, which either require strong distributional assumptions or can collapse in high-dimensional settings. We propose AngularPU, a novel PU framework that operates on the unit hypersphere using cosine similarity and angular margin. In our formulation, the positive class is represented by a learnable prototype vector, and classification reduces to thresholding the cosine similarity between an embedding and this prototype-eliminating the need for explicit negative modeling. To counteract the tendency of unlabeled embeddings to cluster near the positive prototype, we introduce an angular regularizer that encourages dispersion of the unlabeled set over the hypersphere, improving separation. We provide theoretical guarantees on the Bayes-optimality of the angular decision rule, consistency of the learned prototype, and the effect of the regularizer on the unlabeled distribution. Experiments on benchmark datasets demonstrate that AngularPU achieves competitive or superior performance compared to state-of-the-art PU methods, particularly in settings with scarce positives and high-dimensional embeddings, while offering geometric interpretability and scalability. - oai:arXiv.org:2512.06785v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + IoT-based Cost-Effective Fruit Quality Monitoring System using Electronic Nose + https://arxiv.org/abs/2512.08753 + arXiv:2512.08753v1 Announce Type: new +Abstract: Post-harvest losses due to subjective quality assessment cause significant damage to the economy and food safety, especially in countries like Bangladesh. To mitigate such damages, objective decision-making backed by scientific methods is necessary. An IoT-based, cost-effective quality monitoring system can provide a solution by going beyond subjective quality monitoring and decision-making practices. Here, we propose a low-power, cost-effective fruit quality monitoring system with an array of MQ gas sensors, which can be used as an electronic nose. We track the volatile gas emissions, specifically ethanol, methane, and ammonia, encompassing both ripening and decomposition for a set of bananas. Based on the gas concentration thresholds, we develop a mathematical model to accurately assess fruit quality. We also integrate this information into a dashboard for prompt decision-making and monitoring to make it useful to the farmers. This approach has the potential to reduce economic losses, enhance food safety, and provide scalable solutions for the supply chain. + oai:arXiv.org:2512.08753v1 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Vasileios Sevetlidis, George Pavlidis, Antonios Gasteratos + Anindya Bhattacharjee, Nittya Ananda Biswas, Khondakar Ashik Shahriar, Kawsain Bin Salim - LLM4SFC: Sequential Function Chart Generation via Large Language Models - https://arxiv.org/abs/2512.06787 - arXiv:2512.06787v1 Announce Type: new -Abstract: While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain underexplored. Generating SFCs is challenging due to graphical nature and ST actions embedded within, which are not directly compatible with standard generation techniques, often leading to non-executable code that is incompatible with industrial tool-chains In this work, we introduce LLM4SFC, the first framework to receive natural-language descriptions of industrial workflows and provide executable SFCs. LLM4SFC is based on three components: (i) A reduced structured representation that captures essential topology and in-line ST and reduced textual verbosity; (ii) Fine-tuning and few-shot retrieval-augmented generation (RAG) for alignment with SFC programming conventions; and (iii) A structured generation approach that prunes illegal tokens in real-time to ensure compliance with the textual format of SFCs. We evaluate LLM4SFC on a dataset of real-world SFCs from automated manufacturing projects, using both open-source and proprietary LLMs. The results show that LLM4SFC reliably generates syntactically valid SFC programs effectively bridging graphical and textual PLC languages, achieving a generation generation success of 75% - 94%, paving the way for automated industrial programming. - oai:arXiv.org:2512.06787v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + A Multi-Robot Platform for Robotic Triage Combining Onboard Sensing and Foundation Models + https://arxiv.org/abs/2512.08754 + arXiv:2512.08754v1 Announce Type: new +Abstract: This report presents a heterogeneous robotic system designed for remote primary triage in mass-casualty incidents (MCIs). The system employs a coordinated air-ground team of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) to locate victims, assess their injuries, and prioritize medical assistance without risking the lives of first responders. The UAV identify and provide overhead views of casualties, while UGVs equipped with specialized sensors measure vital signs and detect and localize physical injuries. Unlike previous work that focused on exploration or limited medical evaluation, this system addresses the complete triage process: victim localization, vital sign measurement, injury severity classification, mental status assessment, and data consolidation for first responders. Developed as part of the DARPA Triage Challenge, this approach demonstrates how multi-robot systems can augment human capabilities in disaster response scenarios to maximize lives saved. + oai:arXiv.org:2512.08754v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ofek Glick, Vladimir Tchuiev, Marah Ghoummaid, Michal Moshkovitz, Dotan Di-Castro + Jason Hughes, Marcel Hussing, Edward Zhang, Shenbagaraj Kannapiran, Joshua Caswell, Kenneth Chaney, Ruichen Deng, Michaela Feehery, Agelos Kratimenos, Yi Fan Li, Britny Major, Ethan Sanchez, Sumukh Shrote, Youkang Wang, Jeremy Wang, Daudi Zein, Luying Zhang, Ruijun Zhang, Alex Zhou, Tenzi Zhouga, Jeremy Cannon, Zaffir Qasim, Jay Yelon, Fernando Cladera, Kostas Daniilidis, Camillo J. Taylor, Eric Eaton - Small-Gain Nash: Certified Contraction to Nash Equilibria in Differentiable Games - https://arxiv.org/abs/2512.06791 - arXiv:2512.06791v1 Announce Type: new -Abstract: Classical convergence guarantees for gradient-based learning in games require the pseudo-gradient to be (strongly) monotone in Euclidean geometry as shown by rosen(1965), a condition that often fails even in simple games with strong cross-player couplings. We introduce Small-Gain Nash (SGN), a block small-gain condition in a custom block-weighted geometry. SGN converts local curvature and cross-player Lipschitz coupling bounds into a tractable certificate of contraction. It constructs a weighted block metric in which the pseudo-gradient becomes strongly monotone on any region where these bounds hold, even when it is non-monotone in the Euclidean sense. The continuous flow is exponentially contracting in this designed geometry, and projected Euler and RK4 discretizations converge under explicit step-size bounds derived from the SGN margin and a local Lipschitz constant. Our analysis reveals a certified ``timescale band'', a non-asymptotic, metric-based certificate that plays a TTUR-like role: rather than forcing asymptotic timescale separation via vanishing, unequal step sizes, SGN identifies a finite band of relative metric weights for which a single-step-size dynamics is provably contractive. We validate the framework on quadratic games where Euclidean monotonicity analysis fails to predict convergence, but SGN successfully certifies it, and extend the construction to mirror/Fisher geometries for entropy-regularized policy gradient in Markov games. The result is an offline certification pipeline that estimates curvature, coupling, and Lipschitz parameters on compact regions, optimizes block weights to enlarge the SGN margin, and returns a structural, computable convergence certificate consisting of a metric, contraction rate, and safe step-sizes for non-monotone games. - oai:arXiv.org:2512.06791v1 - cs.LG - cs.GT - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Performance Comparison of Aerial RIS and STAR-RIS in 3D Wireless Environments + https://arxiv.org/abs/2512.08755 + arXiv:2512.08755v1 Announce Type: new +Abstract: Reconfigurable intelligent surface (RIS) and simultaneously transmitting and reflecting RIS (STAR-RIS) have emerged as key enablers for enhancing wireless coverage and capacity in next-generation networks. When mounted on unmanned aerial vehicles (UAVs), they benefit from flexible deployment and improved line-of-sight conditions. Despite their promising potential, a comprehensive performance comparison between aerial RIS and STAR-RIS architectures has not been thoroughly investigated. This letter presents a detailed performance comparison between aerial RIS and STAR-RIS in three-dimensional wireless environments. Accurate channel models incorporating directional radiation patterns are established, and the influence of deployment altitude and orientation is thoroughly examined. To optimize the system sum-rate, we formulate joint optimization problems for both architectures and propose an efficient solution based on the weighted minimum mean square error and block coordinate descent algorithms. Simulation results reveal that STAR-RIS outperforms RIS in low-altitude scenarios due to its full-space coverage capability, whereas RIS delivers better performance near the base station at higher altitudes. The findings provide practical insights for the deployment of aerial intelligent surfaces in future 6G communication systems. + oai:arXiv.org:2512.08755v1 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Vedansh Sharma + Dongdong Yang, Bin Li, Jiguang He - Generalized Geometry Encoding Volume for Real-time Stereo Matching - https://arxiv.org/abs/2512.06793 - arXiv:2512.06793v1 Announce Type: new -Abstract: Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In contrast, recent stereo foundation models leverage monocular foundation models (MFMs) to improve generalization, but typically suffer from substantial inference latency. To address this trade-off, we propose Generalized Geometry Encoding Volume (GGEV), a novel real-time stereo matching network that achieves strong generalization. We first extract depth-aware features that encode domain-invariant structural priors as guidance for cost aggregation. Subsequently, we introduce a Depth-aware Dynamic Cost Aggregation (DDCA) module that adaptively incorporates these priors into each disparity hypothesis, effectively enhancing fragile matching relationships in unseen scenes. Both steps are lightweight and complementary, leading to the construction of a generalized geometry encoding volume with strong generalization capability. Experimental results demonstrate that our GGEV surpasses all existing real-time methods in zero-shot generalization capability, and achieves state-of-the-art performance on the KITTI 2012, KITTI 2015, and ETH3D benchmarks. - oai:arXiv.org:2512.06793v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Explainable Learning Based Regularization of Inverse Problems + https://arxiv.org/abs/2512.08758 + arXiv:2512.08758v1 Announce Type: new +Abstract: Machine learning techniques for the solution of inverse problems have become an attractive approach in the last decade, while their theoretical foundations are still in their infancy. In this chapter we want to pursue the study of regularization properties, robustness, convergence rates, and structure of regularizers for inverse problems obtained from different learning paradigms. For this sake we study simple architectures that are explainable in the sense that they allow for a theoretical analysis also in the infinite-dimensional limit. In particular we will advance the study of spectral architectures with new results on convergence rates highlighting the role of the smoothness in the training data set, and a study of adversarial robustness. We can show that adversarial training is actually a convergent regularization method. Moreover, we discuss extensions to frame systems and CNN-type architectures for variational regularizers, where we obtain some results on their structure by carefully designed numerical experiments. + oai:arXiv.org:2512.08758v1 + math.NA + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiaxin Liu, Gangwei Xu, Xianqi Wang, Chengliang Zhang, Xin Yang + http://creativecommons.org/licenses/by/4.0/ + Martin Burger, Samira Kabri, Gitta Kutyniok, Yunseok Lee, Lukas Weigand - db-LaCAM: Fast and Scalable Multi-Robot Kinodynamic Motion Planning with Discontinuity-Bounded Search and Lightweight MAPF - https://arxiv.org/abs/2512.06796 - arXiv:2512.06796v1 Announce Type: new -Abstract: State-of-the-art multi-robot kinodynamic motion planners struggle to handle more than a few robots due to high computational burden, which limits their scalability and results in slow planning time. - In this work, we combine the scalability and speed of modern multi-agent path finding (MAPF) algorithms with the dynamic-awareness of kinodynamic planners to address these limitations. - To this end, we propose discontinuity-Bounded LaCAM (db-LaCAM), a planner that utilizes a precomputed set of motion primitives that respect robot dynamics to generate horizon-length motion sequences, while allowing a user-defined discontinuity between successive motions. - The planner db-LaCAM is resolution-complete with respect to motion primitives and supports arbitrary robot dynamics. - Extensive experiments demonstrate that db-LaCAM scales efficiently to scenarios with up to 50 robots, achieving up to ten times faster runtime compared to state-of-the-art planners, while maintaining comparable solution quality. - The approach is validated in both 2D and 3D environments with dynamics such as the unicycle and 3D double integrator. - We demonstrate the safe execution of trajectories planned with db-LaCAM in two distinct physical experiments involving teams of flying robots and car-with-trailer robots. - oai:arXiv.org:2512.06796v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning + https://arxiv.org/abs/2512.08763 + arXiv:2512.08763v1 Announce Type: new +Abstract: Early graph prompt tuning approaches relied on task-specific designs for Graph Neural Networks (GNNs), limiting their adaptability across diverse pre-training strategies. In contrast, another promising line of research has investigated universal graph prompt tuning, which operates directly in the input graph's feature space and builds a theoretical foundation that universal graph prompt tuning can theoretically achieve an equivalent effect of any prompting function, eliminating dependence on specific pre-training strategies. Recent works propose selective node-based graph prompt tuning to pursue more ideal prompts. However, we argue that selective node-based graph prompt tuning inevitably compromises the theoretical foundation of universal graph prompt tuning. In this paper, we strengthen the theoretical foundation of universal graph prompt tuning by introducing stricter constraints, demonstrating that adding prompts to all nodes is a necessary condition for achieving the universality of graph prompts. To this end, we propose a novel model and paradigm, Learning and Editing Universal GrAph Prompt Tuning (LEAP), which preserves the theoretical foundation of universal graph prompt tuning while pursuing more ideal prompts. Specifically, we first build the basic universal graph prompts to preserve the theoretical foundation and then employ actor-critic reinforcement learning to select nodes and edit prompts. Extensive experiments on graph- and node-level tasks across various pre-training strategies in both full-shot and few-shot scenarios show that LEAP consistently outperforms fine-tuning and other prompt-based approaches. + oai:arXiv.org:2512.08763v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Akmaral Moldagalieva, Keisuke Okumura, Amanda Prorok, Wolfgang H\"onig + http://creativecommons.org/licenses/by/4.0/ + Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Hewei Wang, Yijie Li, Edith C. H. Ngai - Cloud Revolution: Tracing the Origins and Rise of Cloud Computing - https://arxiv.org/abs/2512.06800 - arXiv:2512.06800v1 Announce Type: new -Abstract: The history behind the development of cloud computing is more than several decades of technological progress in the fields of virtualization, distributed systems, and high-speed networking, but its current application is much broader than the underlying technologies that made it possible. This paper reexamines the historical evolution of the field, including the initial ideas of resource sharing and utility-based computing approaches and the development of hyperscale data centers and modern globally federated cloud ecosystems. We also analyze the technological and economic forces and point to the way cloud platforms altered the organizational computing habits, decreasing the entrance-level to the data-intensive and computation-heavy apps. The study also takes into account the ongoing limitations which have come with the large-scale adoption of clouds which include exposure to security due to the weaknesses in configuration, particular establishment regulations, and structural reliance on the single vendors. Lastly, we address some of the new trends that are transforming the cloud environment, including the convergence of edge and cloud infrastructure, the increased prominence of AI-optimised architectures and the initial adoption of quantum computing services. Collectively, the developments above describe an emerging but quickly changing paradigm with its future direction being determined by a strike of balancing between scalability, openness, and trust. - oai:arXiv.org:2512.06800v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 + Financial News Summarization: Can extractive methods still offer a true alternative to LLMs? + https://arxiv.org/abs/2512.08764 + arXiv:2512.08764v1 Announce Type: new +Abstract: Financial markets change rapidly due to news, economic shifts, and geopolitical events. Quick reactions are vital for investors to avoid losses or capture short-term gains. As a result, concise financial news summaries are critical for decision-making. With over 50,000 financial articles published daily, automation in summarization is necessary. This study evaluates a range of summarization methods, from simple extractive techniques to advanced large language models (LLMs), using the FinLLMs Challenge dataset. LLMs generated more coherent and informative summaries, but they are resource-intensive and prone to hallucinations, which can introduce significant errors into financial summaries. In contrast, extractive methods perform well on short, well-structured texts and offer a more efficient alternative for this type of article. The best ROUGE results come from fine-tuned LLM model like FT-Mistral-7B, although our data corpus has limited reliability, which calls for cautious interpretation. + oai:arXiv.org:2512.08764v1 + cs.CE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Deepa Gurung, S M Zia Ur Rashid, Zain ul Abdeen, Suman Rath + 10.1007/978-3-032-09037-9 + Advances in Soft Computing. MICAI 2025. Lecture Notes in Computer Science, vol 16221. Springer + Nicolas Reche, Elvys Linhares-Pontes, Juan-Manuel Torres-Moreno - VDOT: Efficient Unified Video Creation via Optimal Transport Distillation - https://arxiv.org/abs/2512.06802 - arXiv:2512.06802v1 Announce Type: new -Abstract: The rapid development of generative models has significantly advanced image and video applications. Among these, video creation, aimed at generating videos under various conditions, has gained substantial attention. However, existing video creation models either focus solely on a few specific conditions or suffer from excessively long generation times due to complex model inference, making them impractical for real-world applications. To mitigate these issues, we propose an efficient unified video creation model, named VDOT. Concretely, we model the training process with the distribution matching distillation (DMD) paradigm. Instead of using the Kullback-Leibler (KL) minimization, we additionally employ a novel computational optimal transport (OT) technique to optimize the discrepancy between the real and fake score distributions. The OT distance inherently imposes geometric constraints, mitigating potential zero-forcing or gradient collapse issues that may arise during KL-based distillation within the few-step generation scenario, and thus, enhances the efficiency and stability of the distillation process. Further, we integrate a discriminator to enable the model to perceive real video data, thereby enhancing the quality of generated videos. To support training unified video creation models, we propose a fully automated pipeline for video data annotation and filtering that accommodates multiple video creation tasks. Meanwhile, we curate a unified testing benchmark, UVCBench, to standardize evaluation. Experiments demonstrate that our 4-step VDOT outperforms or matches other baselines with 100 denoising steps. - oai:arXiv.org:2512.06802v1 + Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance + https://arxiv.org/abs/2512.08765 + arXiv:2512.08765v1 Announce Type: new +Abstract: We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse control granularity and limited scalability, leaving their outputs insufficient for practical use. We narrow this gap by achieving precise and high-quality motion control. Our core idea is to directly make the original condition features motion-aware for guiding video synthesis. To this end, we first represent object motions with dense point trajectories, allowing fine-grained control over the scene. We then project these trajectories into latent space and propagate the first frame's features along each trajectory, producing an aligned spatiotemporal feature map that tells how each scene element should move. This feature map serves as the updated latent condition, which is naturally integrated into the off-the-shelf image-to-video model, e.g., Wan-I2V-14B, as motion guidance without any architecture change. It removes the need for auxiliary motion encoders and makes fine-tuning base models easily scalable. Through scaled training, Wan-Move generates 5-second, 480p videos whose motion controllability rivals Kling 1.5 Pro's commercial Motion Brush, as indicated by user studies. To support comprehensive evaluation, we further design MoveBench, a rigorously curated benchmark featuring diverse content categories and hybrid-verified annotations. It is distinguished by larger data volume, longer video durations, and high-quality motion annotations. Extensive experiments on MoveBench and the public dataset consistently show Wan-Move's superior motion quality. Code, models, and benchmark data are made publicly available. + oai:arXiv.org:2512.08765v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yutong Wang, Haiyu Zhang, Tianfan Xue, Yu Qiao, Yaohui Wang, Chang Xu, Xinyuan Chen - - - METRION: A Framework for Accurate Software Energy Measurement - https://arxiv.org/abs/2512.06806 - arXiv:2512.06806v1 Announce Type: new -Abstract: The Information and Communication Technology sector accounted for approximately 1.4% of global greenhouse gas emissions and 4% of the world's electricity consumption in 2020, with both expected to rise. To reduce this environmental impact, optimization strategies are employed to reduce energy consumption at the IT infrastructure and application levels. However, effective optimization requires, firstly, the identification of major energy consumers and, secondly, the ability to quantify whether an optimization has achieved the intended energy savings. Accurate determination of application-level energy consumption is thus essential. Therefore, we introduce an energy attribution model that quantifies the energy consumption of applications on CPU and DRAM at the thread level, considering the influence of Simultaneous Multithreading, frequency scaling, multi-socket architectures, and Non-Uniform Memory Access. To ensure cross-platform applicability, we integrate the proposed model into an extensible framework, METRION, including a platform-independent data model and an initial implementation for Linux systems using Intel CPUs. We evaluate METRION across three different workloads and demonstrate that the energy attribution model can accurately capture the CPU energy consumption of applications targeting solely the CPU with a Mean Absolute Percentage Error of 4.2%, and the DRAM energy consumption of applications targeting DRAM with an 16.1% error. - oai:arXiv.org:2512.06806v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Benjamin Weigell, Simon Hornung, Bernhard Bauer + Ruihang Chu, Yefei He, Zhekai Chen, Shiwei Zhang, Xiaogang Xu, Bin Xia, Dingdong Wang, Hongwei Yi, Xihui Liu, Hengshuang Zhao, Yu Liu, Yingya Zhang, Yujiu Yang - A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems - https://arxiv.org/abs/2512.06809 - arXiv:2512.06809v1 Announce Type: new -Abstract: Battery safety is paramount for electric vehicles. Early fault diagnosis remains a challenge due to the subtle nature of anomalies and the interference of dynamic operating noise. Existing data-driven methods often suffer from "physical blindness" leading to missed detections or false alarms. To address this, we propose a Physics-Aware Attention LSTM Autoencoder (PA-ALSTM-AE). This novel framework explicitly integrates battery aging laws (mileage) into the deep learning pipeline through a multi-stage fusion mechanism. Specifically, an adaptive physical feature construction module selects mileage-sensitive features, and a physics-guided latent fusion module dynamically calibrates the memory cells of the LSTM based on the aging state. Extensive experiments on the large-scale Vloong real-world dataset demonstrate that the proposed method significantly outperforms state-of-the-art baselines. Notably, it improves the recall rate of early faults by over 3 times while maintaining high precision, offering a robust solution for industrial battery management systems. - oai:arXiv.org:2512.06809v1 - eess.SY - cs.LG - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Data-Driven Dynamic Parameter Learning of manipulator robots + https://arxiv.org/abs/2512.08767 + arXiv:2512.08767v1 Announce Type: new +Abstract: Bridging the sim-to-real gap remains a fundamental challenge in robotics, as accurate dynamic parameter estimation is essential for reliable model-based control, realistic simulation, and safe deployment of manipulators. Traditional analytical approaches often fall short when faced with complex robot structures and interactions. Data-driven methods offer a promising alternative, yet conventional neural networks such as recurrent models struggle to capture long-range dependencies critical for accurate estimation. In this study, we propose a Transformer-based approach for dynamic parameter estimation, supported by an automated pipeline that generates diverse robot models and enriched trajectory data using Jacobian-derived features. The dataset consists of 8,192 robots with varied inertial and frictional properties. Leveraging attention mechanisms, our model effectively captures both temporal and spatial dependencies. Experimental results highlight the influence of sequence length, sampling rate, and architecture, with the best configuration (sequence length 64, 64 Hz, four layers, 32 heads) achieving a validation R2 of 0.8633. Mass and inertia are estimated with near-perfect accuracy, Coulomb friction with moderate-to-high accuracy, while viscous friction and distal link center-of-mass remain more challenging. These results demonstrate that combining Transformers with automated dataset generation and kinematic enrichment enables scalable, accurate dynamic parameter estimation, contributing to improved sim-to-real transfer in robotic systems + oai:arXiv.org:2512.08767v1 + cs.RO + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiong Yang - - - MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning - https://arxiv.org/abs/2512.06810 - arXiv:2512.06810v1 Announce Type: new -Abstract: Recent advances in video multimodal large language models (Video MLLMs) have significantly enhanced video understanding and multi-modal interaction capabilities. While most existing systems operate in a turn-based manner where the model can only reply after user turns, proactively deciding when to reply during video playback presents a promising yet challenging direction for real-time applications. In this work, we propose a novel text-to-text approach to proactive interaction, where the model autonomously determines whether to respond or remain silent at each turn based on dialogue history and visual context up to current frame of an streaming video. To overcome difficulties in previous methods such as manually tuning response decision thresholds and annotating precise reply times, we introduce a multi-turn RL based training method that encourages timely and accurate responses without requiring precise response time annotations. We train our model MMDuet2 on a dataset of 52k videos with two types of dialogues via SFT and RL. Experimental results demonstrate that MMDuet2 outperforms existing proactive Video MLLM baselines in response timing and quality, achieving state-of-the-art performance on the ProactiveVideoQA benchmark. - oai:arXiv.org:2512.06810v1 - cs.CV - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yueqian Wang, Songxiang Liu, Disong Wang, Nuo Xu, Guanglu Wan, Huishuai Zhang, Dongyan Zhao + Mohammed Elseiagy, Tsige Tadesse Alemayoh, Ranulfo Bezerra, Shotaro Kojima, Kazunori Ohno - RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models - https://arxiv.org/abs/2512.06811 - arXiv:2512.06811v1 Announce Type: new -Abstract: Pre-trained Vision-Language Models (VLMs), \textit{e.g.} CLIP, have become essential tools in multimodal transfer learning. However, fine-tuning VLMs in few-shot scenarios poses significant challenges in balancing task-specific adaptation and generalization in the obtained model. Meanwhile, current researches have predominantly focused on prompt-based adaptation methods, leaving adapter-based approaches underexplored and revealing notable performance gaps. To address these challenges, we introduce a novel Reconstruction-based Multimodal Adapter (RMAdapter), which leverages a dual-branch architecture. Unlike conventional single-branch adapters, RMAdapter consists of: (1) an adaptation branch that injects task-specific knowledge through parameter-efficient fine-tuning, and (2) a reconstruction branch that preserves general knowledge by reconstructing latent space features back into the original feature space. This design facilitates a dynamic balance between general and task-specific knowledge. Importantly, although RMAdapter introduces an additional reconstruction branch, it is carefully optimized to remain lightweight. By computing reconstruction loss locally at each layer and sharing projection modules, the overall computational overhead is kept minimal. A consistency constraint is also incorporated to better regulate the trade-off between discriminability and generalization. We comprehensively evaluate the effectiveness of RMAdapter on three representative tasks: generalization to new categories, generalization to new target datasets, and domain generalization. Without relying on data augmentation or duplicate prompt designs, our RMAdapter consistently outperforms state-of-the-art approaches across all evaluation metrics. - oai:arXiv.org:2512.06811v1 - cs.CV + A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows + https://arxiv.org/abs/2512.08769 + arXiv:2512.08769v1 Announce Type: new +Abstract: Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks. Unlike traditional single model prompting, agentic workflows integrate multiple specialized agents with different Large Language Models(LLMs), tool-augmented capabilities, orchestration logic, and external system interactions to form dynamic pipelines capable of autonomous decision-making and action. As adoption accelerates across industry and research, organizations face a central challenge: how to design, engineer, and operate production-grade agentic AI workflows that are reliable, observable, maintainable, and aligned with safety and governance requirements. This paper provides a practical, end-to-end guide for designing, developing, and deploying production-quality agentic AI systems. We introduce a structured engineering lifecycle encompassing workflow decomposition, multi-agent design patterns, Model Context Protocol(MCP), and tool integration, deterministic orchestration, Responsible-AI considerations, and environment-aware deployment strategies. We then present nine core best practices for engineering production-grade agentic AI workflows, including tool-first design over MCP, pure-function invocation, single-tool and single-responsibility agents, externalized prompt management, Responsible-AI-aligned model-consortium design, clean separation between workflow logic and MCP servers, containerized deployment for scalable operations, and adherence to the Keep it Simple, Stupid (KISS) principle to maintain simplicity and robustness. To demonstrate these principles in practice, we present a comprehensive case study: a multimodal news-analysis and media-generation workflow. By combining architectural guidance, operational patterns, and practical implementation insights, this paper offers a foundational reference to build robust, extensible, and production-ready agentic AI workflows. + oai:arXiv.org:2512.08769v1 cs.AI - cs.LG - cs.MM - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Xiang Lin, Weixin Li, Shu Guo, Lihong Wang, Di Huang + Eranga Bandara, Ross Gore, Peter Foytik, Sachin Shetty, Ravi Mukkamala, Abdul Rahman, Xueping Liang, Safdar H. Bouk, Amin Hass, Sachini Rajapakse, Ng Wee Keong, Kasun De Zoysa, Aruna Withanage, Nilaan Loganathan - Large Language Model-Based Generation of Discharge Summaries - https://arxiv.org/abs/2512.06812 - arXiv:2512.06812v1 Announce Type: new -Abstract: Discharge Summaries are documents written by medical professionals that detail a patient's visit to a care facility. They contain a wealth of information crucial for patient care, and automating their generation could significantly reduce the effort required from healthcare professionals, minimize errors, and ensure that critical patient information is easily accessible and actionable. In this work, we explore the use of five Large Language Models on this task, from open-source models (Mistral, Llama 2) to proprietary systems (GPT-3, GPT-4, Gemini 1.5 Pro), leveraging MIMIC-III summaries and notes. We evaluate them using exact-match, soft-overlap, and reference-free metrics. Our results show that proprietary models, particularly Gemini with one-shot prompting, outperformed others, producing summaries with the highest similarity to the gold-standard ones. Open-source models, while promising, especially Mistral after fine-tuning, lagged in performance, often struggling with hallucinations and repeated information. Human evaluation by a clinical expert confirmed the practical utility of the summaries generated by proprietary models. Despite the challenges, such as hallucinations and missing information, the findings suggest that LLMs, especially proprietary models, are promising candidates for automatic discharge summary generation as long as data privacy is ensured. - oai:arXiv.org:2512.06812v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + De novo generation of functional terpene synthases using TpsGPT + https://arxiv.org/abs/2512.08772 + arXiv:2512.08772v1 Announce Type: new +Abstract: Terpene synthases (TPS) are a key family of enzymes responsible for generating the diverse terpene scaffolds that underpin many natural products, including front-line anticancer drugs such as Taxol. However, de novo TPS design through directed evolution is costly and slow. We introduce TpsGPT, a generative model for scalable TPS protein design, built by fine-tuning the protein language model ProtGPT2 on 79k TPS sequences mined from UniProt. TpsGPT generated de novo enzyme candidates in silico and we evaluated them using multiple validation metrics, including EnzymeExplorer classification, ESMFold structural confidence (pLDDT), sequence diversity, CLEAN classification, InterPro domain detection, and Foldseek structure alignment. From an initial pool of 28k generated sequences, we identified seven putative TPS enzymes that satisfied all validation criteria. Experimental validation confirmed TPS enzymatic activity in at least two of these sequences. Our results show that fine-tuning of a protein language model on a carefully curated, enzyme-class-specific dataset, combined with rigorous filtering, can enable the de novo generation of functional, evolutionarily distant enzymes. + oai:arXiv.org:2512.08772v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Tiago Rodrigues, Carla Teixeira Lopes + Hamsini Ramanathan, Roman Bushuiev, Matou\v{s} Sold\'at, Jir\'i Kohout, T\'eo Hebra, Joshua David Smith, Josef Sivic, Tom\'a\v{s} Pluskal - Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation - https://arxiv.org/abs/2512.06813 - arXiv:2512.06813v1 Announce Type: new -Abstract: High-performance concrete offers exceptional strength and durability but requires complex mix designs involving many interdependent variables and practical constraints. While data-driven methods have advanced predictive modeling for forward design, inverse design, which focuses on determining mix compositions that achieve target performance, remains limited, particularly in design situations where some mix variables are fixed by constraints and only the remaining variables must be determined. This study proposes a cooperative neural network framework for the partial inverse design of high-performance concrete. The framework combines two coupled neural network models, an imputation model that infers the undetermined variables and a surrogate model that predicts compressive strength. Through cooperative learning, the model generates valid and performance-consistent mix designs in a single forward pass while accommodating different constraint combinations without retraining. Its performance is compared with both probabilistic and generative approaches, including Bayesian inference based on a Gaussian process surrogate and autoencoder-based models. Evaluated on a benchmark dataset, the proposed model achieves stable and higher R-squared values of 0.87-0.92 and reduces mean squared error by an average of 50 percent compared with autoencoder baselines and by an average of 70 percent compared with Bayesian inference. The results demonstrate that the cooperative neural network provides an accurate, robust, and computationally efficient foundation for constraint-aware, data-driven mix proportioning in concrete engineering. - oai:arXiv.org:2512.06813v1 - cs.LG + Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps + https://arxiv.org/abs/2512.08774 + arXiv:2512.08774v1 Announce Type: new +Abstract: Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation quality by detecting these flaws. The framework employs an explainable artificial intelligence (XAI)-based flaw highlighter to produce flaw activation maps (FAMs) that identify artifacts and unrealistic regions. These FAMs improve reconstruction quality by amplifying noise in flawed regions during the forward process and by focusing on these regions during the reverse process. The proposed approach achieves up to a 27.3% improvement in Fr\'echet inception distance across various diffusion-based models, demonstrating consistently strong performance on diverse datasets. It also shows robust effectiveness across different tasks, including image generation, text-to-image generation, and inpainting. These results demonstrate that explainable AI techniques can extend beyond interpretability to actively contribute to image refinement. The proposed framework offers a versatile and effective approach applicable to various diffusion models and tasks, significantly advancing the field of image synthesis. + oai:arXiv.org:2512.08774v1 + cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Agung Nugraha, Heungjun Im, Jihwan Lee + Seoyeon Lee, Gwangyeol Yu, Chaewon Kim, Jonghyuk Park - CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation - https://arxiv.org/abs/2512.06814 - arXiv:2512.06814v1 Announce Type: new -Abstract: Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such explanations must faithfully capture the classifier's internal decision making behavior, a property known as faithfulness. In this paper, we propose CAuSE (Causal Abstraction under Simulated Explanations), a novel framework to generate faithful NLEs for any pretrained multimodal classifier. We demonstrate that CAuSE generalizes across datasets and models through extensive empirical evaluations. Theoretically, we show that CAuSE, trained via interchange intervention, forms a causal abstraction of the underlying classifier. We further validate this through a redesigned metric for measuring causal faithfulness in multimodal settings. CAuSE surpasses other methods on this metric, with qualitative analysis reinforcing its advantages. We perform detailed error analysis to pinpoint the failure cases of CAuSE. For replicability, we make the codes available at https://github.com/newcodevelop/CAuSE - oai:arXiv.org:2512.06814v1 + Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages + https://arxiv.org/abs/2512.08777 + arXiv:2512.08777v1 Announce Type: new +Abstract: We propose a post-training method for lower-resource languages that preserves fluency of language models even when aligned by disfluent reward models. Preference-optimization is now a well-researched topic, but previous work has mostly addressed models for English and Chinese. Lower-resource languages lack both datasets written by native speakers and language models capable of generating fluent synthetic data. Thus, in this work, we focus on developing a fluent preference-aligned language model without any instruction-tuning data in the target language. Our approach uses an on-policy training method, which we compare with two common approaches: supervised finetuning on machine-translated data and multilingual finetuning. We conduct a case study on Norwegian Bokm{\aa}l and evaluate fluency through native-speaker assessments. The results show that the on-policy aspect is crucial and outperforms the alternatives without relying on any hard-to-obtain data. + oai:arXiv.org:2512.08777v1 cs.CL cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Dibyanayan Bandyopadhyay, Soham Bhattacharjee, Mohammed Hasanuzzaman, Asif Ekbal + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + David Samuel, Lilja {\O}vrelid, Erik Velldal, Andrey Kutuzov - MeshSplatting: Differentiable Rendering with Opaque Meshes - https://arxiv.org/abs/2512.06818 - arXiv:2512.06818v1 Announce Type: new -Abstract: Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain incompatible with mesh-based pipelines that power AR/VR and game engines. We present MeshSplatting, a mesh-based reconstruction approach that jointly optimizes geometry and appearance through differentiable rendering. By enforcing connectivity via restricted Delaunay triangulation and refining surface consistency, MeshSplatting creates end-to-end smooth, visually high-quality meshes that render efficiently in real-time 3D engines. On Mip-NeRF360, it boosts PSNR by +0.69 dB over the current state-of-the-art MiLo for mesh-based novel view synthesis, while training 2x faster and using 2x less memory, bridging neural rendering and interactive 3D graphics for seamless real-time scene interaction. The project page is available at https://meshsplatting.github.io/. - oai:arXiv.org:2512.06818v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + An Explainable AI Model for the Detecting Malicious Smart Contracts Based on EVM Opcode Based Features + https://arxiv.org/abs/2512.08782 + arXiv:2512.08782v1 Announce Type: new +Abstract: Hackers may create malicious solidity programs and deploy it in the Ethereum block chain. These malicious smart contracts try to attack legitimate programs by exploiting its vulnerabilities such as reentrancy, tx.origin attack, bad randomness, deligatecall and so on. This may lead to drain of the funds, denial of service and so on . Hence, it is necessary to identify and prevent the malicious smart contract before deploying it into the blockchain. In this paper, we propose an ML based malicious smart contract detection mechanism by analyzing the EVM opcodes. After balancing the opcode frequency dataset with SMOTE algorithm, we transformed opcode frequencies to the binary values (0,1) using an entropy based supervised binning method. Then, an explainable AI model is trained with the proposed binary opcode based features. From the implementations, we found that the proposed mechanism can detect 99% of malicious smart contracts with a false positive rate of only 0.01. Finally, we incorporated LIME algorithm in our classifier to justify its predictions. We found that, LIME algorithm can explain why a particular smart contract app is declared as malicious by our ML classifier based on the binary value of EVM opcodes. + oai:arXiv.org:2512.08782v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Jan Held, Sanghyun Son, Renaud Vandeghen, Daniel Rebain, Matheus Gadelha, Yi Zhou, Anthony Cioppa, Ming C. Lin, Marc Van Droogenbroeck, Andrea Tagliasacchi + Roopak Surendran - MagicSkin: Balancing Marker and Markerless Modes in Vision-Based Tactile Sensors with a Translucent Skin - https://arxiv.org/abs/2512.06829 - arXiv:2512.06829v1 Announce Type: new -Abstract: Vision-based tactile sensors (VBTS) face a fundamental trade-off in marker and markerless design on the tactile skin: opaque ink markers enable measurement of force and tangential displacement but completely occlude geometric features necessary for object and texture classification, while markerless skin preserves surface details but struggles in measuring tangential displacements effectively. Current practice to solve the above problem via UV lighting or virtual transfer using learning-based models introduces hardware complexity or computing burdens. This paper introduces MagicSkin, a novel tactile skin with translucent, tinted markers balancing the modes of marker and markerless for VBTS. It enables simultaneous tangential displacement tracking, force prediction, and surface detail preservation. This skin is easy to plug into GelSight-family sensors without requiring additional hardware or software tools. We comprehensively evaluate MagicSkin in downstream tasks. The translucent markers impressively enhance rather than degrade sensing performance compared with traditional markerless and inked marker design: it achieves best performance in object classification (99.17\%), texture classification (93.51\%), tangential displacement tracking (97\% point retention) and force prediction (66\% improvement in total force error). These experimental results demonstrate that translucent skin eliminates the traditional performance trade-off in marker or markerless modes, paving the way for multimodal tactile sensing essential in tactile robotics. See videos at this \href{https://zhuochenn.github.io/MagicSkin_project/}{link}. - oai:arXiv.org:2512.06829v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + LoFA: Learning to Predict Personalized Priors for Fast Adaptation of Visual Generative Models + https://arxiv.org/abs/2512.08785 + arXiv:2512.08785v1 Announce Type: new +Abstract: Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization. While a few hypernetwork-based approaches attempt to predict adaptation weights directly, they struggle to map fine-grained user prompts to complex LoRA distributions, limiting their practical applicability. To bridge this gap, we propose LoFA, a general framework that efficiently predicts personalized priors for fast model adaptation. We first identify a key property of LoRA: structured distribution patterns emerge in the relative changes between LoRA and base model parameters. Building on this, we design a two-stage hypernetwork: first predicting relative distribution patterns that capture key adaptation regions, then using these to guide final LoRA weight prediction. Extensive experiments demonstrate that our method consistently predicts high-quality personalized priors within seconds, across multiple tasks and user prompts, even outperforming conventional LoRA that requires hours of processing. Project page: https://jaeger416.github.io/lofa/. + oai:arXiv.org:2512.08785v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Oluwatimilehin Tijani, Zhuo Chen, Jiankang Deng, Shan Luo + Yiming Hao, Mutian Xu, Chongjie Ye, Jie Qin, Shunlin Lu, Yipeng Qin, Xiaoguang Han - Inverse Discrete Elastic Rod - https://arxiv.org/abs/2512.06830 - arXiv:2512.06830v1 Announce Type: new -Abstract: Inverse design of slender elastic structures underlies a wide range of applications in computer graphics, flexible electronics, biomedical devices, and soft robotics. Traditional optimization-based approaches, however, are often orders of magnitude slower than forward dynamic simulations and typically impose restrictive boundary conditions. In this work, we present an inverse discrete elastic rods (inverse-DER) method that enables efficient and accurate inverse design under general loading and boundary conditions. By reformulating the inverse problem as a static equilibrium in the reference configuration, our method attains computational efficiency comparable to forward simulations while preserving high fidelity. This framework allows rapid determination of undeformed geometries for elastic fabrication structures that naturally deform into desired target shapes upon actuation or loading. We validate the approach through both physical prototypes and forward simulations, demonstrating its accuracy, robustness, and potential for real-world design applications. - oai:arXiv.org:2512.06830v1 - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 + A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs + https://arxiv.org/abs/2512.08786 + arXiv:2512.08786v1 Announce Type: new +Abstract: This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We introduce a comprehensive evaluation framework that systematically assesses the trade-off between alignment quality and fairness when using different aggregation strategies for human preferences. In our federated setting, each group locally evaluates rollouts and produces reward signals, and the server aggregates these group-level rewards without accessing any raw data. Specifically, we evaluate standard reward aggregation techniques (min, max, and average) and introduce a novel adaptive scheme that dynamically adjusts preference weights based on a group's historical alignment performance. Our experiments on question-answering (Q/A) tasks using a PPO-based RLHF pipeline demonstrate that our adaptive approach consistently achieves superior fairness while maintaining competitive alignment scores. This work offers a robust methodology for evaluating LLM behavior across diverse populations and provides a practical solution for developing truly pluralistic and fairly aligned models. + oai:arXiv.org:2512.08786v1 + cs.CL + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jiahao Li, Mingchao Liu, Haiyi Liang, HengAn Wu, Weicheng Huang + http://creativecommons.org/licenses/by/4.0/ + Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki - Soft state reduction of fuzzy automata over residuated lattices - https://arxiv.org/abs/2512.06832 - arXiv:2512.06832v1 Announce Type: new -Abstract: State reduction of finite automata plays a significant role in improving efficiency in formal verification, pattern recognition, and machine learning, where automata-based models are widely used. While deterministic automata have well-defined minimization procedures, reducing states in nondeterministic fuzzy finite automata (FfAs) remains challenging, especially for FfAs over non-locally finite residuated lattices like the product and Hamacher structures. This work introduces soft state reduction, an approximate method that leverages a small threshold $\varepsilon$ possibly combined with a word length bound $k$ to balance reduction accuracy and computational feasibility. By omitting fuzzy values smaller than $\varepsilon$, the underlying residuated lattice usually becomes locally finite, making computations more tractable. We introduce and study approximate invariances, which are fuzzy relations that allow merging of almost equivalent states of an FfA up to a tolerance level $\varepsilon$ and, optionally, to words of bounded length $k$. We further present an algorithm which iteratively applies such invariances to achieve reduction while preserving approximate language equivalence. Our method effectively reduces FfAs where existing techniques fail. - oai:arXiv.org:2512.06832v1 - cs.FL - Tue, 09 Dec 2025 00:00:00 -0500 + Exploring the Grassroots Understanding and Practices of Collective Memory Co-Contribution in a University Community + https://arxiv.org/abs/2512.08787 + arXiv:2512.08787v1 Announce Type: new +Abstract: Collective memory -- community members' interconnected memories and impressions of the group -- is essential to the community's culture and identity. Its development requires members' continuous participatory contribution and sensemaking. However, existing works mainly adopt a holistic sociological perspective to analyze well-developed collective memory, less focusing on member-level conceptualization of this possession or what the co-contribution practices can be. Therefore, this work alternatively adopts the latter perspective and probes such interpretative and interactional patterns with two mobile systems. With one being a locative narrative and exploration system condensed from existing literature's design frameworks, and the other being a conventional online forum representing current practices, they served as the anchors of observation for our two-week, mixed-methods field study (n=38) on a university campus. A core debate we have identified was to retrospectively contemplate or document the presence as a history for the future. This also subsequently impacted the narrative focuses, expectations of collective memory constituents, and the ways participants seek inspiration from the group. We further extracted design considerations that could better embrace the diverse conceptualizations of collective memory and bond different community members together. Lastly, revisiting and reflecting on our design, we provided extra insights on designing devoted locative narrative experiences for community-driven UGC platforms. + oai:arXiv.org:2512.08787v1 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Linh Anh Nguyen, Son Thanh Cao, Stefan Stanimirovi\'c + http://creativecommons.org/licenses/by-sa/4.0/ + Zeyu Huang, Xinyi Cao, Yue Deng, Junze Li, Kangyu Yuan, Xiaojuan Ma - COIVis: Eye tracking-based Visual Exploration of Concept Learning in MOOC Videos - https://arxiv.org/abs/2512.06834 - arXiv:2512.06834v1 Announce Type: new -Abstract: Massive Open Online Courses (MOOCs) make high-quality instruction accessible. However, the lack of face-to-face interaction makes it difficult for instructors to obtain feedback on learners' performance and provide more effective instructional guidance. Traditional analytical approaches, such as clickstream logs or quiz scores, capture only coarse-grained learning outcomes and offer limited insight into learners' moment-to-moment cognitive states. In this study, we propose COIVis, an eye tracking-based visual analytics system that supports concept-level exploration of learning processes in MOOC videos. COIVis first extracts course concepts from multimodal video content and aligns them with the temporal structure and screen space of the lecture, defining Concepts of Interest (COIs), which anchor abstract concepts to specific spatiotemporal regions. Learners' gaze trajectories are transformed into COI sequences, and five interpretable learner-state features -- Attention, Cognitive Load, Interest, Preference, and Synchronicity -- are computed at the COI level based on eye tracking metrics. Building on these representations, COIVis provides a narrative, multi-view visualization enabling instructors to move from cohort-level overviews to individual learning paths, quickly locate problematic concepts, and compare diverse learning strategies. We evaluate COIVis through two case studies and in-depth user-feedback interviews. The results demonstrate that COIVis effectively provides instructors with valuable insights into the consistency and anomalies of learners' learning patterns, thereby supporting timely and personalized interventions for learners and optimizing instructional design. - oai:arXiv.org:2512.06834v1 - cs.HC - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 + MatteViT: High-Frequency-Aware Document Shadow Removal with Shadow Matte Guidance + https://arxiv.org/abs/2512.08789 + arXiv:2512.08789v1 Announce Type: new +Abstract: Document shadow removal is essential for enhancing the clarity of digitized documents. Preserving high-frequency details (e.g., text edges and lines) is critical in this process because shadows often obscure or distort fine structures. This paper proposes a matte vision transformer (MatteViT), a novel shadow removal framework that applies spatial and frequency-domain information to eliminate shadows while preserving fine-grained structural details. To effectively retain these details, we employ two preservation strategies. First, our method introduces a lightweight high-frequency amplification module (HFAM) that decomposes and adaptively amplifies high-frequency components. Second, we present a continuous luminance-based shadow matte, generated using a custom-built matte dataset and shadow matte generator, which provides precise spatial guidance from the earliest processing stage. These strategies enable the model to accurately identify fine-grained regions and restore them with high fidelity. Extensive experiments on public benchmarks (RDD and Kligler) demonstrate that MatteViT achieves state-of-the-art performance, providing a robust and practical solution for real-world document shadow removal. Furthermore, the proposed method better preserves text-level details in downstream tasks, such as optical character recognition, improving recognition performance over prior methods. + oai:arXiv.org:2512.08789v1 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Zhiguang Zhou, Ruiqi Yu, Yuming Ma, Hao Ni, Guojun Li, Li Ye, Xiaoying Wang, Yize Li, Yong Wang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Chaewon Kim, Seoyeon Lee, Jonghyuk Park - Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning - https://arxiv.org/abs/2512.06835 - arXiv:2512.06835v1 Announce Type: new -Abstract: Recent vision-language models (VLMs) achieve remarkable reasoning through reinforcement learning (RL), which provides a feasible solution for realizing continuous self-evolving large vision-language models (LVLMs) in the era of experience. However, RL for VLMs requires abundant high-quality multimodal data, especially challenging in specialized domains like chemistry, earth sciences, and multimodal mathematics. Existing strategies such as synthetic data and self-rewarding mechanisms suffer from limited distributions and alignment difficulties, ultimately causing reward hacking: models exploit high-reward patterns, collapsing policy entropy and destabilizing training. We propose DoGe (Decouple to Generalize), a dual-decoupling framework that guides models to first learn from context rather than problem solving by refocusing on the problem context scenarios overlooked by synthetic data methods. By decoupling learning process into dual components (Thinker and Solver), we reasonably quantify the reward signals of this process and propose a two-stage RL post-training approach from freely exploring context to practically solving tasks. Second, to increase the diversity of training data, DoGe constructs an evolving curriculum learning pipeline: an expanded native domain knowledge corpus and an iteratively evolving seed problems pool. Experiments show that our method consistently outperforms the baseline across various benchmarks, providing a scalable pathway for realizing self-evolving LVLMs. - oai:arXiv.org:2512.06835v1 + Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization? + https://arxiv.org/abs/2512.08798 + arXiv:2512.08798v1 Announce Type: new +Abstract: Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN for tabular data and its recent extension to time series, we investigate whether graph node classification can be effectively reformulated as a tabular learning problem. We introduce TabPFN-GN, which transforms graph data into tabular features by extracting node attributes, structural properties, positional encodings, and optionally smoothed neighborhood features. This enables TabPFN to perform direct node classification without any graph-specific training or language model dependencies. Our experiments on 12 benchmark datasets reveal that TabPFN-GN achieves competitive performance with GNNs on homophilous graphs and consistently outperforms them on heterophilous graphs. These results demonstrate that principled feature engineering can bridge the gap between tabular and graph domains, providing a practical alternative to task-specific GNN training and LLM-dependent graph foundation models. + oai:arXiv.org:2512.08798v1 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tingyu Li, Zheng Sun, Jingxuan Wei, Siyuan Li, Conghui He, Lijun Wu, Cheng Tan + Jeongwhan Choi, Woosung Kang, Minseo Kim, Jongwoo Kim, Noseong Park - Leveraging LLMs to support co-evolution between definitions and instances of textual DSLs - https://arxiv.org/abs/2512.06836 - arXiv:2512.06836v1 Announce Type: new -Abstract: Software languages evolve over time for various reasons, such as the addition of new features. When the language's grammar definition evolves, textual instances that originally conformed to the grammar become outdated. For DSLs in a model-driven engineering context, there exists a plethora of techniques to co-evolve models with the evolving metamodel. However, these techniques are not geared to support DSLs with a textual syntax -- applying them to textual language definitions and instances may lead to the loss of information from the original instances, such as comments and layout information, which are valuable for software comprehension and maintenance. This study explores the potential of Large Language Model (LLM)-based solutions in achieving grammar and instance co-evolution, with attention to their ability to preserve auxiliary information when directly processing textual instances. By applying two advanced language models, Claude-3.5 and GPT-4o, and conducting experiments across seven case languages, we evaluated the feasibility and limitations of this approach. Our results indicate a good ability of the considered LLMs for migrating textual instances in small-scale cases with limited instance size, which are representative of a subset of cases encountered in practice. In addition, we observe significant challenges with the scalability of LLM-based solutions to larger instances, leading to insights that are useful for informing future research. - oai:arXiv.org:2512.06836v1 - cs.SE + Democratizing ML for Enterprise Security: A Self-Sustained Attack Detection Framework + https://arxiv.org/abs/2512.08802 + arXiv:2512.08802v1 Announce Type: new +Abstract: Despite advancements in machine learning for security, rule-based detection remains prevalent in Security Operations Centers due to the resource intensiveness and skill gap associated with ML solutions. While traditional rule-based methods offer efficiency, their rigidity leads to high false positives or negatives and requires continuous manual maintenance. This paper proposes a novel, two-stage hybrid framework to democratize ML-based threat detection. The first stage employs intentionally loose YARA rules for coarse-grained filtering, optimized for high recall. The second stage utilizes an ML classifier to filter out false positives from the first stage's output. To overcome data scarcity, the system leverages Simula, a seedless synthetic data generation framework, enabling security analysts to create high-quality training datasets without extensive data science expertise or pre-labeled examples. A continuous feedback loop incorporates real-time investigation results to adaptively tune the ML model, preventing rule degradation. + This proposed model with active learning has been rigorously tested for a prolonged time in a production environment spanning tens of thousands of systems. The system handles initial raw log volumes often reaching 250 billion events per day, significantly reducing them through filtering and ML inference to a handful of daily tickets for human investigation. Live experiments over an extended timeline demonstrate a general improvement in the model's precision over time due to the active learning feature. This approach offers a self-sustained, low-overhead, and low-maintenance solution, allowing security professionals to guide model learning as expert ``teachers''. + oai:arXiv.org:2512.08802v1 + cs.CR cs.AI - cs.PL - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Weixing Zhang, Regina Hebig, Daniel Str\"uber + http://creativecommons.org/licenses/by/4.0/ + Sadegh Momeni, Ge Zhang, Birkett Huber, Hamza Harkous, Sam Lipton, Benoit Seguin, Yanis Pavlidis - Neural Factorization-based Bearing Fault Diagnosis - https://arxiv.org/abs/2512.06837 - arXiv:2512.06837v1 Announce Type: new -Abstract: This paper studies the key problems of bearing fault diagnosis of high-speed train. As the core component of the train operation system, the health of bearings is directly related to the safety of train operation. The traditional diagnostic methods are facing the challenge of insufficient diagnostic accuracy under complex conditions. To solve these problems, we propose a novel Neural Factorization-based Classification (NFC) framework for bearing fault diagnosis. It is built on two core idea: 1) Embedding vibration time series into multiple mode-wise latent feature vectors to capture diverse fault-related patterns; 2) Leveraging neural factorization principles to fuse these vectors into a unified vibration representation. This design enables effective mining of complex latent fault characteristics from raw time-series data. We further instantiate the framework with two models CP-NFC and Tucker-NFC based on CP and Tucker fusion schemes, respectively. Experimental results show that both models achieve superior diagnostic performance compared with traditional machine learning methods. The comparative analysis provides valuable empirical evidence and practical guidance for selecting effective diagnostic strategies in high-speed train bearing monitoring. - oai:arXiv.org:2512.06837v1 + Identifying counterfactual probabilities using bivariate distributions and uplift modeling + https://arxiv.org/abs/2512.08805 + arXiv:2512.08805v1 Announce Type: new +Abstract: Uplift modeling estimates the causal effect of an intervention as the difference between potential outcomes under treatment and control, whereas counterfactual identification aims to recover the joint distribution of these potential outcomes (e.g., "Would this customer still have churned had we given them a marketing offer?"). This joint counterfactual distribution provides richer information than the uplift but is harder to estimate. However, the two approaches are synergistic: uplift models can be leveraged for counterfactual estimation. We propose a counterfactual estimator that fits a bivariate beta distribution to predicted uplift scores, yielding posterior distributions over counterfactual outcomes. Our approach requires no causal assumptions beyond those of uplift modeling. Simulations show the efficacy of the approach, which can be applied, for example, to the problem of customer churn in telecom, where it reveals insights unavailable to standard ML or uplift models alone. + oai:arXiv.org:2512.08805v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhenhao Li, Xu Cheng, Yi Zhou + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Th\'eo Verhelst, Gianluca Bontempi - SparseCoop: Cooperative Perception with Kinematic-Grounded Queries - https://arxiv.org/abs/2512.06838 - arXiv:2512.06838v1 Announce Type: new -Abstract: Cooperative perception is critical for autonomous driving, overcoming the inherent limitations of a single vehicle, such as occlusions and constrained fields-of-view. However, current approaches sharing dense Bird's-Eye-View (BEV) features are constrained by quadratically-scaling communication costs and the lack of flexibility and interpretability for precise alignment across asynchronous or disparate viewpoints. While emerging sparse query-based methods offer an alternative, they often suffer from inadequate geometric representations, suboptimal fusion strategies, and training instability. In this paper, we propose SparseCoop, a fully sparse cooperative perception framework for 3D detection and tracking that completely discards intermediate BEV representations. Our framework features a trio of innovations: a kinematic-grounded instance query that uses an explicit state vector with 3D geometry and velocity for precise spatio-temporal alignment; a coarse-to-fine aggregation module for robust fusion; and a cooperative instance denoising task to accelerate and stabilize training. Experiments on V2X-Seq and Griffin datasets show SparseCoop achieves state-of-the-art performance. Notably, it delivers this with superior computational efficiency, low transmission cost, and strong robustness to communication latency. Code is available at https://github.com/wang-jh18-SVM/SparseCoop. - oai:arXiv.org:2512.06838v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + WikIPedia: Unearthing a 20-Year History of IPv6 Client Addressing + https://arxiv.org/abs/2512.08808 + arXiv:2512.08808v1 Announce Type: new +Abstract: Due to their article editing policies, Wikimedia sites like Wikipedia have become inadvertent time capsules for IPv6 addresses. When Wikimedia users make edits without signing into an account, their IP addresses are used in lieu of a username. Wikimedia site dumps therefore provide researchers with over two decades worth of timestamped client IPv6 addresses to understand address assignments and how they have changed over time and space. + In this work, we extract 19M unique IPv6 addresses from Wikimedia sites like Wikipedia that were used by editors from 2003 to 2024. We use these addresses to understand the prevalence of IPv6 in countries corresponding to Wikimedia site languages, how IPv6 adoption has grown over time, and the prevalence of EUI-64 addressing on client devices like desktops, laptops, and mobile phones. + oai:arXiv.org:2512.08808v1 + cs.NI + cs.SI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiahao Wang, Zhongwei Jiang, Wenchao Sun, Jiaru Zhong, Haibao Yu, Yuner Zhang, Chenyang Lu, Chuang Zhang, Lei He, Shaobing Xu, Jianqiang Wang + http://creativecommons.org/licenses/by/4.0/ + Erik Rye, Dave Levin - CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles - https://arxiv.org/abs/2512.06840 - arXiv:2512.06840v1 Announce Type: new -Abstract: Video anomaly detection (VAD) has long been studied as a crucial problem in public security and crime prevention. In recent years, weakly-supervised VAD (WVAD) have attracted considerable attention due to their easy annotation process and promising research results. While existing WVAD methods tackle mainly on static datasets, the possibility that the domain of data can vary has been neglected. To adapt such domain-shift, the continual learning (CL) perspective is required because otherwise additional training only with new coming data could easily cause performance degradation for previous data, i.e., forgetting. Therefore, we propose a brand-new approach, called Continual Anomaly Detection with Ensembles (CADE) that is the first work combining CL and WVAD viewpoints. Specifically, CADE uses the Dual-Generator(DG) to address data imbalance and label uncertainty in WVAD. We also found that forgetting exacerbates the "incompleteness'' where the model becomes biased towards certain anomaly modes, leading to missed detections of various anomalies. To address this, we propose to ensemble Multi-Discriminator (MD) that capture missed anomalies in past scenes due to forgetting, using multiple models. Extensive experiments show that CADE significantly outperforms existing VAD methods on the common multi-scene VAD datasets, such as ShanghaiTech and Charlotte Anomaly datasets. - oai:arXiv.org:2512.06840v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration + https://arxiv.org/abs/2512.08809 + arXiv:2512.08809v1 Announce Type: new +Abstract: With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior methods, relying on differential privacy within device-cloud collaboration frameworks, struggle to balance privacy and utility, exposing users to inference attacks or degrading fine-tuning performance. To address this, we propose PrivTune, an efficient and privacy-preserving fine-tuning framework via Split Learning (SL). The key idea of PrivTune is to inject crafted noise into token representations from the SL bottom model, making each token resemble the $n$-hop indirect neighbors. PrivTune formulates this as an optimization problem to compute the optimal noise vector, aligning with defense-utility goals. On this basis, it then adjusts the parameters (i.e., mean) of the $d_\chi$-Privacy noise distribution to align with the optimization direction and scales the noise according to token importance to minimize distortion. Experiments on five datasets (covering both classification and generation tasks) against three embedding inversion and three attribute inference attacks show that, using RoBERTa on the Stanford Sentiment Treebank dataset, PrivTune reduces the attack success rate to 10% with only a 3.33% drop in utility performance, outperforming state-of-the-art baselines. + oai:arXiv.org:2512.08809v1 + cs.CR + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Satoshi Hashimoto, Tatsuya Konishi, Tomoya Kaichi, Kazunori Matsumoto, Mori Kurokawa + http://creativecommons.org/licenses/by/4.0/ + Yi Liu, Weixiang Han, Chengjun Cai, Xingliang Yuan, Cong Wang - Pseudo Anomalies Are All You Need: Diffusion-Based Generation for Weakly-Supervised Video Anomaly Detection - https://arxiv.org/abs/2512.06845 - arXiv:2512.06845v1 Announce Type: new -Abstract: Deploying video anomaly detection in practice is hampered by the scarcity and collection cost of real abnormal footage. We address this by training without any real abnormal videos while evaluating under the standard weakly supervised split, and we introduce PA-VAD, a generation-driven approach that learns a detector from synthesized pseudo-abnormal videos paired with real normal videos, using only a small set of real normal images to drive synthesis. For synthesis, we select class-relevant initial images with CLIP and refine textual prompts with a vision-language model to improve fidelity and scene consistency before invoking a video diffusion model. For training, we mitigate excessive spatiotemporal magnitude in synthesized anomalies by an domain-aligned regularized module that combines domain alignment and memory usage-aware updates. Extensive experiments show that our approach reaches 98.2% on ShanghaiTech and 82.5% on UCF-Crime, surpassing the strongest real-abnormal method on ShanghaiTech by +0.6% and outperforming the UVAD state-of-the-art on UCF-Crime by +1.9%. The results demonstrate that high-accuracy anomaly detection can be obtained without collecting real anomalies, providing a practical path toward scalable deployment. - oai:arXiv.org:2512.06845v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Multicalibration for LLM-based Code Generation + https://arxiv.org/abs/2512.08810 + arXiv:2512.08810v1 Announce Type: new +Abstract: As AI-based code generation becomes widespread, researchers are investigating the calibration of code LLMs - ensuring their confidence scores faithfully represent the true likelihood of code correctness. To do so, we investigate multicalibration, which can capture additional factors about a coding problem, such as complexity, code length, or programming language used. We study four multicalibration approaches on three function synthesis benchmarks, using latest-generation code LLMs (Qwen3 Coder, GPT-OSS, DeepSeek-R1-Distill). Our results demonstrate that multicalibration can yield distinct improvements over both uncalibrated token likelihoods (+1.03 in skill score) and baseline calibrations (+0.37 in skill score). We study the influence of the aforementioned factors in ablations, and make our dataset (consisting of code generations, likelihoods, and correctness labels) available for future research on code LLM calibration. + oai:arXiv.org:2512.08810v1 + cs.SE + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Satoshi Hashimoto, Hitoshi Nishimura, Yanan Wang, Mori Kurokawa + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Viola Campos, Robin Kuschnereit, Adrian Ulges - CKG-LLM: LLM-Assisted Detection of Smart Contract Access Control Vulnerabilities Based on Knowledge Graphs - https://arxiv.org/abs/2512.06846 - arXiv:2512.06846v1 Announce Type: new -Abstract: Traditional approaches for smart contract analysis often rely on intermediate representations such as abstract syntax trees, control-flow graphs, or static single assignment form. However, these methods face limitations in capturing both semantic structures and control logic. Knowledge graphs, by contrast, offer a structured representation of entities and relations, enabling richer intermediate abstractions of contract code and supporting the use of graph query languages to identify rule-violating elements. This paper presents CKG-LLM, a framework for detecting access-control vulnerabilities in smart contracts. Leveraging the reasoning and code generation capabilities of large language models, CKG-LLM translates natural-language vulnerability patterns into executable queries over contract knowledge graphs to automatically locate vulnerable code elements. Experimental evaluation demonstrates that CKG-LLM achieves superior performance in detecting access-control vulnerabilities compared to existing tools. Finally, we discuss potential extensions of CKG-LLM as part of future research directions. - oai:arXiv.org:2512.06846v1 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Emovectors: assessing emotional content in jazz improvisations for creativity evaluation + https://arxiv.org/abs/2512.08812 + arXiv:2512.08812v1 Announce Type: new +Abstract: Music improvisation is fascinating to study, being essentially a live demonstration of a creative process. In jazz, musicians often improvise across predefined chord progressions (leadsheets). How do we assess the creativity of jazz improvisations? And can we capture this in automated metrics for creativity for current LLM-based generative systems? Demonstration of emotional involvement is closely linked with creativity in improvisation. Analysing musical audio, can we detect emotional involvement? This study hypothesises that if an improvisation contains more evidence of emotion-laden content, it is more likely to be recognised as creative. An embeddings-based method is proposed for capturing the emotional content in musical improvisations, using a psychologically-grounded classification of musical characteristics associated with emotions. Resulting 'emovectors' are analysed to test the above hypothesis, comparing across multiple improvisations. Capturing emotional content in this quantifiable way can contribute towards new metrics for creativity evaluation that can be applied at scale. + oai:arXiv.org:2512.08812v1 + cs.SD + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Xiaoqi Li, Hailu Kuang, Wenkai Li, Zongwei Li, Shipeng Ye + Anna Jordanous + + + Heterogeneity in Multi-Robot Environmental Monitoring for Resolving Time-Conflicting Tasks + https://arxiv.org/abs/2512.08813 + arXiv:2512.08813v1 Announce Type: new +Abstract: Multi-robot systems performing continuous tasks face a performance trade-off when interrupted by urgent, time-critical sub-tasks. We investigate this trade-off in a scenario where a team must balance area patrolling with locating an anomalous radio signal. To address this trade-off, we evaluate both behavioral heterogeneity through agent role specialization ("patrollers" and "searchers") and sensing heterogeneity (i.e., only the searchers can sense the radio signal). Through simulation, we identify the Pareto-optimal trade-offs under varying team compositions, with behaviorally heterogeneous teams demonstrating the most balanced trade-offs in the majority of cases. When sensing capability is restricted, heterogeneous teams with half of the sensing-capable agents perform comparably to homogeneous teams, providing cost-saving rationale for restricting sensor payload deployment. Our findings demonstrate that pre-deployment role and sensing specialization are powerful design considerations for multi-robot systems facing time-conflicting tasks, where varying the degree of behavioral heterogeneity can tune system performance toward either task. + oai:arXiv.org:2512.08813v1 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Connor York, Zachary R Madin, Paul O'Dowd, Edmund R Hunt - AquaFusionNet: Lightweight VisionSensor Fusion Framework for Real-Time Pathogen Detection and Water Quality Anomaly Prediction on Edge Devices - https://arxiv.org/abs/2512.06848 - arXiv:2512.06848v1 Announce Type: new -Abstract: Evidence from many low and middle income regions shows that microbial contamination in small scale drinking water systems often fluctuates rapidly, yet existing monitoring tools capture only fragments of this behaviour. Microscopic imaging provides organism level visibility, whereas physicochemical sensors reveal shortterm changes in water chemistry; in practice, operators must interpret these streams separately, making realtime decision-making unreliable. This study introduces AquaFusionNet, a lightweight cross-modal framework that unifies both information sources inside a single edge deployable model. Unlike prior work that treats microscopic detection and water quality prediction as independent tasks, AquaFusionNet learns the statistical dependencies between microbial appearance and concurrent sensor dynamics through a gated crossattention mechanism designed specifically for lowpower hardware. The framework is trained on AquaMicro12K, a new dataset comprising 12,846 annotated 1000 micrographs curated for drinking water contexts, an area where publicly accessible microscopic datasets are scarce. Deployed for six months across seven facilities in East Java, Indonesia, the system processed 1.84 million frames and consistently detected contamination events with 94.8% mAP@0.5 and 96.3% anomaly prediction accuracy, while operating at 4.8 W on a Jetson Nano. Comparative experiments against representative lightweight detectors show that AquaFusionNet provides higher accuracy at comparable or lower power, and field results indicate that cross-modal coupling reduces common failure modes of unimodal detectors, particularly under fouling, turbidity spikes, and inconsistent illumination. All models, data, and hardware designs are released openly to facilitate replication and adaptation in decentralized water safety infrastructures. - oai:arXiv.org:2512.06848v1 + Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts + https://arxiv.org/abs/2512.08814 + arXiv:2512.08814v1 Announce Type: new +Abstract: Understanding human personality is crucial for web applications such as personalized recommendation and mental health assessment. Existing studies on personality detection predominantly adopt a "posts -> user vector -> labels" modeling paradigm, which encodes social media posts into user representations for predicting personality labels (e.g., MBTI labels). While recent advances in large language models (LLMs) have improved text encoding capacities, these approaches remain constrained by limited supervision signals due to label scarcity, and under-specified semantic mappings between user language and abstract psychological constructs. We address these challenges by proposing ROME, a novel framework that explicitly injects psychological knowledge into personality detection. Inspired by standardized self-assessment tests, ROME leverages LLMs' role-play capability to simulate user responses to validated psychometric questionnaires. These generated question-level answers transform free-form user posts into interpretable, questionnaire-grounded evidence linking linguistic cues to personality labels, thereby providing rich intermediate supervision to mitigate label scarcity while offering a semantic reasoning chain that guides and simplifies the text-to-personality mapping learning. A question-conditioned Mixture-of-Experts module then jointly routes over post and question representations, learning to answer questionnaire items under explicit supervision. The predicted answers are summarized into an interpretable answer vector and fused with the user representation for final prediction within a multi-task learning framework, where question answering serves as a powerful auxiliary task for personality detection. Extensive experiments on two real-world datasets demonstrate that ROME consistently outperforms state-of-the-art baselines, achieving improvements (15.41% on Kaggle dataset). + oai:arXiv.org:2512.08814v1 cs.CL - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Sepyan Purnama Kristanto, Lutfi Hakim, Hermansyah + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yifan Lyu, Liang Zhang - Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT - https://arxiv.org/abs/2512.06849 - arXiv:2512.06849v1 Announce Type: new -Abstract: Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both lytic and blastic lesions often resemble benign degenerative changes. We introduce a weakly supervised method trained solely on vertebra-level healthy/malignant labels, without any lesion masks. The method combines a Diffusion Autoencoder (DAE) that produces a classifier-guided healthy edit of each vertebra with pixel-wise difference maps that propose candidate lesion regions. To determine which regions truly reflect malignancy, we introduce Hide-and-Seek Attribution: each candidate is revealed in turn while all others are hidden, the edited image is projected back to the data manifold by the DAE, and a latent-space classifier quantifies the isolated malignant contribution of that component. High-scoring regions form the final lytic or blastic segmentation. On held-out radiologist annotations, we achieve strong blastic/lytic performance despite no mask supervision (F1: 0.91/0.85; Dice: 0.87/0.78), exceeding baselines (F1: 0.79/0.67; Dice: 0.74/0.55). These results show that vertebra-level labels can be transformed into reliable lesion masks, demonstrating that generative editing combined with selective occlusion supports accurate weakly supervised segmentation in CT. - oai:arXiv.org:2512.06849v1 - cs.CV + Do Depth-Grown Models Overcome the Curse of Depth? An In-Depth Analysis + https://arxiv.org/abs/2512.08819 + arXiv:2512.08819v1 Announce Type: new +Abstract: Gradually growing the depth of Transformers during training can not only reduce training cost but also lead to improved reasoning performance, as shown by MIDAS (Saunshi et al., 2024). Thus far, however, a mechanistic understanding of these gains has been missing. In this work, we establish a connection to recent work showing that layers in the second half of non-grown, pre-layernorm Transformers contribute much less to the final output distribution than those in the first half - also known as the Curse of Depth (Sun et al., 2025, Csord\'as et al., 2025). Using depth-wise analyses, we demonstrate that growth via gradual middle stacking yields more effective utilization of model depth, alters the residual stream structure, and facilitates the formation of permutable computational blocks. In addition, we propose a lightweight modification of MIDAS that yields further improvements in downstream reasoning benchmarks. Overall, this work highlights how the gradual growth of model depth can lead to the formation of distinct computational circuits and overcome the limited depth utilization seen in standard non-grown models. + oai:arXiv.org:2512.08819v1 + cs.CL + cs.AI cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Matan Atad, Alexander W. Marka, Lisa Steinhelfer, Anna Curto-Vilalta, Yannik Leonhardt, Sarah C. Foreman, Anna-Sophia Walburga Dietrich, Robert Graf, Alexandra S. Gersing, Bjoern Menze, Daniel Rueckert, Jan S. Kirschke, Hendrik M\"oller + Ferdinand Kapl, Emmanouil Angelis, Tobias H\"oppe, Kaitlin Maile, Johannes von Oswald, Nino Scherrer, Stefan Bauer - Formal that "Floats" High: Formal Verification of Floating Point Arithmetic - https://arxiv.org/abs/2512.06850 - arXiv:2512.06850v1 Announce Type: new -Abstract: Formal verification of floating-point arithmetic remains challenging due to non-linear arithmetic behavior and the tight coupling between control and datapath logic. Existing approaches often rely on high-level C models for equivalence checking against Register Transfer Level (RTL) designs, but this introduces abstraction gaps, translation overhead, and limits scalability at the RTL level. To address these challenges, this paper presents a scalable methodology for verifying floating-point arithmetic using direct RTL-to-RTL model checking against a golden reference model. The approach adopts a divide-and conquer strategy that decomposes verification into modular stages, each captured by helper assertions and lemmas that collectively prove a main correctness theorem. Counterexample (CEX)-guided refinement is used to iteratively localize and resolve implementation defects, while targeted fault injection validates the robustness of the verification process against precision-critical datapath errors. To assess scalability and practicality, the methodology is extended with agentic AI-based formal property generation, integrating large language model (LLM)-driven automation with Human-in-the-Loop (HITL) refinement. Coverage analysis evaluates the effectiveness of the approach by comparing handwritten and AI-generated properties in both RTL-to-RTL model checking and standalone RTL verification settings. Results show that direct RTL-to-RTL model checking achieves higher coverage efficiency and requires fewer assertions than standalone verification, especially when combined with AI-generated properties refined through HITL guidance. - oai:arXiv.org:2512.06850v1 - cs.LO + Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning + https://arxiv.org/abs/2512.08820 + arXiv:2512.08820v1 Announce Type: new +Abstract: Recent research in Vision-Language Models (VLMs) has significantly advanced our capabilities in cross-modal reasoning. However, existing methods suffer from performance degradation with domain changes or require substantial computational resources for fine-tuning in new domains. To address this issue, we develop a new adaptation method for large vision-language models, called \textit{Training-free Dual Hyperbolic Adapters} (T-DHA). We characterize the vision-language relationship between semantic concepts, which typically has a hierarchical tree structure, in the hyperbolic space instead of the traditional Euclidean space. Hyperbolic spaces exhibit exponential volume growth with radius, unlike the polynomial growth in Euclidean space. We find that this unique property is particularly effective for embedding hierarchical data structures using the Poincar\'e ball model, achieving significantly improved representation and discrimination power. Coupled with negative learning, it provides more accurate and robust classifications with fewer feature dimensions. Our extensive experimental results on various datasets demonstrate that the T-DHA method significantly outperforms existing state-of-the-art methods in few-shot image recognition and domain generalization tasks. + oai:arXiv.org:2512.08820v1 + cs.CV cs.AI - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hansa Mohanty, Vaisakh Naduvodi Viswambharan, Deepak Narayan Gadde - - - A Chunked-Object Pattern for Multi-Region Large Payload Storage in Managed NoSQL Databases - https://arxiv.org/abs/2512.06852 - arXiv:2512.06852v1 Announce Type: new -Abstract: Many managed key-value and NoSQL databases - such as Amazon DynamoDB, Azure Cosmos DB, and Google Cloud Firestore - enforce strict maximum item sizes (e.g., 400 KB in DynamoDB). This constraint imposes significant architectural challenges for applications requiring low-latency, multi-region access to objects that exceed these limits. The standard industry recommendation is to offload payloads to object storage (e.g., Amazon S3) while retaining a pointer in the database. While cost-efficient, this "pointer pattern" introduces network overhead and exposes applications to non-deterministic replication lag between the database and the object store, creating race conditions in active-active architectures. - This paper presents a "chunked-object" pattern that persists large logical entities as sets of ordered chunks within the database itself. We precisely define the pattern and provide a reference implementation using Amazon DynamoDB Global Tables. The design generalizes to any key-value store with per-item size limits and multi-region replication. We evaluate the approach using telemetry from a production system processing over 200,000 transactions per hour. Results demonstrate that the chunked-object pattern eliminates cross-system replication lag hazards and reduces p99 cross-region time-to-consistency for 1 MB payloads by keeping data and metadata within a single consistency domain. - oai:arXiv.org:2512.06852v1 - cs.DB - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Manideep Reddy Chinthareddy + Yi Zhang, Chun-Wun Cheng, Junyi He, Ke Yu, Yushun Tang, Carola-Bibiane Sch\"onlieb, Zhihai He, Angelica I. Aviles-Rivero - ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design - https://arxiv.org/abs/2512.06854 - arXiv:2512.06854v1 Announce Type: new -Abstract: Power is the primary design objective of large-scale integrated circuits (ICs), especially for complex modern processors (i.e., CPUs). Accurate CPU power evaluation requires designers to go through the whole time-consuming IC implementation process, easily taking months. At the early design stage (e.g., architecture-level), classical power models are notoriously inaccurate. Recently, ML-based architecture-level power models have been proposed to boost accuracy, but the data availability is a severe challenge. Currently, there is no open-source dataset for this important ML application. A typical dataset generation process involves correct CPU design implementation and repetitive execution of power simulation flows, requiring significant design expertise, engineering effort, and execution time. Even private in-house datasets often fail to reflect realistic CPU design scenarios. In this work, we propose ArchPower, the first open-source dataset for architecture-level processor power modeling. We go through complex and realistic design flows to collect the CPU architectural information as features and the ground-truth simulated power as labels. Our dataset includes 200 CPU data samples, collected from 25 different CPU configurations when executing 8 different workloads. There are more than 100 architectural features in each data sample, including both hardware and event parameters. The label of each sample provides fine-grained power information, including the total design power and the power for each of the 11 components. Each power value is further decomposed into four fine-grained power groups: combinational logic power, sequential logic power, memory power, and clock power. ArchPower is available at https://github.com/hkust-zhiyao/ArchPower. - oai:arXiv.org:2512.06854v1 - cs.AR + CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale + https://arxiv.org/abs/2512.08826 + arXiv:2512.08826v1 Announce Type: new +Abstract: The rapid proliferation of generative components, such as LoRAs, has created a vast but unstructured ecosystem. Existing discovery methods depend on unreliable user descriptions or biased popularity metrics, hindering usability. We present CARLoS, a large-scale framework for characterizing LoRAs without requiring additional metadata. Analyzing over 650 LoRAs, we employ them in image generation over a variety of prompts and seeds, as a credible way to assess their behavior. Using CLIP embeddings and their difference to a base-model generation, we concisely define a three-part representation: Directions, defining semantic shift; Strength, quantifying the significance of the effect; and Consistency, quantifying how stable the effect is. Using these representations, we develop an efficient retrieval framework that semantically matches textual queries to relevant LoRAs while filtering overly strong or unstable ones, outperforming textual baselines in automated and human evaluations. While retrieval is our primary focus, the same representation also supports analyses linking Strength and Consistency to legal notions of substantiality and volition, key considerations in copyright, positioning CARLoS as a practical system with broader relevance for LoRA analysis. + oai:arXiv.org:2512.08826v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by-nc-sa/4.0/ - Qijun Zhang, Yao Lu, Mengming Li, Shang Liu, Zhiyao Xie + Shahar Sarfaty, Adi Haviv, Uri Hacohen, Niva Elkin-Koren, Roi Livni, Amit H. Bermano - JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models - https://arxiv.org/abs/2512.06859 - arXiv:2512.06859v1 Announce Type: new -Abstract: In this work, we present JT-DA-8B (JiuTian Data Analyst 8B), a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios. To address the lack of high-quality supervision in tabular reasoning scenarios, we construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables. An automatic pipeline is proposed to generate realistic multi-step analytical tasks involving reasoning patterns. The model is trained upon open-source JT-Coder-8B model, an 8B-parameter decoder-only foundation model trained from scratch. In the training stage, we leverage LLM-based scoring and workflow-aligned filtering to distill high-quality, table-centric data. Both supervised fine-tuning (SFT) and Reinforcement learning (RL) are adopted to optimize our model. Afterwards, a four-stage table reasoning workflow is proposed, including table preprocessing, table sensing, tool-integrated reasoning, and prompt engineering, to improve model interpretability and execution accuracy. Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks, demonstrating the effectiveness of data-centric generation and workflow-driven optimization. - oai:arXiv.org:2512.06859v1 + InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models + https://arxiv.org/abs/2512.08829 + arXiv:2512.08829v1 Announce Type: new +Abstract: Window attention and linear attention represent two principal strategies for mitigating the quadratic complexity and ever-growing KV cache in Vision-Language Models (VLMs). However, we observe that window-based VLMs suffer performance degradation when sequence length exceeds the window size, while linear attention underperforms on information-intensive tasks such as OCR and document understanding. To overcome these limitations, we propose InfiniteVL, a linear-complexity VLM architecture that synergizes sliding window attention (SWA) with Gated DeltaNet. For achieving competitive multimodal performance under constrained resources, we design a three-stage training strategy comprising distillation pretraining, instruction tuning, and long-sequence SFT. Remarkably, using less than 2\% of the training data required by leading VLMs, InfiniteVL not only substantially outperforms previous linear-complexity VLMs but also matches the performance of leading Transformer-based VLMs, while demonstrating effective long-term memory retention. Compared to similar-sized Transformer-based VLMs accelerated by FlashAttention-2, InfiniteVL achieves over 3.6\times inference speedup while maintaining constant latency and memory footprint. In streaming video understanding scenarios, it sustains a stable 24 FPS real-time prefill speed while preserving long-term memory cache. Code and models are available at https://github.com/hustvl/InfiniteVL. + oai:arXiv.org:2512.08829v1 + cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ce Chi, Xing Wang, Zhendong Wang, Xiaofan Liu, Ce Li, Zhiyan Song, Chen Zhao, Kexin Yang, Boshen Shi, Jingjing Yang, Chao Deng, Junlan Feng + Hongyuan Tao, Bencheng Liao, Shaoyu Chen, Haoran Yin, Qian Zhang, Wenyu Liu, Xinggang Wang - Omni-Referring Image Segmentation - https://arxiv.org/abs/2512.06862 - arXiv:2512.06862v1 Announce Type: new -Abstract: In this paper, we propose a novel task termed Omni-Referring Image Segmentation (OmniRIS) towards highly generalized image segmentation. Compared with existing unimodally conditioned segmentation tasks, such as RIS and visual RIS, OmniRIS supports the input of text instructions and reference images with masks, boxes or scribbles as omni-prompts. This property makes it can well exploit the intrinsic merits of both text and visual modalities, i.e., granular attribute referring and uncommon object grounding, respectively. Besides, OmniRIS can also handle various segmentation settings, such as one v.s. many and many v.s. many, further facilitating its practical use. To promote the research of OmniRIS, we also rigorously design and construct a large dataset termed OmniRef, which consists of 186,939 omni-prompts for 30,956 images, and establish a comprehensive evaluation system. Moreover, a strong and general baseline termed OmniSegNet is also proposed to tackle the key challenges of OmniRIS, such as omni-prompt encoding. The extensive experiments not only validate the capability of OmniSegNet in following omni-modal instructions, but also show the superiority of OmniRIS for highly generalized image segmentation. - oai:arXiv.org:2512.06862v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models + https://arxiv.org/abs/2512.08832 + arXiv:2512.08832v1 Announce Type: new +Abstract: With the increasing reliance on AI models for weather forecasting, it is imperative to evaluate their vulnerability to adversarial perturbations. This work introduces Weather Adaptive Adversarial Perturbation Optimization (WAAPO), a novel framework for generating targeted adversarial perturbations that are both effective in manipulating forecasts and stealthy to avoid detection. WAAPO achieves this by incorporating constraints for channel sparsity, spatial localization, and smoothness, ensuring that perturbations remain physically realistic and imperceptible. Using the ERA5 dataset and FourCastNet (Pathak et al. 2022), we demonstrate WAAPO's ability to generate adversarial trajectories that align closely with predefined targets, even under constrained conditions. Our experiments highlight critical vulnerabilities in AI-driven forecasting models, where small perturbations to initial conditions can result in significant deviations in predicted weather patterns. These findings underscore the need for robust safeguards to protect against adversarial exploitation in operational forecasting systems. + oai:arXiv.org:2512.08832v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Qiancheng Zheng, Yunhang Shen, Gen Luo, Baiyang Song, Xing Sun, Xiaoshuai Sun, Yiyi Zhou, Rongrong Ji + Association for the Advancement of Artificial Intelligence 2025 + Huzaifa Arif, Pin-Yu Chen, Alex Gittens, James Diffenderfer, Bhavya Kailkhura - Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training - https://arxiv.org/abs/2512.06864 - arXiv:2512.06864v1 Announce Type: new -Abstract: Video Instance Segmentation (VIS) faces significant annotation challenges due to its dual requirements of pixel-level masks and temporal consistency labels. While recent unsupervised methods like VideoCutLER eliminate optical flow dependencies through synthetic data, they remain constrained by the synthetic-to-real domain gap. We present AutoQ-VIS, a novel unsupervised framework that bridges this gap through quality-guided self-training. Our approach establishes a closed-loop system between pseudo-label generation and automatic quality assessment, enabling progressive adaptation from synthetic to real videos. Experiments demonstrate state-of-the-art performance with 52.6 $\text{AP}_{50}$ on YouTubeVIS-2019 $\texttt{val}$ set, surpassing the previous state-of-the-art VideoCutLER by 4.4%, while requiring no human annotations. This demonstrates the viability of quality-aware self-training for unsupervised VIS. We will release the code at https://github.com/wcbup/AutoQ-VIS. - oai:arXiv.org:2512.06864v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Interpolation in Knowledge Representation + https://arxiv.org/abs/2512.08833 + arXiv:2512.08833v1 Announce Type: new +Abstract: Craig interpolation and uniform interpolation have many applications in knowledge representation, including explainability, forgetting, modularization and reuse, and even learning. At the same time, many relevant knowledge representation formalisms do in general not have Craig or uniform interpolation, and computing interpolants in practice is challenging. We have a closer look at two prominent knowledge representation formalisms, description logics and logic programming, and discuss theoretical results and practical methods for computing interpolants. + oai:arXiv.org:2512.08833v1 + cs.AI + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Kaixuan Lu, Mehmet Onurcan Kaya, Dim P. Papadopoulos + Jean Christoph Jung, Patrick Koopmann, Matthias Knorr - Spatial Retrieval Augmented Autonomous Driving - https://arxiv.org/abs/2512.06865 - arXiv:2512.06865v1 Announce Type: new -Abstract: Existing autonomous driving systems rely on onboard sensors (cameras, LiDAR, IMU, etc) for environmental perception. However, this paradigm is limited by the drive-time perception horizon and often fails under limited view scope, occlusion or extreme conditions such as darkness and rain. In contrast, human drivers are able to recall road structure even under poor visibility. To endow models with this ``recall" ability, we propose the spatial retrieval paradigm, introducing offline retrieved geographic images as an additional input. These images are easy to obtain from offline caches (e.g, Google Maps or stored autonomous driving datasets) without requiring additional sensors, making it a plug-and-play extension for existing AD tasks. - For experiments, we first extend the nuScenes dataset with geographic images retrieved via Google Maps APIs and align the new data with ego-vehicle trajectories. We establish baselines across five core autonomous driving tasks: object detection, online mapping, occupancy prediction, end-to-end planning, and generative world modeling. Extensive experiments show that the extended modality could enhance the performance of certain tasks. We will open-source dataset curation code, data, and benchmarks for further study of this new autonomous driving paradigm. - oai:arXiv.org:2512.06865v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + "Nothing about us without us": Perspectives of Global Deaf and Hard-of-hearing Community Members on Sign Language Technologies + https://arxiv.org/abs/2512.08839 + arXiv:2512.08839v1 Announce Type: new +Abstract: There is accelerating interest in sign language technologies (SLTs), with increasing attention from both industry and academia. However, the perspectives of Deaf and Hard-of-hearing (DHH) individuals remain marginalized in their development, particularly those outside of the West and in the global South. This paper presents findings from a global, multilingual survey capturing community views on SLTs across a wide range of countries, sign languages, and cultural contexts. While participants recognized the potential of SLTs to support access and independence, many expressed concerns about cultural erasure, inaccurate translation, and hearing-dominated research pipelines. Perceptions of SLTs were shaped by factors including sign language proficiency, policy exposure, and deaf identity. Across regions, participants emphasized the importance of DHH-led design, citing the risk of harm when DHH communities are excluded from technological decision-making. This study offers a novel cross-continental, community-informed analysis of SLTs and concludes with actionable recommendations for researchers, technologists, and policymakers. + oai:arXiv.org:2512.08839v1 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Xiaosong Jia, Chenhe Zhang, Yule Jiang, Songbur Wong, Zhiyuan Zhang, Chen Chen, Shaofeng Zhang, Xuanhe Zhou, Xue Yang, Junchi Yan, Yu-Gang Jiang + http://creativecommons.org/licenses/by/4.0/ + Katherine Atwell, Saki Imai, Danielle Bragg, Malihe Alikhani - Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior - https://arxiv.org/abs/2512.06866 - arXiv:2512.06866v1 Announce Type: new -Abstract: Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long videos. While existing keyframe sampling methods can improve temporal modeling efficiency, additional computational cost is introduced before feature encoding, and the binary frame selection paradigm is found suboptimal. Therefore, in this work, we propose Dynamic Token compression via LLM-guided Keyframe prior (DyToK), a training-free paradigm that enables dynamic token compression by harnessing VLLMs' inherent attention mechanisms. Our analysis reveals that VLLM attention layers naturally encoding query-conditioned keyframe priors, by which DyToK dynamically adjusts per-frame token retention ratios, prioritizing semantically rich frames while suppressing redundancies. Extensive experiments demonstrate that DyToK achieves state-of-the-art efficiency-accuracy tradeoffs. DyToK shows plug-and-play compatibility with existing compression methods, such as VisionZip and FastV, attaining 4.3x faster inference while preserving accuracy across multiple VLLMs, such as LLaVA-OneVision and Qwen2.5-VL. Code is available at https://github.com/yu-lin-li/DyToK . - oai:arXiv.org:2512.06866v1 - cs.CV - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Space-time discretization for barotropic flow stemming from a multisymplectic variational formulation + https://arxiv.org/abs/2512.08841 + arXiv:2512.08841v1 Announce Type: new +Abstract: This study proposes and analyses a novel higher-order, structure preserving discretization method for inviscid barotropic flows from a Lagrangian perspective. The method is built on a multisymplectic variational principle discretized over a full space-time domain. Flow variables are encoded on a staggered space-time mesh, leveraging the principles of mimetic spectral element discretization. Unlike standard Lagrangian methods, which are prone to mesh distortion, this framework computes fluid deformations in a fixed reference configuration and systematically maps them to the physical domain via the Piola-Kirchhoff stress. Further, the structure preserving design ensures that the discrete analogues of the fundamental conservation laws for mass, momentum, and energy are satisfied up to machine precision. The formulation also inherently handles low-Mach number flows without specialized preconditioning. Numerical experiments on expansion and compression flows confirm the accuracy, stability, and exact conservation properties of the discretization. + oai:arXiv.org:2512.08841v1 + math.NA + cs.NA + physics.flu-dyn + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Yulin Li, Haokun Gui, Ziyang Fan, Junjie Wang, Bin Kang, Bin Chen, Zhuotao Tian + http://creativecommons.org/licenses/by/4.0/ + Mukthesh Mahadev, Marc Gerritsma - Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game? - https://arxiv.org/abs/2512.06867 - arXiv:2512.06867v1 Announce Type: new -Abstract: Although persona prompting in large language models appears to trigger different styles of generated text, it is unclear whether these translate into measurable behavioral differences, much less whether they affect decision-making in an adversarial strategic environment that we provide as open-source. We investigate the impact of persona prompting on strategic performance in PERIL, a world-domination board game. Specifically, we compare the effectiveness of persona-derived heuristic strategies to those chosen manually. Our findings reveal that certain personas associated with strategic thinking improve game performance, but only when a mediator is used to translate personas into heuristic values. We introduce this mediator as a structured translation process, inspired by exploratory factor analysis, that maps LLM-generated inventory responses into heuristics. Results indicate our method enhances heuristic reliability and face validity compared to directly inferred heuristics, allowing us to better study the effect of persona types on decision making. These insights advance our understanding of how persona prompting influences LLM-based decision-making and propose a heuristic generation method that applies psychometric principles to LLMs. - oai:arXiv.org:2512.06867v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + A Methodology for Quantitative AI Risk Modeling + https://arxiv.org/abs/2512.08844 + arXiv:2512.08844v1 Announce Type: new +Abstract: Although general-purpose AI systems offer transformational opportunities in science and industry, they simultaneously raise critical concerns about safety, misuse, and potential loss of control. Despite these risks, methods for assessing and managing them remain underdeveloped. Effective risk management requires systematic modeling to characterize potential harms, as emphasized in frameworks such as the EU General-Purpose AI Code of Practice. This paper advances the risk modeling component of AI risk management by introducing a methodology that integrates scenario building with quantitative risk estimation, drawing on established approaches from other high-risk industries. Our methodology models risks through a six-step process: (1) defining risk scenarios, (2) decomposing them into quantifiable parameters, (3) quantifying baseline risk without AI models, (4) identifying key risk indicators such as benchmarks, (5) mapping these indicators to model parameters to estimate LLM uplift, and (6) aggregating individual parameters into risk estimates that enable concrete claims (e.g., X% probability of >\$Y in annual cyber damages). We examine the choices that underlie our methodology throughout the article, with discussions of strengths, limitations, and implications for future research. Our methodology is designed to be applicable to key systemic AI risks, including cyber offense, biological weapon development, harmful manipulation, and loss-of-control, and is validated through extensive application in LLM-enabled cyber offense. Detailed empirical results and cyber-specific insights are presented in a companion paper. + oai:arXiv.org:2512.08844v1 + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - John Licato, Stephen Steinle, Brayden Hollis + Malcolm Murray, Steve Barrett, Henry Papadatos, Otter Quarks, Matt Smith, Alejandro Tlaie Boria, Chlo\'e Touzet, Sim\'eon Campos - Dynamic Visual SLAM using a General 3D Prior - https://arxiv.org/abs/2512.06868 - arXiv:2512.06868v1 Announce Type: new -Abstract: Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is particularly challenging in dynamic natural environments, where scene dynamics can severely deteriorate camera pose estimation accuracy. In this work, we propose a novel monocular visual SLAM system that can robustly estimate camera poses in dynamic scenes. To this end, we leverage the complementary strengths of geometric patch-based online bundle adjustment and recent feed-forward reconstruction models. Specifically, we propose a feed-forward reconstruction model to precisely filter out dynamic regions, while also utilizing its depth prediction to enhance the robustness of the patch-based visual SLAM. By aligning depth prediction with estimated patches from bundle adjustment, we robustly handle the inherent scale ambiguities of the batch-wise application of the feed-forward reconstruction model. - oai:arXiv.org:2512.06868v1 - cs.RO + Generation is Required for Data-Efficient Perception + https://arxiv.org/abs/2512.08854 + arXiv:2512.08854v1 Announce Type: new +Abstract: It has been hypothesized that human-level visual perception requires a generative approach in which internal representations result from inverting a decoder. Yet today's most successful vision models are non-generative, relying on an encoder that maps images to representations without decoder inversion. This raises the question of whether generation is, in fact, necessary for machines to achieve human-level visual perception. To address this, we study whether generative and non-generative methods can achieve compositional generalization, a hallmark of human perception. Under a compositional data generating process, we formalize the inductive biases required to guarantee compositional generalization in decoder-based (generative) and encoder-based (non-generative) methods. We then show theoretically that enforcing these inductive biases on encoders is generally infeasible using regularization or architectural constraints. In contrast, for generative methods, the inductive biases can be enforced straightforwardly, thereby enabling compositional generalization by constraining a decoder and inverting it. We highlight how this inversion can be performed efficiently, either online through gradient-based search or offline through generative replay. We examine the empirical implications of our theory by training a range of generative and non-generative methods on photorealistic image datasets. We find that, without the necessary inductive biases, non-generative methods often fail to generalize compositionally and require large-scale pretraining or added supervision to improve generalization. By comparison, generative methods yield significant improvements in compositional generalization, without requiring additional data, by leveraging suitable inductive biases on a decoder along with search and replay. + oai:arXiv.org:2512.08854v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xingguang Zhong, Liren Jin, Marija Popovi\'c, Jens Behley, Cyrill Stachniss + Jack Brady, Bernhard Sch\"olkopf, Thomas Kipf, Simon Buchholz, Wieland Brendel - Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs - https://arxiv.org/abs/2512.06869 - arXiv:2512.06869v1 Announce Type: new -Abstract: Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations. We define this phenomenon as cumulative contextual decay - a progressive degradation of contextual integrity caused by attention pollution, dilution, and drift. To address this challenge, we propose Rhea (Role-aware Heuristic Episodic Attention), a novel framework that decouples conversation history into two functionally independent memory modules: (1) an Instructional Memory (IM) that persistently stores high-fidelity global constraints via a structural priority mechanism, and (2) an Episodic Memory (EM) that dynamically manages user-model interactions via asymmetric noise control and heuristic context retrieval. During inference, Rhea constructs a high signal-to-noise context by applying its priority attention: selectively integrating relevant episodic information while always prioritizing global instructions. To validate this approach, experiments on multiple multi-turn conversation benchmarks - including MT-Eval and Long-MT-Bench+ - show that Rhea mitigates performance decay and improves overall accuracy by 1.04 points on a 10-point scale (a 16% relative gain over strong baselines). Moreover, Rhea maintains near-perfect instruction fidelity (IAR > 8.1) across long-horizon interactions. These results demonstrate that Rhea provides a principled and effective framework for building more precise, instruction-consistent conversational LLMs. - oai:arXiv.org:2512.06869v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Reinforcement Learning From State and Temporal Differences + https://arxiv.org/abs/2512.08855 + arXiv:2512.08855v1 Announce Type: new +Abstract: TD($\lambda$) with function approximation has proved empirically successful for some complex reinforcement learning problems. For linear approximation, TD($\lambda$) has been shown to minimise the squared error between the approximate value of each state and the true value. However, as far as policy is concerned, it is error in the relative ordering of states that is critical, rather than error in the state values. We illustrate this point, both in simple two-state and three-state systems in which TD($\lambda$)--starting from an optimal policy--converges to a sub-optimal policy, and also in backgammon. We then present a modified form of TD($\lambda$), called STD($\lambda$), in which function approximators are trained with respect to relative state values on binary decision problems. A theoretical analysis, including a proof of monotonic policy improvement for STD($\lambda$) in the context of the two-state system, is presented, along with a comparison with Bertsekas' differential training method [1]. This is followed by successful demonstrations of STD($\lambda$) on the two-state system and a variation on the well known acrobot problem. + oai:arXiv.org:2512.08855v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Wanyang Hong, Zhaoning Zhang, Yi Chen, Libo Zhang, Baihui Liu, Linbo Qiao, Zhiliang Tian, Dongsheng Li + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Lex Weaver, Jonathan Baxter - Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective - https://arxiv.org/abs/2512.06870 - arXiv:2512.06870v1 Announce Type: new -Abstract: Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL). Despite its success, this paradigm can generate erroneous pseudo-labels, which are further amplified during training due to utilization of one-hot encoding. To address this issue, we propose ECOCSeg, a novel perspective for segmentation models that utilizes error-correcting output codes (ECOC) to create a fine-grained encoding for each class. ECOCSeg offers several advantages. First, an ECOC-based classifier is introduced, enabling model to disentangle classes into attributes and handle partial inaccurate bits, improving stability and generalization in pseudo-label learning. Second, a bit-level label denoising mechanism is developed to generate higher-quality pseudo-labels, providing adequate and robust supervision for unlabeled images. ECOCSeg can be easily integrated with existing methods and consistently demonstrates significant improvements on multiple UDA and SSL benchmarks across different segmentation architectures. Code is available at https://github.com/Woof6/ECOCSeg. - oai:arXiv.org:2512.06870v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Can the GPC standard eliminate consent banners in the EU? + https://arxiv.org/abs/2512.08856 + arXiv:2512.08856v1 Announce Type: new +Abstract: In the EU, the General Data Protection Regulation and the ePrivacy Directive mandate informed consent for behavioural advertising and use of tracking technologies. However, the ubiquity of consent banners and popups has led to widespread consent fatigue and questions regarding the effectiveness of these mechanisms in protecting users' data. In contrast, users in California and other US jurisdictions can utilize Global Privacy Control (GPC), a browser-based privacy signal that automatically broadcasts a legally binding opt-out request to websites. In this paper we explore whether, and to what extent, GPC can be adapted to the EU legal framework to mitigate consent fatigue and improve privacy protections for EU residents. + We analyse GPC as a technical specification standardized at the World Wide Web Consortium and examine its standing under current EU data protection law. Generally, GPC can be mapped to the various legal bases for processing under the GDPR. However, our evaluation also identifies friction between the GPC specification and EU data protection law as it stands. These discrepancies are resolvable and present an opportunity for EU legislators and regulators to interpret GPC in alignment with EU data protection requirements, particularly, considering the European Commission's recent Digital Omnibus proposal. We conclude that while GPC is not a silver bullet, its adoption -- supported by clear authoritative guidance and specification updates -- can offer a pragmatic path toward more automated and effective data protection in the EU. + oai:arXiv.org:2512.08856v1 + cs.CY + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wangkai Li, Rui Sun, Zhaoyang Li, Tianzhu Zhang + Sebastian Zimmeck, Harshvardhan J. Pandit, Frederik Zuiderveen Borgesius, Cristiana Teixeira Santos, Konrad Kollnig, Robin Berjon - An Analysis of Large Language Models for Simulating User Responses in Surveys - https://arxiv.org/abs/2512.06874 - arXiv:2512.06874v1 Announce Type: new -Abstract: Using Large Language Models (LLMs) to simulate user opinions has received growing attention. Yet LLMs, especially trained with reinforcement learning from human feedback (RLHF), are known to exhibit biases toward dominant viewpoints, raising concerns about their ability to represent users from diverse demographic and cultural backgrounds. In this work, we examine the extent to which LLMs can simulate human responses to cross-domain survey questions through direct prompting and chain-of-thought prompting. We further propose a claim diversification method CLAIMSIM, which elicits viewpoints from LLM parametric knowledge as contextual input. Experiments on the survey question answering task indicate that, while CLAIMSIM produces more diverse responses, both approaches struggle to accurately simulate users. Further analysis reveals two key limitations: (1) LLMs tend to maintain fixed viewpoints across varying demographic features, and generate single-perspective claims; and (2) when presented with conflicting claims, LLMs struggle to reason over nuanced differences among demographic features, limiting their ability to adapt responses to specific user profiles. - oai:arXiv.org:2512.06874v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + NecoFuzz: Effective Fuzzing of Nested Virtualization via Fuzz-Harness Virtual Machines + https://arxiv.org/abs/2512.08858 + arXiv:2512.08858v1 Announce Type: new +Abstract: Nested virtualization is now widely supported by major cloud vendors, allowing users to leverage virtualization-based technologies in the cloud. However, supporting nested virtualization significantly increases host hypervisor complexity and introduces a new attack surface in cloud platforms. While many prior studies have explored hypervisor fuzzing, none has explicitly addressed nested virtualization due to the challenge of generating effective virtual machine (VM) instances with a vast state space as fuzzing inputs. + We present NecoFuzz, the first fuzzing framework that systematically targets nested virtualization-specific logic in hypervisors. NecoFuzz synthesizes executable fuzz-harness VMs with internal states near the boundary between valid and invalid, guided by an approximate model of hardware-assisted virtualization specifications. Since vulnerabilities in nested virtualization often stem from incorrect handling of unexpected VM states, this specification-guided, boundary-oriented generation significantly improves coverage of security-critical code across different hypervisors. + We implemented NecoFuzz on Intel VT-x and AMD-V by extending AFL++ to support fuzz-harness VMs. NecoFuzz achieved 84.7% and 74.2% code coverage for nested virtualization-specific code on Intel VT-x and AMD-V, respectively, and uncovered six previously unknown vulnerabilities across three hypervisors, including two assigned CVEs. + oai:arXiv.org:2512.08858v1 + cs.OS + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Ziyun Yu, Yiru Zhou, Chen Zhao, Hongyi Wen + 10.1145/3767295.3769347 + Reima Ishii, Takaaki Fukai, Takahiro Shinagawa - Bridging Abstraction-Based Hierarchical Control and Moment Matching: A Conceptual Unification - https://arxiv.org/abs/2512.06875 - arXiv:2512.06875v1 Announce Type: new -Abstract: In this paper, we establish a relation between approximate-simulation-based hierarchical control (ASHC) and moment matching techniques, and build a conceptual bridge between these two frameworks. To this end, we study the two key requirements of the ASHC technique, namely the bounded output discrepancy and the $M$-relation, through the lens of moment matching. We show that, in the linear time-invariant case, both requirements can be interpreted in the moment matching perspective through certain system interconnection structures. Building this conceptual bridge provides a foundation for cross-pollination of ideas between these two frameworks. - oai:arXiv.org:2512.06875v1 - eess.SY - cs.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data + https://arxiv.org/abs/2512.08859 + arXiv:2512.08859v1 Announce Type: new +Abstract: We propose a text-to-IMU (inertial measurement unit) motion-synthesis framework to obtain realistic IMU data by fine-tuning a pretrained diffusion model with an acceleration-based second-order loss (L_acc). L_acc enforces consistency in the discrete second-order temporal differences of the generated motion, thereby aligning the diffusion prior with IMU-specific acceleration patterns. We integrate L_acc into the training objective of an existing diffusion model, finetune the model to obtain an IMU-specific motion prior, and evaluate the model with an existing text-to-IMU framework that comprises surface modelling and virtual sensor simulation. We analysed acceleration signal fidelity and differences between synthetic motion representation and actual IMU recordings. As a downstream application, we evaluated Human Activity Recognition (HAR) and compared the classification performance using data of our method with the earlier diffusion model and two additional diffusion model baselines. When we augmented the earlier diffusion model objective with L_acc and continued training, L_acc decreased by 12.7% relative to the original model. The improvements were considerably larger in high-dynamic activities (i.e., running, jumping) compared to low-dynamic activities~(i.e., sitting, standing). In a low-dimensional embedding, the synthetic IMU data produced by our refined model shifts closer to the distribution of real IMU recordings. HAR classification trained exclusively on our refined synthetic IMU data improved performance by 8.7% compared to the earlier diffusion model and by 7.6% over the best-performing comparison diffusion model. We conclude that acceleration-aware diffusion refinement provides an effective approach to align motion generation and IMU synthesis and highlights how flexible deep learning pipelines are for specialising generic text-to-motion priors to sensor-specific tasks. + oai:arXiv.org:2512.08859v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zirui Niu, Mohammad Fahim Shakib, Giordano Scarciotti + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Lars Ole H\"ausler, Lena Uhlenberg, G\"oran K\"ober, Diyora Salimova, Oliver Amft - SceneMixer: Exploring Convolutional Mixing Networks for Remote Sensing Scene Classification - https://arxiv.org/abs/2512.06877 - arXiv:2512.06877v1 Announce Type: new -Abstract: Remote sensing scene classification plays a key role in Earth observation by enabling the automatic identification of land use and land cover (LULC) patterns from aerial and satellite imagery. Despite recent progress with convolutional neural networks (CNNs) and vision transformers (ViTs), the task remains challenging due to variations in spatial resolution, viewpoint, orientation, and background conditions, which often reduce the generalization ability of existing models. To address these challenges, this paper proposes a lightweight architecture based on the convolutional mixer paradigm. The model alternates between spatial mixing through depthwise convolutions at multiple scales and channel mixing through pointwise operations, enabling efficient extraction of both local and contextual information while keeping the number of parameters and computations low. Extensive experiments were conducted on the AID and EuroSAT benchmarks. The proposed model achieved overall accuracy, average accuracy, and Kappa values of 74.7%, 74.57%, and 73.79 on the AID dataset, and 93.90%, 93.93%, and 93.22 on EuroSAT, respectively. These results demonstrate that the proposed approach provides a good balance between accuracy and efficiency compared with widely used CNN- and transformer-based models. Code will be publicly available on: https://github.com/mqalkhatib/SceneMixer - oai:arXiv.org:2512.06877v1 + Tri-Bench: Stress-Testing VLM Reliability on Spatial Reasoning under Camera Tilt and Object Interference + https://arxiv.org/abs/2512.08860 + arXiv:2512.08860v1 Announce Type: new +Abstract: Verifiable geometric reasoning is a critical component for trustworthy and controllable agentic AI. Despite impressive capabilities, Vision-Language Models (VLMs) often fail under realistic scene changes. We present Tri-Bench, a compact benchmark of planar triangle problems that isolates relative geometric reasoning while stressing two deployment-critical factors: camera pose (planar vs. tilted) and scene context via object interference (10 everyday objects). To test verifiability and control, we evaluate four recent VLMs using a single, fixed prompt whose guardrail explicitly describes a surrounding square border, enabling correct answers via homography. We evaluate six simple tasks over binary and continuous targets, and observe that the overall accuracy with respect to 3D ground truth is modest, ~69% on average (best ~75%, worst ~64%). The same responses align even more closely with 2D projections in the image plane, where mean accuracy is ~72%. All four VLMs consistently fail, with accuracy falling to ~0%, on recognizing minority shape classes (equilateral, isosceles, right-angled triangles). Additionally, overall VLM accuracy degrades by ~4.1% under camera tilt. This demonstrates that models fail to correctly utilize the explicit frame-of-reference hint provided in the prompt and default to 2D image plane cues. Finally, we find that object interference has no significant effect on VLM accuracy. + oai:arXiv.org:2512.08860v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Mohammed Q. Alkhatib, Ali Jamali, Swalpa Kumar Roy + Amit Bendkhale - WisPaper: Your AI Scholar Search Engine - https://arxiv.org/abs/2512.06879 - arXiv:2512.06879v1 Announce Type: new -Abstract: Researchers struggle to efficiently locate and manage relevant literature within the exponentially growing body of scientific publications. We present \textsc{WisPaper}, an intelligent academic retrieval and literature management platform that addresses this challenge through three integrated capabilities: (1) \textit{Scholar Search}, featuring both quick keyword-based and deep agentic search modes for efficient paper discovery; (2) \textit{Library}, a customizable knowledge base for systematic literature organization; and (3) \textit{AI Feeds}, an intelligent recommendation system that automatically delivers relevant new publications based on user interests. Unlike existing academic tools, \textsc{WisPaper} provides a closed-loop workflow that seamlessly connects literature discovery, management, and continuous tracking of research frontiers. Our multilingual and multidisciplinary system significantly reduces the time researchers from diverse backgrounds spend on paper screening and management, enabling them to focus on their core research activities. The platform is publicly accessible and serves researchers across academia and industry. - oai:arXiv.org:2512.06879v1 - cs.IR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Secure and Privacy-Preserving Federated Learning for Next-Generation Underground Mine Safety + https://arxiv.org/abs/2512.08862 + arXiv:2512.08862v1 Announce Type: new +Abstract: Underground mining operations depend on sensor networks to monitor critical parameters such as temperature, gas concentration, and miner movement, enabling timely hazard detection and safety decisions. However, transmitting raw sensor data to a centralized server for machine learning (ML) model training raises serious privacy and security concerns. Federated Learning (FL) offers a promising alternative by enabling decentralized model training without exposing sensitive local data. Yet, applying FL in underground mining presents unique challenges: (i) Adversaries may eavesdrop on shared model updates to launch model inversion or membership inference attacks, compromising data privacy and operational safety; (ii) Non-IID data distributions across mines and sensor noise can hinder model convergence. To address these issues, we propose FedMining--a privacy-preserving FL framework tailored for underground mining. FedMining introduces two core innovations: (1) a Decentralized Functional Encryption (DFE) scheme that keeps local models encrypted, thwarting unauthorized access and inference attacks; and (2) a balancing aggregation mechanism to mitigate data heterogeneity and enhance convergence. Evaluations on real-world mining datasets demonstrate FedMining's ability to safeguard privacy while maintaining high model accuracy and achieving rapid convergence with reduced communication and computation overhead. These advantages make FedMining both secure and practical for real-time underground safety monitoring. + oai:arXiv.org:2512.08862v1 + cs.CR + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Li Ju, Jun Zhao, Mingxu Chai, Ziyu Shen, Xiangyang Wang, Yage Geng, Chunchun Ma, Hao Peng, Guangbin Li, Tao Li, Chengyong Liao, Fu Wang, Xiaolong Wang, Junshen Chen, Rui Gong, Shijia Liang, Feiyan Li, Ming Zhang, Kexin Tan, Jujie Ye, Zhiheng Xi, Shihan Dou, Tao Gui, Yuankai Ying, Yang Shi, Yue Zhang, Qi Zhang + http://creativecommons.org/licenses/by-sa/4.0/ + Mohamed Elmahallawy, Sanjay Madria, Samuel Frimpong - Hierarchical Image-Guided 3D Point Cloud Segmentation in Industrial Scenes via Multi-View Bayesian Fusion - https://arxiv.org/abs/2512.06882 - arXiv:2512.06882v1 Announce Type: new -Abstract: Reliable 3D segmentation is critical for understanding complex scenes with dense layouts and multi-scale objects, as commonly seen in industrial environments. In such scenarios, heavy occlusion weakens geometric boundaries between objects, and large differences in object scale will cause end-to-end models fail to capture both coarse and fine details accurately. Existing 3D point-based methods require costly annotations, while image-guided methods often suffer from semantic inconsistencies across views. To address these challenges, we propose a hierarchical image-guided 3D segmentation framework that progressively refines segmentation from instance-level to part-level. Instance segmentation involves rendering a top-view image and projecting SAM-generated masks prompted by YOLO-World back onto the 3D point cloud. Part-level segmentation is subsequently performed by rendering multi-view images of each instance obtained from the previous stage and applying the same 2D segmentation and back-projection process at each view, followed by Bayesian updating fusion to ensure semantic consistency across views. Experiments on real-world factory data demonstrate that our method effectively handles occlusion and structural complexity, achieving consistently high per-class mIoU scores. Additional evaluations on public dataset confirm the generalization ability of our framework, highlighting its robustness, annotation efficiency, and adaptability to diverse 3D environments. - oai:arXiv.org:2512.06882v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse + https://arxiv.org/abs/2512.08864 + arXiv:2512.08864v1 Announce Type: new +Abstract: Advanced AI systems offer substantial benefits but also introduce risks. In 2025, AI-enabled cyber offense has emerged as a concrete example. This technical report applies a quantitative risk modeling methodology (described in full in a companion paper) to this domain. We develop nine detailed cyber risk models that allow analyzing AI uplift as a function of AI benchmark performance. Each model decomposes attacks into steps using the MITRE ATT&CK framework and estimates how AI affects the number of attackers, attack frequency, probability of success, and resulting harm to determine different types of uplift. To produce these estimates with associated uncertainty, we employ both human experts, via a Delphi study, as well as LLM-based simulated experts, both mapping benchmark scores (from Cybench and BountyBench) to risk model factors. Individual estimates are aggregated through Monte Carlo simulation. The results indicate systematic uplift in attack efficacy, speed, and target reach, with different mechanisms of uplift across risk models. We aim for our quantitative risk modeling to fulfill several aims: to help cybersecurity teams prioritize mitigations, AI evaluators design benchmarks, AI developers make more informed deployment decisions, and policymakers obtain information to set risk thresholds. Similar goals drove the shift from qualitative to quantitative assessment over time in other high-risk industries, such as nuclear power. We propose this methodology and initial application attempt as a step in that direction for AI risk management. While our estimates carry significant uncertainty, publishing detailed quantified results can enable experts to pinpoint exactly where they disagree. This helps to collectively refine estimates, something that cannot be done with qualitative assessments alone. + oai:arXiv.org:2512.08864v1 + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Yu Zhu, Naoya Chiba, Koichi Hashimoto + http://creativecommons.org/licenses/by/4.0/ + Steve Barrett, Malcolm Murray, Otter Quarks, Matthew Smith, Jakub Kry\'s, Sim\'eon Campos, Alejandro Tlaie Boria, Chlo\'e Touzet, Sevan Hayrapet, Fred Heiding, Omer Nevo, Adam Swanda, Jair Aguirre, Asher Brass Gershovich, Eric Clay, Ryan Fetterman, Mario Fritz, Marc Juarez, Vasilios Mavroudis, Henry Papadatos - Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation - https://arxiv.org/abs/2512.06883 - arXiv:2512.06883v1 Announce Type: new -Abstract: Multimodal recommendation enhances accuracy by leveraging visual and textual signals, and its success largely depends on learning high-quality cross-modal representations. Recent advances in Large Vision-Language Models (LVLMs) offer unified multimodal representation learning, making them a promising backbone. However, applying LVLMs to recommendation remains challenging due to (i) representation misalignment, where domain gaps between item data and general pre-training lead to unaligned embedding spaces, and (ii) gradient conflicts during fine-tuning, where shared adapters cause interference and a lack of discriminative power. To address this, we propose SDA, a lightweight framework for Structural and Disentangled Adaptation, which integrates two components: Cross-Modal Structural Alignment (CMSA) and Modality-Disentangled Adaptation. CMSA aligns embeddings using intra-modal structures as a soft teacher, while MoDA mitigates gradient conflicts via expertized, gated low-rank paths to disentangle gradient flows. Experiments on three public Amazon datasets show SDA integrates seamlessly with existing multimodal and sequential recommenders, yielding average gains of 6.15% in Hit@10 and 8.64% in NDCG@10. It also achieves up to 12.83% and 18.70% gains on long-tail items with minimal inference overhead. Our code and full experimental results are available at https://github.com/RaoZhongtao/SDA. - oai:arXiv.org:2512.06883v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 + SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA + https://arxiv.org/abs/2512.08867 + arXiv:2512.08867v1 Announce Type: new +Abstract: The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide natural language answers to knowledge-seeking questions during software development. To investigate its importance and to what extent it has been explored, we analyze real user-LLM dialogues from WildChat and find that: (1) The Dev Knowledge QA task accounts for 39.6% of interactions(highest among all tasks), revealing broad knowledge needs beyond code generation (32.3%). (2) Only 27.5% of real Dev Knowledge QA dialogues focus on code understanding, leaving out development knowledge-seeking. (3) Only 17.1% of real-world Dev Knowledge QA dialogues can be used for constructing a benchmark. Existing benchmarks have two primary limitations for evaluating the Dev Knowledge QA capability of LLMs. First, existing benchmarks offer a limited development knowledge scope, mainly focusing on code understanding and neglecting broader knowledge during development. Second, some benchmarks are not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual benchmark derived from real user dialogues. It contains 2,740 QA pairs in three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers for accurate and simple evaluation. Experiments show that: Code LLMs generally outperform general LLMs of similar scale; Knowledge injection with the Retrieval-Augmented Generation (RAG) strategy can boost LLM accuracy by 11.3% on average; LLMs show systematic overconfidence in Dev Knowledge QA, and the answering accuracy of LLMs shows a positive correlation with their stated confidence; Generally, LLMs with stronger code generation performance also exhibit stronger performance in Dev Knowledge QA. + oai:arXiv.org:2512.08867v1 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhongtao Rao, Peilin Zhou, Dading Chong, Zhiwei Chen, Shoujin Wang, Nan Tang + Jing Zhang, Lianghong Guo, Yanlin Wang, Mingwei Liu, Jiachi Chen, Yuchi Ma, Ensheng Shi, Terry Yue Zhuo, Hongyu Zhang, Zibin Zheng - JoPano: Unified Panorama Generation via Joint Modeling - https://arxiv.org/abs/2512.06885 - arXiv:2512.06885v1 Announce Type: new -Abstract: Panorama generation has recently attracted growing interest in the research community, with two core tasks, text-to-panorama and view-to-panorama generation. However, existing methods still face two major challenges: their U-Net-based architectures constrain the visual quality of the generated panoramas, and they usually treat the two core tasks independently, which leads to modeling redundancy and inefficiency. To overcome these challenges, we propose a joint-face panorama (JoPano) generation approach that unifies the two core tasks within a DiT-based model. To transfer the rich generative capabilities of existing DiT backbones learned from natural images to the panorama domain, we propose a Joint-Face Adapter built on the cubemap representation of panoramas, which enables a pretrained DiT to jointly model and generate different views of a panorama. We further apply Poisson Blending to reduce seam inconsistencies that often appear at the boundaries between cube faces. Correspondingly, we introduce Seam-SSIM and Seam-Sobel metrics to quantitatively evaluate the seam consistency. Moreover, we propose a condition switching mechanism that unifies text-to-panorama and view-to-panorama tasks within a single model. Comprehensive experiments show that JoPano can generate high-quality panoramas for both text-to-panorama and view-to-panorama generation tasks, achieving state-of-the-art performance on FID, CLIP-FID, IS, and CLIP-Score metrics. - oai:arXiv.org:2512.06885v1 - cs.CV + EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce + https://arxiv.org/abs/2512.08868 + arXiv:2512.08868v1 Announce Type: new +Abstract: Foundation agents have rapidly advanced in their ability to reason and interact with real environments, making the evaluation of their core capabilities increasingly important. While many benchmarks have been developed to assess agent performance, most concentrate on academic settings or artificially designed scenarios while overlooking the challenges that arise in real applications. To address this issue, we focus on a highly practical real-world setting, the e-commerce domain, which involves a large volume of diverse user interactions, dynamic market conditions, and tasks directly tied to real decision-making processes. To this end, we introduce EcomBench, a holistic E-commerce Benchmark designed to evaluate agent performance in realistic e-commerce environments. EcomBench is built from genuine user demands embedded in leading global e-commerce ecosystems and is carefully curated and annotated through human experts to ensure clarity, accuracy, and domain relevance. It covers multiple task categories within e-commerce scenarios and defines three difficulty levels that evaluate agents on key capabilities such as deep information retrieval, multi-step reasoning, and cross-source knowledge integration. By grounding evaluation in real e-commerce contexts, EcomBench provides a rigorous and dynamic testbed for measuring the practical capabilities of agents in modern e-commerce. + oai:arXiv.org:2512.08868v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wancheng Feng, Chen An, Zhenliang He, Meina Kan, Shiguang Shan, Lukun Wang + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Rui Min (May), Zile Qiao (May), Ze Xu (May), Jiawen Zhai (May), Wenyu Gao (May), Xuanzhong Chen (May), Haozhen Sun (May), Zhen Zhang (May), Xinyu Wang (May), Hong Zhou (May), Wenbiao Yin (May), Xuan Zhou (May), Yong Jiang (May), Haicheng Liu (May), Liang Ding (May), Ling Zou (May), Yi R. (May), Fung, Yalong Li, Pengjun Xie - Balanced Learning for Domain Adaptive Semantic Segmentation - https://arxiv.org/abs/2512.06886 - arXiv:2512.06886v1 Announce Type: new -Abstract: Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Despite the effectiveness of self-training techniques in UDA, they struggle to learn each class in a balanced manner due to inherent class imbalance and distribution shift in both data and label space between domains. To address this issue, we propose Balanced Learning for Domain Adaptation (BLDA), a novel approach to directly assess and alleviate class bias without requiring prior knowledge about the distribution shift. First, we identify over-predicted and under-predicted classes by analyzing the distribution of predicted logits. Subsequently, we introduce a post-hoc approach to align the logits distributions across different classes using shared anchor distributions. To further consider the network's need to generate unbiased pseudo-labels during self-training, we estimate logits distributions online and incorporate logits correction terms into the loss function. Moreover, we leverage the resulting cumulative density as domain-shared structural knowledge to connect the source and target domains. Extensive experiments on two standard UDA semantic segmentation benchmarks demonstrate that BLDA consistently improves performance, especially for under-predicted classes, when integrated into various existing methods. Code is available at https://github.com/Woof6/BLDA. - oai:arXiv.org:2512.06886v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Differentially Private Synthetic Data Generation Using Context-Aware GANs + https://arxiv.org/abs/2512.08869 + arXiv:2512.08869v1 Announce Type: new +Abstract: The widespread use of big data across sectors has raised major privacy concerns, especially when sensitive information is shared or analyzed. Regulations such as GDPR and HIPAA impose strict controls on data handling, making it difficult to balance the need for insights with privacy requirements. Synthetic data offers a promising solution by creating artificial datasets that reflect real patterns without exposing sensitive information. However, traditional synthetic data methods often fail to capture complex, implicit rules that link different elements of the data and are essential in domains like healthcare. They may reproduce explicit patterns but overlook domain-specific constraints that are not directly stated yet crucial for realism and utility. For example, prescription guidelines that restrict certain medications for specific conditions or prevent harmful drug interactions may not appear explicitly in the original data. Synthetic data generated without these implicit rules can lead to medically inappropriate or unrealistic profiles. To address this gap, we propose ContextGAN, a Context-Aware Differentially Private Generative Adversarial Network that integrates domain-specific rules through a constraint matrix encoding both explicit and implicit knowledge. The constraint-aware discriminator evaluates synthetic data against these rules to ensure adherence to domain constraints, while differential privacy protects sensitive details from the original data. We validate ContextGAN across healthcare, security, and finance, showing that it produces high-quality synthetic data that respects domain rules and preserves privacy. Our results demonstrate that ContextGAN improves realism and utility by enforcing domain constraints, making it suitable for applications that require compliance with both explicit patterns and implicit rules under strict privacy guarantees. + oai:arXiv.org:2512.08869v1 + cs.LG + cs.AI + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wangkai Li, Rui Sun, Bohao Liao, Zhaoyang Li, Tianzhu Zhang + http://creativecommons.org/licenses/by/4.0/ + 10.1109/BigData62323.2024.10826047 + Anantaa Kotal, Anupam Joshi - Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation - https://arxiv.org/abs/2512.06888 - arXiv:2512.06888v1 Announce Type: new -Abstract: The development of contactless respiration monitoring for infants could enable advances in the early detection and treatment of breathing irregularities, which are associated with neurodevelopmental impairments and conditions like sudden infant death syndrome (SIDS). But while respiration estimation for adults is supported by a robust ecosystem of computer vision algorithms and video datasets, only one small public video dataset with annotated respiration data for infant subjects exists, and there are no reproducible algorithms which are effective for infants. We introduce the annotated infant respiration dataset of 400 videos (AIR-400), contributing 275 new, carefully annotated videos from 10 recruited subjects to the public corpus. We develop the first reproducible pipelines for infant respiration estimation, based on infant-specific region-of-interest detection and spatiotemporal neural processing enhanced by optical flow inputs. We establish, through comprehensive experiments, the first reproducible benchmarks for the state-of-the-art in vision-based infant respiration estimation. We make our dataset, code repository, and trained models available for public use. - oai:arXiv.org:2512.06888v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents + https://arxiv.org/abs/2512.08870 + arXiv:2512.08870v1 Announce Type: new +Abstract: LLM agents are widely deployed in complex interactive tasks, yet privacy constraints often preclude centralized optimization and co-evolution across dynamic environments. While Federated Learning (FL) has proven effective on static datasets, its extension to the open-ended self-evolution of agents remains underexplored. Directly applying standard FL is challenging: heterogeneous tasks and sparse, trajectory-level rewards introduce severe gradient conflicts, destabilizing the global optimization process. To bridge this gap, we propose Fed-SE, a Federated Self-Evolution framework for LLM agents. Fed-SE establishes a local evolution-global aggregation paradigm. Locally, agents employ parameter-efficient fine-tuning on filtered, high-return trajectories to achieve stable gradient updates. Globally, Fed-SE aggregates updates within a low-rank subspace that disentangles environment-specific dynamics, effectively reducing negative transfer across clients. Experiments across five heterogeneous environments demonstrate that Fed-SE improves average task success rates by approximately 18% over federated baselines, validating its effectiveness in robust cross-environment knowledge transfer in privacy-constrained deployments. + oai:arXiv.org:2512.08870v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Liyang Song, Hardik Bishnoi, Sai Kumar Reddy Manne, Sarah Ostadabbas, Briana J. Taylor, Michael Wan + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xiang Chen, Yuling Shi, Qizhen Lan, Yuchao Qiu, Xiaodong Gu - AQUILA: A QUIC-Based Link Architecture for Resilient Long-Range UAV Communication - https://arxiv.org/abs/2512.06889 - arXiv:2512.06889v1 Announce Type: new -Abstract: The proliferation of autonomous Unmanned Aerial Vehicles (UAVs) in Beyond Visual Line of Sight (BVLOS) applications is critically dependent on resilient, high-bandwidth, and low-latency communication links. Existing solutions face critical limitations: TCP's head-of-line blocking stalls time-sensitive data, UDP lacks reliability and congestion control, and cellular networks designed for terrestrial users degrade severely for aerial platforms. This paper introduces AQUILA, a cross-layer communication architecture built on QUIC to address these challenges. AQUILA contributes three key innovations: (1) a unified transport layer using QUIC's reliable streams for MAVLink Command and Control (C2) and unreliable datagrams for video, eliminating head-of-line blocking under unified congestion control; (2) a priority scheduling mechanism that structurally ensures C2 latency remains bounded and independent of video traffic intensity; (3) a UAV-adapted congestion control algorithm extending SCReAM with altitude-adaptive delay targeting and telemetry headroom reservation. AQUILA further implements 0-RTT connection resumption to minimize handover blackouts with application-layer replay protection, deployed over an IP-native architecture enabling global operation. Experimental validation demonstrates that AQUILA significantly outperforms TCP- and UDP-based approaches in C2 latency, video quality, and link resilience under realistic conditions, providing a robust foundation for autonomous BVLOS missions. - oai:arXiv.org:2512.06889v1 - cs.NI - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning + https://arxiv.org/abs/2512.08873 + arXiv:2512.08873v1 Announce Type: new +Abstract: Image captioning is essential in many fields including assisting visually impaired individuals, improving content management systems, and enhancing human-computer interaction. However, a recent challenge in this domain is dealing with low-resolution image (LRI). While performance can be improved by using larger models like transformers for encoding, these models are typically heavyweight, demanding significant computational resources and memory, leading to challenges in retraining. To address this, the proposed SOLI (Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning) approach presents a solution specifically designed for lightweight, low-resolution images captioning. It employs a Siamese network architecture to optimize latent embeddings, enhancing the efficiency and accuracy of the image-to-text translation process. By focusing on a dual-pathway neural network structure, SOLI minimizes computational overhead without sacrificing performance, making it an ideal choice for training on resource-constrained scenarios. + oai:arXiv.org:2512.08873v1 + cs.CV + cs.AI + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ximing Huang, Yirui Rao + 10.23919/SPA61993.2024.10715604 + 2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) + Jing Jie Tan, Anissa Mokraoui, Ban-Hoe Kwan, Danny Wee-Kiat Ng, Yan-Chai Hum - What Needs to be Known in Order to Perform a Meaningful Scientific Comparison Between Animal Communications and Human Spoken Language - https://arxiv.org/abs/2512.06890 - arXiv:2512.06890v1 Announce Type: new -Abstract: Human spoken language has long been the subject of scientific investigation, particularly with regard to the mechanisms underpinning speech production. Likewise, the study of animal communications has a substantial literature, with many studies focusing on vocalisation. More recently, there has been growing interest in comparing animal communications and human speech. However, it is proposed here that such a comparison necessitates the appraisal of a minimum set of critical phenomena: i) the number of degrees-of-freedom of the vocal apparatus, ii) the ability to control those degrees-of-freedom independently, iii) the properties of the acoustic environment in which communication takes place, iv) the perceptual salience of the generated sounds, v) the degree to which sounds are contrastive, vi) the presence/absence of compositionality, and vii) the information rate(s) of the resulting communications. - oai:arXiv.org:2512.06890v1 - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 + When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation + https://arxiv.org/abs/2512.08875 + arXiv:2512.08875v1 Announce Type: new +Abstract: Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged for adapting LLMs to tabular data generation: (i) fine-tuning smaller models directly on tabular datasets, and (ii) prompting larger models with examples provided in context. In this work, we show that popular implementations from both regimes exhibit a tendency to compromise privacy by reproducing memorized patterns of numeric digits from their training data. To systematically analyze this risk, we introduce a simple No-box Membership Inference Attack (MIA) called LevAtt that assumes adversarial access to only the generated synthetic data and targets the string sequences of numeric digits in synthetic observations. Using this approach, our attack exposes substantial privacy leakage across a wide range of models and datasets, and in some cases, is even a perfect membership classifier on state-of-the-art models. Our findings highlight a unique privacy vulnerability of LLM-based synthetic data generation and the need for effective defenses. To this end, we propose two methods, including a novel sampling strategy that strategically perturbs digits during generation. Our evaluation demonstrates that this approach can defeat these attacks with minimal loss of fidelity and utility of the synthetic data. + oai:arXiv.org:2512.08875v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Proc. Vocal Interactivity in-and-between Humans, Animals and Robots (VIHAR-24), pp 22-26, Kos, Greece, 6 Sept. 2024 - Roger K. Moore + Joshua Ward, Bochao Gu, Chi-Hua Wang, Guang Cheng - From Zero to High-Speed Racing: An Autonomous Racing Stack - https://arxiv.org/abs/2512.06892 - arXiv:2512.06892v1 Announce Type: new -Abstract: High-speed, head-to-head autonomous racing presents substantial technical and logistical challenges, including precise localization, rapid perception, dynamic planning, and real-time control-compounded by limited track access and costly hardware. This paper introduces the Autonomous Race Stack (ARS), developed by the IU Luddy Autonomous Racing team for the Indy Autonomous Challenge (IAC). We present three iterations of our ARS, each validated on different tracks and achieving speeds up to 260 km/h. Our contributions include: (i) the modular architecture and evolution of the ARS across ARS1, ARS2, and ARS3; (ii) a detailed performance evaluation that contrasts control, perception, and estimation across oval and road-course environments; and (iii) the release of a high-speed, multi-sensor dataset collected from oval and road-course tracks. Our findings highlight the unique challenges and insights from real-world high-speed full-scale autonomous racing. - oai:arXiv.org:2512.06892v1 + IPPO Learns the Game, Not the Team: A Study on Generalization in Heterogeneous Agent Teams + https://arxiv.org/abs/2512.08877 + arXiv:2512.08877v1 Announce Type: new +Abstract: Multi-Agent Reinforcement Learning (MARL) is commonly deployed in settings where agents are trained via self-play with homogeneous teammates, often using parameter sharing and a single policy architecture. This opens the question: to what extent do self-play PPO agents learn general coordination strategies grounded in the underlying game, compared to overfitting to their training partners' behaviors? This paper investigates the question using the Heterogeneous Multi-Agent Challenge (HeMAC) environment, which features distinct Observer and Drone agents with complementary capabilities. We introduce Rotating Policy Training (RPT), an approach that rotates heterogeneous teammate policies of different learning algorithms during training, to expose the agent to a broader range of partner strategies. When playing alongside a withheld teammate policy (DDQN), we find that RPT achieves similar performance to a standard self-play baseline, IPPO, where all agents were trained sharing a single PPO policy. This result indicates that in this heterogeneous multi-agent setting, the IPPO baseline generalizes to novel teammate algorithms despite not experiencing teammate diversity during training. This shows that a simple IPPO baseline may possess the level of generalization to novel teammates that a diverse training regimen was designed to achieve. + oai:arXiv.org:2512.08877v1 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Hassan Jardali, Durgakant Pushp, Youwei Yu, Mahmoud Ali, Ihab S. Mohamed, Alejandro Murillo-Gonzalez, Paul D. Coen, Md. Al-Masrur Khan, Reddy Charan Pulivendula, Saeoul Park, Lingchuan Zhou, Lantao Liu + Ryan LeRoy, Jack Kolb - Control of Powered Ankle-Foot Prostheses on Compliant Terrain: A Quantitative Approach to Stability Enhancement - https://arxiv.org/abs/2512.06896 - arXiv:2512.06896v1 Announce Type: new -Abstract: Walking on compliant terrain presents a substantial challenge for individuals with lower-limb amputation, further elevating their already high risk of falling. While powered ankle-foot prostheses have demonstrated adaptability across speeds and rigid terrains, control strategies optimized for soft or compliant surfaces remain underexplored. This work experimentally validates an admittance-based control strategy that dynamically adjusts the quasi-stiffness of powered prostheses to enhance gait stability on compliant ground. Human subject experiments were conducted with three healthy individuals walking on two bilaterally compliant surfaces with ground stiffness values of 63 and 25 kN/m, representative of real-world soft environments. Controller performance was quantified using phase portraits and two walking stability metrics, offering a direct assessment of fall risk. Compared to a standard phase-variable controller developed for rigid terrain, the proposed admittance controller consistently improved gait stability across all compliant conditions. These results demonstrate the potential of adaptive, stability-aware prosthesis control to reduce fall risk in real-world environments and advance the robustness of human-prosthesis interaction in rehabilitation robotics. - oai:arXiv.org:2512.06896v1 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + DAO-GP Drift Aware Online Non-Linear Regression Gaussian-Process + https://arxiv.org/abs/2512.08879 + arXiv:2512.08879v1 Announce Type: new +Abstract: Real-world datasets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accuracy. Furthermore, the presence of hyperparameters in online models exacerbates this issue. These parameters are typically fixed and cannot be dynamically adjusted by the user in response to the evolving data distribution. Gaussian Process (GP) models offer powerful non-parametric regression capabilities with uncertainty quantification, making them ideal for modeling complex data relationships in an online setting. However, conventional online GP methods face several critical limitations, including a lack of drift-awareness, reliance on fixed hyperparameters, vulnerability to data snooping, absence of a principled decay mechanism, and memory inefficiencies. In response, we propose DAO-GP (Drift-Aware Online Gaussian Process), a novel, fully adaptive, hyperparameter-free, decayed, and sparse non-linear regression model. DAO-GP features a built-in drift detection and adaptation mechanism that dynamically adjusts model behavior based on the severity of drift. Extensive empirical evaluations confirm DAO-GP's robustness across stationary conditions, diverse drift types (abrupt, incremental, gradual), and varied data characteristics. Analyses demonstrate its dynamic adaptation, efficient in-memory and decay-based management, and evolving inducing points. Compared with state-of-the-art parametric and non-parametric models, DAO-GP consistently achieves superior or competitive performance, establishing it as a drift-resilient solution for online non-linear regression. + oai:arXiv.org:2512.08879v1 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chrysostomos Karakasis, Camryn Scully, Robert Salati, Panagiotis Artemiadis + Proc. IEEE International Conference on Big Data (BigData), 2025 + Mohammad Abu-Shaira, Ajita Rattani, Weishi Shi - Ground Compliance Improves Retention of Visual Feedback-Based Propulsion Training for Gait Rehabilitation - https://arxiv.org/abs/2512.06897 - arXiv:2512.06897v1 Announce Type: new -Abstract: This study investigates whether adding ground compliance to visual feedback (VF) gait training is more effective at increasing push-off force (POF) compared to using VF alone, with implications for gait rehabilitation. Ten healthy participants walked on a custom split-belt treadmill. All participants received real-time visual feedback of their ground reaction forces. One group also experienced changes in ground compliance, while a control group received only visual feedback. Intentional increases in propulsive ground reaction forces (POF) were successfully achieved and sustained post-intervention, especially in the group that experienced ground compliance. This group also demonstrated lasting after-effects in muscle activity and joint kinematics, indicating a more robust learning of natural strategies to increase propulsion. This work demonstrates how visual and proprioceptive systems coordinate during gait adaptation. It uniquely shows that combining ground compliance with visual feedback enhances the learning of propulsive forces, supporting the potential use of compliant terrain in long-term rehabilitation targeting propulsion deficits, such as those following a stroke. - oai:arXiv.org:2512.06897v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing + https://arxiv.org/abs/2512.08881 + arXiv:2512.08881v1 Announce Type: new +Abstract: Vision-language models (VLMs) are emerging as powerful generalist tools for remote sensing, capable of integrating information across diverse tasks and enabling flexible, instruction-based interactions via a chat interface. In this work, we enhance VLM-based visual grounding in satellite imagery by proposing a novel structured localization mechanism. Our approach involves finetuning a pretrained VLM on a diverse set of instruction-following tasks, while interfacing a dedicated grounding module through specialized control tokens for localization. This method facilitates joint reasoning over both language and spatial information, significantly enhancing the model's ability to precisely localize objects in complex satellite scenes. We evaluate our framework on several remote sensing benchmarks, consistently improving the state-of-the-art, including a 24.8% relative improvement over previous methods on visual grounding. Our results highlight the benefits of integrating structured spatial reasoning into VLMs, paving the way for more reliable real-world satellite data analysis. + oai:arXiv.org:2512.08881v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bradley Hobbs, Panagiotis Artemiadis + http://creativecommons.org/licenses/by/4.0/ + Aysim Toker, Andreea-Maria Oncescu, Roy Miles, Ismail Elezi, Jiankang Deng - Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models - https://arxiv.org/abs/2512.06899 - arXiv:2512.06899v1 Announce Type: new -Abstract: Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw that fine-tuning on downstream tasks inevitably modifies model parameters, shifting the output distribution and rendering pre-computed defense ineffective. To address this, we propose Patronus, a novel framework that use input-side invariance of triggers against parameter shifts. To overcome the convergence challenges of discrete text optimization, Patronus introduces a multi-trigger contrastive search algorithm that effectively bridges gradient-based optimization with contrastive learning objectives. Furthermore, we employ a dual-stage mitigation strategy combining real-time input monitoring with model purification via adversarial training. Extensive experiments across 15 PLMs and 10 tasks demonstrate that Patronus achieves $\geq98.7\%$ backdoor detection recall and reduce attack success rates to clean settings, significantly outperforming all state-of-the-art baselines in all settings. Code is available at https://github.com/zth855/Patronus. - oai:arXiv.org:2512.06899v1 + Decentralized Trust for Space AI: Blockchain-Based Federated Learning Across Multi-Vendor LEO Satellite Networks + https://arxiv.org/abs/2512.08882 + arXiv:2512.08882v1 Announce Type: new +Abstract: The rise of space AI is reshaping government and industry through applications such as disaster detection, border surveillance, and climate monitoring, powered by massive data from commercial and governmental low Earth orbit (LEO) satellites. Federated satellite learning (FSL) enables joint model training without sharing raw data, but suffers from slow convergence due to intermittent connectivity and introduces critical trust challenges--where biased or falsified updates can arise across satellite constellations, including those injected through cyberattacks on inter-satellite or satellite-ground communication links. We propose OrbitChain, a blockchain-backed framework that empowers trustworthy multi-vendor collaboration in LEO networks. OrbitChain (i) offloads consensus to high-altitude platforms (HAPs) with greater computational capacity, (ii) ensures transparent, auditable provenance of model updates from different orbits owned by different vendors, and (iii) prevents manipulated or incomplete contributions from affecting global FSL model aggregation. Extensive simulations show that OrbitChain reduces computational and communication overhead while improving privacy, security, and global model accuracy. Its permissioned proof-of-authority ledger finalizes over 1000 blocks with sub-second latency (0.16,s, 0.26,s, 0.35,s for 1-of-5, 3-of-5, and 5-of-5 quorums). Moreover, OrbitChain reduces convergence time by up to 30 hours on real satellite datasets compared to single-vendor, demonstrating its effectiveness for real-time, multi-vendor learning. Our code is available at https://github.com/wsu-cyber-security-lab-ai/OrbitChain.git + oai:arXiv.org:2512.08882v1 cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tianhang Zhao, Wei Du, Haodong Zhao, Sufeng Duan, Gongshen Liu + http://creativecommons.org/licenses/by-sa/4.0/ + Mohamed Elmahallawy, Asma Jodeiri Akbarfam - BabelCoder: Agentic Code Translation with Specification Alignment - https://arxiv.org/abs/2512.06902 - arXiv:2512.06902v1 Announce Type: new -Abstract: As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long remained a challenging task. Recent advancements in Large Language Models (LLMs) have shown potential for this task, yet existing approaches remain limited in accuracy and fail to effectively leverage contextual and structural cues within the code. Prior work has explored translation and repair mechanisms, but lacks a structured, agentic framework where multiple specialized agents collaboratively improve translation quality. In this work, we introduce BabelCoder, an agentic framework that performs code translation by decomposing the task into specialized agents for translation, testing, and refinement, each responsible for a specific aspect such as generating code, validating correctness, or repairing errors. We evaluate BabelCoder on four benchmark datasets and compare it against four state-of-the-art baselines. BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%. - oai:arXiv.org:2512.06902v1 - cs.SE - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + AI Didn't Start the Fire: Examining the Stack Exchange Moderator and Contributor Strike + https://arxiv.org/abs/2512.08884 + arXiv:2512.08884v1 Announce Type: new +Abstract: Online communities and their host platforms are mutually dependent yet conflict-prone. When platform policies clash with community values, communities have resisted through strikes, blackouts, and even migration to other platforms. Through such collective actions, communities have sometimes won concessions but these have frequently proved temporary. Prior research has investigated strike events and migration chains, but the processes by which community-platform conflict unfolds remain obscure. How do community-platform relationships deteriorate? How do communities organize collective action? How do participants proceed in the aftermath? We investigate a conflict between the Stack Exchange platform and community that occurred in 2023 around an emergency arising from the release of large language models (LLMs). Based on a qualitative thematic analysis of 2,070 messages on Meta Stack Exchange and 14 interviews with community members, we surface how the 2023 conflict was preceded by a long-term deterioration in the community-platform relationship driven in particular by the platform's disregard for the community's highly-valued participatory role in governance. Moreover, the platform's policy response to LLMs aggravated the community's sense of crisis triggering the strike mobilization. We analyze how the mobilization was coordinated through a tiered leadership and communication structure, as well as how community members pivoted in the aftermath. Building on recent theoretical scholarship in social computing, we use Hirshman's exit, voice and loyalty framework to theorize the challenges of community-platform relations evinced in our data. Finally, we recommend ways that platforms and communities can institute participatory governance to be durable and effective. + oai:arXiv.org:2512.08884v1 + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - Fazle Rabbi, Soumit Kanti Saha, Tri Minh Triet Pham, Song Wang, Jinqiu Yang + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Yiwei Wu, Leah Ajmani, Nathan TeBlunthuis, Hanlin Li + + + Explainable Anomaly Detection for Industrial IoT Data Streams + https://arxiv.org/abs/2512.08885 + arXiv:2512.08885v1 Announce Type: new +Abstract: Industrial maintenance is being transformed by the Internet of Things and edge computing, generating continuous data streams that demand real-time, adaptive decision-making under limited computational resources. While data stream mining (DSM) addresses this challenge, most methods assume fully supervised settings, yet in practice, ground-truth labels are often delayed or unavailable. This paper presents a collaborative DSM framework that integrates unsupervised anomaly detection with interactive, human-in-the-loop learning to support maintenance decisions. We employ an online Isolation Forest and enhance interpretability using incremental Partial Dependence Plots and a feature importance score, derived from deviations of Individual Conditional Expectation curves from a fading average, enabling users to dynamically reassess feature relevance and adjust anomaly thresholds. We describe the real-time implementation and provide initial results for fault detection in a Jacquard loom unit. Ongoing work targets continuous monitoring to predict and explain imminent bearing failures. + oai:arXiv.org:2512.08885v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + new + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.1145/3748522.3780009 + Ana Rita Paup\'erio, Diogo Risca, Afonso Louren\c{c}o, Goreti Marreiros, Ricardo Martins - Scaling Zero-Shot Reference-to-Video Generation - https://arxiv.org/abs/2512.06905 - arXiv:2512.06905v1 Announce Type: new -Abstract: Reference-to-video (R2V) generation aims to synthesize videos that align with a text prompt while preserving the subject identity from reference images. However, current R2V methods are hindered by the reliance on explicit reference image-video-text triplets, whose construction is highly expensive and difficult to scale. We bypass this bottleneck by introducing Saber, a scalable zero-shot framework that requires no explicit R2V data. Trained exclusively on video-text pairs, Saber employs a masked training strategy and a tailored attention-based model design to learn identity-consistent and reference-aware representations. Mask augmentation techniques are further integrated to mitigate copy-paste artifacts common in reference-to-video generation. Moreover, Saber demonstrates remarkable generalization capabilities across a varying number of references and achieves superior performance on the OpenS2V-Eval benchmark compared to methods trained with R2V data. - oai:arXiv.org:2512.06905v1 + Accelerated Rotation-Invariant Convolution for UAV Image Segmentation + https://arxiv.org/abs/2512.08888 + arXiv:2512.08888v1 Announce Type: new +Abstract: Rotation invariance is essential for precise, object-level segmentation in UAV aerial imagery, where targets can have arbitrary orientations and exhibit fine-scale details. Conventional segmentation architectures like U-Net rely on convolution operators that are not rotation-invariant, leading to degraded segmentation accuracy across varying viewpoints. Rotation invariance can be achieved by expanding the filter bank across multiple orientations; however, this will significantly increase computational cost and memory traffic. In this paper, we introduce a GPU-optimized rotation-invariant convolution framework that eliminates the traditional data-lowering (im2col) step required for matrix-multiplication-based convolution. By exploiting structured data sharing among symmetrically rotated filters, our method achieves multi-orientation convolution with greatly reduced memory traffic and computational redundancy. We further generalize the approach to accelerate convolution with arbitrary (non-symmetric) rotation angles. + Across extensive benchmarks, the proposed convolution achieves 20--55% faster training and 15--45% lower energy consumption than CUDNN, while maintaining accuracy comparable to state-of-the-art rotation-invariant methods. In the eight-orientation setting, our approach achieves up to 45% speedup and 41% energy savings on 256\(\times\)256 inputs, and 32% speedup and 23% lower energy usage on 1024\(\times\)1024 inputs. Integrated into a U-Net segmentation model, the framework yields up to 6% improvement in accuracy over the non-rotation-aware baseline. These results demonstrate that the proposed method provides an effective and highly efficient alternative to existing rotation-invariant CNN frameworks. + oai:arXiv.org:2512.08888v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Zijian Zhou, Shikun Liu, Haozhe Liu, Haonan Qiu, Zhaochong An, Weiming Ren, Zhiheng Liu, Xiaoke Huang, Kam Woh Ng, Tian Xie, Xiao Han, Yuren Cong, Hang Li, Chuyan Zhu, Aditya Patel, Tao Xiang, Sen He + Manduhu Manduhu, Alexander Dow, Gerard Dooly, James Riordan - MINES: Explainable Anomaly Detection through Web API Invariant Inference - https://arxiv.org/abs/2512.06906 - arXiv:2512.06906v1 Announce Type: new -Abstract: Detecting the anomalies of web applications, important infrastructures for running modern companies and governments, is crucial for providing reliable web services. Many modern web applications operate on web APIs (e.g., RESTful, SOAP, and WebSockets), their exposure invites intended attacks or unintended illegal visits, causing abnormal system behaviors. However, such anomalies can share very similar logs with normal logs, missing crucial information (which could be in database) for log discrimination. Further, log instances can be also noisy, which can further mislead the state-of-the-art log learning solutions to learn spurious correlation, resulting superficial models and rules for anomaly detection. In this work, we propose MINES which infers explainable API invariants for anomaly detection from the schema level instead of detailed raw log instances, which can (1) significantly discriminate noise in logs to identify precise normalities and (2) detect abnormal behaviors beyond the instrumented logs. Technically, MINES (1) converts API signatures into table schema to enhance the original database shema; and (2) infers the potential database constraints on the enhanced database schema to capture the potential relationships between APIs and database tables. MINES uses LLM for extracting potential relationship based on two given table structures; and use normal log instances to reject and accept LLM-generated invariants. Finally, MINES translates the inferred constraints into invariants to generate Python code for verifying the runtime logs. We extensively evaluate MINES on web-tamper attacks on the benchmarks of TrainTicket, NiceFish, Gitea, Mastodon, and NextCloud against baselines such as LogRobust, LogFormer, and WebNorm. The results show that MINES achieves high recall for the anomalies while introducing almost zero false positives, indicating a new state-of-the-art. - oai:arXiv.org:2512.06906v1 - cs.SE - cs.CR - cs.DB - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers + https://arxiv.org/abs/2512.08889 + arXiv:2512.08889v1 Announce Type: new +Abstract: Visual reasoning is challenging, requiring both precise object grounding and understanding complex spatial relationships. Existing methods fall into two camps: language-only chain-of-thought approaches, which demand large-scale (image, query, answer) supervision, and program-synthesis approaches which use pre-trained models and avoid training, but suffer from flawed logic and erroneous grounding. We propose an annotation-free training framework that improves both reasoning and grounding. Our framework uses AI-powered verifiers: an LLM verifier refines LLM reasoning via reinforcement learning, while a VLM verifier strengthens visual grounding through automated hard-negative mining, eliminating the need for ground truth labels. This design combines the strengths of modern AI systems: advanced language-only reasoning models for decomposing spatial queries into simpler subtasks, and strong vision specialist models improved via performant VLM critics. We evaluate our approach across diverse spatial reasoning tasks, and show that our method improves visual reasoning and surpasses open-source and proprietary models, while with our improved visual grounding model we further outperform recent text-only visual reasoning methods. Project webpage: https://glab-caltech.github.io/valor/ + oai:arXiv.org:2512.08889v1 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Wenjie Zhang, Yun Lin, Chun Fung Amos Kwok, Xiwen Teoh, Xiaofei Xie, Frank Liauw, Hongyu Zhang, Jin Song Dong + Damiano Marsili, Georgia Gkioxari - Robots with Attitudes: Influence of LLM-Driven Robot Personalities on Motivation and Performance - https://arxiv.org/abs/2512.06910 - arXiv:2512.06910v1 Announce Type: new -Abstract: Large language models enable unscripted conversations while maintaining a consistent personality. One desirable personality trait in cooperative partners, known to improve task performance, is agreeableness. To explore the impact of large language models on personality modeling for robots, as well as the effect of agreeable and non-agreeable personalities in cooperative tasks, we conduct a two-part study. This includes an online pre-study for personality validation and a lab-based main study to evaluate the effects on likability, motivation, and task performance. The results demonstrate that the robot's agreeableness significantly enhances its likability. No significant difference in intrinsic motivation was observed between the two personality types. However, the findings suggest that a robot exhibiting agreeableness and openness to new experiences can enhance task performance. This study highlights the advantages of employing large language models for customized modeling of robot personalities and provides evidence that a carefully chosen agreeable robot personality can positively influence human perceptions and lead to greater success in cooperative scenarios. - oai:arXiv.org:2512.06910v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders + https://arxiv.org/abs/2512.08892 + arXiv:2512.08892v1 Announce Type: new +Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a critical challenge. Existing hallucination detection methods for RAG often rely either on large-scale detector training, which requires substantial annotated data, or on querying external LLM judges, which leads to high inference costs. Although some approaches attempt to leverage internal representations of LLMs for hallucination detection, their accuracy remains limited. Motivated by recent advances in mechanistic interpretability, we employ sparse autoencoders (SAEs) to disentangle internal activations, successfully identifying features that are specifically triggered during RAG hallucinations. Building on a systematic pipeline of information-based feature selection and additive feature modeling, we introduce RAGLens, a lightweight hallucination detector that accurately flags unfaithful RAG outputs using LLM internal representations. RAGLens not only achieves superior detection performance compared to existing methods, but also provides interpretable rationales for its decisions, enabling effective post-hoc mitigation of unfaithful RAG. Finally, we justify our design choices and reveal new insights into the distribution of hallucination-related signals within LLMs. The code is available at https://github.com/Teddy-XiongGZ/RAGLens. + oai:arXiv.org:2512.08892v1 + cs.CL + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - 10.1145/3765766.3765780 - Proceedings of the 13th International Conference on Human-Agent Interaction, 2025 - Dennis Becker, Kyra Ahrens, Connor G\"ade, Erik Strahl, Stefan Wermter + Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Aidong Zhang - Energy-Efficient Navigation for Surface Vehicles in Vortical Flow Fields - https://arxiv.org/abs/2512.06912 - arXiv:2512.06912v1 Announce Type: new -Abstract: For centuries, khalasi have skillfully harnessed ocean currents to navigate vast waters with minimal effort. Emulating this intuition in autonomous systems remains a significant challenge, particularly for Autonomous Surface Vehicles tasked with long duration missions under strict energy budgets. In this work, we present a learning-based approach for energy-efficient surface vehicle navigation in vortical flow fields, where partial observability often undermines traditional path-planning methods. We present an end to end reinforcement learning framework based on Soft Actor Critic that learns flow-aware navigation policies using only local velocity measurements. Through extensive evaluation across diverse and dynamically rich scenarios, our method demonstrates substantial energy savings and robust generalization to previously unseen flow conditions, offering a promising path toward long term autonomy in ocean environments. The navigation paths generated by our proposed approach show an improvement in energy conservation 30 to 50 percent compared to the existing state of the art techniques. - oai:arXiv.org:2512.06912v1 - cs.RO + Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training + https://arxiv.org/abs/2512.08894 + arXiv:2512.08894v1 Announce Type: new +Abstract: While scaling laws for Large Language Models (LLMs) traditionally focus on proxy metrics like pretraining loss, predicting downstream task performance has been considered unreliable. This paper challenges that view by proposing a direct framework to model the scaling of benchmark performance from the training budget. We find that for a fixed token-to-parameter ratio, a simple power law can accurately describe the scaling behavior of log accuracy on multiple popular downstream tasks. Our results show that the direct approach extrapolates better than the previously proposed two-stage procedure, which is prone to compounding errors. Furthermore, we introduce functional forms that predict accuracy across token-to-parameter ratios and account for inference compute under repeated sampling. We validate our findings on models with up to 17B parameters trained on up to 350B tokens across two dataset mixtures. To support reproducibility and encourage future research, we release the complete set of pretraining losses and downstream evaluation results. + oai:arXiv.org:2512.08894v1 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + cs.AI + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Rushiraj Gadhvi, Sandeep Manjanna + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jakub Krajewski, Amitis Shidani, Dan Busbridge, Sam Wiseman, Jason Ramapuram - SoK: Trust-Authorization Mismatch in LLM Agent Interactions - https://arxiv.org/abs/2512.06914 - arXiv:2512.06914v1 Announce Type: new -Abstract: Large Language Models (LLMs) are rapidly evolving into autonomous agents capable of interacting with the external world, significantly expanding their capabilities through standardized interaction protocols. However, this paradigm revives the classic cybersecurity challenges of agency and authorization in a novel and volatile context. As decision-making shifts from deterministic code logic to probabilistic inference driven by natural language, traditional security mechanisms designed for deterministic behavior fail. It is fundamentally challenging to establish trust for unpredictable AI agents and to enforce the Principle of Least Privilege (PoLP) when instructions are ambiguous. Despite the escalating threat landscape, the academic community's understanding of this emerging domain remains fragmented, lacking a systematic framework to analyze its root causes. This paper provides a unifying formal lens for agent-interaction security. - We observed that most security threats in this domain stem from a fundamental mismatch between trust evaluation and authorization policies. We introduce a novel risk analysis model centered on this trust-authorization gap. Using this model as a unifying lens, we survey and classify the implementation paths of existing, often seemingly isolated, attacks and defenses. This new framework not only unifies the field but also allows us to identify critical research gaps. Finally, we leverage our analysis to suggest a systematic research direction toward building robust, trusted agents and dynamic authorization mechanisms. - oai:arXiv.org:2512.06914v1 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Unsupervised Learning of Density Estimates with Topological Optimization + https://arxiv.org/abs/2512.08895 + arXiv:2512.08895v1 Announce Type: new +Abstract: Kernel density estimation is a key component of a wide variety of algorithms in machine learning, Bayesian inference, stochastic dynamics and signal processing. However, the unsupervised density estimation technique requires tuning a crucial hyperparameter: the kernel bandwidth. The choice of bandwidth is critical as it controls the bias-variance trade-off by over- or under-smoothing the topological features. Topological data analysis provides methods to mathematically quantify topological characteristics, such as connected components, loops, voids et cetera, even in high dimensions where visualization of density estimates is impossible. In this paper, we propose an unsupervised learning approach using a topology-based loss function for the automated and unsupervised selection of the optimal bandwidth and benchmark it against classical techniques -- demonstrating its potential across different dimensions. + oai:arXiv.org:2512.08895v1 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Guanquan Shi, Haohua Du, Zhiqiang Wang, Xiaoyu Liang, Weiwenpei Liu, Song Bian, Zhenyu Guan + Suina Tanweer, Firas A. Khasawneh - Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering - https://arxiv.org/abs/2512.06915 - arXiv:2512.06915v1 Announce Type: new -Abstract: Automated environment configuration is a critical bottleneck in scaling software engineering (SWE) automation. To provide a reliable evaluation standard for this task, we present Multi-Docker-Eval benchmark. It includes 40 real-world repositories spanning 9 programming languages and measures both success in achieving executable states and efficiency under realistic constraints. Our extensive evaluation of state-of-the-art LLMs and agent frameworks reveals key insights: (1) the overall success rate of current models is low (F2P at most 37.7%), with environment construction being the primary bottleneck; (2) model size and reasoning length are not decisive factors, and open-source models like DeepSeek-V3.1 and Kimi-K2 are competitive in both efficiency and effectiveness; (3) agent framework and programming language also have significantly influence on success rate. These findings provide actionable guidelines for building scalable, fully automated SWE pipelines. - oai:arXiv.org:2512.06915v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Open Polymer Challenge: Post-Competition Report + https://arxiv.org/abs/2512.08896 + arXiv:2512.08896v1 Announce Type: new +Abstract: Machine learning (ML) offers a powerful path toward discovering sustainable polymer materials, but progress has been limited by the lack of large, high-quality, and openly accessible polymer datasets. The Open Polymer Challenge (OPC) addresses this gap by releasing the first community-developed benchmark for polymer informatics, featuring a dataset with 10K polymers and 5 properties: thermal conductivity, radius of gyration, density, fractional free volume, and glass transition temperature. The challenge centers on multi-task polymer property prediction, a core step in virtual screening pipelines for materials discovery. Participants developed models under realistic constraints that include small data, label imbalance, and heterogeneous simulation sources, using techniques such as feature-based augmentation, transfer learning, self-supervised pretraining, and targeted ensemble strategies. The competition also revealed important lessons about data preparation, distribution shifts, and cross-group simulation consistency, informing best practices for future large-scale polymer datasets. The resulting models, analysis, and released data create a new foundation for molecular AI in polymer science and are expected to accelerate the development of sustainable and energy-efficient materials. Along with the competition, we release the test dataset at https://www.kaggle.com/datasets/alexliu99/neurips-open-polymer-prediction-2025-test-data. We also release the data generation pipeline at https://github.com/sobinalosious/ADEPT, which simulates more than 25 properties, including thermal conductivity, radius of gyration, and density. + oai:arXiv.org:2512.08896v1 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kelin Fu, Tianyu Liu, Zeyu Shang, Yingwei Ma, Jian Yang, Jiaheng Liu, Kaigui Bian + http://creativecommons.org/licenses/by/4.0/ + Gang Liu, Sobin Alosious, Subhamoy Mahajan, Eric Inae, Yihan Zhu, Yuhan Liu, Renzheng Zhang, Jiaxin Xu, Addison Howard, Ying Li, Tengfei Luo, Meng Jiang - Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory Analysis - https://arxiv.org/abs/2512.06917 - arXiv:2512.06917v1 Announce Type: new -Abstract: As Reinforcement Learning (RL) agents are increasingly deployed in real-world applications, ensuring their behavior is transparent and trustworthy is paramount. A key component of trust is explainability, yet much of the work in Explainable RL (XRL) focuses on local, single-step decisions. This paper addresses the critical need for explaining an agent's long-term behavior through trajectory-level analysis. We introduce a novel framework that ranks entire trajectories by defining and aggregating a new state-importance metric. This metric combines the classic Q-value difference with a "radical term" that captures the agent's affinity to reach its goal, providing a more nuanced measure of state criticality. We demonstrate that our method successfully identifies optimal trajectories from a heterogeneous collection of agent experiences. Furthermore, by generating counterfactual rollouts from critical states within these trajectories, we show that the agent's chosen path is robustly superior to alternatives, thereby providing a powerful "Why this, and not that?" explanation. Our experiments in standard OpenAI Gym environments validate that our proposed importance metric is more effective at identifying optimal behaviors compared to classic approaches, offering a significant step towards trustworthy autonomous systems. - oai:arXiv.org:2512.06917v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation + https://arxiv.org/abs/2512.08897 + arXiv:2512.08897v1 Announce Type: new +Abstract: Content-aware layout generation is a critical task in graphic design automation, focused on creating visually appealing arrangements of elements that seamlessly blend with a given background image. The variety of real-world applications makes it highly challenging to develop a single model capable of unifying the diverse range of input-constrained generation sub-tasks, such as those conditioned by element types, sizes, or their relationships. Current methods either address only a subset of these tasks or necessitate separate model parameters for different conditions, failing to offer a truly unified solution. In this paper, we propose UniLayDiff: a Unified Diffusion Transformer, that for the first time, addresses various content-aware layout generation tasks with a single, end-to-end trainable model. Specifically, we treat layout constraints as a distinct modality and employ Multi-Modal Diffusion Transformer framework to capture the complex interplay between the background image, layout elements, and diverse constraints. Moreover, we integrate relation constraints through fine-tuning the model with LoRA after pretraining the model on other tasks. Such a schema not only achieves unified conditional generation but also enhances overall layout quality. Extensive experiments demonstrate that UniLayDiff achieves state-of-the-art performance across from unconditional to various conditional generation tasks and, to the best of our knowledge, is the first model to unify the full range of content-aware layout generation tasks. + oai:arXiv.org:2512.08897v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Clifford F, Devika Jay, Abhishek Sarkar, Satheesh K Perepu, Santhosh G S, Kaushik Dey, Balaraman Ravindran + Zeyang Liu, Le Wang, Sanping Zhou, Yuxuan Wu, Xiaolong Sun, Gang Hua, Haoxiang Li - Automated PRO-CTCAE Symptom Selection based on Prior Adverse Event Profiles - https://arxiv.org/abs/2512.06919 - arXiv:2512.06919v1 Announce Type: new -Abstract: The PRO-CTCAE is an NCI-developed patient-reported outcome system for capturing symptomatic adverse events in oncology trials. It comprises a large library drawn from the CTCAE vocabulary, and item selection for a given trial is typically guided by expected toxicity profiles from prior data. Selecting too many PRO-CTCAE items can burden patients and reduce compliance, while too few may miss important safety signals. We present an automated method to select a minimal yet comprehensive PRO-CTCAE subset based on historical safety data. Each candidate PRO-CTCAE symptom term is first mapped to its corresponding MedDRA Preferred Terms (PTs), which are then encoded into Safeterm, a high-dimensional semantic space capturing clinical and contextual diversity in MedDRA terminology. We score each candidate PRO item for relevance to the historical list of adverse event PTs and combine relevance and incidence into a utility function. Spectral analysis is then applied to the combined utility and diversity matrix to identify an orthogonal set of medical concepts that balances relevance and diversity. Symptoms are rank-ordered by importance, and a cut-off is suggested based on the explained information. The tool is implemented as part of the Safeterm trial-safety app. We evaluate its performance using simulations and oncology case studies in which PRO-CTCAE was employed. This automated approach can streamline PRO-CTCAE design by leveraging MedDRA semantics and historical data, providing an objective and reproducible method to balance signal coverage against patient burden. - oai:arXiv.org:2512.06919v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Self-Evolving 3D Scene Generation from a Single Image + https://arxiv.org/abs/2512.08905 + arXiv:2512.08905v1 Announce Type: new +Abstract: Generating high-quality, textured 3D scenes from a single image remains a fundamental challenge in vision and graphics. Recent image-to-3D generators recover reasonable geometry from single views, but their object-centric training limits generalization to complex, large-scale scenes with faithful structure and texture. We present EvoScene, a self-evolving, training-free framework that progressively reconstructs complete 3D scenes from single images. The key idea is combining the complementary strengths of existing models: geometric reasoning from 3D generation models and visual knowledge from video generation models. Through three iterative stages--Spatial Prior Initialization, Visual-guided 3D Scene Mesh Generation, and Spatial-guided Novel View Generation--EvoScene alternates between 2D and 3D domains, gradually improving both structure and appearance. Experiments on diverse scenes demonstrate that EvoScene achieves superior geometric stability, view-consistent textures, and unseen-region completion compared to strong baselines, producing ready-to-use 3D meshes for practical applications. + oai:arXiv.org:2512.08905v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla + http://creativecommons.org/licenses/by/4.0/ + Kaizhi Zheng, Yue Fan, Jing Gu, Zishuo Xu, Xuehai He, Xin Eric Wang - Parent-Guided Semantic Reward Model (PGSRM): Embedding-Based Reward Functions for Reinforcement Learning of Transformer Language Models - https://arxiv.org/abs/2512.06920 - arXiv:2512.06920v1 Announce Type: new -Abstract: We introduce the Parent-Guided Semantic Reward Model (PGSRM), a lightweight reward framework for reinforcement learning (RL) of transformer language models. PGSRM replaces binary correctness signals, human preference data, and trained reward models with a simple signal: cosine similarity between a parent model's reference output embedding and a child model's generated output for the same input. This yields a dense, semantically meaningful reward with no human annotation or additional model training. We apply PGSRM on five language tasks and find that it produces smoother reward improvement and more stable PPO dynamics than a binary reward baseline, suggesting that embedding-based semantic rewards are a practical alternative to RLHF-style reward modeling for parent-guided alignment in smaller transformer models. - oai:arXiv.org:2512.06920v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Exploring the Garden of Forking Paths in Empirical Software Engineering Research: A Multiverse Analysis + https://arxiv.org/abs/2512.08910 + arXiv:2512.08910v1 Announce Type: new +Abstract: In empirical software engineering (SE) research, researchers have considerable freedom to decide how to process data, what operationalizations to use, and which statistical model to fit. Gelman and Loken refer to this freedom as leading to a "garden of forking paths". Although this freedom is often seen as an advantage, it also poses a threat to robustness and replicability: variations in analytical decisions, even when justifiable, can lead to divergent conclusions. + To better understand this risk, we conducted a so-called multiverse analysis on a published empirical SE paper. The paper we picked is a Mining Software Repositories study, as MSR studies commonly use non-trivial statistical models to analyze post-hoc, observational data. In the study, we identified nine pivotal analytical decisions-each with at least one equally defensible alternative and systematically reran all the 3,072 resulting analysis pipelines on the original dataset. Interestingly, only 6 of these universes (<0.2%) reproduced the published results; the overwhelming majority produced qualitatively different, and sometimes even opposite, findings. + This case study of a data analytical method commonly applied to empirical software engineering data reveals how methodological choices can exert a more profound influence on outcomes than is often acknowledged. We therefore advocate that SE researchers complement standard reporting with robustness checks across plausible analysis variants or, at least, explicitly justify each analytical decision. We propose a structured classification model to help classify and improve justification for methodological choices. Secondly, we show how the multiverse analysis is a practical tool in the methodological arsenal of SE researchers, one that can help produce more reliable, reproducible science. + oai:arXiv.org:2512.08910v1 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Alexandr Plashchinsky + Nathan Cassee, Robert Feldt - NeuroABench: A Multimodal Evaluation Benchmark for Neurosurgical Anatomy Identification - https://arxiv.org/abs/2512.06921 - arXiv:2512.06921v1 Announce Type: new -Abstract: Multimodal Large Language Models (MLLMs) have shown significant potential in surgical video understanding. With improved zero-shot performance and more effective human-machine interaction, they provide a strong foundation for advancing surgical education and assistance. However, existing research and datasets primarily focus on understanding surgical procedures and workflows, while paying limited attention to the critical role of anatomical comprehension. In clinical practice, surgeons rely heavily on precise anatomical understanding to interpret, review, and learn from surgical videos. To fill this gap, we introduce the Neurosurgical Anatomy Benchmark (NeuroABench), the first multimodal benchmark explicitly created to evaluate anatomical understanding in the neurosurgical domain. NeuroABench consists of 9 hours of annotated neurosurgical videos covering 89 distinct procedures and is developed using a novel multimodal annotation pipeline with multiple review cycles. The benchmark evaluates the identification of 68 clinical anatomical structures, providing a rigorous and standardized framework for assessing model performance. Experiments on over 10 state-of-the-art MLLMs reveal significant limitations, with the best-performing model achieving only 40.87% accuracy in anatomical identification tasks. To further evaluate the benchmark, we extract a subset of the dataset and conduct an informative test with four neurosurgical trainees. The results show that the best-performing student achieves 56% accuracy, with the lowest scores of 28% and an average score of 46.5%. While the best MLLM performs comparably to the lowest-scoring student, it still lags significantly behind the group's average performance. This comparison underscores both the progress of MLLMs in anatomical understanding and the substantial gap that remains in achieving human-level performance. - oai:arXiv.org:2512.06921v1 + LiDAS: Lighting-driven Dynamic Active Sensing for Nighttime Perception + https://arxiv.org/abs/2512.08912 + arXiv:2512.08912v1 Announce Type: new +Abstract: Nighttime environments pose significant challenges for camera-based perception, as existing methods passively rely on the scene lighting. We introduce Lighting-driven Dynamic Active Sensing (LiDAS), a closed-loop active illumination system that combines off-the-shelf visual perception models with high-definition headlights. Rather than uniformly brightening the scene, LiDAS dynamically predicts an optimal illumination field that maximizes downstream perception performance, i.e., decreasing light on empty areas to reallocate it on object regions. LiDAS enables zero-shot nighttime generalization of daytime-trained models through adaptive illumination control. Trained on synthetic data and deployed zero-shot in real-world closed-loop driving scenarios, LiDAS enables +18.7% mAP50 and +5.0% mIoU over standard low-beam at equal power. It maintains performances while reducing energy use by 40%. LiDAS complements domain-generalization methods, further strengthening robustness without retraining. By turning readily available headlights into active vision actuators, LiDAS offers a cost-effective solution to robust nighttime perception. + oai:arXiv.org:2512.08912v1 cs.CV - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ziyang Song, Zelin Zang, Xiaofan Ye, Boqiang Xu, Long Bai, Jinlin Wu, Hongliang Ren, Hongbin Liu, Jiebo Luo, Zhen Lei + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Simon de Moreau, Andrei Bursuc, Hafid El-Idrissi, Fabien Moutarde - Large Language Models and Forensic Linguistics: Navigating Opportunities and Threats in the Age of Generative AI - https://arxiv.org/abs/2512.06922 - arXiv:2512.06922v1 Announce Type: new -Abstract: Large language models (LLMs) present a dual challenge for forensic linguistics. They serve as powerful analytical tools enabling scalable corpus analysis and embedding-based authorship attribution, while simultaneously destabilising foundational assumptions about idiolect through style mimicry, authorship obfuscation, and the proliferation of synthetic texts. Recent stylometric research indicates that LLMs can approximate surface stylistic features yet exhibit detectable differences from human writers, a tension with significant forensic implications. However, current AI-text detection techniques, whether classifier-based, stylometric, or watermarking approaches, face substantial limitations: high false positive rates for non-native English writers and vulnerability to adversarial strategies such as homoglyph substitution. These uncertainties raise concerns under legal admissibility standards, particularly the Daubert and Kumho Tire frameworks. The article concludes that forensic linguistics requires methodological reconfiguration to remain scientifically credible and legally admissible. Proposed adaptations include hybrid human-AI workflows, explainable detection paradigms beyond binary classification, and validation regimes measuring error and bias across diverse populations. The discipline's core insight, i.e., that language reveals information about its producer, remains valid but must accommodate increasingly complex chains of human and machine authorship. - oai:arXiv.org:2512.06922v1 - cs.CL - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + Improved Pseudorandom Codes from Permuted Puzzles + https://arxiv.org/abs/2512.08918 + arXiv:2512.08918v1 Announce Type: new +Abstract: Watermarks are an essential tool for identifying AI-generated content. Recently, Christ and Gunn (CRYPTO '24) introduced pseudorandom error-correcting codes (PRCs), which are equivalent to watermarks with strong robustness and quality guarantees. A PRC is a pseudorandom encryption scheme whose decryption algorithm tolerates a high rate of errors. Pseudorandomness ensures quality preservation of the watermark, and error tolerance of decryption translates to the watermark's ability to withstand modification of the content. + In the short time since the introduction of PRCs, several works (NeurIPS '24, RANDOM '25, STOC '25) have proposed new constructions. Curiously, all of these constructions are vulnerable to quasipolynomial-time distinguishing attacks. Furthermore, all lack robustness to edits over a constant-sized alphabet, which is necessary for a meaningfully robust LLM watermark. Lastly, they lack robustness to adversaries who know the watermarking detection key. Until now, it was not clear whether any of these properties was achievable individually, let alone together. + We construct pseudorandom codes that achieve all of the above: plausible subexponential pseudorandomness security, robustness to worst-case edits over a binary alphabet, and robustness against even computationally unbounded adversaries that have the detection key. Pseudorandomness rests on a new assumption that we formalize, the permuted codes conjecture, which states that a distribution of permuted noisy codewords is pseudorandom. We show that this conjecture is implied by the permuted puzzles conjecture used previously to construct doubly efficient private information retrieval. To give further evidence, we show that the conjecture holds against a broad class of simple distinguishers, including read-once branching programs. + oai:arXiv.org:2512.08918v1 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - George Mikros + Miranda Christ, Noah Golowich, Sam Gunn, Ankur Moitra, Daniel Wichs - XAM: Interactive Explainability for Authorship Attribution Models - https://arxiv.org/abs/2512.06924 - arXiv:2512.06924v1 Announce Type: new -Abstract: We present IXAM, an Interactive eXplainability framework for Authorship Attribution Models. Given an authorship attribution (AA) task and an embedding-based AA model, our tool enables users to interactively explore the model's embedding space and construct an explanation of the model's prediction as a set of writing style features at different levels of granularity. Through a user evaluation, we demonstrate the value of our framework compared to predefined stylistic explanations. - oai:arXiv.org:2512.06924v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer + https://arxiv.org/abs/2512.08920 + arXiv:2512.08920v1 Announce Type: new +Abstract: Human video demonstrations provide abundant training data for learning robot policies, but video alone cannot capture the rich contact signals critical for mastering manipulation. We introduce OSMO, an open-source wearable tactile glove designed for human-to-robot skill transfer. The glove features 12 three-axis tactile sensors across the fingertips and palm and is designed to be compatible with state-of-the-art hand-tracking methods for in-the-wild data collection. We demonstrate that a robot policy trained exclusively on human demonstrations collected with OSMO, without any real robot data, is capable of executing a challenging contact-rich manipulation task. By equipping both the human and the robot with the same glove, OSMO minimizes the visual and tactile embodiment gap, enabling the transfer of continuous shear and normal force feedback while avoiding the need for image inpainting or other vision-based force inference. On a real-world wiping task requiring sustained contact pressure, our tactile-aware policy achieves a 72% success rate, outperforming vision-only baselines by eliminating contact-related failure modes. We release complete hardware designs, firmware, and assembly instructions to support community adoption. + oai:arXiv.org:2512.08920v1 + cs.RO + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Milad Alshomary, Anisha Bhatnagar, Peter Zeng, Smaranda Muresan, Owen Rambow, Kathleen McKeown + Jessica Yin, Haozhi Qi, Youngsun Wi, Sayantan Kundu, Mike Lambeta, William Yang, Changhao Wang, Tingfan Wu, Jitendra Malik, Tess Hellebrekers - Deep Reinforcement Learning for Phishing Detection with Transformer-Based Semantic Features - https://arxiv.org/abs/2512.06925 - arXiv:2512.06925v1 Announce Type: new -Abstract: Phishing is a cybercrime in which individuals are deceived into revealing personal information, often resulting in financial loss. These attacks commonly occur through fraudulent messages, misleading advertisements, and compromised legitimate websites. This study proposes a Quantile Regression Deep Q-Network (QR-DQN) approach that integrates RoBERTa semantic embeddings with handcrafted lexical features to enhance phishing detection while accounting for uncertainties. Unlike traditional DQN methods that estimate single scalar Q-values, QR-DQN leverages quantile regression to model the distribution of returns, improving stability and generalization on unseen phishing data. A diverse dataset of 105,000 URLs was curated from PhishTank, OpenPhish, Cloudflare, and other sources, and the model was evaluated using an 80/20 train-test split. The QR-DQN framework achieved a test accuracy of 99.86%, precision of 99.75%, recall of 99.96%, and F1-score of 99.85%, demonstrating high effectiveness. Compared to standard DQN with lexical features, the hybrid QR-DQN with lexical and semantic features reduced the generalization gap from 1.66% to 0.04%, indicating significant improvement in robustness. Five-fold cross-validation confirmed model reliability, yielding a mean accuracy of 99.90% with a standard deviation of 0.04%. These results suggest that the proposed hybrid approach effectively identifies phishing threats, adapts to evolving attack strategies, and generalizes well to unseen data. - oai:arXiv.org:2512.06925v1 - cs.LG - cs.AI - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration + https://arxiv.org/abs/2512.08922 + arXiv:2512.08922v1 Announce Type: new +Abstract: Text-Aware Image Restoration (TAIR) aims to recover high- quality images from low-quality inputs containing degraded textual content. While diffusion models provide strong gen- erative priors for general image restoration, they often pro- duce text hallucinations in text-centric tasks due to the ab- sence of explicit linguistic knowledge. To address this, we propose UniT, a unified text restoration framework that in- tegrates a Diffusion Transformer (DiT), a Vision-Language Model (VLM), and a Text Spotting Module (TSM) in an it- erative fashion for high-fidelity text restoration. In UniT, the VLM extracts textual content from degraded images to provide explicit textual guidance. Simultaneously, the TSM, trained on diffusion features, generates intermedi- ate OCR predictions at each denoising step, enabling the VLM to iteratively refine its guidance during the denoising process. Finally, the DiT backbone, leveraging its strong representational power, exploit these cues to recover fine- grained textual content while effectively suppressing text hallucinations. Experiments on the SA-Text and Real-Text benchmarks demonstrate that UniT faithfully reconstructs degraded text, substantially reduces hallucinations, and achieves state-of-the-art end-to-end F1-score performance in TAIR task. + oai:arXiv.org:2512.08922v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new http://creativecommons.org/licenses/by/4.0/ - Aseer Al Faisal + Jin Hyeon Kim, Paul Hyunbin Cho, Claire Kim, Jaewon Min, Jaeeun Lee, Jihye Park, Yeji Choi, Seungryong Kim - Evaluating the Sensitivity of BiLSTM Forecasting Models to Sequence Length and Input Noise - https://arxiv.org/abs/2512.06926 - arXiv:2512.06926v1 Announce Type: new -Abstract: Deep learning (DL) models, a specialized class of multilayer neural networks, have become central to time-series forecasting in critical domains such as environmental monitoring and the Internet of Things (IoT). Among these, Bidirectional Long Short-Term Memory (BiLSTM) architectures are particularly effective in capturing complex temporal dependencies. However, the robustness and generalization of such models are highly sensitive to input data characteristics - an aspect that remains underexplored in existing literature. This study presents a systematic empirical analysis of two key data-centric factors: input sequence length and additive noise. To support this investigation, a modular and reproducible forecasting pipeline is developed, incorporating standardized preprocessing, sequence generation, model training, validation, and evaluation. Controlled experiments are conducted on three real-world datasets with varying sampling frequencies to assess BiLSTM performance under different input conditions. The results yield three key findings: (1) longer input sequences significantly increase the risk of overfitting and data leakage, particularly in data-constrained environments; (2) additive noise consistently degrades predictive accuracy across sampling frequencies; and (3) the simultaneous presence of both factors results in the most substantial decline in model stability. While datasets with higher observation frequencies exhibit greater robustness, they remain vulnerable when both input challenges are present. These findings highlight important limitations in current DL-based forecasting pipelines and underscore the need for data-aware design strategies. This work contributes to a deeper understanding of DL model behavior in dynamic time-series environments and provides practical insights for developing more reliable and generalizable forecasting systems. - oai:arXiv.org:2512.06926v1 - cs.LG + Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs + https://arxiv.org/abs/2512.08923 + arXiv:2512.08923v1 Announce Type: new +Abstract: We introduce two new benchmarks REST and REST+(Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (MLLMs). MLLMs are trained to represent vision and language in the same embedding space, yet they cannot perform the same tasks in both modalities. Our benchmarks contain samples with the same semantic information in three modalities (image, text, mixed) and we show that state-of-the-art MLLMs cannot consistently reason over these different modalities. We evaluate 15 MLLMs and find that the degree of modality inconsistency varies substantially, even when accounting for problems with text recognition (OCR). Neither rendering text as image nor rendering an image as text solves the inconsistency. Even if OCR is correct, we find that visual characteristics (text colour and resolution, but not font) and the number of vision tokens have an impact on model performance. Finally, we find that our consistency score correlates with the modality gap between text and images, highlighting a mechanistic interpretation of cross-modal inconsistent MLLMs. + oai:arXiv.org:2512.08923v1 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/publicdomain/zero/1.0/ - Salma Albelali, Moataz Ahmed + http://creativecommons.org/licenses/by/4.0/ + Angela van Sprang, Laurens Samson, Ana Lucic, Erman Acar, Sennay Ghebreab, Yuki M. Asano - Adaptive Normalization Mamba with Multi Scale Trend Decomposition and Patch MoE Encoding - https://arxiv.org/abs/2512.06929 - arXiv:2512.06929v1 Announce Type: new -Abstract: Time series forecasting in real world environments faces significant challenges non stationarity, multi scale temporal patterns, and distributional shifts that degrade model stability and accuracy. This study propose AdaMamba, a unified forecasting architecture that integrates adaptive normalization, multi scale trend extraction, and contextual sequence modeling to address these challenges. AdaMamba begins with an Adaptive Normalization Block that removes non stationary components through multi scale convolutional trend extraction and channel wise recalibration, enabling consistent detrending and variance stabilization. The normalized sequence is then processed by a Context Encoder that combines patch wise embeddings, positional encoding, and a Mamba enhanced Transformer layer with a mixture of experts feed forward module, allowing efficient modeling of both long range dependencies and local temporal dynamics. A lightweight prediction head generates multi horizon forecasts, and a denormalization mechanism reconstructs outputs by reintegrating local trends to ensure robustness under varying temporal conditions. AdaMamba provides strong representational capacity with modular extensibility, supporting deterministic prediction and compatibility with probabilistic extensions. Its design effectively mitigates covariate shift and enhances predictive reliability across heterogeneous datasets. Experimental evaluations demonstrate that AdaMamba's combination of adaptive normalization and expert augmented contextual modeling yields consistent improvements in stability and accuracy over conventional Transformer based baselines. - oai:arXiv.org:2512.06929v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Efficiently Reconstructing Dynamic Scenes One D4RT at a Time + https://arxiv.org/abs/2512.08924 + arXiv:2512.08924v1 Announce Type: new +Abstract: Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simple yet powerful feedforward model designed to efficiently solve this task. D4RT utilizes a unified transformer architecture to jointly infer depth, spatio-temporal correspondence, and full camera parameters from a single video. Its core innovation is a novel querying mechanism that sidesteps the heavy computation of dense, per-frame decoding and the complexity of managing multiple, task-specific decoders. Our decoding interface allows the model to independently and flexibly probe the 3D position of any point in space and time. The result is a lightweight and highly scalable method that enables remarkably efficient training and inference. We demonstrate that our approach sets a new state of the art, outperforming previous methods across a wide spectrum of 4D reconstruction tasks. We refer to the project webpage for animated results: https://d4rt-paper.github.io/. + oai:arXiv.org:2512.08924v1 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by/4.0/ - MinCheol Jeon + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Chuhan Zhang, Guillaume Le Moing, Skanda Koppula, Ignacio Rocco, Liliane Momeni, Junyu Xie, Shuyang Sun, Rahul Sukthankar, Jo\"elle K Barral, Raia Hadsell, Zoubin Ghahramani, Andrew Zisserman, Junlin Zhang, Mehdi SM Sajjadi - Hidden Leaks in Time Series Forecasting: How Data Leakage Affects LSTM Evaluation Across Configurations and Validation Strategies - https://arxiv.org/abs/2512.06932 - arXiv:2512.06932v1 Announce Type: new -Abstract: Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data leakage, a methodological flaw in which input-output sequences are constructed before dataset partitioning, allowing future information to unintentionally influence training. This study investigates the impact of data leakage on performance, focusing on how validation design mediates leakage sensitivity. Three widely used validation techniques (2-way split, 3-way split, and 10-fold cross-validation) are evaluated under both leaky (pre-split sequence generation) and clean conditions, with the latter mitigating leakage risk by enforcing temporal separation during data splitting prior to sequence construction. The effect of leakage is assessed using RMSE Gain, which measures the relative increase in RMSE caused by leakage, computed as the percentage difference between leaky and clean setups. Empirical results show that 10-fold cross-validation exhibits RMSE Gain values of up to 20.5% at extended lag steps. In contrast, 2-way and 3-way splits demonstrate greater robustness, typically maintaining RMSE Gain below 5% across diverse configurations. Moreover, input window size and lag step significantly influence leakage sensitivity: smaller windows and longer lags increase the risk of leakage, whereas larger windows help reduce it. These findings underscore the need for configuration-aware, leakage-resistant evaluation pipelines to ensure reliable performance estimation. - oai:arXiv.org:2512.06932v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Toward Practical Forecasts of Public Sentiments via Convexification for Mean Field Games: Evidence from Real World COVID-19 Discussion Data + https://arxiv.org/abs/2512.08925 + arXiv:2512.08925v1 Announce Type: new +Abstract: We apply a convexification-based numerical method to forecast public sentiment dynamics using Mean Field Games (MFGs). The theoretical foundation for the convexification approach, established in our prior work, guarantees global convergence to the unique solution to the MFG system. The present work demonstrates the practical potential of this framework using real-world sentiment data extracted from social media public discussion during the COVID-19 pandemic. The results show that the MFG model with appropriate parameters and convexification yields sentiment density predictions that align closely with observed data and satisfy the governing equations. While current parameter selection relies on manual calibration, our findings establish the first proof-of-concept evidence that MFG models can capture complex temporal patterns in public sentiment, laying the groundwork for future work on systematic parameter identification methods, i.e. solutions of coefficient inverse problems for the MFG system. + oai:arXiv.org:2512.08925v1 + math.NA + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/publicdomain/zero/1.0/ - Salma Albelali, Moataz Ahmed + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Shi Chen, Michael V. Klibanov, Kevin McGoff, Trung Truong, Wangjiaxuan Xin, Shuhua Yin - MATEX: A Multi-Agent Framework for Explaining Ethereum Transactions - https://arxiv.org/abs/2512.06933 - arXiv:2512.06933v1 Announce Type: new -Abstract: Understanding a complicated Ethereum transaction remains challenging: multi-hop token flows, nested contract calls, and opaque execution paths routinely lead users to blind signing. Based on interviews with everyday users, developers, and auditors, we identify the need for faithful, step-wise explanations grounded in both on-chain evidence and real-world protocol semantics. To meet this need, we introduce (matex, a cognitive multi-agent framework that models transaction understanding as a collaborative investigation-combining rapid hypothesis generation, dynamic off-chain knowledge retrieval, evidence-aware synthesis, and adversarial validation to produce faithful explanations. - oai:arXiv.org:2512.06933v1 - cs.CE - cs.CL - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment + https://arxiv.org/abs/2512.08930 + arXiv:2512.08930v1 Announce Type: new +Abstract: Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. Recent vision foundation models like VGGT take an orthogonal approach -- 3D knowledge is gained implicitly through training data and loss objectives, enabling feed-forward prediction of both camera parameters and 3D representations directly from a set of uncalibrated images. While flexible, VGGT features lack explicit multi-view geometric consistency, and we find that improving such 3D feature consistency benefits both NVS and pose estimation tasks. We introduce Selfi, a self-improving 3D reconstruction pipeline via feature alignment, transforming a VGGT backbone into a high-fidelity 3D reconstruction engine by leveraging its own outputs as pseudo-ground-truth. Specifically, we train a lightweight feature adapter using a reprojection-based consistency loss, which distills VGGT outputs into a new geometrically-aligned feature space that captures spatial proximity in 3D. This enables state-of-the-art performance in both NVS and camera pose estimation, demonstrating that feature alignment is a highly beneficial step for downstream 3D reasoning. + oai:arXiv.org:2512.08930v1 + cs.CV + cs.GR + Wed, 10 Dec 2025 00:00:00 -0500 new - http://creativecommons.org/licenses/by-sa/4.0/ - Zifan Peng + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Youming Deng, Songyou Peng, Junyi Zhang, Kathryn Heal, Tiancheng Sun, John Flynn, Steve Marschner, Lucy Chai - Interconnection and Damping Assignment Passivity-Based Control using Sparse Neural ODEs - https://arxiv.org/abs/2512.06935 - arXiv:2512.06935v1 Announce Type: new -Abstract: Interconnection and Damping Assignment Passivity-Based Control (IDA-PBC) is a nonlinear control technique that assigns a port-Hamiltonian (pH) structure to a controlled system using a state-feedback law. While IDA-PBC has been extensively studied and applied to many systems, its practical implementation often remains confined to academic examples and, almost exclusively, to stabilization tasks. The main limitation of IDA-PBC stems from the complexity of analytically solving a set of partial differential equations (PDEs), referred to as the matching conditions, which enforce the pH structure of the closed-loop system. However, this is extremely challenging, especially for complex physical systems and tasks. - In this work, we propose a novel numerical approach for designing IDA-PBC controllers without solving the matching PDEs exactly. We cast the IDA-PBC problem as the learning of a neural ordinary differential equation. In particular, we rely on sparse dictionary learning to parametrize the desired closed-loop system as a sparse linear combination of nonlinear state-dependent functions. Optimization of the controller parameters is achieved by solving a multi-objective optimization problem whose cost function is composed of a generic task-dependent cost and a matching condition-dependent cost. Our numerical results show that the proposed method enables (i) IDA-PBC to be applicable to complex tasks beyond stabilization, such as the discovery of periodic oscillatory behaviors, (ii) the derivation of closed-form expressions of the controlled system, including residual terms - oai:arXiv.org:2512.06935v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Astra: General Interactive World Model with Autoregressive Denoising + https://arxiv.org/abs/2512.08931 + arXiv:2512.08931v1 Announce Type: new +Abstract: Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose scenarios and various forms of actions. To bridge this gap, we introduce Astra, an interactive general world model that generates real-world futures for diverse scenarios (e.g., autonomous driving, robot grasping) with precise action interactions (e.g., camera motion, robot action). We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations and support streaming outputs. We use a noise-augmented history memory to avoid over-reliance on past frames to balance responsiveness with temporal coherence. For precise action control, we introduce an action-aware adapter that directly injects action signals into the denoising process. We further develop a mixture of action experts that dynamically route heterogeneous action modalities, enhancing versatility across diverse real-world tasks such as exploration, manipulation, and camera control. Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions. Experiments across multiple datasets demonstrate the improvements of Astra in fidelity, long-range prediction, and action alignment over existing state-of-the-art world models. + oai:arXiv.org:2512.08931v1 + cs.CV + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 new http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nicol\`o Botteghi, Owen Brook, Urban Fasel, Federico Califano + Yixuan Zhu, Jiaqi Feng, Wenzhao Zheng, Yuan Gao, Xin Tao, Pengfei Wan, Jie Zhou, Jiwen Lu - Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation - https://arxiv.org/abs/2512.06938 - arXiv:2512.06938v1 Announce Type: new -Abstract: Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a recent length control method based on Reverse Positional Embeddings (RPE) and show its limits when control is requested beyond the training distribution. In particular, using a discrete countdown signal tied to the absolute remaining token count leads to instability. To provide robust length control, we introduce Progress Ratio Embeddings (PRE), as continuous embeddings tied to a trigonometric impatience signal. PRE integrates seamlessly into standard Transformer architectures, providing stable length fidelity without degrading text accuracy under standard evaluation metrics. We further show that PRE generalizes well to unseen target lengths. Experiments on two widely used news-summarization benchmarks validate these findings. - oai:arXiv.org:2512.06938v1 + MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs + https://arxiv.org/abs/2508.05502 + arXiv:2508.05502v1 Announce Type: cross +Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable performance in high-resource languages. However, their effectiveness diminishes significantly in the contexts of low-resource languages. Current multilingual enhancement methods are often limited to text modality or rely solely on machine translation. While such approaches help models acquire basic linguistic capabilities and produce "thin descriptions", they neglect the importance of multimodal informativeness and cultural groundedness, both of which are crucial for serving low-resource language users effectively. To bridge this gap, in this study, we identify two significant objectives for a truly effective MLLM in low-resource language settings, namely 1) linguistic capability and 2) cultural groundedness, placing special emphasis on cultural awareness. To achieve these dual objectives, we propose a dual-source strategy that guides the collection of data tailored to each goal, sourcing native web alt-text for culture and MLLM-generated captions for linguistics. As a concrete implementation, we introduce MELLA, a multimodal, multilingual dataset. Experiment results show that after fine-tuning on MELLA, there is a general performance improvement for the eight languages on various MLLM backbones, with models producing "thick descriptions". We verify that the performance gains are from both cultural knowledge enhancement and linguistic capability enhancement. Our dataset can be found at https://opendatalab.com/applyMultilingualCorpus. + oai:arXiv.org:2508.05502v1 + cs.CV + cs.AI cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Ivanho\'e Botcazou, Tassadit Amghar, Sylvain Lamprier, Fr\'ed\'eric Saubion + Yufei Gao, Jiaying Fei, Nuo Chen, Ruirui Chen, Guohang Yan, Yunshi Lan, Botian Shi - A Unifying Human-Centered AI Fairness Framework - https://arxiv.org/abs/2512.06944 - arXiv:2512.06944v1 Announce Type: new -Abstract: The increasing use of Artificial Intelligence (AI) in critical societal domains has amplified concerns about fairness, particularly regarding unequal treatment across sensitive attributes such as race, gender, and socioeconomic status. While there has been substantial work on ensuring AI fairness, navigating trade-offs between competing notions of fairness as well as predictive accuracy remains challenging, creating barriers to the practical deployment of fair AI systems. To address this, we introduce a unifying human-centered fairness framework that systematically covers eight distinct fairness metrics, formed by combining individual and group fairness, infra-marginal and intersectional assumptions, and outcome-based and equality-of-opportunity (EOO) perspectives. This structure allows stakeholders to align fairness interventions with their values and contextual considerations. The framework uses a consistent and easy-to-understand formulation for all metrics to reduce the learning curve for non-experts. Rather than privileging a single fairness notion, the framework enables stakeholders to assign weights across multiple fairness objectives, reflecting their priorities and facilitating multi-stakeholder compromises. We apply this approach to four real-world datasets: the UCI Adult census dataset for income prediction, the COMPAS dataset for criminal recidivism, the German Credit dataset for credit risk assessment, and the MEPS dataset for healthcare utilization. We show that adjusting weights reveals nuanced trade-offs between different fairness metrics. Finally, through case studies in judicial decision-making and healthcare, we demonstrate how the framework can inform practical and value-sensitive deployment of fair AI systems. - oai:arXiv.org:2512.06944v1 - cs.LG - cs.AI - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Munshi Mahbubur Rahman, Shimei Pan, James R. Foulds + Formally and Empirically Verified Methodologies for Scalable Hierarchical Full-Stack Systems + https://arxiv.org/abs/2510.00002 + arXiv:2510.00002v2 Announce Type: cross +Abstract: This paper introduces Primary Breadth-First Development (PBFD) and Primary Depth-First Development (PDFD)-formally and empirically verified methodologies for scalable, industrial-grade full-stack software engineering. Both approaches enforce structural and behavioral correctness through graph-theoretic modeling, bridging formal methods and real-world practice. PBFD and PDFD model software development as layered directed graphs with unified state machines, verified using Communicating Sequential Processes (CSP) and Linear Temporal Logic (LTL). This guarantees bounded-refinement termination, deadlock freedom, and structural completeness. To manage hierarchical data at scale, we present the Three-Level Encapsulation (TLE)-a novel bitmask-based encoding scheme. TLE operations are verified via CSP failures-divergences refinement, ensuring constant-time updates and compact storage that underpin PBFD's robust performance. PBFD demonstrates exceptional industrial viability through eight years of enterprise deployment with zero critical failures, achieving approximately 20x faster develop-ment than Salesforce OmniScript, 7-8x faster query performance, and 11.7x storage reduction compared to conventional relational models. These results are established through longitudinal observational studies, quasi-experimental runtime comparisons, and controlled schema-level experiments. Open-source Minimum Viable Product implementations validate key behavioral properties, including bounded refinement and constant-time bitmask operations, un-der reproducible conditions. All implementations, formal specifications, and non-proprietary datasets are publicly available. + oai:arXiv.org:2510.00002v2 + cs.SE + cs.DB + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Dong Liu - Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology - https://arxiv.org/abs/2512.06949 - arXiv:2512.06949v1 Announce Type: new -Abstract: Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-tissue relationships remains a challenge, especially in regions with overlapping or morphologically similar tissues. Current convolutional neural network (CNN)-based approaches operate primarily on visual texture, often treating tissues as independent regions and failing to encode biological context. To this end, we introduce Neural Tissue Relation Modeling (NTRM), a novel segmentation framework that augments CNNs with a tissue-level graph neural network to model spatial and functional relationships across tissue types. NTRM constructs a graph over predicted regions, propagates contextual information via message passing, and refines segmentation through spatial projection. Unlike prior methods, NTRM explicitly encodes inter-tissue dependencies, enabling structurally coherent predictions in boundary-dense zones. On the benchmark Histopathology Non-Melanoma Skin Cancer Segmentation Dataset, NTRM outperforms state-of-the-art methods, achieving a robust Dice similarity coefficient that is 4.9\% to 31.25\% higher than the best-performing models among the evaluated approaches. Our experiments indicate that relational modeling offers a principled path toward more context-aware and interpretable histological segmentation, compared to local receptive-field architectures that lack tissue-level structural awareness. Our code is available at https://github.com/shravan-18/NTRM. - oai:arXiv.org:2512.06949v1 + Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm + https://arxiv.org/abs/2512.05791 + arXiv:2512.05791v1 Announce Type: cross +Abstract: Purpose: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high quality MRI reconstructions with uncertainty estimation from highly undersampled k-space data. However, sampling methods such as diffusion posterior sampling or likelihood annealing suffer from long reconstruction times and the need for parameter tuning. The purpose of this work is to develop a robust sampling algorithm with fast convergence. + Theory and Methods: In the reverse diffusion process used for sampling the posterior, the exact likelihood is multiplied with the diffused prior at all noise scales. To overcome the issue of slow convergence, preconditioning is used. The method is trained on fastMRI data and tested on retrospectively undersampled brain data of a healthy volunteer. + Results: For posterior sampling in Cartesian and non-Cartesian accelerated MRI the new approach outperforms annealed sampling in terms of reconstruction speed and sample quality. + Conclusion: The proposed exact likelihood with preconditioning enables rapid and reliable posterior sampling across various MRI reconstruction tasks without the need for parameter tuning. + oai:arXiv.org:2512.05791v1 + physics.med-ph cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shravan Venkatraman, Muthu Subash Kavitha, Joe Dhanith P R, V Manikandarajan, Jia Wu + cs.LG + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Moritz Blumenthal, Tina Holliber, Jonathan I. Tamir, Martin Uecker - Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge - https://arxiv.org/abs/2512.06951 - arXiv:2512.06951v1 Announce Type: new -Abstract: We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and context-aware decision making. - Building on the Pi0.5 architecture, we introduce several innovations. Our primary contribution is correlated noise for flow matching, which improves training efficiency and enables correlation-aware inpainting for smooth action sequences. We also apply learnable mixed-layer attention and System 2 stage tracking for ambiguity resolution. Training employs multi-sample flow matching to reduce variance, while inference uses action compression and challenge-specific correction rules. - Our approach achieves 26% q-score across all 50 tasks on both public and private leaderboards. - oai:arXiv.org:2512.06951v1 + Cascaded Tightly-Coupled Observer Design for Single-Range-Aided Inertial Navigation + https://arxiv.org/abs/2512.06198 + arXiv:2512.06198v1 Announce Type: cross +Abstract: This work introduces a single-range-aided navigation observer that reconstructs the full state of a rigid body using only an Inertial Measurement Unit (IMU), a body-frame vector measurement (e.g., magnetometer), and a distance measurement from a fixed anchor point. The design first formulates an extended linear time-varying (LTV) system to estimate body-frame position, body-frame velocity, and the gravity direction. The recovered gravity direction, combined with the body-frame vector measurement, is then used to reconstruct the full orientation on $\mathrm{SO}(3)$, resulting in a cascaded observer architecture. Almost Global Asymptotic Stability (AGAS) of the cascaded design is established under a uniform observability condition, ensuring robustness to sensor noise and trajectory variations. Simulation studies on three-dimensional trajectories demonstrate accurate estimation of position, velocity, and orientation, highlighting single-range aiding as a lightweight and effective modality for autonomous navigation. + oai:arXiv.org:2512.06198v1 cs.RO + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by/4.0/ + Oussama Sifour, Soulaimane Berkane, Abdelhamid Tayebi + + + Artificial Intelligence and Nuclear Weapons Proliferation: The Technological Arms Race for (In)visibility + https://arxiv.org/abs/2512.07487 + arXiv:2512.07487v1 Announce Type: cross +Abstract: A robust nonproliferation regime has contained the spread of nuclear weapons to just nine states. Yet, emerging and disruptive technologies are reshaping the landscape of nuclear risks, presenting a critical juncture for decision makers. This article lays out the contours of an overlooked but intensifying technological arms race for nuclear (in)visibility, driven by the interplay between proliferation-enabling technologies (PETs) and detection-enhancing technologies (DETs). We argue that the strategic pattern of proliferation will be increasingly shaped by the innovation pace in these domains. Artificial intelligence (AI) introduces unprecedented complexity to this equation, as its rapid scaling and knowledge substitution capabilities accelerate PET development and challenge traditional monitoring and verification methods. To analyze this dynamic, we develop a formal model centered on a Relative Advantage Index (RAI), quantifying the shifting balance between PETs and DETs. Our model explores how asymmetric technological advancement, particularly logistic AI-driven PET growth versus stepwise DET improvements, expands the band of uncertainty surrounding proliferation detectability. Through replicable scenario-based simulations, we evaluate the impact of varying PET growth rates and DET investment strategies on cumulative nuclear breakout risk. We identify a strategic fork ahead, where detection may no longer suffice without broader PET governance. Governments and international organizations should accordingly invest in policies and tools agile enough to keep pace with tomorrow's technology. + oai:arXiv.org:2512.07487v1 + cs.CY cs.AI - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.ET + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Ilia Larchenko, Gleb Zarin, Akash Karnatak + 10.1111/risa.70105 + Risk Analysis 45(11): 3839-3859 (2025) + David M. Allison, Stephen Herzog - Resource-Bounded Type Theory: Compositional Cost Analysis via Graded Modalities - https://arxiv.org/abs/2512.06952 - arXiv:2512.06952v1 Announce Type: new -Abstract: We present a compositional framework for certifying resource bounds in typed programs. Terms are typed with synthesized bounds drawn from an abstract resource lattice, enabling uniform treatment of time, memory, gas, and domain-specific costs. - We introduce a graded feasibility modality with co-unit and monotonicity laws. Our main result is a syntactic cost soundness theorem for the recursion-free simply-typed fragment: if a closed term has synthesized bound b under a given budget, its operational cost is bounded by b. We provide a syntactic term model in the topos of presheaves over the lattice -- where resource bounds index a cost-stratified family of definable values -- with cost extraction as a natural transformation. We prove canonical forms via reification and establish initiality of the syntactic model: it embeds uniquely into all resource-bounded models. - A case study demonstrates compositional reasoning for binary search using Lean's native recursion with separate bound proofs. - oai:arXiv.org:2512.06952v1 - cs.LO - cs.CE - math.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Automating High Energy Physics Data Analysis with LLM-Powered Agents + https://arxiv.org/abs/2512.07785 + arXiv:2512.07785v1 Announce Type: cross +Abstract: We present a proof-of-principle study demonstrating the use of large language model (LLM) agents to automate a representative high energy physics (HEP) analysis. Using the Higgs boson diphoton cross-section measurement as a case study with ATLAS Open Data, we design a hybrid system that combines an LLM-based supervisor-coder agent with the Snakemake workflow manager. In this architecture, the workflow manager enforces reproducibility and determinism, while the agent autonomously generates, executes, and iteratively corrects analysis code in response to user instructions. We define quantitative evaluation metrics including success rate, error distribution, costs per specific task, and average number of API calls, to assess agent performance across multi-stage workflows. To characterize variability across architectures, we benchmark a representative selection of state-of-the-art LLMs spanning the Gemini and GPT-5 series, the Claude family, and leading open-weight models. While the workflow manager ensures deterministic execution of all analysis steps, the final outputs still show stochastic variation. Although we set the temperature to zero, other sampling parameters (e.g., top-p, top-k) remained at their defaults, and some reasoning-oriented models internally adjust these settings. Consequently, the models do not produce fully deterministic results. This study establishes the first LLM-agent-driven automated data-analysis framework in HEP, enabling systematic benchmarking of model capabilities, stability, and limitations in real-world scientific computing environments. The baseline code used in this work is available at https://huggingface.co/HWresearch/LLM4HEP. This work was accepted as a poster at the Machine Learning and the Physical Sciences (ML4PS) workshop at NeurIPS 2025. The initial submission was made on August 30, 2025. + oai:arXiv.org:2512.07785v1 + physics.data-an + cs.AI + cs.LG + hep-ex + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Mirco A. Mannucci, Corey Thuro + Eli Gendreau-Distler, Joshua Ho, Dongwon Kim, Luc Tomas Le Pottier, Haichen Wang, Chengxi Yang - Hereditary History-Preserving Bisimilarity: Characterizations via Backward Ready Multisets - https://arxiv.org/abs/2512.06959 - arXiv:2512.06959v1 Announce Type: new -Abstract: We devise two complementary characterizations of hereditary history-preserving bisimilarity (HHPB): a denotational one, based on stable configuration structures, and an operational one, formulated in a reversible process calculus. Our characterizations rely on forward-reverse bisimilarity augmented with backward ready multiset equality. This shifts the emphasis from uniquely identifying events, as done in previous characterizations, to counting occurrences of identically labeled events associated with incoming transitions, which yields a more lightweight behavioral equivalence than HHPB. We show that our characterizations correctly distinguish between autoconcurrency and autocausation, but are valid only in the absence of non-local conflicts. We then study the logical foundations of these characterizations by relating event identifier logic, which captures the classical view of HHPB, and backward ready multiset logic, developed for our new equivalence. - oai:arXiv.org:2512.06959v1 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Signal and Noise Classification in Bio-Signals via unsupervised Machine Learning + https://arxiv.org/abs/2512.07851 + arXiv:2512.07851v1 Announce Type: cross +Abstract: Real-world biosignal data is frequently corrupted by various types of noise, such as motion artifacts, and baseline wander. Although digital signal processing techniques exist to process such signals; however, heavily degraded signals cannot be recovered. In this study, we aim to classify two things: first, a binary classification of noisy and clean biosignals, and next, to categorize various kinds of noise such as motion artifacts, sensor failure, etc. We implemented K-means clustering, and our results indicate that the algorithm can most reliably group clean segments from noisy ones, particularly strong performance in identifying clean data compared to various categories of noise. This approach enables the selection of only high-quality bio-signal segments and provides accurate results for feature engineering that may enhance the precision of machine learning models trained on biosignals. + oai:arXiv.org:2512.07851v1 + eess.SP + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Marco Bernardo, Andrea Esposito, Claudio A. Mezzina + Sansrit Paudel - VideoVLA: Video Generators Can Be Generalizable Robot Manipulators - https://arxiv.org/abs/2512.06963 - arXiv:2512.06963v1 Announce Type: new -Abstract: Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained understanding models for perception and instruction following, their ability to generalize to novel tasks, objects, and settings remains limited. In this work, we present VideoVLA, a simple approach that explores the potential of transforming large video generation models into robotic VLA manipulators. Given a language instruction and an image, VideoVLA predicts an action sequence as well as the future visual outcomes. Built on a multi-modal Diffusion Transformer, VideoVLA jointly models video, language, and action modalities, using pre-trained video generative models for joint visual and action forecasting. Our experiments show that high-quality imagined futures correlate with reliable action predictions and task success, highlighting the importance of visual imagination in manipulation. VideoVLA demonstrates strong generalization, including imitating other embodiments' skills and handling novel objects. This dual-prediction strategy - forecasting both actions and their visual consequences - explores a paradigm shift in robot learning and unlocks generalization capabilities in manipulation systems. - oai:arXiv.org:2512.06963v1 - cs.RO - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Integrating LSTM Networks with Neural Levy Processes for Financial Forecasting + https://arxiv.org/abs/2512.07860 + arXiv:2512.07860v1 Announce Type: cross +Abstract: This paper investigates an optimal integration of deep learning with financial models for robust asset price forecasting. Specifically, we developed a hybrid framework combining a Long Short-Term Memory (LSTM) network with the Merton-L\'evy jump-diffusion model. To optimise this framework, we employed the Grey Wolf Optimizer (GWO) for the LSTM hyperparameter tuning, and we explored three calibration methods for the Merton-Levy model parameters: Artificial Neural Networks (ANNs), the Marine Predators Algorithm (MPA), and the PyTorch-based TorchSDE library. To evaluate the predictive performance of our hybrid model, we compared it against several benchmark models, including a standard LSTM and an LSTM combined with the Fractional Heston model. This evaluation used three real-world financial datasets: Brent oil prices, the STOXX 600 index, and the IT40 index. Performance was assessed using standard metrics, including Mean Squared Error (MSE), Mean Absolute Error(MAE), Mean Squared Percentage Error (MSPE), and the coefficient of determination (R2). Our experimental results demonstrate that the hybrid model, combining a GWO-optimized LSTM network with the Levy-Merton Jump-Diffusion model calibrated using an ANN, outperformed the base LSTM model and all other models developed in this study. + oai:arXiv.org:2512.07860v1 + q-fin.ST + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - The Thirty-ninth Annual Conference on Neural Information Processing Systems(NeurIPS2025) - Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo + Mohammed Alruqimi, Luca Di Persio - Neuro-Vesicles: Neuromodulation Should Be a Dynamical System, Not a Tensor Decoration - https://arxiv.org/abs/2512.06966 - arXiv:2512.06966v1 Announce Type: new -Abstract: We introduce Neuro-Vesicles, a framework that augments conventional neural networks with a missing computational layer: a dynamical population of mobile, discrete vesicles that live alongside the network rather than inside its tensors. Each vesicle is a self contained object v = (c, kappa, l, tau, s) carrying a vector payload, type label, location on the graph G = (V, E), remaining lifetime, and optional internal state. Vesicles are emitted in response to activity, errors, or meta signals; migrate along learned transition kernels; probabilistically dock at nodes; locally modify activations, parameters, learning rules, or external memory through content dependent release operators; and finally decay or are absorbed. - This event based interaction layer reshapes neuromodulation. Instead of applying the same conditioning tensors on every forward pass, modulation emerges from the stochastic evolution of a vesicle population that can accumulate, disperse, trigger cascades, carve transient pathways, and write structured traces into topological memory. Dense, short lived vesicles approximate familiar tensor mechanisms such as FiLM, hypernetworks, or attention. Sparse, long lived vesicles resemble a small set of mobile agents that intervene only at rare but decisive moments. - We give a complete mathematical specification of the framework, including emission, migration, docking, release, decay, and their coupling to learning; a continuous density relaxation that yields differentiable reaction diffusion dynamics on the graph; and a reinforcement learning view where vesicle control is treated as a policy optimized for downstream performance. We also outline how the same formalism extends to spiking networks and neuromorphic hardware such as the Darwin3 chip, enabling programmable neuromodulation on large scale brain inspired computers. - oai:arXiv.org:2512.06966v1 - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 - new + LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline + https://arxiv.org/abs/2512.07867 + arXiv:2512.07867v1 Announce Type: cross +Abstract: We develop a transparent and fully auditable LLM-based pipeline for macro-financial stress testing, combining structured prompting with optional retrieval of country fundamentals and news. The system generates machine-readable macroeconomic scenarios for the G7, which cover GDP growth, inflation, and policy rates, and are translated into portfolio losses through a factor-based mapping that enables Value-at-Risk and Expected Shortfall assessment relative to classical econometric baselines. Across models, countries, and retrieval settings, the LLMs produce coherent and country-specific stress narratives, yielding stable tail-risk amplification with limited sensitivity to retrieval choices. Comprehensive plausibility checks, scenario diagnostics, and ANOVA-based variance decomposition show that risk variation is driven primarily by portfolio composition and prompt design rather than by the retrieval mechanism. The pipeline incorporates snapshotting, deterministic modes, and hash-verified artifacts to ensure reproducibility and auditability. Overall, the results demonstrate that LLM-generated macro scenarios, when paired with transparent structure and rigorous validation, can provide a scalable and interpretable complement to traditional stress-testing frameworks. + oai:arXiv.org:2512.07867v1 + q-fin.RM + cs.AI + econ.EM + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zilin Li, Weiwei Xu, Vicki Kane + Masoud Soleimani - Comparing BFGS and OGR for Second-Order Optimization - https://arxiv.org/abs/2512.06969 - arXiv:2512.06969v1 Announce Type: new -Abstract: Estimating the Hessian matrix, especially for neural network training, is a challenging problem due to high dimensionality and cost. In this work, we compare the classical Sherman-Morrison update used in the popular BFGS method (Broy-den-Fletcher-Goldfarb-Shanno), which maintains a positive definite Hessian approximation under a convexity assumption, with a novel approach called Online Gradient Regression (OGR). OGR performs regression of gradients against positions using an exponential moving average to estimate second derivatives online, without requiring Hessian inversion. Unlike BFGS, OGR allows estimation of a general (not necessarily positive definite) Hessian and can thus handle non-convex structures. We evaluate both methods across standard test functions and demonstrate that OGR achieves faster convergence and improved loss, particularly in non-convex settings. - oai:arXiv.org:2512.06969v1 - cs.LG + Manifolds and Modules: How Function Develops in a Neural Foundation Model + https://arxiv.org/abs/2512.07869 + arXiv:2512.07869v1 Announce Type: cross +Abstract: Foundation models have shown remarkable success in fitting biological visual systems; however, their black-box nature inherently limits their utility for under- standing brain function. Here, we peek inside a SOTA foundation model of neural activity (Wang et al., 2025) as a physiologist might, characterizing each 'neuron' based on its temporal response properties to parametric stimuli. We analyze how different stimuli are represented in neural activity space by building decoding man- ifolds, and we analyze how different neurons are represented in stimulus-response space by building neural encoding manifolds. We find that the different processing stages of the model (i.e., the feedforward encoder, recurrent, and readout modules) each exhibit qualitatively different representational structures in these manifolds. The recurrent module shows a jump in capabilities over the encoder module by 'pushing apart' the representations of different temporal stimulus patterns; while the readout module achieves biological fidelity by using numerous specialized feature maps rather than biologically plausible mechanisms. Overall, we present this work as a study of the inner workings of a prominent neural foundation model, gaining insights into the biological relevance of its internals through the novel analysis of its neurons' joint temporal response patterns. + oai:arXiv.org:2512.07869v1 + q-bio.NC cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Adrian Przybysz, Miko{\l}aj Ko{\l}ek, Franciszek Sobota, Jarek Duda + Johannes Bertram, Luciano Dyballa, T. Anderson Keller, Savik Kinger, Steven W. Zucker - Prediction with Expert Advice under Local Differential Privacy - https://arxiv.org/abs/2512.06971 - arXiv:2512.06971v1 Announce Type: new -Abstract: We study the classic problem of prediction with expert advice under the constraint of local differential privacy (LDP). In this context, we first show that a classical algorithm naturally satisfies LDP and then design two new algorithms that improve it: RW-AdaBatch and RW-Meta. For RW-AdaBatch, we exploit the limited-switching behavior induced by LDP to provide a novel form of privacy amplification that grows stronger on easier data, analogous to the shuffle model in offline learning. Drawing on the theory of random walks, we prove that this improvement carries essentially no utility cost. For RW-Meta, we develop a general method for privately selecting between experts that are themselves non-trivial learning algorithms, and we show that in the context of LDP this carries no extra privacy cost. In contrast, prior work has only considered data-independent experts. We also derive formal regret bounds that scale inversely with the degree of independence between experts. Our analysis is supplemented by evaluation on real-world data reported by hospitals during the COVID-19 pandemic; RW-Meta outperforms both the classical baseline and a state-of-the-art \textit{central} DP algorithm by 1.5-3$\times$ on the task of predicting which hospital will report the highest density of COVID patients each week. - oai:arXiv.org:2512.06971v1 - cs.LG - cs.CR - cs.DS - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - new + Quantum Circuit Reasoning Models: A Variational Framework for Differentiable Logical Inference + https://arxiv.org/abs/2512.07871 + arXiv:2512.07871v1 Announce Type: cross +Abstract: This report introduces a novel class of reasoning architectures, termed Quantum Circuit Reasoning Models (QCRM), which extend the concept of Variational Quantum Circuits (VQC) from energy minimization and classification tasks to structured logical inference and reasoning. We posit that fundamental quantum mechanical operations, superposition, entanglement, interference, and measurement, naturally map to essential reasoning primitives such as hypothesis branching, constraint propagation, consistency enforcement, and decision making. The resulting framework combines quantum-inspired computation with differentiable optimization, enabling reasoning to emerge as a process of amplitude evolution and interference-driven selection of self-consistent states. We develop the mathematical foundation of QCRM, define its parameterized circuit architecture, and show how logical rules can be encoded as unitary transformations over proposition-qubit states. We further formalize a training objective grounded in classical gradient descent over circuit parameters and discuss simulation-based implementations on classical hardware. Finally, we propose the Quantum Reasoning Layer (QRL) as a differentiable hybrid component for composable reasoning models applicable to scientific, biomedical, and chemical inference domains. + oai:arXiv.org:2512.07871v1 + quant-ph + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Ben Jacobsen, Kassem Fawaz + Andrew Kiruluta - Joint Learning of Feasibility-Aware Signal Temporal Logic and BarrierNet for Robust and Correct Control - https://arxiv.org/abs/2512.06973 - arXiv:2512.06973v1 Announce Type: new -Abstract: Control Barrier Functions (CBFs) have emerged as a powerful tool for enforcing safety in optimization-based controllers, and their integration with Signal Temporal Logic (STL) has enabled the specification-driven synthesis of complex robotic behaviors. However, existing CBF-STL approaches typically rely on fixed hyperparameters and myopic, per-time step optimization, which can lead to overly conservative behavior, infeasibility near tight input limits, and difficulty satisfying long-horizon STL tasks. To address these limitations, we propose a feasibility-aware learning framework that embeds trainable, time-varying High Order Control Barrier Functions (HOCBFs) into a differentiable Quadratic Program (dQP). Our approach provides a systematic procedure for constructing time-varying HOCBF constraints for a broad fragment of STL and introduces a unified robustness measure that jointly captures STL satisfaction, QP feasibility, and control-bound compliance. Three neural networks-InitNet, RefNet, and an extended BarrierNet-collaborate to generate reference inputs and adapt constraint-related hyperparameters automatically over time and across initial conditions, reducing conservativeness while maximizing robustness. The resulting controller achieves STL satisfaction with strictly feasible dQPs and requires no manual tuning. Simulation results demonstrate that the proposed framework maintains high STL robustness under tight input bounds and significantly outperforms fixed-parameter and non-adaptive baselines in complex environments. - oai:arXiv.org:2512.06973v1 - eess.SY - cs.LG - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new + Referenceless Proton Resonance Frequency Thermometry Using Deep Learning with Self-Attention + https://arxiv.org/abs/2512.07882 + arXiv:2512.07882v1 Announce Type: cross +Abstract: Background: Accurate proton resonance frequency (PRF) MR thermometry is essential for monitoring temperature rise during thermal ablation with high intensity focused ultrasound (FUS). Conventional referenceless methods such as complex field estimation (CFE) and phase finite difference (PFD) tend to exhibit errors when susceptibility-induced phase discontinuities occur at tissue interfaces. + oai:arXiv.org:2512.07882v1 + physics.med-ph + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shuo Liu, Wenliang Liu, Wei Xiao, Calin A. Belta + Yueran Zhao, Chang-Sheng Mei, Nathan J. McDannold, Shenyan Zong, Guofeng Shen - Smooth geometry extraction from SIMP topology optimization: Signed distance function approach with volume preservation - https://arxiv.org/abs/2512.06976 - arXiv:2512.06976v1 Announce Type: new -Abstract: This paper presents a novel post-processing methodology for extracting high-quality geometries from density-based topology optimization results. Current post-processing approaches often struggle to simultaneously achieve smooth boundaries, preserve volume fraction, and maintain topological features. We propose a robust method based on a signed distance function (SDF) that addresses these challenges through a two-stage process: first, an SDF representation of density isocontours is constructed, which is followed by geometry refinement using radial basis functions (RBFs). The method generates smooth boundary representations that appear to originate from much finer discretizations while maintaining the computational efficiency of coarse mesh optimization. Through comprehensive validation, our approach demonstrates a 18% reduction in maximum equivalent stress values compared to conventional methods, achieved through continuous geometric transitions at boundaries. The resulting implicit boundary representation facilitates seamless export to standard manufacturing formats without intermediate reconstruction steps, providing a robust foundation for practical engineering applications where high-quality geometric representations are essential. - oai:arXiv.org:2512.06976v1 - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - new + On the discrete to continuous condensing aggregation equation: A weak convergence approach + https://arxiv.org/abs/2512.07883 + arXiv:2512.07883v1 Announce Type: cross +Abstract: In this article, we study the passage of limits from discrete to continuous condensing aggregation equation which comprises of Oort-Hulst-Safronov (OHS) equation together with inverse aggregation process. We establish the relation between discrete and continuous condensing aggregation equations in its most generalized form, where kinetic-kernels with respect to OHS and inverse aggregation equations are not always equal. Convergence criterion is proved under suitable a priori estimates by approximating the continuous equation through a sequence of discrete equations, which subsequently converges towards the solution of the continuous equation by weak compactness principles. Existence of solution to the discrete model and uniform bounds on different order moments over finite time under particular conditions on kinetic-kernels are investigated. We analyze long-time dynamics and blowup of the solution leading to mass-loss or gelation for specific kernels. Three numerical experiments show the accuracy and convergence of approximated solutions to the exact solution of the continuous equation when $\varepsilon$ approaches zero. + oai:arXiv.org:2512.07883v1 + math.AP + cs.NA + math.FA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - 10.2139/ssrn.5374550 - Ond\v{r}ej Je\v{z}ek (Institute of Thermomechanics, Czech Academy of Sciences, Prague, Czech Republic, Faculty of Mechanical Engineering, Czech Technical University in Prague, Prague, Czech Republic), J\'an Kopa\v{c}ka (Institute of Thermomechanics, Czech Academy of Sciences, Prague, Czech Republic), Martin Isoz (Institute of Thermomechanics, Czech Academy of Sciences, Prague, Czech Republic), Du\v{s}an Gabriel (Institute of Thermomechanics, Czech Academy of Sciences, Prague, Czech Republic), Pavel Mar\v{s}\'alek (Faculty of Mechanical Engineering, VSB - Technical University of Ostrava, Ostrava, Czech Republic), Martin \v{S}otola (Faculty of Mechanical Engineering, VSB - Technical University of Ostrava, Ostrava, Czech Republic), Radim Halama (Faculty of Mechanical Engineering, VSB - Technical University of Ostrava, Ostrava, Czech Republic) - - - DC-Biased Homogenized Harmonic Balance Finite Element Method - https://arxiv.org/abs/2512.06978 - arXiv:2512.06978v1 Announce Type: new -Abstract: The homogenized harmonic balance finite element (FE) method enables efficient nonlinear eddy-current simulations of 3-D devices with lamination stacks by combining the harmonic balance method with a frequency-domain-based homogenization technique. This approach avoids expensive time stepping of the eddy-current field problem and allows the use of a relatively coarse FE mesh that does not resolve the individual laminates. In this paper, we extend the method to handle excitation signals with a dc bias. To achieve this, we adapt the original homogenization technique to better account for ferromagnetic saturation. The resulting formula for the homogenized reluctivity is evaluated using a look-up table computed from a 1-D FE simulation of a lamination and containing the average magnetic flux density in the lamination and the corresponding skin depth. We compare the results of the proposed method to those from a fine-mesh transient reference simulation. The tests cover different levels of ferromagnetic saturation and frequencies between 50 Hz and 10 kHz. For moderate ferromagnetic saturation, the method gives a good approximation of the eddy-current losses and the magnetic energy, with relative errors below 10%, while reducing the required number of degrees of freedom at 10 kHz by 1.5 orders of magnitude. This results in a reduction in simulation time from 2 days on a contemporary server to 90 minutes on a standard workstation. - oai:arXiv.org:2512.06978v1 - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jan-Magnus Christmann, Laura A. M. D'Angelo, Herbert De Gersem, Sven Pfeiffer, Sajjad H. Mirza + Anupama Ghorai, Jitraj Saha - Selective Masking based Self-Supervised Learning for Image Semantic Segmentation - https://arxiv.org/abs/2512.06981 - arXiv:2512.06981v1 Announce Type: new -Abstract: This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked image modelling pretraining methods. The proposed selective masking method selectively masks image patches with the highest reconstruction loss by breaking the image reconstruction pretraining into iterative steps to leverage the trained model's knowledge. We show on two general datasets (Pascal VOC and Cityscapes) and two weed segmentation datasets (Nassar 2020 and Sugarbeets 2016) that our proposed selective masking method outperforms the traditional random masking method and supervised ImageNet pretraining on downstream segmentation accuracy by 2.9% for general datasets and 2.5% for weed segmentation datasets. Furthermore, we found that our selective masking method significantly improves accuracy for the lowest-performing classes. Lastly, we show that using the same pretraining and downstream dataset yields the best result for low-budget self-supervised pretraining. Our proposed Selective Masking Image Reconstruction method provides an effective and practical solution to improve end-to-end semantic segmentation workflows, especially for scenarios that require limited model capacity to meet inference speed and computational resource requirements. - oai:arXiv.org:2512.06981v1 - cs.CV + Functional Random Forest with Adaptive Cost-Sensitive Splitting for Imbalanced Functional Data Classification + https://arxiv.org/abs/2512.07888 + arXiv:2512.07888v1 Announce Type: cross +Abstract: Classification of functional data where observations are curves or trajectories poses unique challenges, particularly under severe class imbalance. Traditional Random Forest algorithms, while robust for tabular data, often fail to capture the intrinsic structure of functional observations and struggle with minority class detection. This paper introduces Functional Random Forest with Adaptive Cost-Sensitive Splitting (FRF-ACS), a novel ensemble framework designed for imbalanced functional data classification. The proposed method leverages basis expansions and Functional Principal Component Analysis (FPCA) to represent curves efficiently, enabling trees to operate on low dimensional functional features. To address imbalance, we incorporate a dynamic cost sensitive splitting criterion that adjusts class weights locally at each node, combined with a hybrid sampling strategy integrating functional SMOTE and weighted bootstrapping. Additionally, curve specific similarity metrics replace traditional Euclidean measures to preserve functional characteristics during leaf assignment. Extensive experiments on synthetic and real world datasets including biomedical signals and sensor trajectories demonstrate that FRF-ACS significantly improves minority class recall and overall predictive performance compared to existing functional classifiers and imbalance handling techniques. This work provides a scalable, interpretable solution for high dimensional functional data analysis in domains where minority class detection is critical. + oai:arXiv.org:2512.07888v1 + stat.ML + cs.AI cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + stat.AP + stat.CO + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Yuemin Wang, Ian Stavness + Fahad Mostafa, Hafiz Khan - LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding - https://arxiv.org/abs/2512.06982 - arXiv:2512.06982v1 Announce Type: new -Abstract: Designing state encoders for reinforcement learning (RL) with multiple information sources -- such as sensor measurements, time-series signals, image observations, and textual instructions -- remains underexplored and often requires manual design. We formalize this challenge as a problem of composite neural architecture search (NAS), where multiple source-specific modules and a fusion module are jointly optimized. Existing NAS methods overlook useful side information from the intermediate outputs of these modules -- such as their representation quality -- limiting sample efficiency in multi-source RL settings. To address this, we propose an LLM-driven NAS pipeline that leverages language-model priors and intermediate-output signals to guide sample-efficient search for high-performing composite state encoders. On a mixed-autonomy traffic control task, our approach discovers higher-performing architectures with fewer candidate evaluations than traditional NAS baselines and the LLM-based GENIUS framework. - oai:arXiv.org:2512.06982v1 - cs.LG - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yu Yu, Qian Xie, Nairen Cao, Li Jin + Harmonizing Community Science Datasets to Model Highly Pathogenic Avian Influenza (HPAI) in Birds in the Subantarctic + https://arxiv.org/abs/2512.07907 + arXiv:2512.07907v1 Announce Type: cross +Abstract: Community science observational datasets are useful in epidemiology and ecology for modeling species distributions, but the heterogeneous nature of the data presents significant challenges for standardization, data quality assurance and control, and workflow management. In this paper, we present a data workflow for cleaning and harmonizing multiple community science datasets, which we implement in a case study using eBird, iNaturalist, GBIF, and other datasets to model the impact of highly pathogenic avian influenza in populations of birds in the subantarctic. We predict population sizes for several species where the demographics are not known, and we present novel estimates for potential mortality rates from HPAI for those species, based on a novel aggregated dataset of mortality rates in the subantarctic. + oai:arXiv.org:2512.07907v1 + q-bio.PE + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Proceedings of Pacific Rim International Conference on Artificial Intelligence 2025 (PRICAI 2025): Artificial Intelligence for Earth and Environmental Science 2025 (AIEES 2025) Workshop, 17-21 Nov 2025, Wellington, New Zealand + Richard Littauer, Kris Bubendorfer - On Memory: A comparison of memory mechanisms in world models - https://arxiv.org/abs/2512.06983 - arXiv:2512.06983v1 Announce Type: new -Abstract: World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. However, their ability to plan over long horizons is limited by the effective memory span of the backbone architecture. This limitation leads to perceptual drift in long rollouts, hindering the model's capacity to perform loop closures within imagined trajectories. In this work, we investigate the effective memory span of transformer-based world models through an analysis of several memory augmentation mechanisms. We introduce a taxonomy that distinguishes between memory encoding and memory injection mechanisms, motivating their roles in extending the world model's memory through the lens of residual stream dynamics. Using a state recall evaluation task, we measure the memory recall of each mechanism and analyze its respective trade-offs. Our findings show that memory mechanisms improve the effective memory span in vision transformers and provide a path to completing loop closures within a world model's imagination. - oai:arXiv.org:2512.06983v1 - cs.AI + Conformal Defects in Neural Network Field Theories + https://arxiv.org/abs/2512.07946 + arXiv:2512.07946v1 Announce Type: cross +Abstract: Neural Network Field Theories (NN-FTs) represent a novel construction of arbitrary field theories, including those of conformal fields, through the specification of the network architecture and prior distribution for the network parameters. In this work, we present a formalism for the construction of conformally invariant defects in these NN-FTs. We demonstrate this new formalism in two toy models of NN scalar field theories. We develop an NN interpretation of an expansion akin to the defect OPE in two-point correlation functions in these models. + oai:arXiv.org:2512.07946v1 + hep-th cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Eli J. Laird, Corey Clark + Pietro Capuozzo, Brandon Robinson, Benjamin Suzzoni - Extending Action Logic with Omega Iteration - https://arxiv.org/abs/2512.06985 - arXiv:2512.06985v1 Announce Type: new -Abstract: We present a proof system that extends action logic by omega iteration, which is viewed as infinitary multiplicative conjunction. We prove cut admissibility and establish complexity bounds for the provability predicate. - oai:arXiv.org:2512.06985v1 - cs.LO - math.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tikhon Pshenitsyn + ALS Storage Ring RF Control System Upgrade Plan and Status + https://arxiv.org/abs/2512.07996 + arXiv:2512.07996v1 Announce Type: cross +Abstract: The Advanced Light Source (ALS) at Lawrence Berkeley National Laboratory, a third-generation synchrotron light source operational since 1992, is undergoing a comprehensive upgrade of its storage ring RF control system. The legacy Horner PLC controllers and remote I/O modules, now at end-of-life, are being replaced with an Allen-Bradley PLC platform to improve maintainability, reliability, and long-term support. This paper presents the planning, design, and current status of the upgrade project. + oai:arXiv.org:2512.07996v1 + physics.acc-ph + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by/4.0/ + 10.18429/jacow-icalepcs2025-tupd030 + ICALEPCS 2025 + Najm Us Saqib, Angel Jurado, Esteban Andrade, Qiang Du, Jeong Han Lee, Miroslaw Dach, Benjamin Flugstad - OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction - https://arxiv.org/abs/2512.06987 - arXiv:2512.06987v1 Announce Type: new -Abstract: Accurately predicting experimentally-realizable 3D molecular crystal structures from their 2D chemical graphs is a long-standing open challenge in computational chemistry called crystal structure prediction (CSP). Efficiently solving this problem has implications ranging from pharmaceuticals to organic semiconductors, as crystal packing directly governs the physical and chemical properties of organic solids. In this paper, we introduce OXtal, a large-scale 100M parameter all-atom diffusion model that directly learns the conditional joint distribution over intramolecular conformations and periodic packing. To efficiently scale OXtal, we abandon explicit equivariant architectures imposing inductive bias arising from crystal symmetries in favor of data augmentation strategies. We further propose a novel crystallization-inspired lattice-free training scheme, Stoichiometric Stochastic Shell Sampling ($S^4$), that efficiently captures long-range interactions while sidestepping explicit lattice parametrization -- thus enabling more scalable architectural choices at all-atom resolution. By leveraging a large dataset of 600K experimentally validated crystal structures (including rigid and flexible molecules, co-crystals, and solvates), OXtal achieves orders-of-magnitude improvements over prior ab initio machine learning CSP methods, while remaining orders of magnitude cheaper than traditional quantum-chemical approaches. Specifically, OXtal recovers experimental structures with conformer $\text{RMSD}_1<0.5$ {\AA} and attains over 80\% packing similarity rate, demonstrating its ability to model both thermodynamic and kinetic regularities of molecular crystallization. - oai:arXiv.org:2512.06987v1 + Provable Diffusion Posterior Sampling for Bayesian Inversion + https://arxiv.org/abs/2512.08022 + arXiv:2512.08022v1 Announce Type: cross +Abstract: This paper proposes a novel diffusion-based posterior sampling method within a plug-and-play (PnP) framework. Our approach constructs a probability transport from an easy-to-sample terminal distribution to the target posterior, using a warm-start strategy to initialize the particles. To approximate the posterior score, we develop a Monte Carlo estimator in which particles are generated using Langevin dynamics, avoiding the heuristic approximations commonly used in prior work. The score governing the Langevin dynamics is learned from data, enabling the model to capture rich structural features of the underlying prior distribution. On the theoretical side, we provide non-asymptotic error bounds, showing that the method converges even for complex, multi-modal target posterior distributions. These bounds explicitly quantify the errors arising from posterior score estimation, the warm-start initialization, and the posterior sampling procedure. Our analysis further clarifies how the prior score-matching error and the condition number of the Bayesian inverse problem influence overall performance. Finally, we present numerical experiments demonstrating the effectiveness of the proposed method across a range of inverse problems. + oai:arXiv.org:2512.08022v1 + stat.ML cs.LG - cond-mat.mtrl-sci - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.NA + math.NA + math.PR + math.ST + stat.TH + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Emily Jin, Andrei Cristian Nica, Mikhail Galkin, Jarrid Rector-Brooks, Kin Long Kelvin Lee, Santiago Miret, Frances H. Arnold, Michael Bronstein, Avishek Joey Bose, Alexander Tong, Cheng-Hao Liu + Jinyuan Chang, Chenguang Duan, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang, Cheng Yuan - Space efficient implementation of hypergraph dualization in the D-basis algorithm - https://arxiv.org/abs/2512.06988 - arXiv:2512.06988v1 Announce Type: new -Abstract: We present a new implementation of the $D$-basis algorithm called the Small Space which considerably reduces the algorithm's memory usage for data analysis applications. The previous implementation delivers the complete set of implications that hold on the set of attributes of an input binary table. In the new version, the only output is the frequencies of attributes that appear in the antecedents of implications from the $D$-basis, with a fixed consequent attribute. Such frequencies, rather than the implications themselves, became the primary focus in analysis of datasets where the $D$-basis has been applied over the last decade. The $D$-basis employs a hypergraph dualization algorithm, and a dualization implementation known as Reverse Search allows for the gradual computation of frequencies without the need for storing all discovered implications. We demonstrate the effectiveness of the Small Space implementation by comparing the runtimes and maximum memory usage of this new version with the current implementation. - oai:arXiv.org:2512.06988v1 - cs.DB - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new + Locally Recoverable Codes with availability from a family of fibered surfaces + https://arxiv.org/abs/2512.08100 + arXiv:2512.08100v1 Announce Type: cross +Abstract: We construct Locally Recoverable Codes (LRCs) with availability $2$ from a family of fibered surfaces. To obtain the locality and availability properties, and to estimate the minimum distance of the codes, we combine techniques coming from the theory of one-variable function fields and from the theory of fibrations on surfaces. When the locality parameter is $r=3$, we obtain a sharp bound on the minimum distance of the codes. In that case, we give a geometric interpretation of our codes in terms of doubly elliptic surfaces. In particular, this provides the first instance of an error correcting code constructed using a (doubly elliptic) K3 surface. + oai:arXiv.org:2512.08100v1 + math.AG + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Skylar Homan, Anoop Krishnadas, Kira Adaricheva + Cec\'ilia Salgado, Lara Vicino - Flash Multi-Head Feed-Forward Network - https://arxiv.org/abs/2512.06989 - arXiv:2512.06989v1 Announce Type: new -Abstract: We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively applying them to FFNs faces two challenges: memory consumption scaling with the head count, and an imbalanced ratio between the growing intermediate size and the fixed head dimension as models scale, which degrades scalability and expressive power. To address these challenges, we propose Flash Multi-Head FFN (FlashMHF), with two key innovations: an I/O-aware fused kernel computing outputs online in SRAM akin to FlashAttention, and a design using dynamically weighted parallel sub-networks to maintain a balanced ratio between intermediate and head dimensions. Validated on models from 128M to 1.3B parameters, FlashMHF consistently improves perplexity and downstream task accuracy over SwiGLU FFNs, while reducing peak memory usage by 3-5x and accelerating inference by up to 1.08x. Our work establishes the multi-head design as a superior architectural principle for FFNs, presenting FlashMHF as a powerful, efficient, and scalable alternative to FFNs in Transformers. - oai:arXiv.org:2512.06989v1 - cs.LG - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Minshen Zhang, Xiang Hu, Jianguo Li, Wei Wu, Kewei Tu + FlowSteer: Conditioning Flow Field for Consistent Image Restoration + https://arxiv.org/abs/2512.08125 + arXiv:2512.08125v1 Announce Type: cross +Abstract: Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. Prior work mitigate this drift with data-specific flows or task-specific adapters that are computationally heavy and not scalable across tasks. This raises the question "Can't we efficiently manipulate the existing generative capabilities of a flow model?" To this end, we introduce FlowSteer (FS), an operator-aware conditioning scheme that injects measurement priors along the sampling path,coupling a frozed flow's implicit guidance with explicit measurement constraints. Across super-resolution, deblurring, denoising, and colorization, FS improves measurement consistency and identity preservation in a strictly zero-shot setting-no retrained models, no adapters. We show how the nature of flow models and their sensitivities to noise inform the design of such a scheduler. FlowSteer, although simple, achieves a higher fidelity of reconstructed images, while leveraging the rich generative priors of flow models. + oai:arXiv.org:2512.08125v1 + eess.IV + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by/4.0/ + Tharindu Wickremasinghe, Chenyang Qi, Harshana Weligampola, Zhengzhong Tu, Stanley H. Chan - Utilizing Multi-Agent Reinforcement Learning with Encoder-Decoder Architecture Agents to Identify Optimal Resection Location in Glioblastoma Multiforme Patients - https://arxiv.org/abs/2512.06990 - arXiv:2512.06990v1 Announce Type: new -Abstract: Currently, there is a noticeable lack of AI in the medical field to support doctors in treating heterogenous brain tumors such as Glioblastoma Multiforme (GBM), the deadliest human cancer in the world with a five-year survival rate of just 5.1%. This project develops an AI system offering the only end-to-end solution by aiding doctors with both diagnosis and treatment planning. In the diagnosis phase, a sequential decision-making framework consisting of 4 classification models (Convolutional Neural Networks and Support Vector Machine) are used. Each model progressively classifies the patient's brain into increasingly specific categories, with the final step being named diagnosis. For treatment planning, an RL system consisting of 3 generative models is used. First, the resection model (diffusion model) analyzes the diagnosed GBM MRI and predicts a possible resection outcome. Second, the radiotherapy model (Spatio-Temporal Vision Transformer) generates an MRI of the brain's progression after a user-defined number of weeks. Third, the chemotherapy model (Diffusion Model) produces the post-treatment MRI. A survival rate calculator (Convolutional Neural Network) then checks if the generated post treatment MRI has a survival rate within 15% of the user defined target. If not, a feedback loop using proximal policy optimization iterates over this system until an optimal resection location is identified. When compared to existing solutions, this project found 3 key findings: (1) Using a sequential decision-making framework consisting of 4 small diagnostic models reduced computing costs by 22.28x, (2) Transformers regression capabilities decreased tumor progression inference time by 113 hours, and (3) Applying Augmentations resembling Real-life situations improved overall DICE scores by 2.9%. These results project to increase survival rates by 0.9%, potentially saving approximately 2,250 lives. - oai:arXiv.org:2512.06990v1 - cs.AI - cs.CV - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Adversarial Barrier in Uniform Class Separation + https://arxiv.org/abs/2512.08149 + arXiv:2512.08149v1 Announce Type: cross +Abstract: We identify a strong structural obstruction to Uniform Separation in constructive arithmetic. The mechanism is independent of semantic content; it emerges whenever two distinct evaluator predicates are sustained in parallel and inference remains uniformly representable in an extension of HA. Under these conditions, any putative Uniform Class Separation principle becomes a distinguished instance of a fixed point construction. The resulting limitation is stricter in scope than classical separation barriers (Baker; Rudich; Aaronson et~al.) insofar as it constrains the logical form of uniform separation within HA, rather than limiting particular relativizing, naturalizing, or algebrizing techniques. + oai:arXiv.org:2512.08149v1 + math.LO + cs.CC + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Krishna Arun, Moinak Bhattachrya, Paras Goel + Milan Rosko - Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models - https://arxiv.org/abs/2512.06991 - arXiv:2512.06991v1 Announce Type: new -Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks. This research introduces a novel "Prompting-in-a-Series" algorithm, termed PICEPR (Psychology-Informed Contents Embeddings for Personality Recognition), featuring two pipelines: (a) Contents and (b) Embeddings. The approach demonstrates how a modularised decoder-only LLM can summarize or generate content, which can aid in classifying or enhancing personality recognition functions as a personality feature extractor and a generator for personality-rich content. We conducted various experiments to provide evidence to justify the rationale behind the PICEPR algorithm. Meanwhile, we also explored closed-source models such as \textit{gpt4o} from OpenAI and \textit{gemini} from Google, along with open-source models like \textit{mistral} from Mistral AI, to compare the quality of the generated content. The PICEPR algorithm has achieved a new state-of-the-art performance for personality recognition by 5-15\% improvement. The work repository and models' weight can be found at https://research.jingjietan.com/?q=PICEPR. - oai:arXiv.org:2512.06991v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Worst-case generation via minimax optimization in Wasserstein space + https://arxiv.org/abs/2512.08176 + arXiv:2512.08176v1 Announce Type: cross +Abstract: Worst-case generation plays a critical role in evaluating robustness and stress-testing systems under distribution shifts, in applications ranging from machine learning models to power grids and medical prediction systems. We develop a generative modeling framework for worst-case generation for a pre-specified risk, based on min-max optimization over continuous probability distributions, namely the Wasserstein space. Unlike traditional discrete distributionally robust optimization approaches, which often suffer from scalability issues, limited generalization, and costly worst-case inference, our framework exploits the Brenier theorem to characterize the least favorable (worst-case) distribution as the pushforward of a transport map from a continuous reference measure, enabling a continuous and expressive notion of risk-induced generation beyond classical discrete DRO formulations. Based on the min-max formulation, we propose a Gradient Descent Ascent (GDA)-type scheme that updates the decision model and the transport map in a single loop, establishing global convergence guarantees under mild regularity assumptions and possibly without convexity-concavity. We also propose to parameterize the transport map using a neural network that can be trained simultaneously with the GDA iterations by matching the transported training samples, thereby achieving a simulation-free approach. The efficiency of the proposed method as a risk-induced worst-case generator is validated by numerical experiments on synthetic and image data. + oai:arXiv.org:2512.08176v1 + stat.ML + cs.LG + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/TCSS.2025.3593323 - IEEE Transactions on Computational Social Systems, pages 1-15, 2025 - Jing Jie Tan, Ban-Hoe Kwan, Danny Wee-Kiat Ng, Yan-Chai Hum, Anissa Mokraoui, Shih-Yu Lo + Xiuyuan Cheng, Yao Xie, Linglingzhi Zhu, Yunqin Zhu - Toward Reliable Machine Unlearning: Theory, Algorithms, and Evaluation - https://arxiv.org/abs/2512.06993 - arXiv:2512.06993v1 Announce Type: new -Abstract: We propose new methodologies for both unlearning random set of samples and class unlearning and show that they outperform existing methods. The main driver of our unlearning methods is the similarity of predictions to a retrained model on both the forget and remain samples. We introduce Adversarial Machine UNlearning (AMUN), which surpasses prior state-of-the-art methods for image classification based on SOTA MIA scores. AMUN lowers the model's confidence on forget samples by fine-tuning on their corresponding adversarial examples. Through theoretical analysis, we identify factors governing AMUN's performance, including smoothness. To facilitate training of smooth models with a controlled Lipschitz constant, we propose FastClip, a scalable method that performs layer-wise spectral-norm clipping of affine layers. In a separate study, we show that increased smoothness naturally improves adversarial example transfer, thereby supporting the second factor above. - Following the same principles for class unlearning, we show that existing methods fail in replicating a retrained model's behavior by introducing a nearest-neighbor membership inference attack (MIA-NN) that uses the probabilities assigned to neighboring classes to detect unlearned samples and demonstrate the vulnerability of such methods. We then propose a fine-tuning objective that mitigates this leakage by approximating, for forget-class inputs, the distribution over remaining classes that a model retrained from scratch would produce. To construct this approximation, we estimate inter-class similarity and tilt the target model's distribution accordingly. The resulting Tilted ReWeighting(TRW) distribution serves as the desired target during fine-tuning. Across multiple benchmarks, TRW matches or surpasses existing unlearning methods on prior metrics. - oai:arXiv.org:2512.06993v1 + Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation + https://arxiv.org/abs/2512.08216 + arXiv:2512.08216v1 Announce Type: cross +Abstract: Accurate segmentation of cancerous lesions from 3D computed tomography (CT) scans is essential for automated treatment planning and response assessment. However, even state-of-the-art models combining self-supervised learning (SSL) pretrained transformers with convolutional decoders are susceptible to out-of-distribution (OOD) inputs, generating confidently incorrect tumor segmentations, posing risks for safe clinical deployment. Existing logit-based methods suffer from task-specific model biases, while architectural enhancements to explicitly detect OOD increase parameters and computational costs. Hence, we introduce a plug-and-play and lightweight post-hoc random forests-based OOD detection framework called RF-Deep that leverages deep features with limited outlier exposure. RF-Deep enhances generalization to imaging variations by repurposing the hierarchical features from the pretrained-then-finetuned backbone encoder, providing task-relevant OOD detection by extracting the features from multiple regions of interest anchored to the predicted tumor segmentations. Hence, it scales to images of varying fields-of-view. We compared RF-Deep against existing OOD detection methods using 1,916 CT scans across near-OOD (pulmonary embolism, negative COVID-19) and far-OOD (kidney cancer, healthy pancreas) datasets. RF-Deep achieved AUROC > 93.50 for the challenging near-OOD datasets and near-perfect detection (AUROC > 99.00) for the far-OOD datasets, substantially outperforming logit-based and radiomics approaches. RF-Deep maintained similar performance consistency across networks of different depths and pretraining strategies, demonstrating its effectiveness as a lightweight, architecture-agnostic approach to enhance the reliability of tumor segmentation from CT volumes. + oai:arXiv.org:2512.08216v1 + eess.IV + cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ali Ebrahimpour-Boroojeny + Aneesh Rangnekar, Harini Veeraraghavan - Parametric Design of a Cable-Driven Coaxial Spherical Parallel Mechanism for Ultrasound Scans - https://arxiv.org/abs/2512.06995 - arXiv:2512.06995v1 Announce Type: new -Abstract: Haptic interfaces play a critical role in medical teleoperation by enabling surgeons to interact with remote environments through realistic force and motion feedback. Achieving high fidelity in such systems requires balancing performance trade-off among workspace, dexterity, stiffness, inertia, and bandwidth, particularly in applications demanding pure rotational motion. This paper presents the design methodology and kinematic analysis of a Cable-Driven Coaxial Spherical Parallel Mechanism (CDC-SPM) developed to address these challenges. The proposed cable-driven interface design allows for reducing the mass placed at the robot arm end-effector, thereby minimizing inertial loads, enhancing stiffness, and improving dynamic responsiveness. Through parallel and coaxial actuation, the mechanism achieves decoupled rotational degrees of freedom with isotropic force and torque transmission. Simulation and analysis demonstrate that the CDC-SPM provides accurate, responsive, and safe motion characteristics suitable for high-precision haptic applications. These results highlight the mechanism's potential for medical teleoperation tasks such as ultrasound imaging, where precise and intuitive manipulation is essential. - oai:arXiv.org:2512.06995v1 - cs.RO - physics.class-ph - Tue, 09 Dec 2025 00:00:00 -0500 - new + Self-Reinforced Deep Priors for Reparameterized Full Waveform Inversion + https://arxiv.org/abs/2512.08284 + arXiv:2512.08284v1 Announce Type: cross +Abstract: Full waveform inversion (FWI) has become a widely adopted technique for high-resolution subsurface imaging. However, its inherent strong nonlinearity often results in convergence toward local minima. Recently, deep image prior-based reparameterized FWI (DIP-FWI) has been proposed to alleviate the dependence on massive training data. By exploiting the spectral bias and implicit regularization in the neural network architecture, DIP-FWI can effectively avoid local minima and reconstruct more geologically plausible velocity models. Nevertheless, existing DIP-FWI typically use a fixed random input throughout the inversion process, which fails to utilize the mapping and correlation between the input and output of the network. Moreover, under complex geological conditions, the lack of informative prior in the input can exacerbate the ill-posedness of the inverse problem, leading to artifacts and unstable reconstructions. To address these limitations, we propose a self-reinforced DIP-FWI (SRDIP-FWI) framework, in which a steering algorithm alternately updates both the network parameters and the input at each iteration using feedback from the current network output. This design allows adaptive structural enhancement and improved regularization, thereby effectively mitigating the ill-posedness in FWI. Additionally, we analyze the spectral bias of the network in SRDIP-FWI and quantify its role in multiscale velocity model building. Synthetic tests and field land data application demonstrate that SRDIP-FWI achieves superior resolution, improved accuracy and greater depth penetration compared to multiscale FWI. More importantly, SRDIP-FWI eliminates the need for manual frequency-band selection and time-window picking, substantially simplifying the inversion workflow. Overall, the proposed method provides a novel, adaptive and robust framework for accurate subsurface velocity model reconstruction. + oai:arXiv.org:2512.08284v1 + physics.geo-ph + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Maryam Seraj, Mohammad Hossein Kamrava, Carlo Tiseo + Guangyuan Zou, Junlun Li, Feng Liu, Xuejing Zheng, Jianjian Xie, Guoyi Chen - Near-Optimal Bayesian Online Assortment of Reusable Resources - https://arxiv.org/abs/2512.06997 - arXiv:2512.06997v1 Announce Type: new -Abstract: Motivated by the applications of rental services in e-commerce, we consider revenue maximization in online assortment of reusable resources for a stream of arriving consumers with different types. We design competitive online algorithms with respect to the optimum online policy in the Bayesian setting, in which types are drawn independently from known heterogeneous distributions over time. In the regime where the minimum of initial inventories $c_0$ is large, our main result is a near-optimal $1-\min\left(\frac{1}{2},\sqrt{\log(c_0)/c_0}\right)$ competitive algorithm for the general case of reusable resources. Our algorithm relies on an expected LP benchmark for the problem, solves this LP, and simulates the solution through an independent randomized rounding. The main challenge is obtaining point-wise inventory feasibility in a computationally efficient fashion from these simulation-based algorithms. To this end, we use several technical ingredients to design $\textit{discarding policies}$ -- one for each resource. These policies handle the trade-off between the inventory feasibility under reusability and the revenue loss of each of the resources. However, discarding a unit of a resource changes the future consumption of other resources. To handle this new challenge, we also introduce $\textit{post-processing}$ assortment procedures that help with designing and analyzing our discarding policies as they run in parallel, which might be of independent interest. As a side result, by leveraging techniques from the literature on prophet inequality, we further show an improved near-optimal $1-1/\sqrt{c_0+3}$ competitive algorithm for the special case of non-reusable resources. We finally evaluate the performance of our algorithms using the numerical simulations on the synthetic data. - oai:arXiv.org:2512.06997v1 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 - new + M\"obius Transformations and the Analytic--Geometric Reconstruction of the Induction--Machine Circle Diagram + https://arxiv.org/abs/2512.08302 + arXiv:2512.08302v1 Announce Type: cross +Abstract: The Heyland circle diagram is a classical graphical method for representing the steady--state behavior of induction machines using no--load and blocked--rotor test data. Despite its long pedagogical history, the traditional geometric construction has not been formalized within a closed analytic framework. This note develops a complete Euclidean reconstruction of the diagram using only the two measured phasors and elementary geometric operations, yielding a unique circle, a torque chord, a slip scale, and a maximum--torque point. We prove that this constructed circle coincides precisely with the analytic steady--state current locus obtained from the per--phase equivalent circuit. A M\"obius transformation interpretation reveals the complex--analytic origin of the diagram's circularity and offers a compact explanation of its geometric structure. + oai:arXiv.org:2512.08302v1 + math.DS + cs.SY + eess.SY + math.CV + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1287/opre.2020.0687 - Yiding Feng, Rad Niazadeh, Amin Saberi + Anubhav Gupta - Cell-free ISAC for Drone Detection Considering Coverage and Age of Sensing - https://arxiv.org/abs/2512.06998 - arXiv:2512.06998v1 Announce Type: new -Abstract: The growing presence of unauthorized drones poses significant threats to public safety, underscoring the need for aerial surveillance solutions. This work proposes a cell-free integrated sensing and communication (ISAC) framework enabling drone detection within the existing communication network infrastructure, while maintaining communication services. The system exploits the spatial diversity and coordination of distributed access points (APs) in a cell-free massive MIMO architecture to detect aerial passive targets. To evaluate sensing performance, we introduce two key metrics: age of sensing (AoS), capturing the freshness of sensing information, and sensing coverage. The proposed AoS metric includes not only the transmission delays as in the existing models, but also the processing for sensing and networking delay, which are critical in dynamic environments like drone detection. We introduce an ambiguity parameter quantifying the similarity between the target-to-receiver channels for two hotspots and develop a novel network configuration strategy, including hotspot grouping, AP clustering, and sensing pilot assignment, leveraging simultaneous multi-point sensing to minimize AoS. Our results show that the best trade-off between AoS and sensing coverage is achieved when the number of hotspots sharing the same time/frequency resource matches the number of sensing pilots, indicating ambiguity as the primary factor limiting the sensing performance. - oai:arXiv.org:2512.06998v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new + Magnetic activity of ultracool dwarfs in the LAMOST DR11 + https://arxiv.org/abs/2512.08305 + arXiv:2512.08305v1 Announce Type: cross +Abstract: Ultracool dwarfs consist of lowest-mass stars and brown dwarfs. Their interior is fully convective, different from that of the partly-convective Sun-like stars. Magnetic field generation process beneath the surface of ultracool dwarfs is still poorly understood and controversial. To increase samples of active ultracool dwarfs significantly, we have identified 962 ultracool dwarfs in the latest LAMOST data release, DR11. We also simulate the Chinese Space Station Survey Telescope (CSST) low-resolution slitless spectra by degrading the LAMOST spectra. A semi-supervised machine learning approach with an autoencoder model is built to identify ultracool dwarfs with the simulated CSST spectra, which demonstrates the capability of the CSST all-sky slitless spectroscopic survey on the detection of ultracool dwarfs. Magnetic activity of the ultracool dwarfs is investigated by using the H$\alpha$ line emission as a proxy. The rotational periods of 82 ultracool dwarfs are derived based on the Kepler/K2 light curves. We also derive the activity-rotation relation of the ultracool dwarfs, which is saturated around a Rossby number of 0.12. + oai:arXiv.org:2512.08305v1 + astro-ph.SR + astro-ph.IM + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zinat Behdad, Ozan Alp Topal, Cicek Cavdar + Yue Xiang, Shenghong Gu, Dongtao Cao - Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model - https://arxiv.org/abs/2512.06999 - arXiv:2512.06999v1 Announce Type: new -Abstract: Automated singing assessment is crucial for education and entertainment. However, existing systems face two fundamental limitations: reliance on reference tracks, which stifles creative expression, and the simplification of complex performances into non-diagnostic scores based solely on pitch and rhythm. We advocate for a shift from discriminative to descriptive evaluation, creating a complete ecosystem for reference-free, multi-dimensional assessment. First, we introduce Sing-MD, a large-scale dataset annotated by experts across four dimensions: breath control, timbre quality, emotional expression, and vocal technique. Our analysis reveals significant annotation inconsistencies among experts, challenging the validity of traditional accuracy-based metrics. Second, addressing the memory limitations of Multimodal Large Language Models (MLLMs) in analyzing full-length songs, we propose VocalVerse. This efficient hybrid architecture leverages a lightweight acoustic encoder to model global performance features and long-term dependencies. Third, to address automated metric shortcomings, we establish the H-TPR (Human-in-the-loop Tiered Perceptual Ranking) benchmark, which evaluates a model's ability to generate perceptually valid rankings rather than predicting noisy ground-truth scores. - oai:arXiv.org:2512.06999v1 - cs.SD - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Learned iterative networks: An operator learning perspective + https://arxiv.org/abs/2512.08444 + arXiv:2512.08444v1 Announce Type: cross +Abstract: Learned image reconstruction has become a pillar in computational imaging and inverse problems. Among the most successful approaches are learned iterative networks, which are formulated by unrolling classical iterative optimisation algorithms for solving variational problems. While the underlying algorithm is usually formulated in the functional analytic setting, learned approaches are often viewed as purely discrete. In this chapter we present a unified operator view for learned iterative networks. Specifically, we formulate a learned reconstruction operator, defining how to compute, and separately the learning problem, which defines what to compute. In this setting we present common approaches and show that many approaches are closely related in their core. We review linear as well as nonlinear inverse problems in this framework and present a short numerical study to conclude. + oai:arXiv.org:2512.08444v1 + eess.IV + cs.LG + cs.NA + math.FA + math.NA + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3746027.3758148 - Proceedings of the 33rd ACM International Conference on Multimedia (ACMMM 2025), Pages 12227-12236 - Zihao Wang, Ruibin Yuan, Ziqi Geng, Hengjia Li, Xingwei Qu, Xinyi Li, Songye Chen, Haoying Fu, Roger B. Dannenberg, Kejun Zhang + Andreas Hauptmann, Ozan \"Oktem - Benchmarking Deep Neural Networks for Modern Recommendation Systems - https://arxiv.org/abs/2512.07000 - arXiv:2512.07000v1 Announce Type: new -Abstract: This paper examines the deployment of seven different neural network architectures CNN, RNN, GNN, Autoencoder, Transformer, NCF, and Siamese Networks on three distinct datasets: Retail E-commerce, Amazon Products, and Netflix Prize. It evaluates their effectiveness through metrics such as accuracy, recall, F1-score, and diversity in recommendations. The results demonstrate that GNNs are particularly adept at managing complex item relationships in e-commerce environments, whereas RNNs are effective in capturing the temporal dynamics that are essential for platforms such as Netflix.. Siamese Networks are emphasized for their contribution to the diversification of recommendations, particularly in retail settings. Despite their benefits, issues like computational demands, reliance on extensive data, and the challenge of balancing accurate and diverse recommendations are addressed. The study seeks to inform the advancement of recommendation systems by suggesting hybrid methods that merge the strengths of various models to better satisfy user preferences and accommodate the evolving demands of contemporary digital platforms. - oai:arXiv.org:2512.07000v1 - cs.IR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Fused Gromov-Wasserstein Contrastive Learning for Effective Enzyme-Reaction Screening + https://arxiv.org/abs/2512.08508 + arXiv:2512.08508v1 Announce Type: cross +Abstract: Enzymes are crucial catalysts that enable a wide range of biochemical reactions. Efficiently identifying specific enzymes from vast protein libraries is essential for advancing biocatalysis. Traditional computational methods for enzyme screening and retrieval are time-consuming and resource-intensive. Recently, deep learning approaches have shown promise. However, these methods focus solely on the interaction between enzymes and reactions, overlooking the inherent hierarchical relationships within each domain. To address these limitations, we introduce FGW-CLIP, a novel contrastive learning framework based on optimizing the fused Gromov-Wasserstein distance. FGW-CLIP incorporates multiple alignments, including inter-domain alignment between reactions and enzymes and intra-domain alignment within enzymes and reactions. By introducing a tailored regularization term, our method minimizes the Gromov-Wasserstein distance between enzyme and reaction spaces, which enhances information integration across these domains. Extensive evaluations demonstrate the superiority of FGW-CLIP in challenging enzyme-reaction tasks. On the widely-used EnzymeMap benchmark, FGW-CLIP achieves state-of-the-art performance in enzyme virtual screening, as measured by BEDROC and EF metrics. Moreover, FGW-CLIP consistently outperforms across all three splits of ReactZyme, the largest enzyme-reaction benchmark, demonstrating robust generalization to novel enzymes and reactions. These results position FGW-CLIP as a promising framework for enzyme discovery in complex biochemical settings, with strong adaptability across diverse screening scenarios. + oai:arXiv.org:2512.08508v1 + q-bio.BM + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by-nc-nd/4.0/ - Abderaouf Bahi, Ibtissem Gasmi - - - Synergies between AI Computing and Power Systems: Metrics, Scheduling, and Resilience - https://arxiv.org/abs/2512.07001 - arXiv:2512.07001v1 Announce Type: new -Abstract: In this paper, we first clarify the concepts of green AI versus frugal AI, positioning frugality as efficiency by design and green AI as transparency and accountability. We then argue that these approaches, while complementary, are insufficient without a shared quantitative foundation that links AI computing to power system contexts. This motivates the development of standardized carbon metrics as a bridge between algorithmic decisions and their physical consequences. We next embed these signals into scheduling and planning frameworks, presenting two architectures: (i) an iterative signal-response loop for real-time operations, and (ii) an integrated optimization that learns and encodes flexible-load behavior for long-term planning. Finally, we show how the same coordination stack supports resilience, enabling signals to shift from emissions-first to stability-first during stress events, providing targeted relief and faster restoration. - oai:arXiv.org:2512.07001v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/publicdomain/zero/1.0/ - Farzaneh Pourahmadi, Olivier Corradi, Pierre Pinson + Gengmo Zhou, Feng Yu, Wenda Wang, Zhifeng Gao, Guolin Ke, Zhewei Wei, Zhen Wang - Accurate Models of NVIDIA Tensor Cores - https://arxiv.org/abs/2512.07004 - arXiv:2512.07004v1 Announce Type: new -Abstract: Matrix multiplication is a fundamental operation in for both training of neural networks and inference. To accelerate matrix multiplication, Graphical Processing Units (GPUs) provide it implemented in hardware. Due to the increased throughput over the software-based matrix multiplication, the multipliers are increasingly used outside of AI, to accelerate various applications in scientific computing. However, matrix multipliers targeted at AI are at present not compliant with IEEE 754 floating-point arithmetic behaviour, with different vendors offering different numerical features. This leads to non-reproducible results across different generations of GPU architectures, at the matrix multiply-accumulate instruction level. To study numerical characteristics of matrix multipliers-such as rounding behaviour, accumulator width, normalization points, extra carry bits, and others-test vectors are typically constructed. Yet, these vectors may or may not distinguish between different hardware models, and due to limited hardware availability, their reliability across many different platforms remains largely untested. We present software models for emulating the inner product behavior of low- and mixed-precision matrix multipliers in the V100, A100, H100 and B200 data center GPUs in most supported input formats of interest to mixed-precision algorithm developers: 8-, 16-, and 19-bit floating point. - oai:arXiv.org:2512.07004v1 - cs.MS - cs.AR - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Faizan A. Khattak, Mantas Mikaitis + Data-Efficient Learning of Anomalous Diffusion with Wavelet Representations: Enabling Direct Learning from Experimental Trajectories + https://arxiv.org/abs/2512.08510 + arXiv:2512.08510v1 Announce Type: cross +Abstract: Machine learning (ML) has become a versatile tool for analyzing anomalous diffusion trajectories, yet most existing pipelines are trained on large collections of simulated data. In contrast, experimental trajectories, such as those from single-particle tracking (SPT), are typically scarce and may differ substantially from the idealized models used for simulation, leading to degradation or even breakdown of performance when ML methods are applied to real data. To address this mismatch, we introduce a wavelet-based representation of anomalous diffusion that enables data-efficient learning directly from experimental recordings. This representation is constructed by applying six complementary wavelet families to each trajectory and combining the resulting wavelet modulus scalograms. We first evaluate the wavelet representation on simulated trajectories from the andi-datasets benchmark, where it clearly outperforms both feature-based and trajectory-based methods with as few as 1000 training trajectories and still retains an advantage on large training sets. We then use this representation to learn directly from experimental SPT trajectories of fluorescent beads diffusing in F-actin networks, where the wavelet representation remains superior to existing alternatives for both diffusion-exponent regression and mesh-size classification. In particular, when predicting the diffusion exponents of experimental trajectories, a model trained on 1200 experimental tracks using the wavelet representation achieves significantly lower errors than state-of-the-art deep learning models trained purely on $10^6$ simulated trajectories. We associate this data efficiency with the emergence of distinct scale fingerprints disentangling underlying diffusion mechanisms in the wavelet spectra. + oai:arXiv.org:2512.08510v1 + physics.bio-ph + cond-mat.soft + cs.LG + physics.data-an + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Gongyi Wang, Yu Zhang, Zihan Huang - Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition - https://arxiv.org/abs/2512.07005 - arXiv:2512.07005v1 Announce Type: new -Abstract: Singing accent research is underexplored compared to speech accent studies, primarily due to the scarcity of suitable datasets. Existing singing datasets often suffer from detail loss, frequently resulting from the vocal-instrumental separation process. Additionally, they often lack regional accent annotations. To address this, we introduce the Multi-Accent Mandarin Dry-Vocal Singing Dataset (MADVSD). MADVSD comprises over 670 hours of dry vocal recordings from 4,206 native Mandarin speakers across nine distinct Chinese regions. In addition to each participant recording audio of three popular songs in their native accent, they also recorded phonetic exercises covering all Mandarin vowels and a full octave range. We validated MADVSD through benchmark experiments in singing accent recognition, demonstrating its utility for evaluating state-of-the-art speech models in singing contexts. Furthermore, we explored dialectal influences on singing accent and analyzed the role of vowels in accentual variations, leveraging MADVSD's unique phonetic exercises. - oai:arXiv.org:2512.07005v1 - cs.SD - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3746027.3758210 - Proceedings of the 33rd ACM International Conference on Multimedia (ACMMM 2025), Pages 12714-12721, October 27, 2025. Dublin, Ireland - Zihao Wang, Ruibin Yuan, Ziqi Geng, Hengjia Li, Xingwei Qu, Xinyi Li, Songye Chen, Haoying Fu, Roger B. Dannenberg, Kejun Zhang + Minimax and Bayes Optimal Adaptive Experimental Design for Treatment Choice + https://arxiv.org/abs/2512.08513 + arXiv:2512.08513v1 Announce Type: cross +Abstract: We consider an adaptive experiment for treatment choice and design a minimax and Bayes optimal adaptive experiment with respect to regret. Given binary treatments, the experimenter's goal is to choose the treatment with the highest expected outcome through an adaptive experiment, in order to maximize welfare. We consider adaptive experiments that consist of two phases, the treatment allocation phase and the treatment choice phase. The experiment starts with the treatment allocation phase, where the experimenter allocates treatments to experimental subjects to gather observations. During this phase, the experimenter can adaptively update the allocation probabilities using the observations obtained in the experiment. After the allocation phase, the experimenter proceeds to the treatment choice phase, where one of the treatments is selected as the best. For this adaptive experimental procedure, we propose an adaptive experiment that splits the treatment allocation phase into two stages, where we first estimate the standard deviations and then allocate each treatment proportionally to its standard deviation. We show that this experiment, often referred to as Neyman allocation, is minimax and Bayes optimal in the sense that its regret upper bounds exactly match the lower bounds that we derive. To show this optimality, we derive minimax and Bayes lower bounds for the regret using change-of-measure arguments. Then, we evaluate the corresponding upper bounds using the central limit theorem and large deviation bounds. + oai:arXiv.org:2512.08513v1 + econ.EM + cs.LG + math.ST + stat.ME + stat.ML + stat.TH + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Masahiro Kato - Green O-RAN Operation: a Modern ML-Driven Network Energy Consumption Optimisation - https://arxiv.org/abs/2512.07006 - arXiv:2512.07006v1 Announce Type: new -Abstract: The increasing energy demand of next-generation mobile networks, especially 6G, is becoming a major concern, particularly due to the high power usage of base station components RU, which often remain active even during low traffic periods. To tackle this challenge, our study focuses on improving energy efficiency in O-RAN systems using intelligent control strategies. TD3 leverages a continuous action space to overcome the limitations of traditional discrete-action methods like DQN. By avoiding exponential growth in action space, TD3 enables more precise control of RU sleep modes in dense and large radio environments. Simulation results show that our approach consistently achieves over 50% energy savings compared to the always-on baseline, with TD3 outperforming DQN-based methods by up to 6%, while also offering better stability and faster convergence. - oai:arXiv.org:2512.07006v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/publicdomain/zero/1.0/ - Xuanyu Liang, Ahmed Al-Tahmeesschi, Swarna Chetty, Hamed Ahmadi + Realization of relational presheaves + https://arxiv.org/abs/2512.08566 + arXiv:2512.08566v1 Announce Type: cross +Abstract: Relational presheaves generalize traditional presheaves by going to the category of sets and relations (as opposed to sets and functions) and by allowing functors which are lax. This added generality is useful because it intuitively allows one to encode situations where we have representables without boundaries or with multiple boundaries at once. In particular, the relational generalization of precubical sets has natural application to modeling concurrency. In this article, we study categories of relational presheaves, and construct realization functors for those. We begin by observing that they form the category of set-based models of a cartesian theory, which implies in particular that they are locally finitely presentable categories. By using general results from categorical logic, we then show that the realization of such presheaves in a cocomplete category is a model of the theory in the opposite category, which allows characterizing situations in which we have a realization functor. Finally, we explain that our work has applications in the semantics of concurrency theory. The realization namely allows one to compare syntactic constructions on relational presheaves and geometric ones. Thanks to it, we are able to provide a syntactic counterpart of the blowup operation, which was recently introduced by Haucourt on directed geometric semantics, as way of turning a directed space into a manifold. + oai:arXiv.org:2512.08566v1 + math.CT + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by/4.0/ + Yorgo Chamoun, Samuel Mimram - Optimizing video analytics inference pipelines: a case study - https://arxiv.org/abs/2512.07009 - arXiv:2512.07009v1 Announce Type: new -Abstract: Cost-effective and scalable video analytics are essential for precision livestock monitoring, where high-resolution footage and near-real-time monitoring needs from commercial farms generates substantial computational workloads. This paper presents a comprehensive case study on optimizing a poultry welfare monitoring system through system-level improvements across detection, tracking, clustering, and behavioral analysis modules. We introduce a set of optimizations, including multi-level parallelization, Optimizing code with substituting CPU code with GPU-accelerated code, vectorized clustering, and memory-efficient post-processing. Evaluated on real-world farm video footage, these changes deliver up to a 2x speedup across pipelines without compromising model accuracy. Our findings highlight practical strategies for building high-throughput, low-latency video inference systems that reduce infrastructure demands in agricultural and smart sensing deployments as well as other large-scale video analytics applications. - oai:arXiv.org:2512.07009v1 - cs.DC - cs.AI + Heuristics for Combinatorial Optimization via Value-based Reinforcement Learning: A Unified Framework and Analysis + https://arxiv.org/abs/2512.08601 + arXiv:2512.08601v1 Announce Type: cross +Abstract: Since the 1990s, considerable empirical work has been carried out to train statistical models, such as neural networks (NNs), as learned heuristics for combinatorial optimization (CO) problems. When successful, such an approach eliminates the need for experts to design heuristics per problem type. Due to their structure, many hard CO problems are amenable to treatment through reinforcement learning (RL). Indeed, we find a wealth of literature training NNs using value-based, policy gradient, or actor-critic approaches, with promising results, both in terms of empirical optimality gaps and inference runtimes. Nevertheless, there has been a paucity of theoretical work undergirding the use of RL for CO problems. To this end, we introduce a unified framework to model CO problems through Markov decision processes (MDPs) and solve them using RL techniques. We provide easy-to-test assumptions under which CO problems can be formulated as equivalent undiscounted MDPs that provide optimal solutions to the original CO problems. Moreover, we establish conditions under which value-based RL techniques converge to approximate solutions of the CO problem with a guarantee on the associated optimality gap. Our convergence analysis provides: (1) a sufficient rate of increase in batch size and projected gradient descent steps at each RL iteration; (2) the resulting optimality gap in terms of problem parameters and targeted RL accuracy; and (3) the importance of a choice of state-space embedding. Together, our analysis illuminates the success (and limitations) of the celebrated deep Q-learning algorithm in this problem context. + oai:arXiv.org:2512.08601v1 + stat.ML cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Saeid Ghafouri, Yuming Ding, Katerine Diaz Chito, Jes\'us Martinez del Rinc\'on, Niamh O'Connell, Hans Vandierendonck + Orit Davidovich, Shimrit Shtern, Segev Wasserkrug, Nimrod Megiddo - Always Keep Your Promises: DynamicLRP, A Model-Agnostic Solution To Layer-Wise Relevance Propagation - https://arxiv.org/abs/2512.07010 - arXiv:2512.07010v1 Announce Type: new -Abstract: Layer-wise Relevance Propagation (LRP) provides principled attribution for neural networks through conservation properties and foundations in Deep Taylor Decomposition. However, existing implementations operate at the module level, requiring architecture-specific propagation rules and modifications. These limit the generality of target model and sustainability of implementations as architectures evolve. We introduce DynamicLRP, a model-agnostic LRP framework operating at the tensor operation level. By decomposing attribution to individual operations within computation graphs and introducing a novel mechanism for deferred activation resolution, named the Promise System, our approach achieves true architecture agnosticity while maintaining LRP's theoretical guarantees. This design operates independently of backpropagation machinery, enabling operation on arbitrary computation graphs without model modification and side-by-side execution with gradient backpropagation. Being based on computation graphs, this method is theoretically extensible to other deep learning libraries that support auto-differentiation. We demonstrate faithfulness matching or exceeding specialized implementations (1.77 vs 1.69 ABPC on VGG, equivalent performance on ViT, 93.70\% and 95.06\% top-1 attribution accuracy for explaining RoBERTa-large and Flan-T5-large answers on SQuADv2, respectively) while maintaining practical efficiency on models with hundreds of millions of parameters. We achieved 99.92\% node coverage across 31,465 computation graph nodes from 15 diverse architectures, including state-space models (Mamba), audio transformers (Whisper), and multimodal systems (DePlot) without any model-specific code with rules for 47 fundamental operations implemented. Our operation-level decomposition and Promise System establish a sustainable, extensible foundation for LRP across evolving architectures. - oai:arXiv.org:2512.07010v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + An Efficient Secret Communication Scheme for the Bosonic Wiretap Channel + https://arxiv.org/abs/2512.08623 + arXiv:2512.08623v1 Announce Type: cross +Abstract: We propose a new secret communication scheme over the bosonic wiretap channel. It uses readily available hardware such as lasers and direct photodetectors. The scheme is based on randomness extractors, pulse-position modulation, and Reed-Solomon codes and is therefore computationally efficient. It is secure against an eavesdropper performing coherent joint measurements on the quantum states it observes. In the low-photon-flow limit, the scheme is asymptotically optimal and achieves the same dominant term as the secrecy capacity of the same channel. + oai:arXiv.org:2512.08623v1 + quant-ph + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.1109/LCOMM.2025.3625640 + Esther H\"anggi, Iy\'an M\'endez Veiga, Ligong Wang + + + Resolvable Triple Arrays + https://arxiv.org/abs/2512.08681 + arXiv:2512.08681v1 Announce Type: cross +Abstract: We present a new construction of triple arrays by combining a symmetric 2-design with a resolution of another 2-design. This is the first general method capable of producing non-extremal triple arrays. We call the triple arrays which can be obtained in this way resolvable. We employ the construction to produce the first examples of $(21 \times 15, 63)$-triple arrays, and enumerate all resolvable $(7 \times 15, 35)$-triple arrays, of which there was previously only a single known example. An infinite subfamily of Paley triple arrays turns out to be resolvable. + We also introduce a new intermediate object, unordered triple arrays, that are to triple arrays what symmetric 2-designs are to Youden rectangles, and propose a strengthening of Agrawal's long-standing conjecture on the existence of extremal triple arrays. For small parameters, we completely enumerate all unordered triple arrays, and use this data to corroborate the new conjecture. We construct several infinite families of resolvable unordered triple arrays, and, in particular, show that all $((q + 1) \times q^2, q(q + 1))$-triple arrays are resolvable and are in correspondence with finite affine planes of order $q$. + oai:arXiv.org:2512.08681v1 + math.CO + cs.DM + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Kevin Lee, Pablo Millan Arias + Alexey Gordeev, Lars-Daniel \"Ohman - Block Sparse Flash Attention - https://arxiv.org/abs/2512.07011 - arXiv:2512.07011v1 Announce Type: new -Abstract: Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottleneck. We present Block-Sparse FlashAttention (BSFA), a drop-in replacement that accelerates long-context inference while preserving model quality. Unlike methods that predict importance before computing scores, BSFA computes exact query-key similarities to select the top-k most important value blocks for each query. By comparing per-block maximum scores against calibrated thresholds, we skip approximately 50% of the computation and memory transfers for pruned blocks. Our training-free approach requires only a one-time threshold calibration on a small dataset to learn the per-layer and per-head attention score distributions. We provide a CUDA kernel implementation that can be used as a drop-in replacement for FlashAttention. On Llama-3.1-8B, BSFA achieves up to 1.10x speedup on real-world reasoning benchmarks and up to 1.24x for needle-in-a-haystack retrieval tasks while maintaining above 99% baseline accuracy, with certain configurations even improving accuracy by focusing on the most relevant content, substantially outperforming existing sparse attention methods. The implementation is available at https://github.com/Danielohayon/Block-Sparse-Flash-Attention - oai:arXiv.org:2512.07011v1 - cs.LG - cs.CL - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - new + Calibration of a DEM contact model for wet industrial granular materials + https://arxiv.org/abs/2512.08685 + arXiv:2512.08685v1 Announce Type: cross +Abstract: This study presents and calibrates a Discrete Element Method (DEM) contact model for wet granular materials in the pendular regime. The model extends a previously calibrated dry contact formulation by incorporating liquid bridges that generate capillary adhesion between particles, while liquid migration is represented through evolving bridge volumes. Two reactor-grade polypropylene powders with different particle size distributions, bulk densities, and surface morphologies are investigated, resulting in distinct wetting behavior. A schematic framework is introduced to relate increasing liquid content to the transition from dry to wet contacts using two key parameters: the minimum liquid film volume and the maximum liquid bridge volume. These parameters are calibrated using dynamic angle of repose measurements from rotating drum experiments. The calibrated model reproduces the experimental flow behavior of both powders: full agreement is obtained for the coarser, more porous powder across all liquid contents, while for the finer, denser powder, agreement is achieved at low to moderate liquid contents. At higher liquid contents, discrepancies arise due to agglomeration effects amplified by particle scaling. These results demonstrate the effectiveness of the dynamic angle of repose as a calibration target and highlight the limitations of particle scaling for strongly cohesive wet granular systems. The proposed framework provides a practical basis for DEM-based modeling of wet powder flow in industrial processes. + oai:arXiv.org:2512.08685v1 + cond-mat.soft + cs.NA + math-ph + math.MP + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Daniel Ohayon, Itay Lamprecht, Itay Hubara, Israel Cohen, Daniel Soudry, Noam Elata + Sahar Pourandi, P. Christian van der Sande, Igor A. Ostanin, Thomas Weinhart - Learning Paths to Multi-Sector Equilibrium: Belief Dynamics Under Uncertain Returns to Scale - https://arxiv.org/abs/2512.07013 - arXiv:2512.07013v1 Announce Type: new -Abstract: This paper explores the dynamics of learning in a multi-sector general equilibrium model where firms operate under incomplete information about their production returns to scale. Firms iteratively update their beliefs using maximum a-posteriori estimation, derived from observed production outcomes, to refine their knowledge of their returns to scale. The implications of these learning dynamics for market equilibrium and the conditions under which firms can effectively learn their true returns to scale are the key objects of this study. Our results shed light on how idiosyncratic shocks influence the learning process and demonstrate that input decisions encode all pertinent information for belief updates. Additionally, we show that a long-memory (path-dependent) learning which keeps track of all past estimations ends up having a worse performance than a short-memory (path-independent) approach. - oai:arXiv.org:2512.07013v1 - cs.GT - econ.TH - math.OC - math.PR - math.ST - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 - new + Applications of Singular Entropy to Signals and Singular Smoothness to Images + https://arxiv.org/abs/2512.08717 + arXiv:2512.08717v1 Announce Type: cross +Abstract: This paper explores signal and image analysis by using the Singular Value Decomposition (SVD) and its extension, the Generalized Singular Value Decomposition (GSVD). A key strength of SVD lies in its ability to separate information into orthogonal subspaces. While SVD is a well-established tool in ECG analysis, particularly for source separation, this work proposes a refined method for selecting a threshold to distinguish between maternal and fetal components more effectively. In the first part of the paper, the focus is onmedical signal analysis,where the concepts of Energy Gap Variation (EGV) and Singular Energy are introduced to isolate fetal and maternal ECG signals, improving the known ones. Furthermore, the approach is significantly enhanced by the application of GSVD, which provides additional discriminative power for more accurate signal separation. The second part introduces a novel technique called Singular Smoothness, developed for image analysis. This method incorporates Singular Entropy and the Frobenius normto evaluate information density, and is applied to the detection of natural anomalies such asmountain fractures and burned forest regions. Numerical experiments are presented to demonstrate the effectiveness of the proposed approaches. + oai:arXiv.org:2512.08717v1 + eess.SP + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Stefano Nasini, Rabia Nessah, Bertrand Wigniolle + Oscar Romero, N\'estor Thome - FVA-RAG: Falsification-Verification Alignment for Mitigating Sycophantic Hallucinations - https://arxiv.org/abs/2512.07015 - arXiv:2512.07015v1 Announce Type: new -Abstract: Retrieval-Augmented Generation (RAG) systems have significantly reduced hallucinations in Large Language Models (LLMs) by grounding responses in external context. However, standard RAG architectures suffer from a critical vulnerability: Retrieval Sycophancy. When presented with a query based on a false premise or a common misconception, vector-based retrievers tend to fetch documents that align with the user's bias rather than objective truth, leading the model to "hallucinate with citations." - In this work, we introduce Falsification-Verification Alignment RAG (FVA-RAG), a framework that shifts the retrieval paradigm from Inductive Verification (seeking support) to Deductive Falsification (seeking disproof). Unlike existing "Self-Correction" methods that rely on internal consistency, FVA-RAG deploys a distinct Adversarial Retrieval Policy that actively generates "Kill Queries"-targeted search terms designed to surface contradictory evidence. We introduce a dual-verification mechanism that explicitly weighs the draft answer against this "Anti-Context." Preliminary experiments on a dataset of common misconceptions demonstrate that FVA-RAG significantly improves robustness against sycophantic hallucinations compared to standard RAG baselines, effectively acting as an inference-time "Red Team" for factual generation. - oai:arXiv.org:2512.07015v1 - cs.CL - cs.AI - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mayank Ravishankara + Saturation-based robustly optimal hierarchical operation control of microgrids + https://arxiv.org/abs/2512.08757 + arXiv:2512.08757v1 Announce Type: cross +Abstract: This paper studies the problem of robustly optimal operation control of microgrids with a high share of renewable energy sources. The main goal is to ensure optimal operation under a wide range of circumstances, given the highly intermittent and uncertain nature of renewable sources and load demand. We formally state this problem, and, in order to solve it, we make effective use of the hierarchical power system control approach. We consider an enhanced primary control layer including droop control and autonomous limitation of power and energy. We prove that this enables the use of constant power setpoints to achieve optimal operation under certain conditions. In order to relax these conditions, the approach is combined with an energy management system, which solves a robust unit commitment problem within a model predictive control framework. Finally, a case study demonstrates the viability of the control design. + oai:arXiv.org:2512.08757v1 + math.OC + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://creativecommons.org/licenses/by/4.0/ + Ujjwal Pratap, Steffen Hofmann - Dynamic Boolean Synthesis with Zero-suppressed Decision Diagrams - https://arxiv.org/abs/2512.07018 - arXiv:2512.07018v1 Announce Type: new -Abstract: Motivated by functional synthesis in sequential circuit construction and quantified boolean formulas (QBF), boolean synthesis serves as one of the core problems in Formal Methods. Recent advances show that decision diagrams (DD) are particularly competitive in symbolic approaches for boolean synthesis, among which zero-suppressed decision diagram (ZDD) is a relatively new algorithmic approach, but is complementary to the industrial portfolio, where binary decision diagrams (BDDs) are more often applied. We propose a new dynamic-programming ZDD-based framework in the context of boolean synthesis, show solutions to theoretical challenges, develop a tool, and investigate the experimental performance. We also propose an idea of magic number that functions as the upper bound of planning-phase time and treewidth, showing how to interpret the exploration-exploitation dilemma in planning-execution synthesis framework. The algorithm we propose shows its strengths in general, gives inspiration for future needs to determine industrial magic numbers, and justifies that the framework we propose is an appropriate addition to the industrial synthesis solvers portfolio. - oai:arXiv.org:2512.07018v1 - cs.SC - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Yi Lin, Moshe Y. Vardi + Delay-Oriented Distributed Scheduling with TransGNN + https://arxiv.org/abs/2512.08799 + arXiv:2512.08799v1 Announce Type: cross +Abstract: Minimizing transmission delay in wireless multi-hop networks is a fundamental yet challenging task due to the complex coupling among interference, queue dynamics, and distributed control. Traditional scheduling algorithms, such as max-weight or queue-length-based policies, primarily aim to optimize throughput but often suffer from high latency, especially in heterogeneous or dynamically changing topologies. Recent learning-based approaches, particularly those employing Graph Neural Networks (GNNs), have shown promise in capturing spatial interference structures. However, conventional Graph Convolutional Networks (GCNs) remain limited by their local aggregation mechanism and their inability to model long-range dependencies within the conflict graph. To address these challenges, this paper proposes a delay-oriented distributed scheduling framework based on Transformer GNN. The proposed model employs an attention-based graph encoder to generate adaptive per-link utility scores that reflect both queue backlog and interference intensity. A Local Greedy Solver (LGS) then utilizes these utilities to construct a feasible independent set of links for transmission, ensuring distributed and conflict-free scheduling. + oai:arXiv.org:2512.08799v1 + eess.SP + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 + cross + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Boxuan Wen, Junyu Luo - Transferring Clinical Knowledge into ECGs Representation - https://arxiv.org/abs/2512.07021 - arXiv:2512.07021v1 Announce Type: new -Abstract: Deep learning models have shown high accuracy in classifying electrocardiograms (ECGs), but their black box nature hinders clinical adoption due to a lack of trust and interpretability. To address this, we propose a novel three-stage training paradigm that transfers knowledge from multimodal clinical data (laboratory exams, vitals, biometrics) into a powerful, yet unimodal, ECG encoder. We employ a self-supervised, joint-embedding pre-training stage to create an ECG representation that is enriched with contextual clinical information, while only requiring the ECG signal at inference time. Furthermore, as an indirect way to explain the model's output we train it to also predict associated laboratory abnormalities directly from the ECG embedding. Evaluated on the MIMIC-IV-ECG dataset, our model outperforms a standard signal-only baseline in multi-label diagnosis classification and successfully bridges a substantial portion of the performance gap to a fully multimodal model that requires all data at inference. Our work demonstrates a practical and effective method for creating more accurate and trustworthy ECG classification models. By converting abstract predictions into physiologically grounded \emph{explanations}, our approach offers a promising path toward the safer integration of AI into clinical workflows. - oai:arXiv.org:2512.07021v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + The Cahill-Casazza-Daubechies problem on H\"older stable phase retrieval + https://arxiv.org/abs/2512.08806 + arXiv:2512.08806v1 Announce Type: cross +Abstract: Phase retrieval using a frame for a finite-dimensional Hilbert space is known to always be Lipschitz stable. However, phase retrieval using a frame or a continuous frame for an infinite-dimensional Hilbert space is always unstable. In order to bridge the gap between the finite and infinite dimensional phenomena, Cahill-Casazza-Daubechies (Trans.Amer.Math.Soc. 2016) gave a construction of a family of nonlinear subsets of an infinite-dimensional Hilbert space where phase retrieval could be performed with a H\"older stability estimate. They then posed the question of whether these subsets satisfied Lipschitz stable phase retrieval. We solve this problem both by giving examples which fail Lipschitz stability and by giving examples which satisfy Lipschitz stability. + oai:arXiv.org:2512.08806v1 + math.FA + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Jose Geraldo Fernandes, Luiz Facury de Souza, Pedro Robles Dutenhefner, Gisele L. Pappa, Wagner Meira Jr + Daniel Freeman, Mitchell A. Taylor - Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization - https://arxiv.org/abs/2512.07022 - arXiv:2512.07022v1 Announce Type: new -Abstract: Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely on unchanged bug descriptions, which often contain noisy information, leading to poor retrieval accuracy. Recent advances in large language models (LLMs) have improved bug localization through query reformulation, yet the effect on agent performance remains unexplored. In this study, we investigate how an LLM-powered agent can improve file-level bug localization via lightweight query reformulation and summarization. We first employ an open-source, non-fine-tuned LLM to extract key information from bug reports, such as identifiers and code snippets, and reformulate queries pre-retrieval. Our agent then orchestrates BM25 retrieval using these preprocessed queries, automating localization workflow at scale. Using the best-performing query reformulation technique, our agent achieves 35% better ranking in first-file retrieval than our BM25 baseline and up to +22% file retrieval performance over SWE-agent. - oai:arXiv.org:2512.07022v1 - cs.SE - cs.AI - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new + Axial Symmetric Navier Stokes Equations and the Beltrami /anti Beltrami spectrum in view of Physics Informed Neural Networks + https://arxiv.org/abs/2512.08846 + arXiv:2512.08846v1 Announce Type: cross +Abstract: In this paper, I further continue an investigation on Beltrami Flows began in 2015 with A. Sorin and amply reprised and developed in 2022 with M. Trigiante. Instead of a compact $3$-torus $T^3=\mathbb{R}^3/\Lambda$ where $\Lambda$ is a crystallographic lattice, as done in previous work, here I considered flows confined in a cylinder with identified opposite bases. In this topology I considered axial symmetric flows and found a complete basis of axial symmetric harmonic $1$-forms that, for each energy level, decomposes into six components: two Beltrami, two anti-Beltrami and two closed forms. These objects, that are written in terms of trigonometric and Bessel functions, constitute a function basis for an $L^2$ space of axial symmetric flows. I have presented a general scheme for the search of axial symmetric solutions of Navier Stokes equation by reducing the latter to an hierachy of quadratic relations on the development coefficients of the flow in the above described functional basis. It is proposed that the coefficients can be determined by means of a Physics Informed like Neural Network optimization recursive algorithm. Indeed the present paper provides the theoretical foundations for such a algorithmic construction that is planned for a future publication. + oai:arXiv.org:2512.08846v1 + physics.flu-dyn + cs.IT + math-ph + math.IT + math.MP + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Genevieve Caumartin, Glaucia Melo + Pietro Fr\'e - A Comprehensive Study of Supervised Machine Learning Models for Zero-Day Attack Detection: Analyzing Performance on Imbalanced Data - https://arxiv.org/abs/2512.07030 - arXiv:2512.07030v1 Announce Type: new -Abstract: Among the various types of cyberattacks, identifying zero-day attacks is problematic because they are unknown to security systems as their pattern and characteristics do not match known blacklisted attacks. There are many Machine Learning (ML) models designed to analyze and detect network attacks, especially using supervised models. However, these models are designed to classify samples (normal and attacks) based on the patterns they learn during the training phase, so they perform inefficiently on unseen attacks. This research addresses this issue by evaluating five different supervised models to assess their performance and execution time in predicting zero-day attacks and find out which model performs accurately and quickly. The goal is to improve the performance of these supervised models by not only proposing a framework that applies grid search, dimensionality reduction and oversampling methods to overcome the imbalance problem, but also comparing the effectiveness of oversampling on ml model metrics, in particular the accuracy. To emulate attack detection in real life, this research applies a highly imbalanced data set and only exposes the classifiers to zero-day attacks during the testing phase, so the models are not trained to flag the zero-day attacks. Our results show that Random Forest (RF) performs best under both oversampling and non-oversampling conditions, this increased effectiveness comes at the cost of longer processing times. Therefore, we selected XG Boost (XGB) as the top model due to its fast and highly accurate performance in detecting zero-day attacks. - oai:arXiv.org:2512.07030v1 - cs.CR + SAQ: Stabilizer-Aware Quantum Error Correction Decoder + https://arxiv.org/abs/2512.08914 + arXiv:2512.08914v1 Announce Type: cross +Abstract: Quantum Error Correction (QEC) decoding faces a fundamental accuracy-efficiency tradeoff. Classical methods like Minimum Weight Perfect Matching (MWPM) exhibit variable performance across noise models and suffer from polynomial complexity, while tensor network decoders achieve high accuracy but at prohibitively high computational cost. Recent neural decoders reduce complexity but lack the accuracy needed to compete with computationally expensive classical methods. We introduce SAQ-Decoder, a unified framework combining transformer-based learning with constraint aware post-processing that achieves both near Maximum Likelihood (ML) accuracy and linear computational scalability with respect to the syndrome size. Our approach combines a dual-stream transformer architecture that processes syndromes and logical information with asymmetric attention patterns, and a novel differentiable logical loss that directly optimizes Logical Error Rates (LER) through smooth approximations over finite fields. SAQ-Decoder achieves near-optimal performance, with error thresholds of 10.99% (independent noise) and 18.6% (depolarizing noise) on toric codes that approach the ML bounds of 11.0% and 18.9% while outperforming existing neural and classical baselines in accuracy, complexity, and parameter efficiency. Our findings establish that learned decoders can simultaneously achieve competitive decoding accuracy and computational efficiency, addressing key requirements for practical fault-tolerant quantum computing systems. + oai:arXiv.org:2512.08914v1 + quant-ph cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + cross http://creativecommons.org/licenses/by/4.0/ - Zahra Lotfi, Mostafa Lotfi + David Zenati, Eliya Nachmani - A Hetero-Associative Sequential Memory Model Utilizing Neuromorphic Signals: Validated on a Mobile Manipulator - https://arxiv.org/abs/2512.07032 - arXiv:2512.07032v1 Announce Type: new -Abstract: This paper presents a hetero-associative sequential memory system for mobile manipulators that learns compact, neuromorphic bindings between robot joint states and tactile observations to produce step-wise action decisions with low compute and memory cost. The method encodes joint angles via population place coding and converts skin-measured forces into spike-rate features using an Izhikevich neuron model; both signals are transformed into bipolar binary vectors and bound element-wise to create associations stored in a large-capacity sequential memory. To improve separability in binary space and inject geometry from touch, we introduce 3D rotary positional embeddings that rotate subspaces as a function of sensed force direction, enabling fuzzy retrieval through a softmax weighted recall over temporally shifted action patterns. On a Toyota Human Support Robot covered by robot skin, the hetero-associative sequential memory system realizes a pseudocompliance controller that moves the link under touch in the direction and with speed correlating to the amplitude of applied force, and it retrieves multi-joint grasp sequences by continuing tactile input. The system sets up quickly, trains from synchronized streams of states and observations, and exhibits a degree of generalization while remaining economical. Results demonstrate single-joint and full-arm behaviors executed via associative recall, and suggest extensions to imitation learning, motion planning, and multi-modal integration. - oai:arXiv.org:2512.07032v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Proportional Justified Representation + https://arxiv.org/abs/1611.09928 + arXiv:1611.09928v2 Announce Type: replace +Abstract: The goal of multi-winner elections is to choose a fixed-size committee based on voters' preferences. An important concern in this setting is representation: large groups of voters with cohesive preferences should be adequately represented by the election winners. In an influential paper, Aziz et al. proposed two axioms that aim to capture this idea: justified representation (JR) and its strengthening extended justified representation (EJR). We observe that EJR is incompatible with the highly desirable Perfect Representation (PR) criterion, and propose a relaxation of EJR, which we call Proportional Justified Representation (PJR). PJR is more demanding than JR, but, unlike EJR, it is compatible with PR, as well as with a stronger variant of this axiom, which we term Fractional Perfect Representation (FPR). Moreover, just like EJR, PJR can be used to characterise the classic Proportional Approval Voting (PAV) rule in the class of weighted PAV rules. On the other hand, we show that EJR provides stronger guarantees with respect to average voter satisfaction than PJR does. + oai:arXiv.org:1611.09928v2 + cs.GT + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Runcong Wang, Fengyi Wang, Gordon Cheng - - - Managed TLS Under Migration: Authentication Authority Across CDN and Hosting Transitions - https://arxiv.org/abs/2512.07033 - arXiv:2512.07033v1 Announce Type: new -Abstract: Managed TLS has become a common approach for deploying HTTPS, with platforms generating and storing private keys and automating certificate issuance on behalf of domain operators. This model simplifies operational management but shifts control of authentication material from the domain owner to the platform. The implications of this shift during provider transitions remain insufficiently examined. This study investigates how managed TLS platforms behave when a domain is moved away from the platform that originally issued and stored its certificate. A controlled measurement environment was used to monitor multiple platforms after migration. Each platform was observed for the full remaining lifetime of the certificate that had been active during delegation. The measurements show that platforms continue to serve the same certificate until it expires, even after DNS resolvers direct traffic toward new infrastructure. No platform revoked, replaced, or retired the certificate, and no new certificate was issued after delegation ended. Direct connections to the previous platform continued to complete TLS handshakes with the stale certificate, which confirms that authentication capability persisted independently of DNS state. These findings indicate that authentication authority remains with the previous platform for the entire lifetime of certificates issued during the delegation period. The gap between DNS control and control of authentication material introduces a window in which multiple environments can authenticate the same domain. As managed TLS adoption grows, clearer mechanisms for key retirement and certificate invalidation are needed to ensure that the authentication authority follows operational authority during transitions. - oai:arXiv.org:2512.07033v1 - cs.CR - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Daniyal Ganiuly, Nurzhau Bolatbek, Assel Smaiyl + Luis S\'anchez-Fern\'andez, Edith Elkind, Martin Lackner, Norberto Fern\'andez, Jes\'us A. Fisteus, Pablo Basanta Val, Piotr Skowron - Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues - https://arxiv.org/abs/2512.07034 - arXiv:2512.07034v1 Announce Type: new -Abstract: Glass is a prevalent material among solid objects in everyday life, yet segmentation methods struggle to distinguish it from opaque materials due to its transparency and reflection. While it is known that human perception relies on boundary and reflective-object features to distinguish glass objects, the existing literature has not yet sufficiently captured both properties when handling transparent objects. Hence, we propose incorporating both of these powerful visual cues via the Boundary Feature Enhancement and Reflection Feature Enhancement modules in a mutually beneficial way. Our proposed framework, TransCues, is a pyramidal transformer encoder-decoder architecture to segment transparent objects. We empirically show that these two modules can be used together effectively, improving overall performance across various benchmark datasets, including glass object semantic segmentation, mirror object semantic segmentation, and generic segmentation datasets. Our method outperforms the state-of-the-art by a large margin, achieving +4.2% mIoU on Trans10K-v2, +5.6% mIoU on MSD, +10.1% mIoU on RGBD-Mirror, +13.1% mIoU on TROSD, and +8.3% mIoU on Stanford2D3D, showing the effectiveness of our method against glass objects. - oai:arXiv.org:2512.07034v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Tuan-Anh Vu, Hai Nguyen-Truong, Ziqiang Zheng, Binh-Son Hua, Qing Guo, Ivor Tsang, Sai-Kit Yeung + Discovering Influential Factors in Variational Autoencoders + https://arxiv.org/abs/1809.01804 + arXiv:1809.01804v3 Announce Type: replace +Abstract: In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset. + oai:arXiv.org:1809.01804v3 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Shiqi Liu, Jingxin Liu, Qian Zhao, Xiangyong Cao, Huibin Li, Deyu Meng, Hongying Meng, Sheng Liu - Evaluating and Preserving High-level Fidelity in Super-Resolution - https://arxiv.org/abs/2512.07037 - arXiv:2512.07037v1 Announce Type: new -Abstract: Recent image Super-Resolution (SR) models are achieving impressive effects in reconstructing details and delivering visually pleasant outputs. However, the overpowering generative ability can sometimes hallucinate and thus change the image content despite gaining high visual quality. This type of high-level change can be easily identified by humans yet not well-studied in existing low-level image quality metrics. In this paper, we establish the importance of measuring high-level fidelity for SR models as a complementary criterion to reveal the reliability of generative SR models. We construct the first annotated dataset with fidelity scores from different SR models, and evaluate how state-of-the-art (SOTA) SR models actually perform in preserving high-level fidelity. Based on the dataset, we then analyze how existing image quality metrics correlate with fidelity measurement, and further show that this high-level task can be better addressed by foundation models. Finally, by fine-tuning SR models based on our fidelity feedback, we show that both semantic fidelity and perceptual quality can be improved, demonstrating the potential value of our proposed criteria, both in model evaluation and optimization. We will release the dataset, code, and models upon acceptance. - oai:arXiv.org:2512.07037v1 - cs.CV + Generative Learning of Heterogeneous Tail Dependence + https://arxiv.org/abs/2011.13132 + arXiv:2011.13132v3 Announce Type: replace +Abstract: We propose a multivariate generative model to capture the complex dependence structure often encountered in business and financial data. Our model features heterogeneous and asymmetric tail dependence between all pairs of individual dimensions while also allowing heterogeneity and asymmetry in the tails of the marginals. A significant merit of our model structure is that it is not prone to error propagation in the parameter estimation process, hence very scalable, as the dimensions of datasets grow large. However, the likelihood methods are infeasible for parameter estimation in our case due to the lack of a closed-form density function. Instead, we devise a novel moment learning algorithm to learn the parameters. To demonstrate the effectiveness of the model and its estimator, we test them on simulated as well as real-world datasets. Results show that this framework gives better finite-sample performance compared to the copula-based benchmarks as well as recent similar models. + oai:arXiv.org:2011.13132v3 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Josep M. Rocafort, Shaolin Su, Javier Vazquez-Corral, Alexandra Gomez-Villa + q-fin.RM + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xiangqian Sun, Xing Yan, Qi Wu - Ideal Attribution and Faithful Watermarks for Language Models - https://arxiv.org/abs/2512.07038 - arXiv:2512.07038v1 Announce Type: new -Abstract: We introduce ideal attribution mechanisms, a formal abstraction for reasoning about attribution decisions over strings. At the core of this abstraction lies the ledger, an append-only log of the prompt-response interaction history between a model and its user. Each mechanism produces deterministic decisions based on the ledger and an explicit selection criterion, making it well-suited to serve as a ground truth for attribution. We frame the design goal of watermarking schemes as faithful representation of ideal attribution mechanisms. This novel perspective brings conceptual clarity, replacing piecemeal probabilistic statements with a unified language for stating the guarantees of each scheme. It also enables precise reasoning about desiderata for future watermarking schemes, even when no current construction achieves them, since the ideal functionalities are specified first. In this way, the framework provides a roadmap that clarifies which guarantees are attainable in an idealized setting and worth pursuing in practice. - oai:arXiv.org:2512.07038v1 - cs.CR + Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise + https://arxiv.org/abs/2210.11075 + arXiv:2210.11075v3 Announce Type: replace +Abstract: The existence of spurious correlations such as image backgrounds in the training environment can make empirical risk minimization (ERM) perform badly in the test environment. To address this problem, Kirichenko et al. (2022) empirically found that the core features that are related to the outcome can still be learned well even with the presence of spurious correlations. This opens a promising strategy to first train a feature learner rather than a classifier, and then perform linear probing (last layer retraining) in the test environment. However, a theoretical understanding of when and why this approach works is lacking. In this paper, we find that core features are only learned well when their associated non-realizable noise is smaller than that of spurious features, which is not necessarily true in practice. We provide both theories and experiments to support this finding and to illustrate the importance of non-realizable noise. Moreover, we propose an algorithm called Freeze then Train (FTT), that first freezes certain salient features and then trains the rest of the features using ERM. We theoretically show that FTT preserves features that are more beneficial to test time probing. Across two commonly used spurious correlation datasets, FTT outperforms ERM, IRM, JTT and CVaR-DRO, with substantial improvement in accuracy (by 4.5%) when the feature noise is large. FTT also performs better on general distribution shift benchmarks. + oai:arXiv.org:2210.11075v3 cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Min Jae Song, Kameron Shahabi + Haotian Ye, James Zou, Linjun Zhang - Transformation of Biological Networks into Images via Semantic Cartography for Visual Interpretation and Scalable Deep Analysis - https://arxiv.org/abs/2512.07040 - arXiv:2512.07040v1 Announce Type: new -Abstract: Complex biological networks are fundamental to biomedical science, capturing interactions among molecules, cells, genes, and tissues. Deciphering these networks is critical for understanding health and disease, yet their scale and complexity represent a daunting challenge for current computational methods. Traditional biological network analysis methods, including deep learning approaches, while powerful, face inherent challenges such as limited scalability, oversmoothing long-range dependencies, difficulty in multimodal integration, expressivity bounds, and poor interpretability. We present Graph2Image, a framework that transforms large biological networks into sets of two-dimensional images by spatially arranging representative network nodes on a 2D grid. This transformation decouples the nodes as images, enabling the use of convolutional neural networks (CNNs) with global receptive fields and multi-scale pyramids, thus overcoming limitations of existing biological network analysis methods in scalability, memory efficiency, and long-range context capture. Graph2Image also facilitates seamless integration with other imaging and omics modalities and enhances interpretability through direct visualization of node-associated images. When applied to several large-scale biological network datasets, Graph2Image improved classification accuracy by up to 67.2% over existing methods and provided interpretable visualizations that revealed biologically coherent patterns. It also allows analysis of very large biological networks (nodes > 1 billion) on a personal computer. Graph2Image thus provides a scalable, interpretable, and multimodal-ready approach for biological network analysis, offering new opportunities for disease diagnosis and the study of complex biological systems. - oai:arXiv.org:2512.07040v1 + Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning + https://arxiv.org/abs/2305.19600 + arXiv:2305.19600v4 Announce Type: replace +Abstract: Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial heterogeneity (e.g., class imbalance) across the local data distributions observed by each of these clients. Under such non-iid label distributions across clients, FL suffers from the 'client-drift' problem where every client drifts to its own local optimum. This results in slower convergence and poor performance of the aggregated model. To address this limitation, we propose a novel regularization technique based on adaptive self-distillation (ASD) for training models on the client side. Our regularization scheme adaptively adjusts to each client's training data based on the global model's prediction entropy and the client-data label distribution. We show in this paper that our proposed regularization (ASD) can be easily integrated atop existing, state-of-the-art FL algorithms, leading to a further boost in the performance of these off-the-shelf methods. We theoretically explain how incorporation of ASD regularizer leads to reduction in client-drift and empirically justify the generalization ability of the trained model. We demonstrate the efficacy of our approach through extensive experiments on multiple real-world benchmarks and show substantial gains in performance when the proposed regularizer is combined with popular FL methods. + oai:arXiv.org:2305.19600v4 cs.LG - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Sakib Mostafa, Lei Xing, Md. Tauhidul Islam + M Yashwanth, Gaurav Kumar Nayak, Arya Singh, Yogesh Simmhan, Anirban Chakraborty - CERNet: Class-Embedding Predictive-Coding RNN for Unified Robot Motion, Recognition, and Confidence Estimation - https://arxiv.org/abs/2512.07041 - arXiv:2512.07041v1 Announce Type: new -Abstract: Robots interacting with humans must not only generate learned movements in real-time, but also infer the intent behind observed behaviors and estimate the confidence of their own inferences. This paper proposes a unified model that achieves all three capabilities within a single hierarchical predictive-coding recurrent neural network (PC-RNN) equipped with a class embedding vector, CERNet, which leverages a dynamically updated class embedding vector to unify motor generation and recognition. The model operates in two modes: generation and inference. In the generation mode, the class embedding constrains the hidden state dynamics to a class-specific subspace; in the inference mode, it is optimized online to minimize prediction error, enabling real-time recognition. Validated on a humanoid robot across 26 kinesthetically taught alphabets, our hierarchical model achieves 76% lower trajectory reproduction error than a parameter-matched single-layer baseline, maintains motion fidelity under external perturbations, and infers the demonstrated trajectory class online with 68% Top-1 and 81% Top-2 accuracy. Furthermore, internal prediction errors naturally reflect the model's confidence in its recognition. This integration of robust generation, real-time recognition, and intrinsic uncertainty estimation within a compact PC-RNN framework offers a compact and extensible approach to motor memory in physical robots, with potential applications in intent-sensitive human-robot collaboration. - oai:arXiv.org:2512.07041v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Degenerate crossing number and signed reversal distance + https://arxiv.org/abs/2308.10666 + arXiv:2308.10666v3 Announce Type: replace +Abstract: Given a graph drawn in the plane, the degenerate crossing number of the drawing is the number of points in the plane which are contained in the relative interior of at least two edges, where each edge is required to be drawn as a simple arc. The degenerate crossing number of a graph is the minimum degenerate crossing number among all its drawings. + Given a drawing, cutting a neighborhood of the surface around each crossing and pasting a M\"obius band gives a non-orientable surface, on which the drawing of the graph can be extended to an embedding. From this observation, Mohar derived that the degenerate crossing number of a graph is at most its non-orientable genus, and conjectured that these quantities are equal for every graph. He also made a stronger conjecture for loopless pseudo-triangulations with a fixed embedding scheme. + In this paper, we prove a structure theorem that allows to understand when the degenerate crossing number and non-orientable genus coincide in a large class of loopless bipartite embedding schemes. In particular, we provide a counterexample to Mohar's stronger conjecture, but show that in the vast majority of the 2-vertex cases, as well as for many bipartite graphs, Mohar's conjecture is satisfied. + The reversal distance between two signed permutations is the minimum number of reversals that transform one permutation to the other one. If we represent the trajectory of each element of a signed permutation under successive reversals by a simple arc, we obtain a drawing of a 2-vertex embedding scheme with degenerate crossings. Our main result is proved by leveraging this connection and a classical result in genome rearrangement (the Hannenhalli--Pevzner algorithm) and can also be understood as an extension of this algorithm when the reversals do not necessarily happen in a monotone order. + oai:arXiv.org:2308.10666v3 + cs.CG + math.CO + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Hiroki Sawada, Alexandre Pitti, Mathias Quoy + Niloufar Fuladi, Alfredo Hubard, Arnaud de Mesmay - DAUNet: A Lightweight UNet Variant with Deformable Convolutions and Parameter-Free Attention for Medical Image Segmentation - https://arxiv.org/abs/2512.07051 - arXiv:2512.07051v1 Announce Type: new -Abstract: Medical image segmentation plays a pivotal role in automated diagnostic and treatment planning systems. In this work, we present DAUNet, a novel lightweight UNet variant that integrates Deformable V2 Convolutions and Parameter-Free Attention (SimAM) to improve spatial adaptability and context-aware feature fusion without increasing model complexity. DAUNet's bottleneck employs dynamic deformable kernels to handle geometric variations, while the decoder and skip pathways are enhanced using SimAM attention modules for saliency-aware refinement. Extensive evaluations on two challenging datasets, FH-PS-AoP (fetal head and pubic symphysis ultrasound) and FUMPE (CT-based pulmonary embolism detection), demonstrate that DAUNet outperforms state-of-the-art models in Dice score, HD95, and ASD, while maintaining superior parameter efficiency. Ablation studies highlight the individual contributions of deformable convolutions and SimAM attention. DAUNet's robustness to missing context and low-contrast regions establishes its suitability for deployment in real-time and resource-constrained clinical environments. - oai:arXiv.org:2512.07051v1 + MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens + https://arxiv.org/abs/2310.02239 + arXiv:2310.02239v4 Announce Type: replace +Abstract: The effectiveness of Multimodal Large Language Models (MLLMs) demonstrates a profound capability in multimodal understanding. However, the simultaneous generation of images with coherent texts is still underdeveloped. Addressing this, we introduce a novel interleaved vision-and-language generation method, centered around the concept of ``generative vokens". These vokens serve as pivotal elements contributing to coherent image-text outputs. Our method is marked by a unique two-stage training strategy for description-free multimodal generation, which does not necessitate extensive descriptions of images. We integrate classifier-free guidance to enhance the alignment of generated images and texts, ensuring more seamless and contextually relevant multimodal interactions. Our model, MiniGPT-5, exhibits substantial improvement over the baseline models on multimodal generation datasets, including MMDialog and VIST. The human evaluation shows MiniGPT-5 is better than the baseline model on more than 56\% cases for multimodal generation, highlighting its efficacy across diverse benchmarks. + oai:arXiv.org:2310.02239v4 cs.CV cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Adnan Munir, Shujaat Khan + Kaizhi Zheng, Xuehai He, Xin Eric Wang - RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting - https://arxiv.org/abs/2512.07052 - arXiv:2512.07052v1 Announce Type: new -Abstract: Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its efficiency, 3DGS suffers from large memory requirements and costly training procedures, motivating efforts toward compression. Existing approaches, however, operate at fixed rates, limiting adaptability to varying bandwidth and device constraints. In this work, we propose a flexible compression scheme for 3DGS that supports interpolation at any rate between predefined bounds. Our method is computationally lightweight, requires no retraining for any rate, and preserves rendering quality across a broad range of operating points. Experiments demonstrate that the approach achieves efficient, high-quality compression while offering dynamic rate control, making it suitable for practical deployment in immersive applications. The code will be provided open-source upon acceptance of the work. - oai:arXiv.org:2512.07052v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hoang-Nhat Tran, Francesco Di Sario, Gabriele Spadaro, Giuseppe Valenzise, Enzo Tartaglione + Diffusion Models for Wireless Communications + https://arxiv.org/abs/2310.07312 + arXiv:2310.07312v4 Announce Type: replace +Abstract: A comprehensive study on the applications of denoising diffusion models for wireless systems is provided. The article highlights the capabilities of diffusion models in learning complicated signal distributions, modeling wireless channels, and denoising and reconstructing distorted signals. First, fundamental working mechanism of diffusion models is introduced. Then the recent advances in applying diffusion models to wireless systems are reviewed. Next, two case studies are provided, where conditional diffusion models (CDiff) are proposed for data reconstruction enhancement, covering both the conventional digital communication systems, as well as the semantic communication (SemCom) setups. The first case study highlights about 10 dB improvement in data reconstruction under low-SNR regimes, while mitigating the need to transmit redundant bits for error correction codes in digital systems. The second study further extends the case to a SemCom setup, where diffusion autoencoders showcase superior performance compared to legacy autoencoders and variational autoencoder (VAE) architectures. Finally, future directions and existing challenges are discussed. + oai:arXiv.org:2310.07312v4 + cs.IT + cs.AI + cs.LG + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Mehdi Letafati, Samad Ali, Matti Latva-aho - Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models - https://arxiv.org/abs/2512.07059 - arXiv:2512.07059v1 Announce Type: new -Abstract: Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction. - oai:arXiv.org:2512.07059v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + On the convergence of adaptive approximations for stochastic differential equations + https://arxiv.org/abs/2311.14201 + arXiv:2311.14201v5 Announce Type: replace +Abstract: In this paper, we study numerical approximations for stochastic differential equations (SDEs) that use adaptive step sizes. In particular, we consider a general setting where decisions to reduce step sizes are allowed to depend on the future trajectory of the underlying Brownian motion. Since these adaptive step sizes may not be previsible, the standard mean squared error analysis cannot be directly applied to show that the numerical method converges to the solution of the SDE. Building upon the pioneering work of Gaines and Lyons, we instead use rough path theory to establish pathwise convergence for a wide class of adaptive numerical methods on general Stratonovich SDEs (with sufficiently smooth vector fields). To our knowledge, this is the first convergence guarantee that applies to standard solvers, such as the Milstein and Heun methods, with non-previsible step sizes. In our analysis, we require adaptive step sizes to have a "no skip" property and to take values at only dyadic times. Secondly, in contrast to the Euler-Maruyama method, we require the SDE solver to have unbiased "L\'evy area" terms in its Taylor expansion. We conjecture that for adaptive SDE solvers more generally, convergence is still possible provided the method does not introduce "L\'evy area bias". We present a simple example where the step size control can skip over previously considered times, resulting in the numerical method converging to an incorrect limit (i.e. not the Stratonovich SDE). Finally, we conclude with an experiment demonstrating the accuracy of Heun's method and a newly introduced Splitting Path-based Runge-Kutta scheme (SPaRK) when used with adaptive step sizes. + oai:arXiv.org:2311.14201v5 + math.NA + cs.NA + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Richard Young + James Foster, Andra\v{z} Jelin\v{c}i\v{c} - $\mathrm{D}^{\mathrm{3}}$-Predictor: Noise-Free Deterministic Diffusion for Dense Prediction - https://arxiv.org/abs/2512.07062 - arXiv:2512.07062v1 Announce Type: new -Abstract: Although diffusion models with strong visual priors have emerged as powerful dense prediction backboens, they overlook a core limitation: the stochastic noise at the core of diffusion sampling is inherently misaligned with dense prediction that requires a deterministic mapping from image to geometry. In this paper, we show that this stochastic noise corrupts fine-grained spatial cues and pushes the model toward timestep-specific noise objectives, consequently destroying meaningful geometric structure mappings. To address this, we introduce $\mathrm{D}^{\mathrm{3}}$-Predictor, a noise-free deterministic framework built by reformulating a pretrained diffusion model without stochasticity noise. Instead of relying on noisy inputs to leverage diffusion priors, $\mathrm{D}^{\mathrm{3}}$-Predictor views the pretrained diffusion network as an ensemble of timestep-dependent visual experts and self-supervisedly aggregates their heterogeneous priors into a single, clean, and complete geometric prior. Meanwhile, we utilize task-specific supervision to seamlessly adapt this noise-free prior to dense prediction tasks. Extensive experiments on various dense prediction tasks demonstrate that $\mathrm{D}^{\mathrm{3}}$-Predictor achieves competitive or state-of-the-art performance in diverse scenarios. In addition, it requires less than half the training data previously used and efficiently performs inference in a single step. Our code, data, and checkpoints are publicly available at https://x-gengroup.github.io/HomePage_D3-Predictor/. - oai:arXiv.org:2512.07062v1 - cs.CV + Detecting value-expressive text posts in Russian social media + https://arxiv.org/abs/2312.08968 + arXiv:2312.08968v3 Announce Type: replace +Abstract: Basic values are concepts or beliefs which pertain to desirable end-states and transcend specific situations. Studying personal values in social media can illuminate how and why societal values evolve especially when the stimuli-based methods, such as surveys, are inefficient, for instance, in hard-to-reach populations. On the other hand, user-generated content is driven by the massive use of stereotyped, culturally defined speech constructions rather than authentic expressions of personal values. We aimed to find a model that can accurately detect value-expressive posts in Russian social media VKontakte. A training dataset of 5,035 posts was annotated by three experts, 304 crowd-workers and ChatGPT. Crowd-workers and experts showed only moderate agreement in categorizing posts. ChatGPT was more consistent but struggled with spam detection. We applied an ensemble of human- and AI-assisted annotation involving active learning approach, subsequently trained several classification models using embeddings from various pre-trained transformer-based language models. The best performance was achieved with embeddings from a fine-tuned rubert-tiny2 model, yielding high value detection quality (F1 = 0.77, F1-macro = 0.83). This model provides a crucial step to a study of values within and between Russian social media users. + oai:arXiv.org:2312.08968v3 + cs.CL cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Changliang Xia, Chengyou Jia, Minnan Luo, Zhuohang Dang, Xin Shen, Bowen Ping + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Maria Milkova, Maksim Rudnev, Lidia Okolskaya - Soft Computing Tools To Predict Varied Weight Components, Material and Tribological Properties of Al2219-B4C-Gr - https://arxiv.org/abs/2512.07063 - arXiv:2512.07063v1 Announce Type: new -Abstract: Soft computing tools emerged as most reliable alternatives of traditional regression and statistical methods. In recent times, these tools can predict the optimum material compositions, mechanical and tribological properties of composite materials accurately without much experiment or even without experiment. In the present study, soft computing tools like fuzzy logic, Decision tree, genetic algorithms are employed to predict the reinforcement weight percentage of B4C(Boron Carbide) and Graphite(Gr) along with Aluminum (matrix material) weight percentage for Al2219 with B4C and graphite. The optimized material and tribological properties of Al2219 were also predicted using NSGA II genetic algorithms for multi-objective optimization. It is found that the predictions are at par with earlier ANN (artificial neural network) studies and experimental findings. It can be inferred that inclusion B4C has more impact on enhancement of mechanical properties as well as wear strength compared to Gr. - oai:arXiv.org:2512.07063v1 - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - new + Spike-EVPR: Deep Spiking Residual Networks with SNN-Tailored Representations for Event-Based Visual Place Recognition + https://arxiv.org/abs/2402.10476 + arXiv:2402.10476v2 Announce Type: replace +Abstract: Event cameras are ideal for visual place recognition (VPR) in challenging environments due to their high temporal resolution and high dynamic range. However, existing methods convert sparse events into dense frame-like representations for Artificial Neural Networks (ANNs), ignoring event sparsity and incurring high computational cost. Spiking Neural Networks (SNNs) complement event data through discrete spike signals to enable energy-efficient VPR, but their application is hindered by the lack of effective spike-compatible representations and deep architectures capable of learning discriminative global descriptors. To address these limitations, we propose Spike-EVPR, a directly trained, end-to-end SNN framework tailored for event-based VPR. First, we introduce two complementary event representations, MCS-Tensor and TSS-Tensor, designed to reduce temporal redundancy while preserving essential spatio-temporal cues. Furthermore, we propose a deep spiking residual architecture that effectively aggregates these features to generate robust place descriptors. Extensive experiments on the Brisbane-Event-VPR and DDD20 datasets demonstrate that Spike-EVPR achieves state-of-the-art performance, improving Recall@1 by 7.61% and 13.20%, respectively, while significantly reducing energy consumption. + oai:arXiv.org:2402.10476v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Maitreyi Chatterjee, Biplab Chatterjee + Zuntao Liu, Yaohui Li, Chenming Hu, Delei Kong, Junjie Jiang, Zheng Fang - Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design - https://arxiv.org/abs/2512.07064 - arXiv:2512.07064v1 Announce Type: new -Abstract: Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and lack principled evaluation, obscuring which design choices are genuinely effective. This work cast the entire pretrain-finetune workflow into a unified probabilistic framework, enabling a transparent comparison and deeper understanding of masking strategies. Building on this formalism, we conduct a controlled study of three core design dimensions: masking distribution, prediction target, and encoder architecture, under rigorously controlled settings. We further employ information-theoretic measures to assess the informativeness of pretraining signals and connect them to empirically benchmarked downstream performance. Our findings reveal a surprising insight: sophisticated masking distributions offer no consistent benefit over uniform sampling for common node-level prediction tasks. Instead, the choice of prediction target and its synergy with the encoder architecture are far more critical. Specifically, shifting to semantically richer targets yields substantial downstream improvements, particularly when paired with expressive Graph Transformer encoders. These insights offer practical guidance for developing more effective SSL methods for molecular graphs. - oai:arXiv.org:2512.07064v1 + BG-HGNN: Toward Efficient Learning for Complex Heterogeneous Graphs + https://arxiv.org/abs/2403.08207 + arXiv:2403.08207v2 Announce Type: replace +Abstract: Heterogeneous graphs, comprising diverse node and edge types connected through varied relations, are ubiquitous in real-world applications. Message-passing heterogeneous graph neural networks (HGNNs) have emerged as a powerful model class for such data. However, existing HGNNs typically allocate a separate set of learnable weights for each relation type to model relational heterogeneity. Despite their promise, these models are effective primarily on simple heterogeneous graphs with only a few relation types. In this paper, we show that this standard design inherently leads to parameter explosion (the number of learnable parameters grows rapidly with the number of relation types) and relation collapse (the model loses the ability to distinguish among different relations). These issues make existing HGNNs inefficient or impractical for complex heterogeneous graphs with many relation types. To address these challenges, we propose Blend&Grind-HGNN (BG-HGNN), a unified feature-representation framework that integrates and distills relational heterogeneity into a shared low-dimensional feature space. This design eliminates the need for relation-specific parameter sets and enables efficient, expressive learning even as the number of relations grows. Empirically, BG-HGNN achieves substantial gains over state-of-the-art HGNNs, improving parameter efficiency by up to 28.96x and training throughput by up to 110.30x, while matching or surpassing their accuracy on complex heterogeneous graphs. + oai:arXiv.org:2403.08207v2 cs.LG - cs.AI - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiannan Yang, Veronika Thost, Tengfei Ma - - - Persistent Homology-Guided Frequency Filtering for Image Compression - https://arxiv.org/abs/2512.07065 - arXiv:2512.07065v1 Announce Type: new -Abstract: Feature extraction in noisy image datasets presents many challenges in model reliability. In this paper, we use the discrete Fourier transform in conjunction with persistent homology analysis to extract specific frequencies that correspond with certain topological features of an image. This method allows the image to be compressed and reformed while ensuring that meaningful data can be differentiated. Our experimental results show a level of compression comparable to that of using JPEG using six different metrics. The end goal of persistent homology-guided frequency filtration is its potential to improve performance in binary classification tasks (when augmenting a Convolutional Neural Network) compared to traditional feature extraction and compression methods. These findings highlight a useful end result: enhancing the reliability of image compression under noisy conditions. - oai:arXiv.org:2512.07065v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Anil Chintapalli, Peter Tenholder, Henry Chen, Arjun Rao + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Junwei Su, Lingjun Mao, Zheng Da, Chuan Wu - SETUP: Sentence-level English-To-Uniform Meaning Representation Parser - https://arxiv.org/abs/2512.07068 - arXiv:2512.07068v1 Announce Type: new -Abstract: Uniform Meaning Representation (UMR) is a novel graph-based semantic representation which captures the core meaning of a text, with flexibility incorporated into the annotation schema such that the breadth of the world's languages can be annotated (including low-resource languages). While UMR shows promise in enabling language documentation, improving low-resource language technologies, and adding interpretability, the downstream applications of UMR can only be fully explored when text-to-UMR parsers enable the automatic large-scale production of accurate UMR graphs at test time. Prior work on text-to-UMR parsing is limited to date. In this paper, we introduce two methods for English text-to-UMR parsing, one of which fine-tunes existing parsers for Abstract Meaning Representation and the other, which leverages a converter from Universal Dependencies, using prior work as a baseline. Our best-performing model, which we call SETUP, achieves an AnCast score of 84 and a SMATCH++ score of 91, indicating substantial gains towards automatic UMR parsing. - oai:arXiv.org:2512.07068v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Numerical integrators for confined Langevin dynamics + https://arxiv.org/abs/2404.16584 + arXiv:2404.16584v2 Announce Type: replace +Abstract: We derive and analyze numerical methods for underdamped (kinetic) Langevin dynamics in a domain with elastic reflection at the boundary. First-order approximations are based on an Euler-type scheme incorporating collision-handling at the boundary. To achieve second order, composition schemes are derived based on decomposition of the generator into collisional drift, impulse, and stochastic momentum evolution. In a deterministic setting, this approach would typically lead to first-order approximation, even in symmetric compositions, but we find that the stochastic method can provide second-order weak approximation with a single gradient evaluation, both at finite times and in the ergodic limit. We provide analysis of this observation, as well as numerical demonstration, and we compare and contrast the performance of different variants of the integration method using model problems. + oai:arXiv.org:2404.16584v2 + math.NA + cs.NA + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Emma Markle, Javier Gutierrez Bach, Shira Wein + B. Leimkuhler, A. Sharma, M. V. Tretyakov - Do Large Language Models Truly Understand Cross-cultural Differences? - https://arxiv.org/abs/2512.07075 - arXiv:2512.07075v1 Announce Type: new -Abstract: In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks for evaluating whether LLMs genuinely possess this capability suffer from three key limitations: a lack of contextual scenarios, insufficient cross-cultural concept mapping, and limited deep cultural reasoning capabilities. To address these gaps, we propose SAGE, a scenario-based benchmark built via cross-cultural core concept alignment and generative task design, to evaluate LLMs' cross-cultural understanding and reasoning. Grounded in cultural theory, we categorize cross-cultural capabilities into nine dimensions. Using this framework, we curated 210 core concepts and constructed 4530 test items across 15 specific real-world scenarios, organized under four broader categories of cross-cultural situations, following established item design principles. The SAGE dataset supports continuous expansion, and experiments confirm its transferability to other languages. It reveals model weaknesses across both dimensions and scenarios, exposing systematic limitations in cross-cultural reasoning. While progress has been made, LLMs are still some distance away from reaching a truly nuanced cross-cultural understanding. In compliance with the anonymity policy, we include data and code in the supplement materials. In future versions, we will make them publicly available online. - oai:arXiv.org:2512.07075v1 + CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale + https://arxiv.org/abs/2405.17537 + arXiv:2405.17537v5 Announce Type: replace +Abstract: Measuring biodiversity is crucial for understanding ecosystem health. While prior works have developed machine learning models for taxonomic classification of photographic images and DNA separately, in this work, we introduce a multimodal approach combining both, using CLIP-style contrastive learning to align images, barcode DNA, and text-based representations of taxonomic labels in a unified embedding space. This allows for accurate classification of both known and unknown insect species without task-specific fine-tuning, leveraging contrastive learning for the first time to fuse barcode DNA and image data. Our method surpasses previous single-modality approaches in accuracy by over 8% on zero-shot learning tasks, showcasing its effectiveness in biodiversity studies. + oai:arXiv.org:2405.17537v5 + cs.AI cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/publicdomain/zero/1.0/ - Shiwei Guo, Sihang Jiang, Qianxi He, Yanghua Xiao, Jiaqing Liang, Bi Yude, Minggui He, Shimin Tao, Li Zhang - - - Context-measure: Contextualizing Metric for Camouflage - https://arxiv.org/abs/2512.07076 - arXiv:2512.07076v1 Announce Type: new -Abstract: Camouflage is primarily context-dependent yet current metrics for camouflaged scenarios overlook this critical factor. Instead, these metrics are originally designed for evaluating general or salient objects, with an inherent assumption of uncorrelated spatial context. In this paper, we propose a new contextualized evaluation paradigm, Context-measure, built upon a probabilistic pixel-aware correlation framework. By incorporating spatial dependencies and pixel-wise camouflage quantification, our measure better aligns with human perception. Extensive experiments across three challenging camouflaged object segmentation datasets show that Context-measure delivers more reliability than existing context-independent metrics. Our measure can provide a foundational evaluation benchmark for various computer vision applications involving camouflaged patterns, such as agricultural, industrial, and medical scenarios. Code is available at https://github.com/pursuitxi/Context-measure. - oai:arXiv.org:2512.07076v1 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Chen-Yang Wang, Gepeng Ji, Song Shao, Ming-Ming Cheng, Deng-Ping Fan - - - Momentum-Accelerated Online Feedback Optimization for Power System Flexibility - https://arxiv.org/abs/2512.07077 - arXiv:2512.07077v1 Announce Type: new -Abstract: Flexibility is increasingly gaining importance in modern power system operation. This paper presents a controller framework based on Online Feedback Optimization for real-time coordination of power system flexibility. The proposed approach introduces a momentum-augmented projection-step to accelerate convergence and improve dynamic performance. We derive the controller formulation, and evaluate its performance and stability in two representative case studies. The first examines online congestion management in distribution feeders, and the second addresses multi-layer flexibility dispatch across system interfaces. Numerical results demonstrate that the momentum-based controller achieves faster convergence and maintains constraint satisfaction, highlighting its potential for real-time flexibility control in large-scale power systems. - oai:arXiv.org:2512.07077v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Florian Klein-Helmkamp, Matthis Berger, Irina Zettl, Andreas Ulbig + ZeMing Gong, Austin T. Wang, Xiaoliang Huo, Joakim Bruslund Haurum, Scott C. Lowe, Graham W. Taylor, Angel X. Chang - DFIR-DETR: Frequency Domain Enhancement and Dynamic Feature Aggregation for Cross-Scene Small Object Detection - https://arxiv.org/abs/2512.07078 - arXiv:2512.07078v1 Announce Type: new -Abstract: Detecting small objects in UAV remote sensing images and identifying surface defects in industrial inspection remain difficult tasks. These applications face common obstacles: features are sparse and weak, backgrounds are cluttered, and object scales vary dramatically. Current transformer-based detectors, while powerful, struggle with three critical issues. First, features degrade severely as networks downsample progressively. Second, spatial convolutions cannot capture long-range dependencies effectively. Third, standard upsampling methods inflate feature maps unnecessarily. - We introduce DFIR-DETR to tackle these problems through dynamic feature aggregation combined with frequency-domain processing. Our architecture builds on three novel components. The DCFA module uses dynamic K-sparse attention, cutting complexity from O(N2) down to O(NK), and employs spatial gated linear units for better nonlinear modeling. The DFPN module applies amplitude-normalized upsampling to prevent feature inflation and uses dual-path shuffle convolution to retain spatial details across scales. The FIRC3 module operates in the frequency domain, achieving global receptive fields without sacrificing efficiency. - We tested our method extensively on NEU-DET and VisDrone datasets. Results show mAP50 scores of 92.9% and 51.6% respectively-both state-of-the-art. The model stays lightweight with just 11.7M parameters and 41.2 GFLOPs. Strong performance across two very different domains confirms that DFIR-DETR generalizes well and works effectively in resource-limited settings for cross-scene small object detection. - oai:arXiv.org:2512.07078v1 - cs.CV + Neural Surrogate HMC: On Using Neural Likelihoods for Hamiltonian Monte Carlo in Simulation-Based Inference + https://arxiv.org/abs/2407.20432 + arXiv:2407.20432v2 Announce Type: replace +Abstract: Bayesian inference methods such as Markov Chain Monte Carlo (MCMC) typically require repeated computations of the likelihood function, but in some scenarios this is infeasible and alternative methods are needed. Simulation-based inference (SBI) methods address this problem by using machine learning to amortize computations. In this work, we highlight a particular synergy between the SBI method of neural likelihood estimation and the classic MCMC method of Hamiltonian Monte Carlo. We show that approximating the likelihood function with a neural network model can provide three distinct advantages: (1) amortizing the computations for MCMC; (2) providing gradients for Hamiltonian Monte Carlo, and (3) smoothing over noisy simulations resulting from numerical instabilities. We provide practical guidelines for defining a prior, sampling a training set, and evaluating convergence. The method is demonstrated in an application modeling the heliospheric transport of galactic cosmic rays, where it enables efficient inference of latent parameters in the Parker equation. + oai:arXiv.org:2407.20432v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Bo Gao, Jingcheng Tong, Xingsheng Chen, Han Yu, Zichen Li + astro-ph.HE + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Linnea M Wolniewicz, Peter Sadowski, Claudio Corti - Procrustean Bed for AI-Driven Retrosynthesis: A Unified Framework for Reproducible Evaluation - https://arxiv.org/abs/2512.07079 - arXiv:2512.07079v1 Announce Type: new -Abstract: Progress in computer-aided synthesis planning (CASP) is obscured by the lack of standardized evaluation infrastructure and the reliance on metrics that prioritize topological completion over chemical validity. We introduce RetroCast, a unified evaluation suite that standardizes heterogeneous model outputs into a common schema to enable statistically rigorous, apples-to-apples comparison. The framework includes a reproducible benchmarking pipeline with stratified sampling and bootstrapped confidence intervals, accompanied by SynthArena, an interactive platform for qualitative route inspection. We utilize this infrastructure to evaluate leading search-based and sequence-based algorithms on a new suite of standardized benchmarks. Our analysis reveals a divergence between "solvability" (stock-termination rate) and route quality; high solvability scores often mask chemical invalidity or fail to correlate with the reproduction of experimental ground truths. Furthermore, we identify a "complexity cliff" in which search-based methods, despite high solvability rates, exhibit a sharp performance decay in reconstructing long-range synthetic plans compared to sequence-based approaches. We release the full framework, benchmark definitions, and a standardized database of model predictions to support transparent and reproducible development in the field. - oai:arXiv.org:2512.07079v1 - cs.LG + Rolling in the deep of cognitive and AI biases + https://arxiv.org/abs/2407.21202 + arXiv:2407.21202v3 Announce Type: replace +Abstract: Nowadays, we delegate many of our decisions to Artificial Intelligence (AI) that acts either in solo or as a human companion in decisions made to support several sensitive domains, like healthcare, financial services and law enforcement. AI systems, even carefully designed to be fair, are heavily criticized for delivering misjudged and discriminated outcomes against individuals and groups. Numerous work on AI algorithmic fairness is devoted on Machine Learning pipelines which address biases and quantify fairness under a pure computational view. However, the continuous unfair and unjust AI outcomes, indicate that there is urgent need to understand AI as a sociotechnical system, inseparable from the conditions in which it is designed, developed and deployed. Although, the synergy of humans and machines seems imperative to make AI work, the significant impact of human and societal factors on AI bias is currently overlooked. We address this critical issue by following a radical new methodology under which human cognitive biases become core entities in our AI fairness overview. Inspired by the cognitive science definition and taxonomy of human heuristics, we identify how harmful human actions influence the overall AI lifecycle, and reveal human to AI biases hidden pathways. We introduce a new mapping, which justifies the human heuristics to AI biases reflections and we detect relevant fairness intensities and inter-dependencies. We envision that this approach will contribute in revisiting AI fairness under deeper human-centric case studies, revealing hidden biases cause and effects. + oai:arXiv.org:2407.21202v3 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Anton Morgunov, Victor S. Batista + Athena Vakali, Nicoleta Tantalaki - ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes - https://arxiv.org/abs/2512.07081 - arXiv:2512.07081v1 Announce Type: new -Abstract: Heart failure (HF) is one of the leading causes of rehospitalization among older adults in the United States. Although clinical notes contain rich, detailed patient information and make up a large portion of electronic health records (EHRs), they remain underutilized for HF readmission risk analysis. Traditional computational models for HF readmission often rely on expert-crafted rules, medical thesauri, and ontologies to interpret clinical notes, which are typically written under time pressure and may contain misspellings, abbreviations, and domain-specific jargon. We present ClinNoteAgents, an LLM-based multi-agent framework that transforms free-text clinical notes into (1) structured representations of clinical and social risk factors for association analysis and (2) clinician-style abstractions for HF 30-day readmission prediction. We evaluate ClinNoteAgents on 3,544 notes from 2,065 patients (readmission rate=35.16%), demonstrating strong performance in extracting risk factors from free-text, identifying key contributing factors, and predicting readmission risk. By reducing reliance on structured fields and minimizing manual annotation and model training, ClinNoteAgents provides a scalable and interpretable approach to note-based HF readmission risk modeling in data-limited healthcare systems. - oai:arXiv.org:2512.07081v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Rongjia Zhou, Chengzhuo Li, Carl Yang, Jiaying Lu + Two-Edge Connectivity via Pac-Man Gluing + https://arxiv.org/abs/2408.05282 + arXiv:2408.05282v2 Announce Type: replace +Abstract: We study the 2-edge-connected spanning subgraph (2-ECSS) problem: Given a graph $G$, compute a connected subgraph $H$ of $G$ with the minimum number of edges such that $H$ is spanning, i.e., $V(H) = V(G)$, and $H$ is 2-edge-connected, i.e., $H$ remains connected upon the deletion of any single edge, if such an $H$ exists. The $2$-ECSS problem is known to be NP-hard. In this work, we provide a polynomial-time $(\frac 5 4 + \varepsilon)$-approximation for the problem for an arbitrarily small $\varepsilon>0$, improving the previous best approximation ratio of $\frac{13}{10}+\varepsilon$. + Our improvement is based on two main innovations: First, we reduce solving the problem on general graphs to solving it on structured graphs with high vertex connectivity. This high vertex connectivity ensures the existence of a 4-matching across any bipartition of the vertex set with at least 10 vertices in each part. Second, we exploit this property in a later gluing step, where isolated 2-edge-connected components need to be merged without adding too many edges. Using the 4-matching property, we can repeatedly glue a huge component (containing at least 10 vertices) to other components. This step is reminiscent of the Pac-Man game, where a Pac-Man (a huge component) consumes all the dots (other components) as it moves through a maze. These two innovations lead to a significantly simpler algorithm and analysis for the gluing step compared to the previous best approximation algorithm, which required a long and tedious case analysis. + oai:arXiv.org:2408.05282v2 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Mohit Garg, Felix Hommelsheim, Alexander Lindermayr - TRACE: A Generalizable Drift Detector for Streaming Data-Driven Optimization - https://arxiv.org/abs/2512.07082 - arXiv:2512.07082v1 Announce Type: new -Abstract: Many optimization tasks involve streaming data with unknown concept drifts, posing a significant challenge as Streaming Data-Driven Optimization (SDDO). Existing methods, while leveraging surrogate model approximation and historical knowledge transfer, are often under restrictive assumptions such as fixed drift intervals and fully environmental observability, limiting their adaptability to diverse dynamic environments. We propose TRACE, a TRAnsferable C}oncept-drift Estimator that effectively detects distributional changes in streaming data with varying time scales. TRACE leverages a principled tokenization strategy to extract statistical features from data streams and models drift patterns using attention-based sequence learning, enabling accurate detection on unseen datasets and highlighting the transferability of learned drift patterns. Further, we showcase TRACE's plug-and-play nature by integrating it into a streaming optimizer, facilitating adaptive optimization under unknown drifts. Comprehensive experimental results on diverse benchmarks demonstrate the superior generalization, robustness, and effectiveness of our approach in SDDO scenarios. - oai:arXiv.org:2512.07082v1 + Learning effective pruning at initialization from iterative pruning + https://arxiv.org/abs/2408.14757 + arXiv:2408.14757v2 Announce Type: replace +Abstract: Pruning at initialization (PaI) reduces training costs by removing weights before training, which becomes increasingly crucial with the growing network size. However, current PaI methods still have a large accuracy gap with iterative pruning, especially at high sparsity levels. This raises an intriguing question: can we get inspiration from iterative pruning to improve the PaI performance? In the lottery ticket hypothesis, the iterative rewind pruning (IRP) finds subnetworks retroactively by rewinding the parameter to the original initialization in every pruning iteration, which means all the subnetworks are based on the initial state. Here, we hypothesise the surviving subnetworks are more important and bridge the initial feature and their surviving score as the PaI criterion. We employ an end-to-end neural network (\textbf{AutoS}parse) to learn this correlation, input the model's initial features, output their score and then prune the lowest score parameters before training. To validate the accuracy and generalization of our method, we performed PaI across various models. Results show that our approach outperforms existing methods in high-sparsity settings. Notably, as the underlying logic of model pruning is consistent in different models, only one-time IRP on one model is needed (e.g., once IRP on ResNet-18/CIFAR-10, AutoS can be generalized to VGG-16/CIFAR-10, ResNet-18/TinyImageNet, et al.). As the first neural network-based PaI method, we conduct extensive experiments to validate the factors influencing this approach. These results reveal the learning tendencies of neural networks and provide new insights into our understanding and research of PaI from a practical perspective. Our code is available at: https://github.com/ChengYaofeng/AutoSparse.git. + oai:arXiv.org:2408.14757v2 + cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yuan-Ting Zhong, Ting Huang, Xiaolin Xiao, Yue-Jiao Gong + Shengkai Liu, Yaofeng Cheng, Fusheng Zha, Wei Guo, Lining Sun, Zhenshan Bing, Chenguang Yang - ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking - https://arxiv.org/abs/2512.07086 - arXiv:2512.07086v1 Announce Type: new -Abstract: Large Language Models (LLMs) have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as cloud-based services, allowing users to access powerful LLMs via the Internet. However, this deployment model introduces a new class of threat: denial-of-service (DoS) attacks via unbounded reasoning, where adversaries craft specially designed inputs that cause the model to enter excessively long or infinite generation loops. These attacks can exhaust backend compute resources, degrading or denying service to legitimate users. To mitigate such risks, many LLM providers adopt a closed-source, black-box setting to obscure model internals. In this paper, we propose ThinkTrap, a novel input-space optimization framework for DoS attacks against LLM services even in black-box environments. The core idea of ThinkTrap is to first map discrete tokens into a continuous embedding space, then undertake efficient black-box optimization in a low-dimensional subspace exploiting input sparsity. The goal of this optimization is to identify adversarial prompts that induce extended or non-terminating generation across several state-of-the-art LLMs, achieving DoS with minimal token overhead. We evaluate the proposed attack across multiple commercial, closed-source LLM services. Our results demonstrate that, even far under the restrictive request frequency limits commonly enforced by these platforms, typically capped at ten requests per minute (10 RPM), the attack can degrade service throughput to as low as 1% of its original capacity, and in some cases, induce complete service failure. - oai:arXiv.org:2512.07086v1 - cs.CR - cs.AI + Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning + https://arxiv.org/abs/2409.03915 + arXiv:2409.03915v3 Announce Type: replace +Abstract: This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof method of Borkar and Meyn to accommodate more general noise conditions than previously considered, thereby yielding broader convergence guarantees for asynchronous SA. To sharpen the convergence analysis, we further examine the shadowing properties of asynchronous SA, building on a dynamical systems approach of Hirsch and Bena\"{i}m. These results provide a theoretical foundation for a class of relative value iteration-based reinforcement learning algorithms -- developed and analyzed in a companion paper -- for solving average-reward Markov and semi-Markov decision processes. + oai:arXiv.org:2409.03915v3 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yunzhe Li, Jianan Wang, Hongzi Zhu, James Lin, Shan Chang, Minyi Guo + Huizhen Yu, Yi Wan, Richard S. Sutton - Leveraging KV Similarity for Online Structured Pruning in LLMs - https://arxiv.org/abs/2512.07090 - arXiv:2512.07090v1 Announce Type: new -Abstract: Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not generalize across inputs. In this work, we introduce Token Filtering, a lightweight online structured pruning technique that makes pruning decisions directly during inference without any calibration data. The key idea is to measure token redundancy via joint key-value similarity and skip redundant attention computations, thereby reducing inference cost while preserving critical information. To further enhance stability, we design a variance-aware fusion strategy that adaptively weights key and value similarity across heads, ensuring that informative tokens are retained even under high pruning ratios. This design introduces no additional memory overhead and provides a more reliable criterion for token importance. Extensive experiments on LLaMA-2 (7B/13B), LLaMA-3 (8B), and Mistral (7B) demonstrate that Token Filtering consistently outperforms prior structured pruning methods, preserving accuracy on commonsense reasoning benchmarks and maintaining strong performance on challenging tasks such as MMLU, even with 50% pruning. - oai:arXiv.org:2512.07090v1 - cs.CL + SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records + https://arxiv.org/abs/2409.08936 + arXiv:2409.08936v4 Announce Type: replace +Abstract: Clinical information extraction, which involves structuring clinical concepts from unstructured medical text, remains a challenging problem that could benefit from the inclusion of tabular background information available in electronic health records. Existing open-source datasets lack explicit links between structured features and clinical concepts in the text, motivating the need for a new research dataset. We introduce SimSUM, a benchmark dataset of 10,000 simulated patient records that link unstructured clinical notes with structured background variables. Each record simulates a patient encounter in the domain of respiratory diseases and includes tabular data (e.g., symptoms, diagnoses, underlying conditions) generated from a Bayesian network whose structure and parameters are defined by domain experts. A large language model (GPT-4o) is prompted to generate a clinical note describing the encounter, including symptoms and relevant context. These notes are annotated with span-level symptom mentions. We conduct an expert evaluation to assess note quality and run baseline predictive models on both the tabular and textual data. The SimSUM dataset is primarily designed to support research on clinical information extraction in the presence of tabular background variables, which can be linked through domain knowledge to concepts of interest to be extracted from the text -- namely, symptoms in the case of SimSUM. Secondary uses include research on the automation of clinical reasoning over both tabular data and text, causal effect estimation in the presence of tabular and/or textual confounders, and multi-modal synthetic data generation. SimSUM is not intended for training clinical decision support systems or production-grade models, but rather to facilitate reproducible research in a simplified and controlled setting. + oai:arXiv.org:2409.08936v4 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Jungmin Lee, Gwangeun Byeon, Yulhwa Kim, Seokin Hong + Paloma Rabaey, Stefan Heytens, Thomas Demeester - A Flexible Funnel-Shaped Robotic Hand with an Integrated Single-Sheet Valve for Milligram-Scale Powder Handling - https://arxiv.org/abs/2512.07091 - arXiv:2512.07091v1 Announce Type: new -Abstract: Laboratory Automation (LA) has the potential to accelerate solid-state materials discovery by enabling continuous robotic operation without human intervention. While robotic systems have been developed for tasks such as powder grinding and X-ray diffraction (XRD) analysis, fully automating powder handling at the milligram scale remains a significant challenge due to the complex flow dynamics of powders and the diversity of laboratory tasks. To address this challenge, this study proposes a novel, funnel-shaped, flexible robotic hand that preserves the softness and conical sheet designs in prior work while incorporating a controllable valve at the cone apex to enable precise, incremental dispensing of milligram-scale powder quantities. The hand is integrated with an external balance through a feedback control system based on a model of powder flow and online parameter identification. Experimental evaluations with glass beads, monosodium glutamate, and titanium dioxide demonstrated that 80% of the trials achieved an error within 2 mg, and the maximum error observed was approximately 20 mg across a target range of 20 mg to 3 g. In addition, by incorporating flow prediction models commonly used for hoppers and performing online parameter identification, the system is able to adapt to variations in powder dynamics. Compared to direct PID control, the proposed model-based control significantly improved both accuracy and convergence speed. These results highlight the potential of the proposed system to enable efficient and flexible powder weighing, with scalability toward larger quantities and applicability to a broad range of laboratory automation tasks. - oai:arXiv.org:2512.07091v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tomoya Takahashi, Yusaku Nakajima, Cristian Camilo Beltran-Hernandez, Yuki Kuroda, Kazutoshi Tanaka, Masashi Hamaya, Kanta Ono, Yoshitaka Ushiku + Beyond accuracy: quantifying the reliability of Multiple Instance Learning for Whole Slide Image classification + https://arxiv.org/abs/2409.11110 + arXiv:2409.11110v3 Announce Type: replace +Abstract: Machine learning models have become integral to many fields, but their reliability, defined as producing dependable, trustworthy, and domain-consistent predictions, remains a critical concern. Multiple Instance Learning (MIL) models designed for Whole Slide Image (WSI) classification in computational pathology are rarely evaluated in terms of reliability, leaving a key gap in understanding their suitability for high-stakes applications like clinical decision-making. In this paper, we address this gap by introducing three quantitative metrics for reliability assessment and applying them to several widely used MIL architectures across three region-wise annotated pathology datasets. Our findings indicate that the mean pooling instance (MEAN-POOL-INS)model demonstrates superior reliability compared to other networks, despite its simple architectural design and computational efficiency. These findings underscore the need of reliability evaluation alongside predictive performance in MIL models and establish MEAN-POOL-INS as a strong, trustworthy baseline for future research. + oai:arXiv.org:2409.11110v3 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + 10.1371/journal.pone.0337261 + PloS one. 2025 Dec 5;20(12):e0337261 + Hassan Keshvarikhojasteh, Marc Aubreville, Christof A. Bertram, Josien P. W. Pluim, Mitko Veta - The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models - https://arxiv.org/abs/2512.07092 - arXiv:2512.07092v1 Announce Type: new -Abstract: Background: The deployment of personalized Large Language Models (LLMs) is currently constrained by the stability-plasticity dilemma. Prevailing alignment methods, such as Supervised Fine-Tuning (SFT), rely on stochastic weight updates that often incur an "alignment tax" -- degrading general reasoning capabilities. - Methods: We propose the Soul Engine, a framework based on the Linear Representation Hypothesis, which posits that personality traits exist as orthogonal linear subspaces. We introduce SoulBench, a dataset constructed via dynamic contextual sampling. Using a dual-head architecture on a frozen Qwen-2.5 base, we extract disentangled personality vectors without modifying the backbone weights. - Results: Our experiments demonstrate three breakthroughs. First, High-Precision Profiling: The model achieves a Mean Squared Error (MSE) of 0.011 against psychological ground truth. Second, Geometric Orthogonality: T-SNE visualization confirms that personality manifolds are distinct and continuous, allowing for "Zero-Shot Personality Injection" that maintains original model intelligence. Third, Deterministic Steering: We achieve robust control over behavior via vector arithmetic, validated through extensive ablation studies. - Conclusion: This work challenges the necessity of fine-tuning for personalization. By transitioning from probabilistic prompting to deterministic latent intervention, we provide a mathematically rigorous foundation for safe, controllable AI personalization. - oai:arXiv.org:2512.07092v1 + Learning Generalized Hamiltonians using fully Symplectic Mappings + https://arxiv.org/abs/2409.11138 + arXiv:2409.11138v3 Announce Type: replace +Abstract: Many important physical systems can be described as the evolution of a Hamiltonian system, which has the important property of being conservative, that is, energy is conserved throughout the evolution. Physics Informed Neural Networks and in particular Hamiltonian Neural Networks have emerged as a mechanism to incorporate structural inductive bias into the NN model. By ensuring physical invariances are conserved, the models exhibit significantly better sample complexity and out-of-distribution accuracy than standard NNs. Learning the Hamiltonian as a function of its canonical variables, typically position and velocity, from sample observations of the system thus becomes a critical task in system identification and long-term prediction of system behavior. However, to truly preserve the long-run physical conservation properties of Hamiltonian systems, one must use symplectic integrators for a forward pass of the system's simulation. While symplectic schemes have been used in the literature, they are thus far limited to situations when they reduce to explicit algorithms, which include the case of separable Hamiltonians or augmented non-separable Hamiltonians. We extend it to generalized non-separable Hamiltonians, and noting the self-adjoint property of symplectic integrators, we bypass computationally intensive backpropagation through an ODE solver. We show that the method is robust to noise and provides a good approximation of the system Hamiltonian when the state variables are sampled from a noisy observation. In the numerical results, we show the performance of the method concerning Hamiltonian reconstruction and conservation, indicating its particular advantage for non-separable systems. + oai:arXiv.org:2409.11138v3 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhixiang Wang - - - VIGIL: A Reflective Runtime for Self-Healing Agents - https://arxiv.org/abs/2512.07094 - arXiv:2512.07094v1 Announce Type: new -Abstract: Agentic LLM frameworks promise autonomous behavior via task decomposition, tool use, and iterative planning, but most deployed systems remain brittle. They lack runtime introspection, cannot diagnose their own failure modes, and do not improve over time without human intervention. In practice, many agent stacks degrade into decorated chains of LLM calls with no structural mechanisms for reliability. We present VIGIL (Verifiable Inspection and Guarded Iterative Learning), a reflective runtime that supervises a sibling agent and performs autonomous maintenance rather than task execution. VIGIL ingests behavioral logs, appraises each event into a structured emotional representation, maintains a persistent EmoBank with decay and contextual policies, and derives an RBT diagnosis that sorts recent behavior into strengths, opportunities, and failures. From this analysis, VIGIL generates both guarded prompt updates that preserve core identity semantics and read only code proposals produced by a strategy engine that operates on log evidence and code hotspots. VIGIL functions as a state gated pipeline. Illegal transitions produce explicit errors rather than allowing the LLM to improvise. In a reminder latency case study, VIGIL identified elevated lag, proposed prompt and code repairs, and when its own diagnostic tool failed due to a schema conflict, it surfaced the internal error, produced a fallback diagnosis, and emitted a repair plan. This demonstrates meta level self repair in a deployed agent runtime. - oai:arXiv.org:2512.07094v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Christopher Cruz + Harsh Choudhary, Chandan Gupta, Vyacheslav Kungurtsev, Melvin Leok, Georgios Korpas - Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph - https://arxiv.org/abs/2512.07100 - arXiv:2512.07100v1 Announce Type: new -Abstract: Pretrained language models offer strong text understanding capabilities but remain difficult to deploy in real-world text-attributed networks due to their heavy dependence on labeled data. Meanwhile, community detection methods typically ignore textual semantics, limiting their usefulness in downstream applications such as content organization, recommendation, and risk monitoring. To overcome these limitations, we present Dual Refinement Cycle Learning (DRCL), a fully unsupervised framework designed for practical scenarios where no labels or category definitions are available. - DRCL integrates structural and semantic information through a warm-start initialization and a bidirectional refinement cycle between a GCN-based Community Detection Module (GCN-CDM) and a Text Semantic Modeling Module (TSMM). The two modules iteratively exchange pseudo-labels, allowing semantic cues to enhance structural clustering and structural patterns to guide text representation learning without manual supervision. - Across several text-attributed graph datasets, DRCL consistently improves the structural and semantic quality of discovered communities. Moreover, a Mamba-based classifier trained solely from DRCL's community signals achieves accuracy comparable to supervised models, demonstrating its potential for deployment in large-scale systems where labeled data are scarce or costly. - oai:arXiv.org:2512.07100v1 + Geometry Aware Meta-Learning Neural Network for Joint Phase and Precoder Optimization in RIS + https://arxiv.org/abs/2409.11270 + arXiv:2409.11270v2 Announce Type: replace +Abstract: In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we propose a complex-valued, geometry aware meta-learning neural network that maximizes the weighted sum rate in a multi-user multiple input single output system. By leveraging the complex circle geometry for phase shifts and spherical geometry for the precoder, the optimization occurs on Riemannian manifolds, leading to faster convergence. We use a complex-valued neural network for phase shifts and an Euler inspired update for the precoder network. Our approach outperforms existing neural network-based algorithms, offering higher weighted sum rates, lower power consumption, and significantly faster convergence. Specifically, it converges faster by nearly 100 epochs, with a 0.7 bps improvement in weighted sum rate and a 1.8 dB power gain when compared with existing work. Further it outperforms the state-of-the-art alternating optimization algorithm by 0.86 bps with a 2.6 dB power gain. + oai:arXiv.org:2409.11270v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Hong Wang, Yinglong Zhang, Hanhan Guo, Xuewen Xia, Xing Xu + eess.SP + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Dahlia Devapriya, Aparna V C, Sheetal Kalyani - COREA: Coarse-to-Fine 3D Representation Alignment Between Relightable 3D Gaussians and SDF via Bidirectional 3D-to-3D Supervision - https://arxiv.org/abs/2512.07107 - arXiv:2512.07107v1 Announce Type: new -Abstract: We present COREA, the first unified framework that jointly learns relightable 3D Gaussians and a Signed Distance Field (SDF) for accurate geometry reconstruction and faithful relighting. While recent 3D Gaussian Splatting (3DGS) methods have extended toward mesh reconstruction and physically-based rendering (PBR), their geometry is still learned from 2D renderings, leading to coarse surfaces and unreliable BRDF-lighting decomposition. To address these limitations, COREA introduces a coarse-to-fine bidirectional 3D-to-3D alignment strategy that allows geometric signals to be learned directly in 3D space. Within this strategy, depth provides coarse alignment between the two representations, while depth gradients and normals refine fine-scale structure, and the resulting geometry supports stable BRDF-lighting decomposition. A density-control mechanism further stabilizes Gaussian growth, balancing geometric fidelity with memory efficiency. Experiments on standard benchmarks demonstrate that COREA achieves superior performance in novel-view synthesis, mesh reconstruction, and PBR within a unified framework. - oai:arXiv.org:2512.07107v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Jaeyoon Lee, Hojoon Jung, Sungtae Hwang, Jihyong Oh, Jongwon Choi + 2Fast-2Lamaa: Large-Scale Lidar-Inertial Localization and Mapping with Continuous Distance Fields + https://arxiv.org/abs/2410.05433 + arXiv:2410.05433v2 Announce Type: replace +Abstract: This paper introduces 2Fast-2Lamaa, a lidar-inertial state estimation framework for odometry, mapping, and localization. Its first key component is the optimization-based undistortion of lidar scans, which uses continuous IMU preintegration to model the system's pose at every lidar point timestamp. The continuous trajectory over 100-200ms is parameterized only by the initial scan conditions (linear velocity and gravity orientation) and IMU biases, yielding eleven state variables. These are estimated by minimizing point-to-line and point-to-plane distances between lidar-extracted features without relying on previous estimates, resulting in a prior-less motion-distortion correction strategy. Because the method performs local state estimation, it directly provides scan-to-scan odometry. To maintain geometric consistency over longer periods, undistorted scans are used for scan-to-map registration. The map representation employs Gaussian Processes to form a continuous distance field, enabling point-to-surface distance queries anywhere in space. Poses of the undistorted scans are refined by minimizing these distances through non-linear least-squares optimization. For odometry and mapping, the map is built incrementally in real time; for pure localization, existing maps are reused. The incremental map construction also includes mechanisms for removing dynamic objects. We benchmark 2Fast-2Lamaa on 250km (over 10h) of public and self-collected datasets from both automotive and handheld systems. The framework achieves state-of-the-art performance across diverse and challenging scenarios, reaching odometry and localization errors as low as 0.27% and 0.06 m, respectively. The real-time implementation is publicly available at https://github.com/clegenti/2fast2lamaa. + oai:arXiv.org:2410.05433v2 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Cedric Le Gentil, Raphael Falque, Daniil Lisus, Timothy D. Barfoot - A Neural Affinity Framework for Abstract Reasoning: Diagnosing the Compositional Gap in Transformer Architectures via Procedural Task Taxonomy - https://arxiv.org/abs/2512.07109 - arXiv:2512.07109v1 Announce Type: new -Abstract: Responding to Hodel et al.'s (2024) call for a formal definition of task relatedness in re-arc, we present the first 9-category taxonomy of all 400 tasks, validated at 97.5% accuracy via rule-based code analysis. We prove the taxonomy's visual coherence by training a CNN on raw grid pixels (95.24% accuracy on S3, 36.25% overall, 3.3x chance), then apply the taxonomy diagnostically to the original ARC-AGI-2 test set. Our curriculum analysis reveals 35.3% of tasks exhibit low neural affinity for Transformers--a distributional bias mirroring ARC-AGI-2. To probe this misalignment, we fine-tuned a 1.7M-parameter Transformer across 302 tasks, revealing a profound Compositional Gap: 210 of 302 tasks (69.5%) achieve >80% cell accuracy (local patterns) but <10% grid accuracy (global synthesis). This provides direct evidence for a Neural Affinity Ceiling Effect, where performance is bounded by architectural suitability, not curriculum. Applying our framework to Li et al.'s independent ViTARC study (400 specialists, 1M examples each) confirms its predictive power: Very Low affinity tasks achieve 51.9% versus 77.7% for High affinity (p<0.001), with a task at 0% despite massive data. The taxonomy enables precise diagnosis: low-affinity tasks (A2) hit hard ceilings, while high-affinity tasks (C1) reach 99.8%. These findings indicate that progress requires hybrid architectures with affinity-aligned modules. We release our validated taxonomy, - oai:arXiv.org:2512.07109v1 - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + PP-GWAS: Privacy Preserving Multi-Site Genome-wide Association Studies + https://arxiv.org/abs/2410.08122 + arXiv:2410.08122v2 Announce Type: replace +Abstract: Genome-wide association studies are pivotal in understanding the genetic underpinnings of complex traits and diseases. Collaborative, multi-site GWAS aim to enhance statistical power but face obstacles due to the sensitive nature of genomic data sharing. Current state-of-the-art methods provide a privacy-focused approach utilizing computationally expensive methods such as Secure Multi-Party Computation and Homomorphic Encryption. In this context, we present a novel algorithm PP-GWAS designed to improve upon existing standards in terms of computational efficiency and scalability without sacrificing data privacy. This algorithm employs randomized encoding within a distributed architecture to perform stacked ridge regression on a Linear Mixed Model to ensure rigorous analysis. Experimental evaluation with real world and synthetic data indicates that PP-GWAS can achieve computational speeds twice as fast as similar state-of-the-art algorithms while using lesser computational resources, all while adhering to a robust security model that caters to an all-but-one semi-honest adversary setting. We have assessed its performance using various datasets, emphasizing its potential in facilitating more efficient and private genomic analyses. + oai:arXiv.org:2410.08122v2 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Miguel Ingram, Arthur Joseph Merritt III + Arjhun Swaminathan, Anika Hannemann, Ali Burak \"Unal, Nico Pfeifer, Mete Akg\"un - MSN: Multi-directional Similarity Network for Hand-crafted and Deep-synthesized Copy-Move Forgery Detection - https://arxiv.org/abs/2512.07110 - arXiv:2512.07110v1 Announce Type: new -Abstract: Copy-move image forgery aims to duplicate certain objects or to hide specific contents with copy-move operations, which can be achieved by a sequence of manual manipulations as well as up-to-date deep generative network-based swapping. Its detection is becoming increasingly challenging for the complex transformations and fine-tuned operations on the tampered regions. In this paper, we propose a novel two-stream model, namely Multi-directional Similarity Network (MSN), to accurate and efficient copy-move forgery detection. It addresses the two major limitations of existing deep detection models in \textbf{representation} and \textbf{localization}, respectively. In representation, an image is hierarchically encoded by a multi-directional CNN network, and due to the diverse augmentation in scales and rotations, the feature achieved better measures the similarity between sampled patches in two streams. In localization, we design a 2-D similarity matrix based decoder, and compared with the current 1-D similarity vector based one, it makes full use of spatial information in the entire image, leading to the improvement in detecting tampered regions. Beyond the method, a new forgery database generated by various deep neural networks is presented, as a new benchmark for detecting the growing deep-synthesized copy-move. Extensive experiments are conducted on two classic image forensics benchmarks, \emph{i.e.} CASIA CMFD and CoMoFoD, and the newly presented one. The state-of-the-art results are reported, which demonstrate the effectiveness of the proposed approach. - oai:arXiv.org:2512.07110v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Liangwei Jiang, Jinluo Xie, Yecheng Huang, Hua Zhang, Hongyu Yang, Di Huang + Kamp Theorem for Pomset Languages of Higher Dimensional Automata + https://arxiv.org/abs/2410.12493 + arXiv:2410.12493v4 Announce Type: replace +Abstract: Temporal logics are a powerful tool to specify properties of computational systems. For concurrent programs, Higher Dimensional Automata (HDA) are a very expressive model of non-interleaving concurrency. HDA recognize languages of partially ordered multisets, or pomsets. Recent work has shown that Monadic Second Order (MSO) logic is as expressive as HDA for pomset languages. In the case of words, Kamp's theorem states that First Order (FO) logic is as expressive as Linear Temporal Logic (LTL). In this paper, we extend this result to pomsets. To do so, we first investigate the class of pomset languages that are definable in FO. As expected, this is a strict subclass of MSO-definable languages. Then, we define a Linear Temporal Logic for pomsets, and show that it is equivalent to FO. + oai:arXiv.org:2410.12493v4 + cs.FL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Emily Clement, Enzo Erlich, J\'er\'emy Ledent - FOAM: Blocked State Folding for Memory-Efficient LLM Training - https://arxiv.org/abs/2512.07112 - arXiv:2512.07112v1 Announce Type: new -Abstract: Large language models (LLMs) have demonstrated remarkable performance due to their large parameter counts and extensive training data. However, their scale leads to significant memory bottlenecks during training, especially when using memory-intensive optimizers like Adam. Existing memory-efficient approaches often rely on techniques such as singular value decomposition (SVD), projections, or weight freezing, which can introduce substantial computational overhead, require additional memory for projections, or degrade model performance. In this paper, we propose Folded Optimizer with Approximate Moment (FOAM), a method that compresses optimizer states by computing block-wise gradient means and incorporates a residual correction to recover lost information. Theoretically, FOAM achieves convergence rates equivalent to vanilla Adam under standard non-convex optimization settings. Empirically, FOAM reduces total training memory by approximately 50\%, eliminates up to 90\% of optimizer state memory overhead, and accelerates convergence. Furthermore, FOAM is compatible with other memory-efficient optimizers, delivering performance and throughput that match or surpass both full-rank and existing memory-efficient baselines. - oai:arXiv.org:2512.07112v1 + Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shift + https://arxiv.org/abs/2410.17506 + arXiv:2410.17506v2 Announce Type: replace +Abstract: Distribution shifts between training and testing datasets significantly impair the model performance on graph learning. A commonly-taken causal view in graph invariant learning suggests that stable predictive features of graphs are causally associated with labels, whereas varying environmental features lead to distribution shifts. In particular, covariate shifts caused by unseen environments in test graphs underscore the critical need for out-of-distribution (OOD) generalization. Existing graph augmentation methods designed to address the covariate shift often disentangle the stable and environmental features in the input space, and selectively perturb or mixup the environmental features. However, such perturbation-based methods heavily rely on an accurate separation of stable and environmental features, and their exploration ability is confined to existing environmental features in the training distribution. To overcome these limitations, we introduce a novel distributional augmentation approach enabled by a tailored score-based conditional graph generation strategies to explore and synthesize unseen environments while preserving the validity and stable features of overall graph patterns. Our comprehensive empirical evaluations demonstrate the enhanced effectiveness of our method in improving graph OOD generalization. + oai:arXiv.org:2410.17506v2 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Ziqing Wen, Jiahuan Wang, Ping Luo, Dongsheng Li, Tao Sun + Bohan Wang, Yurui Chang, Wei Jin, Lu Lin - PlantBiMoE: A Bidirectional Foundation Model with SparseMoE for Plant Genomes - https://arxiv.org/abs/2512.07113 - arXiv:2512.07113v1 Announce Type: new -Abstract: Understanding the underlying linguistic rules of plant genomes remains a fundamental challenge in computational biology. Recent advances including AgroNT and PDLLMs have made notable progress although, they suffer from excessive parameter size and limited ability to model the bidirectional nature of DNA strands respectively. To address these limitations, we propose PlantBiMoE, a lightweight and expressive plant genome language model that integrates bidirectional Mamba and a Sparse Mixture-of-Experts (SparseMoE) framework. The bidirectional Mamba enables the model to effectively capture structural dependencies across both the forward and reverse DNA strands, while SparseMoE significantly reduces the number of active parameters, improving computational efficiency without sacrificing modeling capacity. We evaluated and tested our model on the Modified Plants Genome Benchmark (MPGB), an enhanced genomic benchmark, which consolidates 31 datasets across 11 representative tasks, with input sequence lengths ranging from 50 to 6,000 bp. Experimental results demonstrate that PlantBiMoE achieves the best performance on 20 out of 31 datasets and the average best when comparing with existing models. In summary, all above results demonstrate that our model can effectively represent plant genomic sequences, serving as a robust computational tool for diverse genomic tasks, while making substantive contributions to plant genomics, gene editing, and synthetic biology. The code is available at: https://github.com/HUST-Keep-Lin/PlantBiMoE - oai:arXiv.org:2512.07113v1 - cs.LG - q-bio.GN - Tue, 09 Dec 2025 00:00:00 -0500 - new + Learning Geodesics of Geometric Shape Deformations From Images + https://arxiv.org/abs/2410.18797 + arXiv:2410.18797v3 Announce Type: replace +Abstract: This paper presents a novel method, named geodesic deformable networks (GDN), that for the first time enables the learning of geodesic flows of deformation fields derived from images. In particular, the capability of our proposed GDN being able to predict geodesics is important for quantifying and comparing deformable shape presented in images. The geodesic deformations, also known as optimal transformations that align pairwise images, are often parameterized by a time sequence of smooth vector fields governed by nonlinear differential equations. A bountiful literature has been focusing on learning the initial conditions (e.g., initial velocity fields) based on registration networks. However, the definition of geodesics central to deformation-based shape analysis is blind to the networks. To address this problem, we carefully develop an efficient neural operator to treat the geodesics as unknown mapping functions learned from the latent deformation spaces. A composition of integral operators and smooth activation functions is then formulated to effectively approximate such mappings. In contrast to previous works, our GDN jointly optimizes a newly defined geodesic loss, which adds additional benefits to promote the network regularizability and generalizability. We demonstrate the effectiveness of GDN on both 2D synthetic data and 3D real brain magnetic resonance imaging (MRI). + oai:arXiv.org:2410.18797v3 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + 10.59275/j.melba.2025-f9f4 + Machine.Learning.for.Biomedical.Imaging. 3 (2025) + Nian Wu, Miaomiao Zhang + + + Deep Learning, Machine Learning -- Digital Signal and Image Processing: From Theory to Application + https://arxiv.org/abs/2410.20304 + arXiv:2410.20304v2 Announce Type: replace +Abstract: Digital Signal Processing (DSP) and Digital Image Processing (DIP) with Machine Learning (ML) and Deep Learning (DL) are popular research areas in Computer Vision and related fields. We highlight transformative applications in image enhancement, filtering techniques, and pattern recognition. By integrating frameworks like the Discrete Fourier Transform (DFT), Z-Transform, and Fourier Transform methods, we enable robust data manipulation and feature extraction essential for AI-driven tasks. Using Python, we implement algorithms that optimize real-time data processing, forming a foundation for scalable, high-performance solutions in computer vision. This work illustrates the potential of ML and DL to advance DSP and DIP methodologies, contributing to artificial intelligence, automated feature extraction, and applications across diverse domains. + oai:arXiv.org:2410.20304v2 + cs.CV + cs.GR + eess.IV + eess.SP + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kepeng Lin, Qizhe Zhang, Rui Wang, Xuehai Hu, Wei Xu + Weiche Hsieh, Ziqian Bi, Junyu Liu, Benji Peng, Sen Zhang, Xuanhe Pan, Jiawei Xu, Jinlang Wang, Keyu Chen, Caitlyn Heqi Yin, Pohsun Feng, Yizhu Wen, Tianyang Wang, Ming Li, Jintao Ren, Xinyuan Song, Qian Niu, Silin Chen, Ming Liu - Surrogate compliance modeling enables reinforcement learned locomotion gaits for soft robots - https://arxiv.org/abs/2512.07114 - arXiv:2512.07114v1 Announce Type: new -Abstract: Adaptive morphogenetic robots adapt their morphology and control policies to meet changing tasks and environmental conditions. Many such systems leverage soft components, which enable shape morphing but also introduce simulation and control challenges. Soft-body simulators remain limited in accuracy and computational tractability, while rigid-body simulators cannot capture soft-material dynamics. Here, we present a surrogate compliance modeling approach: rather than explicitly modeling soft-body physics, we introduce indirect variables representing soft-material deformation within a rigid-body simulator. We validate this approach using our amphibious robotic turtle, a quadruped with soft morphing limbs designed for multi-environment locomotion. By capturing deformation effects as changes in effective limb length and limb center of mass, and by applying reinforcement learning with extensive randomization of these indirect variables, we achieve reliable policy learning entirely in a rigid-body simulation. The resulting gaits transfer directly to hardware, demonstrating high-fidelity sim-to-real performance on hard, flat substrates and robust, though lower-fidelity, transfer on rheologically complex terrains. The learned closed-loop gaits exhibit unprecedented terrestrial maneuverability and achieve an order-of-magnitude reduction in cost of transport compared to open-loop baselines. Field experiments with the robot further demonstrate stable, multi-gait locomotion across diverse natural terrains, including gravel, grass, and mud. - oai:arXiv.org:2512.07114v1 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new + Architecture Proposal for 6G Systems Integrating Sensing and Communication + https://arxiv.org/abs/2411.10138 + arXiv:2411.10138v2 Announce Type: replace +Abstract: Integrating sensing functionality into 6G communication networks requires some changes to existing components as well as new entities processing the radar sensing signals received by the communication antennas. This whitepaper provides a comprehensive overview of the 6G design proposal for ISaC (Integrated Sensing and Communication). The whitepaper has been created by the architecture group of the KOMSENS-6G project with the intend to serve as a basis for further discussions and alignment across innovative 6G projects. + oai:arXiv.org:2411.10138v2 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Jue Wang, Mingsong Jiang, Luis A. Ramirez, Bilige Yang, Mujun Zhang, Esteban Figueroa, Wenzhong Yan, Rebecca Kramer-Bottiglio + Peter Gersing, Mark Doll, Joerg Huschke, Jan Plachy, Stefan K\"opsell - Human Agency and Creativity in AI-Assisted Learning Environments - https://arxiv.org/abs/2512.07117 - arXiv:2512.07117v1 Announce Type: new -Abstract: This chapter explores human creativity in AI-assisted learning environments through the lens of student agency. We begin by examining four theoretical perspectives on agency, including instrumental, effortful, dynamically emergent, and authorial agency, and analyze how each frames the relationship between agency and creativity. Under each theoretical perspective, we discuss how the integration of generative AI (GenAI) tools reshapes these dynamics by altering students' roles in cognitive, social, and creative processes. In the second part, we introduce a theoretical framework for AI agentic engagement, contextualizing agency within specific cognitive, relational, and ethical dynamics introduced by GenAI tools. This framework is linked to the concept of Mini-c creativity, emphasizing personal relevance and self-directed learning. Together, these perspectives support a shift from viewing creativity as product-oriented to understanding it as a process of agentive participation and meaning-making. We conclude with two directions for future research focused on the creative process and performance in AI-assisted learning. - oai:arXiv.org:2512.07117v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Oxford Handbook of Human Creativity x Generative AI in Education, 2026 - Yun Dai + NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive Learning + https://arxiv.org/abs/2411.12950 + arXiv:2411.12950v3 Announce Type: replace +Abstract: Knowledge graphs (KGs) serve as a vital backbone for a wide range of AI applications, including natural language understanding and recommendation. A promising yet underexplored direction is numerical reasoning over KGs, which involves inferring new facts by leveraging not only symbolic triples but also numerical attribute values (e.g., length, weight). However, existing methods fall short in two key aspects: (1) Incomplete semantic integration: Most models struggle to jointly encode entities, relations, and numerical attributes in a unified representation space, limiting their ability to extract relation-aware semantics from numeric information. (2) Ordinal indistinguishability: Due to subtle differences between close values and sampling imbalance, models often fail to capture fine-grained ordinal relationships (e.g., longer, heavier), especially in the presence of hard negatives. To address these challenges, we propose NumCoKE, a numerical reasoning framework for KGs based on Mixture-of-Experts and Ordinal Contrastive Embedding. To overcome (C1), we introduce a Mixture-of-Experts Knowledge-Aware (MoEKA) encoder that jointly aligns symbolic and numeric components into a shared semantic space, while dynamically routing attribute features to relation-specific experts. To handle (C2), we propose Ordinal Knowledge Contrastive Learning (OKCL), which constructs ordinal-aware positive and negative samples using prior knowledge, enabling the model to better discriminate subtle semantic shifts. Extensive experiments on three public KG benchmarks demonstrate that NumCoKE consistently outperforms competitive baselines across diverse attribute distributions, validating its superiority in both semantic integration and ordinal reasoning. + oai:arXiv.org:2411.12950v3 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ming Yin, Zongsheng Cao, Qiqing Xia, Chenyang Tu, Neng Gao - Chromatic Feature Vectors for 2-Trees: Exact Formulas for Partition Enumeration with Network Applications - https://arxiv.org/abs/2512.07120 - arXiv:2512.07120v1 Announce Type: new -Abstract: We establish closed-form enumeration formulas for chromatic feature vectors of 2-trees under the bichromatic triangle constraint. These efficiently computable structural features derive from constrained graph colorings where each triangle uses exactly two colors, forbidding monochromatic and rainbow triangles, a constraint arising in distributed systems where components avoid complete concentration or isolation. For theta graphs Theta_n, we prove r_k(Theta_n) = S(n-2, k-1) for k >= 3 (Stirling numbers of the second kind) and r_2(Theta_n) = 2^(n-2) + 1, computable in O(n) time. For fan graphs Phi_n, we establish r_2(Phi_n) = F_{n+1} (Fibonacci numbers) and derive explicit formulas r_k(Phi_n) = sum_{t=k-1}^{n-1} a_{n-1,t} * S(t, k-1) with efficiently computable binomial coefficients, achieving O(n^2) computation per component. Unlike classical chromatic polynomials, which assign identical features to all n-vertex 2-trees, bichromatic constraints provide informative structural features. While not complete graph invariants, these features capture meaningful structural properties through connections to Fibonacci polynomials, Bell numbers, and independent set enumeration. Applications include Byzantine fault tolerance in hierarchical networks, VM allocation in cloud computing, and secret-sharing protocols in distributed cryptography. - oai:arXiv.org:2512.07120v1 - cs.DS - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - J. Allagan, G. Morgan, S. Langley, R. Lopez-Bonilla, V. Deriglazov + Fast Switching in Mixed-Integer Model Predictive Control + https://arxiv.org/abs/2411.19300 + arXiv:2411.19300v4 Announce Type: replace +Abstract: We deduce stability results for finite control set and mixed-integer model predictive control with a downstream oversampling phase. The presentation rests upon the inherent robustness of model predictive control with stabilizing terminal conditions and techniques for solving mixed-integer optimal control problems by continuous optimization. Partial outer convexification and binary relaxation transform mixed-integer problems into common optimal control problems. We deduce nominal asymptotic stability for the resulting relaxed system formulation and implement sum-up rounding to restore efficiently integer feasibility on an oversampling time grid. If fast control switching is technically possible and inexpensive, we can approximate the relaxed system behavior in the state space arbitrarily close. We integrate input perturbed model predictive control with practical asymptotic stability. Numerical experiments illustrate practical relevance of fast control switching. + oai:arXiv.org:2411.19300v4 + eess.SY + cs.SY + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Artemi Makarow, Christian Kirches - The relationship between offline partisan geographical segregation and online partisan segregation - https://arxiv.org/abs/2512.07121 - arXiv:2512.07121v1 Announce Type: new -Abstract: Social media is often blamed for the creation of echo chambers. However, these claims fail to consider the prevalence of offline echo chambers resulting from high levels of partisan segregation in the United States. Our article empirically assesses these online versus offline dynamics by linking a novel dataset of voters' offline partisan segregation extracted from publicly available voter files for 180 million US voters with their online network segregation on Twitter. We investigate offline and online partisan segregation using measures of geographical and network isolation of every matched voter-twitter user to their co-partisans online and offline. Our results show that while social media users tend to form politically homogeneous online networks, these levels of partisan sorting are significantly lower than those found in offline settings. Notably, Democrats are more isolated than Republicans in both settings, and only older Republicans exhibit higher online than offline segregation. Our results contribute to the emerging literature on political communication and the homophily of online networks, providing novel evidence on partisan sorting both online and offline. - oai:arXiv.org:2512.07121v1 - cs.SI - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - new + Optimal Transmission Switching and Busbar Splitting in Hybrid AC/DC Grids + https://arxiv.org/abs/2412.00270 + arXiv:2412.00270v2 Announce Type: replace +Abstract: Driven by global climate goals, an increasing amount of Renewable Energy Sources (RES) is currently being installed worldwide. Especially in the context of offshore wind integration, hybrid AC/DC grids are considered to be the most effective technology to transmit this RES power over long distances. As hybrid AC/DC systems develop, they are expected to become increasingly complex and meshed as the current AC system. Nevertheless, there is still limited literature on how to optimize hybrid AC/DC topologies while minimizing the total power generation cost. For this reason, this paper proposes a methodology to optimize the steady-state switching states of transmission lines and busbar configurations in hybrid AC/DC grids. The proposed optimization model includes optimal transmission switching (OTS) and busbar splitting (BS), which can be applied to both AC and DC parts of hybrid AC/DC grids. To solve the problem, a scalable and exact nonlinear, non-convex model using a big M approach is formulated. In addition, convex relaxations and linear approximations of the model are tested, and their accuracy, feasibility, and optimality are analyzed. The numerical experiments show that a solution to the combined OTS/BS problem can be found in acceptable computation time and that the investigated relaxations and linearisations provide AC feasible results. + oai:arXiv.org:2412.00270v2 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Megan A. Brown, Tiago Ventura, Joshua A. Tucker, Jonathan Nagler + Giacomo Bastianel, Marta Vanin, Dirk Van Hertem, Hakan Ergun - RisConFix: LLM-based Automated Repair of Risk-Prone Drone Configurations - https://arxiv.org/abs/2512.07122 - arXiv:2512.07122v1 Announce Type: new -Abstract: Flight control software is typically designed with numerous configurable parameters governing multiple functionalities, enabling flexible adaptation to mission diversity and environmental uncertainty. Although developers and manufacturers usually provide recommendations for these parameters to ensure safe and stable operations, certain combinations of parameters with recommended values may still lead to unstable flight behaviors, thereby degrading the drone's robustness. To this end, we propose a Large Language Model (LLM) based approach for real-time repair of risk-prone configurations (named RisConFix) that degrade drone robustness. RisConFix continuously monitors the drone's operational state and automatically triggers a repair mechanism once abnormal flight behaviors are detected. The repair mechanism leverages an LLM to analyze relationships between configuration parameters and flight states, and then generates corrective parameter updates to restore flight stability. To ensure the validity of the updated configuration, RisConFix operates as an iterative process; it continuously monitors the drone's flight state and, if an anomaly persists after applying an update, automatically triggers the next repair cycle. We evaluated RisConFix through a case study of ArduPilot (with 1,421 groups of misconfigurations). Experimental results show that RisConFix achieved a best repair success rate of 97% and an optimal average number of repairs of 1.17, demonstrating its capability to effectively and efficiently repair risk-prone configurations in real time. - oai:arXiv.org:2512.07122v1 - cs.SE - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + GLL: A Differentiable Graph Learning Layer for Neural Networks + https://arxiv.org/abs/2412.08016 + arXiv:2412.08016v2 Announce Type: replace +Abstract: Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods fail to leverage the relational information between samples for generating label predictions. In recent works, graph-based learning techniques, namely Laplace learning, have been heuristically combined with neural networks for both supervised and semi-supervised learning (SSL) tasks. However, prior works approximate the gradient of the loss function with respect to the graph learning algorithm or decouple the processes; end-to-end integration with neural networks is not achieved. In this work, we derive backpropagation equations, via the adjoint method, for inclusion of a general family of graph learning layers into a neural network. The resulting method, distinct from graph neural networks, allows us to precisely integrate similarity graph construction and graph Laplacian-based label propagation into a neural network layer, replacing a projection head and softmax activation function for general classification task. Our experimental results demonstrate smooth label transitions across data, improved generalization and robustness to adversarial attacks, and improved training dynamics compared to a standard softmax-based approach. + oai:arXiv.org:2412.08016v2 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Liping Han, Tingting Nie, Le Yu, Mingzhe Hu, Tao Yue + Jason Brown, Bohan Chen, Harris Hardiman-Mostow, Jeff Calder, Andrea L. Bertozzi - Hyperflex: A SIMD-based DFA Model for Deep Packet Inspection - https://arxiv.org/abs/2512.07123 - arXiv:2512.07123v1 Announce Type: new -Abstract: Deep Packet Inspection (DPI) has been extensively employed for network security. It examines traffic payloads by searching for regular expressions (regex) with the Deterministic Finite Automaton (DFA) model. However, as the network bandwidth and ruleset size are increasing rapidly, the conventional DFA model has emerged as a significant performance bottleneck of DPI. Leveraging the Single-Instruction-Multiple-Data (SIMD) instruction to perform state transitions can substantially boost the efficiency of the DFA model. In this paper, we propose Hyperflex, a novel SIMD-based DFA model designed for high-performance regex matching. Hyperflex incorporates a region detection algorithm to identify regions suitable for acceleration by SIMD instructions across the whole DFA graph. Also, we design a hybrid state transition algorithm that enables state transition in both SIMD-accelerated and normal regions, and ensures seamless state transition across the two types of regions. We have implemented Hyperflex on the commodity CPU and evaluated it with real network traffic and DPI regexes. Our evaluation results indicate that Hyperflex reaches a throughput of 8.89Gbit/s, representing an improvement of up to 2.27 times over Mcclellan, the default DFA model of the prominent multi-pattern regex matching engine Hyperscan. As a result, Hyperflex has been successfully deployed in Hyperscan, significantly enhancing its performance. - oai:arXiv.org:2512.07123v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Private Synthetic Data Generation in Bounded Memory + https://arxiv.org/abs/2412.09756 + arXiv:2412.09756v4 Announce Type: replace +Abstract: We propose $\mathtt{PrivHP}$, a lightweight synthetic data generator with \textit{differential privacy} guarantees. $\mathtt{PrivHP}$ uses a novel hierarchical decomposition that approximates the input's cumulative distribution function (CDF) in bounded memory. It balances hierarchy depth, noise addition, and pruning of low-frequency subdomains while preserving frequent ones. Private sketches estimate subdomain frequencies efficiently without full data access. + A key feature is the pruning parameter $k$, which controls the trade-off between space and utility. We define the skew measure $\mathtt{tail}_k$, capturing all but the top $k$ subdomain frequencies. Given a dataset $\mathcal{X}$, $\mathtt{PrivHP}$ uses $M=\mathcal{O}(k\log^2 |X|)$ space and, for input domain $\Omega = [0,1]$, ensures $\varepsilon$-differential privacy. It yields a generator with expected Wasserstein distance: \[ \mathcal{O}\left(\frac{\log^2 M}{\varepsilon n} + \frac{||\mathtt{tail}_k(\mathcal{X})||_1}{M n}\right) \] from the empirical distribution. This parameterized trade-off offers a level of flexibility unavailable in prior work. We also provide interpretable utility bounds that account for hierarchy depth, privacy noise, pruning, and frequency estimation errors. + oai:arXiv.org:2412.09756v4 + cs.CR + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yang Liu, Wenjun Zhu, Harry Chang, Yang Hong, Geoff Langdale, Kun Qiu, Jin Zhao + Rayne Holland, Seyit Camtepe, Chandra Thapa, Minhui Xue - Enhancing Urban Sensing Utility with Sensor-enabled Vehicles and Easily Accessible Data - https://arxiv.org/abs/2512.07124 - arXiv:2512.07124v1 Announce Type: new -Abstract: Urban sensing is essential for the development of smart cities, enabling monitoring, computing, and decision-making for urban management.Thanks to the advent of vehicle technologies, modern vehicles are transforming from solely mobility tools to valuable sensors for urban data collection, and hold the potential of improving traffic congestion, transport sustainability, and infrastructure inspection.Vehicle-based sensing is increasingly recognized as a promising technology due to its flexibility, cost-effectiveness, and extensive spatiotemporal coverage. However, optimizing sensing strategies to balance spatial and temporal coverage, minimize redundancy, and address budget constraints remains a key challenge.This study proposes an adaptive framework for enhancing the sensing utility of sensor-equipped vehicles.By integrating heterogeneous open-source data, the framework leverages spatiotemporal weighting to optimize vehicle selection and sensing coverage across various urban contexts.An entropy-based vehicle selection strategy, \texttt{Improved OptiFleet}, is developed to maximize sensing utility while minimizing redundancy.The framework is validated using real-world air quality data from 320 sensor-equipped vehicles operating in Guangzhou, China, over two months.Key findings show that the proposed method outperforms baseline strategies, providing up to 5\% higher sensing utility with reduced fleet sizes, and also highlights the critical role of dynamic urban data in optimizing mobile sensing strategies. - oai:arXiv.org:2512.07124v1 - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 - new + AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models + https://arxiv.org/abs/2412.18123 + arXiv:2412.18123v3 Announce Type: replace +Abstract: As text-to-image (T2I) models advance and gain widespread adoption, their associated safety concerns are becoming increasingly critical. Malicious users exploit these models to generate Not-Safe-for-Work (NSFW) images using harmful or adversarial prompts, underscoring the need for effective safeguards to ensure the integrity and compliance of model outputs. However, existing detection methods often exhibit low accuracy and inefficiency. In this paper, we propose AEIOU, a defense framework that is adaptable, efficient, interpretable, optimizable, and unified against NSFW prompts in T2I models. AEIOU extracts NSFW features from the hidden states of the model's text encoder, utilizing the separable nature of these features to detect NSFW prompts. The detection process is efficient, requiring minimal inference time. AEIOU also offers real-time interpretation of results and supports optimization through data augmentation techniques. The framework is versatile, accommodating various T2I architectures. Our extensive experiments show that AEIOU significantly outperforms both commercial and open-source moderation tools, achieving over 95\% accuracy across all datasets and improving efficiency by at least tenfold. It effectively counters adaptive attacks and excels in few-shot and multi-label scenarios. + oai:arXiv.org:2412.18123v3 + cs.CR + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hui Zhong, Qing-Long Lu, Qiming Zhang, Hongliang Lu, Xinhu Zheng + Yiming Wang, Jiahao Chen, Qingming Li, Tong Zhang, Rui Zeng, Xing Yang, Shouling Ji - Training-free Clothing Region of Interest Self-correction for Virtual Try-On - https://arxiv.org/abs/2512.07126 - arXiv:2512.07126v1 Announce Type: new -Abstract: VTON (Virtual Try-ON) aims at synthesizing the target clothing on a certain person, preserving the details of the target clothing while keeping the rest of the person unchanged. Existing methods suffer from the discrepancies between the generated clothing results and the target ones, in terms of the patterns, textures and boundaries. Therefore, we propose to use an energy function to impose constraints on the attention map extracted through the generation process. Thus, at each generation step, the attention can be more focused on the clothing region of interest, thereby influencing the generation results to be more consistent with the target clothing details. Furthermore, to address the limitation that existing evaluation metrics concentrate solely on image realism and overlook the alignment with target elements, we design a new metric, Virtual Try-on Inception Distance (VTID), to bridge this gap and ensure a more comprehensive assessment. On the VITON-HD and DressCode datasets, our approach has outperformed the previous state-of-the-art (SOTA) methods by 1.4%, 2.3%, 12.3%, and 5.8% in the traditional metrics of LPIPS, FID, KID, and the new VTID metrics, respectively. Additionally, by applying the generated data to downstream Clothing-Change Re-identification (CC-Reid) methods, we have achieved performance improvements of 2.5%, 1.1%, and 1.6% on the LTCC, PRCC, VC-Clothes datasets in the metrics of Rank-1. The code of our method is public at https://github.com/MrWhiteSmall/CSC-VTON.git. - oai:arXiv.org:2512.07126v1 + Neural Radiance Fields for the Real World: A Survey + https://arxiv.org/abs/2501.13104 + arXiv:2501.13104v2 Announce Type: replace +Abstract: Neural Radiance Fields (NeRFs) have remodeled 3D scene representation since release. NeRFs can effectively reconstruct complex 3D scenes from 2D images, advancing different fields and applications such as scene understanding, 3D content generation, and robotics. Despite significant research progress, a thorough review of recent innovations, applications, and challenges is lacking. This survey compiles key theoretical advancements and alternative representations and investigates emerging challenges. It further explores applications on reconstruction, highlights NeRFs' impact on computer vision and robotics, and reviews essential datasets and toolkits. By identifying gaps in the literature, this survey discusses open challenges and offers directions for future research. + oai:arXiv.org:2501.13104v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shengjie Lu, Zhibin Wan, Jiejie Liu, Quan Zhang, Mingjie Sun + cs.GR + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Wenhui Xiao, Remi Chierchia, Rodrigo Santa Cruz, Xuesong Li, David Ahmedt-Aristizabal, Olivier Salvado, Clinton Fookes, Leo Lebrat - MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP - https://arxiv.org/abs/2512.07128 - arXiv:2512.07128v1 Announce Type: new -Abstract: Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging region-proposal information to map visual regions with corresponding sentences from lengthy captions, yet incurring notable deployment costs. We introduce MulCLIP, a novel end-to-end multi-level alignment framework that bridges natural long-text structures with image components. MulCLIP first preserves global contrastive alignment between images and both summary and long captions, while extending positional embeddings for longer text sequences. To further enhance fine-grained understanding, we propose two novel strategies: (1) a token reconstruction alignment over locally calibrated features to strengthen semantic connections between words and image patches, and (2) a subcaption-aggregated patch alignment that automatically extracts and aggregates context-rich patches for each subcaption. Experimental results across diverse benchmarks demonstrate our method consistently improves downstream performance, while ablation studies confirm its multi-scale alignment is the key factor driving better fine-grained capability than region-proposal-assisted approaches, making it particularly suitable for diverse real-world applications. - oai:arXiv.org:2512.07128v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + On the algorithmic structure of Dialectica realisers + https://arxiv.org/abs/2501.16208 + arXiv:2501.16208v2 Announce Type: replace +Abstract: G\"odel's Dialectica interpretation is a fundamental tool for the extraction of computational content from proofs, and plays a central role in today's proof mining program. In the past decades, it has also been studied from the perspective of programming languages, and our contribution is in that direction. Specifically, we present Dialectica as a collection of rules in the style of Hoare logic, where Dialectica is now viewed as a language for specifying procedural programs that come with a forward and backward direction. This viewpoint captures the interesting dynamics of realisers extracted by the Dialectica interpretation, and we illustrate this by defining a generalised backpropagation semantics for a fragment of this language. We envisage this work as providing a base for several future developments, both theoretical and practical, which we outline at the end. + oai:arXiv.org:2501.16208v2 + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Chau Truong, Hieu Ta Quang, Dung D. Le + Davide Barbarossa, Thomas Powell - Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving - https://arxiv.org/abs/2512.07130 - arXiv:2512.07130v1 Announce Type: new -Abstract: End-to-end autonomous driving has emerged as a pivotal direction in the field of autonomous systems. Recent works have demonstrated impressive performance by incorporating high-level guidance signals to steer low-level trajectory planners. However, their potential is often constrained by inaccurate high-level guidance and the computational overhead of complex guidance modules. To address these limitations, we propose Mimir, a novel hierarchical dual-system framework capable of generating robust trajectories relying on goal points with uncertainty estimation: (1) Unlike previous approaches that deterministically model, we estimate goal point uncertainty with a Laplace distribution to enhance robustness; (2) To overcome the slow inference speed of the guidance system, we introduce a multi-rate guidance mechanism that predicts extended goal points in advance. Validated on challenging Navhard and Navtest benchmarks, Mimir surpasses previous state-of-the-art methods with a 20% improvement in the driving score EPDMS, while achieving 1.6 times improvement in high-level module inference speed without compromising accuracy. The code and models will be released soon to promote reproducibility and further development. The code is available at https://github.com/ZebinX/Mimir-Uncertainty-Driving - oai:arXiv.org:2512.07130v1 - cs.RO - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zebin Xing, Yupeng Zheng, Qichao Zhang, Zhixing Ding, Pengxuan Yang, Songen Gu, Zhongpu Xia, Dongbin Zhao + Oscillations Make Neural Networks Robust to Quantization + https://arxiv.org/abs/2502.00490 + arXiv:2502.00490v2 Announce Type: replace +Abstract: We challenge the prevailing view that weight oscillations observed during Quantization Aware Training (QAT) are merely undesirable side-effects and argue instead that they are an essential part of QAT. We show in a univariate linear model that QAT results in an additional loss term that causes oscillations by pushing weights away from their nearest quantization level. Based on the mechanism from the analysis, we then derive a regularizer that induces oscillations in the weights of neural networks during training. Our empirical results on ResNet-18 and Tiny Vision Transformer, evaluated on CIFAR-10 and Tiny ImageNet datasets, demonstrate across a range of quantization levels that training with oscillations followed by post-training quantization (PTQ) is sufficient to recover the performance of QAT in most cases. With this work we provide further insight into the dynamics of QAT and contribute a novel insight into explaining the role of oscillations in QAT which until now have been considered to have a primarily negative effect on quantization. + oai:arXiv.org:2502.00490v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + TMLR, 2835-8856, 2025 + Jonathan Wensh{\o}j, Bob Pepin, Raghavendra Selvan - DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning - https://arxiv.org/abs/2512.07132 - arXiv:2512.07132v1 Announce Type: new -Abstract: Specialized visual tools can augment large language models or vision language models with expert knowledge (e.g., grounding, spatial reasoning, medical knowledge, etc.), but knowing which tools to call (and when to call them) can be challenging. We introduce DART, a multi-agent framework that uses disagreements between multiple debating visual agents to identify useful visual tools (e.g., object detection, OCR, spatial reasoning, etc.) that can resolve inter-agent disagreement. These tools allow for fruitful multi-agent discussion by introducing new information, and by providing tool-aligned agreement scores that highlight agents in agreement with expert tools, thereby facilitating discussion. We utilize an aggregator agent to select the best answer by providing the agent outputs and tool information. We test DART on four diverse benchmarks and show that our approach improves over multi-agent debate as well as over single agent tool-calling frameworks, beating the next-strongest baseline (multi-agent debate with a judge model) by 3.4% and 2.4% on A-OKVQA and MMMU respectively. We also find that DART adapts well to new tools in applied domains, with a 1.3% improvement on the M3D medical dataset over other strong tool-calling, single agent, and multi-agent baselines. Additionally, we measure text overlap across rounds to highlight the rich discussion in DART compared to existing multi-agent methods. Finally, we study the tool call distribution, finding that diverse tools are reliably used to help resolve disagreement. - oai:arXiv.org:2512.07132v1 - cs.CL + Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 + https://arxiv.org/abs/2502.03544 + arXiv:2502.03544v3 Announce Type: replace +Abstract: We present AlphaGeometry2 (AG2), a significantly improved version of AlphaGeometry introduced in (Trinh et al., 2024), which has now surpassed an average gold medalist in solving Olympiad geometry problems. To achieve this, we first extend the original AlphaGeometry language to tackle problems involving movements of objects, and problems containing linear equations of angles, ratios, and distances. This, together with support for non-constructive problems, has markedly improved the coverage rate of the AlphaGeometry language on International Math Olympiads (IMO) 2000-2024 geometry problems from 66% to 88%. The search process of AG2 has also been greatly improved through the use of Gemini architecture for better language modeling, and a novel knowledge-sharing mechanism that enables effective communication between search trees. Together with further enhancements to the symbolic engine and synthetic data generation, we have significantly boosted the overall solving rate of AG to 84% on all geometry problems over the last 25 years, compared to 54% previously. AG2 was also part of the system that achieved the silver-medal standard at IMO 2024 https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/. Finally, we report progress towards using AG2 as a part of a fully automated system that reliably solves geometry problems from natural language input. Code: https://github.com/google-deepmind/alphageometry2. + oai:arXiv.org:2502.03544v3 cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nithin Sivakumaran, Justin Chih-Yao Chen, David Wan, Yue Zhang, Jaehong Yoon, Elias Stengel-Eskin, Mohit Bansal + Yuri Chervonyi, Trieu H. Trinh, Miroslav Ol\v{s}\'ak, Xiaomeng Yang, Hoang Nguyen, Marcelo Menegali, Junehyuk Jung, Junsu Kim, Vikas Verma, Quoc V. Le, Thang Luong - GUMBridge: a Corpus for Varieties of Bridging Anaphora - https://arxiv.org/abs/2512.07134 - arXiv:2512.07134v1 Announce Type: new -Abstract: Bridging is an anaphoric phenomenon where the referent of an entity in a discourse is dependent on a previous, non-identical entity for interpretation, such as in "There is 'a house'. 'The door' is red," where the door is specifically understood to be the door of the aforementioned house. While there are several existing resources in English for bridging anaphora, most are small, provide limited coverage of the phenomenon, and/or provide limited genre coverage. In this paper, we introduce GUMBridge, a new resource for bridging, which includes 16 diverse genres of English, providing both broad coverage for the phenomenon and granular annotations for the subtype categorization of bridging varieties. We also present an evaluation of annotation quality and report on baseline performance using open and closed source contemporary LLMs on three tasks underlying our data, showing that bridging resolution and subtype classification remain difficult NLP tasks in the age of LLMs. - oai:arXiv.org:2512.07134v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Lauren Levine, Amir Zeldes + Flow-based Conformal Prediction for Multi-dimensional Time Series + https://arxiv.org/abs/2502.05709 + arXiv:2502.05709v2 Announce Type: replace +Abstract: Time series prediction underpins a broad range of downstream tasks across many scientific domains. Recent advances and increasing adoption of black-box machine learning models for time series prediction highlight the critical need for reliable uncertainty quantification. While conformal prediction has gained attention as a reliable uncertainty quantification method, conformal prediction for time series faces two key challenges: (1) adaptively leveraging correlations in features and non-conformity scores to overcome the exchangeability assumption, and (2) constructing prediction sets for multi-dimensional outcomes. To address these challenges jointly, we propose a novel conformal prediction method for time series using flow with classifier-free guidance. We provide coverage guarantees by establishing exact non-asymptotic marginal coverage and a finite-sample bound on conditional coverage for the proposed method. Evaluations on real-world time series datasets demonstrate that our method constructs significantly smaller prediction sets than existing conformal prediction methods while maintaining target coverage. + oai:arXiv.org:2502.05709v2 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Junghwan Lee, Chen Xu, Yao Xie - TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning - https://arxiv.org/abs/2512.07135 - arXiv:2512.07135v1 Announce Type: new -Abstract: Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better planning performance when provided with a prior distribution of possible trajectories. However, these approaches often overlook two critical aspects: 1) The appropriate trajectory prior can vary significantly across different driving scenarios. 2) Their trajectory evaluation mechanism lacks policy-driven refinement, remaining constrained by the limitations of one-stage supervised training. To address these issues, we explore improvements in two key areas. For problem 1, we employ MoE to apply different trajectory priors tailored to different scenarios. For problem 2, we utilize Reinforcement Learning to fine-tune the trajectory scoring mechanism. Additionally, we integrate models with different perception backbones to enhance perceptual features. Our integrated model achieved a score of 51.08 on the navsim ICCV benchmark, securing third place. - oai:arXiv.org:2512.07135v1 - cs.CV + Meta-Computing Enhanced Federated Learning in IIoT: Satisfaction-Aware Incentive Scheme via DRL-Based Stackelberg Game + https://arxiv.org/abs/2502.06909 + arXiv:2502.06909v3 Announce Type: replace +Abstract: The Industrial Internet of Things (IIoT) leverages Federated Learning (FL) for distributed model training while preserving data privacy, and meta-computing enhances FL by optimizing and integrating distributed computing resources, improving efficiency and scalability. Efficient IIoT operations require a trade-off between model quality and training latency. Consequently, a primary challenge of FL in IIoT is to optimize overall system performance by balancing model quality and training latency. This paper designs a satisfaction function that accounts for data size, Age of Information (AoI), and training latency for meta-computing. Additionally, the satisfaction function is incorporated into the utility function to incentivize IIoT nodes to participate in model training. We model the utility functions of servers and nodes as a two-stage Stackelberg game and employ a deep reinforcement learning approach to learn the Stackelberg equilibrium. This approach ensures balanced rewards and enhances the applicability of the incentive scheme for IIoT. Simulation results demonstrate that, under the same budget constraints, the proposed incentive scheme improves utility by at least 23.7% compared to existing FL schemes without compromising model accuracy. + oai:arXiv.org:2502.06909v3 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.GT + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zebin Xing, Pengxuan Yang, Linbo Wang, Yichen Zhang, Yiming Hu, Yupeng Zheng, Junli Wang, Yinfeng Gao, Guang Li, Kun Ma, Long Chen, Zhongpu Xia, Qichao Zhang, Hangjun Ye, Dongbin Zhao + Xiaohuan Li, Shaowen Qin, Xin Tang, Jiawen Kang, Jin Ye, Zhonghua Zhao, Yusi Zheng, Dusit Niyato - A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning - https://arxiv.org/abs/2512.07136 - arXiv:2512.07136v1 Announce Type: new -Abstract: Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable detailed descriptions and causal reasoning, motivating new tasks: human action understanding (HAU) and human action reasoning (HARn). However, most LLMs, especially large vision language models (LVLMs), struggle with non-RGB modalities such as depth, IMU, and mmWave due to the lack of large-scale data-caption resources. Existing HAR datasets mainly provide coarse data-label annotations, which are insufficient to capture fine-grained action dynamics needed for HAU and HARn. We consider two ground-truth pair types: (1) data label (discrete category) and (2) data caption (textual description). Naively generating captions from labels often lacks logical and spatiotemporal consistency. We introduce CUHK-X, a large-scale multimodal dataset and benchmark suite for HAR, HAU, and HARn. CUHK-X contains 58,445 samples covering 40 actions performed by 30 participants across two indoor environments. To improve caption consistency, we propose a prompt-based scene creation method that leverages LLMs to generate logically connected activity sequences, followed by human validation. CUHK-X includes three benchmarks with six evaluation tasks. Experiments report average accuracies of 76.52% (HAR), 40.76% (HAU), and 70.25% (HARn). CUHK-X aims to enable the community to apply and develop data-intensive learning methods for robust, multimodal human activity analysis. Project page and code: https://openaiotlab.github.io/CUHK-X/ and https://github.com/openaiotlab/CUHK-X. - oai:arXiv.org:2512.07136v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Siyang Jiang, Mu Yuan, Xiang Ji, Bufang Yang, Zeyu Liu, Lilin Xu, Yang Li, Yuting He, Liran Dong, Wenrui Lu, Zhenyu Yan, Xiaofan Jiang, Wei Gao, Hongkai Chen, Guoliang Xing + Proper Learnability and the Role of Unlabeled Data + https://arxiv.org/abs/2502.10359 + arXiv:2502.10359v2 Announce Type: replace +Abstract: Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class $H$, and often leads to learners with simple algorithmic forms (e.g. empirical risk minimization (ERM), structural risk minimization (SRM)). The limitation of proper learning, however, is that there exist problems which can only be learned improperly, e.g. in multiclass classification. Thus, we ask: Under what assumptions on the hypothesis class or the information provided to the learner is a problem properly learnable? We first demonstrate that when the unlabeled data distribution is given, there always exists an optimal proper learner governed by distributional regularization, a randomized generalization of regularization. We refer to this setting as the distribution-fixed PAC model, and continue to evaluate the learner on its worst-case performance over all distributions. Our result holds for all metric loss functions and any finite learning problem (with no dependence on its size). Further, we demonstrate that sample complexities in the distribution-fixed PAC model can shrink by only a logarithmic factor from the classic PAC model, strongly refuting the role of unlabeled data in PAC learning (from a worst-case perspective). + We complement this with impossibility results which obstruct any characterization of proper learnability in the realizable PAC model. First, we observe that there are problems whose proper learnability is logically undecidable, i.e., independent of the ZFC axioms. We then show that proper learnability is not a monotone property of the underlying hypothesis class, and that it is not a local property (in a precise sense). Our impossibility results all hold even for the fundamental setting of multiclass classification, and go through a reduction of EMX learning (Ben-David et al., 2019) to proper classification which may be of independent interest. + oai:arXiv.org:2502.10359v2 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng - Time-Varying Formation Tracking Control of Wheeled Mobile Robots With Region Constraint: A Generalized Udwadia-Kalaba Framework - https://arxiv.org/abs/2512.07137 - arXiv:2512.07137v1 Announce Type: new -Abstract: In this paper, the time-varying formation tracking control of wheeled mobile robots with region constraint is investigated from a generalized Udwadia-Kalaba framework. The communication topology is directed, weighted and has a spanning tree with the leader being the root. By reformulating the time-varying formation tracking control objective as a constrained equation and transforming the region constraint by a diffeomorphism, the time-varying formation tracking controller with the region constraint is designed under the generalized Udwadia-Kalaba framework. Compared with the existing works on time-varying formation tracking control, the region constraint is takeninto account in this paper, which ensures the safety of the robots.Finally, some numerical simulations are presented to illustrate the effectiveness of the proposed control strategy. - oai:arXiv.org:2512.07137v1 - cs.RO - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kang Yijie, Hao Yuqing, Wang Qingyun, Chen Guanrong + Privacy Preservation through Practical Machine Unlearning + https://arxiv.org/abs/2502.10635 + arXiv:2502.10635v3 Announce Type: replace +Abstract: Machine Learning models thrive on vast datasets, continuously adapting to provide accurate predictions and recommendations. However, in an era dominated by privacy concerns, Machine Unlearning emerges as a transformative approach, enabling the selective removal of data from trained models. This paper examines methods such as Naive Retraining and Exact Unlearning via the SISA framework, evaluating their Computational Costs, Consistency, and feasibility using the $\texttt{HSpam14}$ dataset. We explore the potential of integrating unlearning principles into Positive Unlabeled (PU) Learning to address challenges posed by partially labeled datasets. Our findings highlight the promise of unlearning frameworks like $\textit{DaRE}$ for ensuring privacy compliance while maintaining model performance, albeit with significant computational trade-offs. This study underscores the importance of Machine Unlearning in achieving ethical AI and fostering trust in data-driven systems. + oai:arXiv.org:2502.10635v3 + cs.LG + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Robert Dilworth - Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models - https://arxiv.org/abs/2512.07141 - arXiv:2512.07141v1 Announce Type: new -Abstract: As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore safety-oriented reasoning, aiming to enhance safety awareness by analyzing potential safety risks during the reasoning process before generating the final response. Although such approaches improve safety awareness and interpretability, this single-pass think-then-answer paradigm remains vulnerable to contextual or visual jailbreak attacks. This reveals a critical flaw: single-pass reasoning may overlook explicit harmful content in its own output. Our key insight is to exploit this wasted signal through reflection, which can effectively leverage the malicious content revealed in the first-pass reasoning to enable genuine self-correction and prevent unsafe generations. Motivated by this, we propose Think-Reflect-Revise (TRR), a three-stage training framework designed to enhance the safety alignment of LVLMs through policy-guided self-reflection. We first build a Reflective Safety Reasoning (ReSafe) dataset with 5,000 examples that follow a think-reflect-revise process. We then fine-tune the target model using the ReSafe dataset to initialize reflective behavior, and finally reinforce policy-guided reflection through reinforcement learning. Experimental results show that TRR substantially improves the safety performance of LVLMs across both safety-awareness benchmarks and jailbreak attack evaluations, increasing the overall safe response rate from 42.8% to 87.7% on Qwen2.5-VL-7B, while preserving stable performance on general benchmarks such as MMMU and MMStar. The project page is available at https://think-reflect-revise.github.io/. - oai:arXiv.org:2512.07141v1 - cs.CV - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fenghua Weng, Chaochao Lu, Xia Hu, Wenqi Shao, Wenjie Wang + Dark Deceptions in DHCP: Dismantling Network Defenses + https://arxiv.org/abs/2502.10646 + arXiv:2502.10646v3 Announce Type: replace +Abstract: This paper explores vulnerabilities in the Dynamic Host Configuration Protocol (DHCP) and their implications on the Confidentiality, Integrity, and Availability (CIA) Triad. Through an analysis of various attacks, including DHCP Starvation, Rogue DHCP Servers, Replay Attacks, and TunnelVision exploits, the paper provides a taxonomic classification of threats, assesses risks, and proposes appropriate controls. The discussion also highlights the dangers of VPN decloaking through DHCP exploits and underscores the importance of safeguarding network infrastructures. By bringing awareness to the TunnelVision exploit, this paper aims to mitigate risks associated with these prevalent vulnerabilities. + oai:arXiv.org:2502.10646v3 + cs.CR + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Robert Dilworth - Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search - https://arxiv.org/abs/2512.07142 - arXiv:2512.07142v1 Announce Type: new -Abstract: The Lottery Ticket Hypothesis asserts the existence of highly sparse, trainable subnetworks ('winning tickets') within dense, randomly initialized neural networks. However, state-of-the-art methods of drawing these tickets, like Lottery Ticket Rewinding (LTR), are computationally prohibitive, while more efficient saliency-based Pruning-at-Initialization (PaI) techniques suffer from a significant accuracy-sparsity trade-off and fail basic sanity checks. In this work, we argue that PaI's reliance on first-order saliency metrics, which ignore inter-weight dependencies, contributes substantially to this performance gap, especially in the sparse regime. To address this, we introduce Concrete Ticket Search (CTS), an algorithm that frames subnetwork discovery as a holistic combinatorial optimization problem. By leveraging a Concrete relaxation of the discrete search space and a novel gradient balancing scheme (GRADBALANCE) to control sparsity, CTS efficiently identifies high-performing subnetworks near initialization without requiring sensitive hyperparameter tuning. Motivated by recent works on lottery ticket training dynamics, we further propose a knowledge distillation-inspired family of pruning objectives, finding that minimizing the reverse Kullback-Leibler divergence between sparse and dense network outputs (CTS-KL) is particularly effective. Experiments on varying image classification tasks show that CTS produces subnetworks that robustly pass sanity checks and achieve accuracy comparable to or exceeding LTR, while requiring only a small fraction of the computation. For example, on ResNet-20 on CIFAR10, it reaches 99.3% sparsity with 74.0% accuracy in 7.9 minutes, while LTR attains the same sparsity with 68.3% accuracy in 95.2 minutes. CTS's subnetworks outperform saliency-based methods across all sparsities, but its advantage over LTR is most pronounced in the highly sparse regime. - oai:arXiv.org:2512.07142v1 - cs.LG + B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability + https://arxiv.org/abs/2502.12992 + arXiv:2502.12992v4 Announce Type: replace +Abstract: Post-hoc explanation methods for black-box models often struggle with faithfulness and human interpretability due to the lack of explainability in current neural architectures. Meanwhile, B-cos networks have been introduced to improve model explainability by proposing an architecture that removes bias terms and promotes input-weight alignment. Although B-cos networks have shown success in building explainable systems, their application has so far been limited to computer vision models and their associated training pipelines. In this work, we introduce B-cos LMs, i.e., B-cos Language Models (LMs) empowered for natural language processing (NLP) tasks. Our approach directly transforms pre-trained language models into B-cos LMs by combining B-cos conversion and task fine-tuning, improving efficiency compared to previous methods. Automatic and human evaluation results demonstrate that B-cos LMs produce more faithful and human interpretable explanations than post-hoc methods, while maintaining task performance comparable to conventional fine-tuning. Our in-depth analysis explores how B-cos LMs differ from conventionally fine-tuned models in their learning processes and explanation patterns. Finally, we present a first exploration of transforming decoder-only models to B-cos LMs for generation tasks. Our code is available at https://github.com/Ewanwong/bcos_lm. + oai:arXiv.org:2502.12992v4 + cs.CL cs.AI - cs.CV - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Tanay Arora, Christof Teuscher + Yifan Wang, Sukrut Rao, Ji-Ung Lee, Mayank Jobanputra, Vera Demberg - A Theoretical Framework of Student Agency in AI- Assisted Learning: A Grounded Theory Approach - https://arxiv.org/abs/2512.07143 - arXiv:2512.07143v1 Announce Type: new -Abstract: Generative AI(GenAI) is a kind of AI model capable of producing human-like content in various modalities, including text, image, audio, video, and computer programming. Although GenAI offers great potential for education, its value often depends on students' ability to engage with it actively, responsibly, and critically - qualities central to student agency. Nevertheless, student agency has long been a complex and ambiguous concept in educational discourses, with few empirical studies clarifying its distinct nature and process in AI-assisted learning environments. To address this gap, the qualitative study presented in this article examines how higher education students exercise agency in AI-assisted learning and proposes a theoretical framework using a grounded theory approach. Guided by agentic engagement theory, this article analyzes the authentic experiences of 26 students using data from their GenAI conversation records and cognitive interviews that capture their thought processes and decision-making. The findings identify four key aspects of student agency: initiating and (re)directing, mindful adoption, external help-seeking, and reflective learning. Together, these aspects form an empirically developed framework that characterizes student agency in AI-assisted learning as a proactive, intentional, adaptive, reflective, and iterative process. Based on the empirical findings, theoretical and practical implications are discussed for researchers, educators, and policymakers. - oai:arXiv.org:2512.07143v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - 10.1093/9780198945253.003.0009 - Oxford Intersections: Social Media in Society and Culture, 2025 - Yun Dai, Sichen Lai + OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest + https://arxiv.org/abs/2503.01260 + arXiv:2503.01260v2 Announce Type: replace +Abstract: With the growing adoption of time-series anomaly detection (TAD) technology, numerous studies have employed deep learning-based detectors to analyze time-series data in the fields of Internet services, industrial systems, and sensors. The selection and optimization of anomaly detectors strongly rely on the availability of an effective evaluation for TAD performance. Since anomalies in time-series data often manifest as a sequence of points, conventional metrics that solely consider the detection of individual points are inadequate. Existing TAD evaluators typically employ point-based or event-based metrics to capture the temporal context. However, point-based evaluators tend to overestimate detectors that excel only in detecting long anomalies, while event-based evaluators are susceptible to being misled by fragmented detection results. To address these limitations, we propose OIPR (Operator Interest-based Precision and Recall metrics), a novel TAD evaluator with area-based metrics. It models the process of operators receiving detector alarms and handling anomalies, utilizing area under the operator interest curve to evaluate TAD performance. Furthermore, we build a special scenario dataset to compare the characteristics of different evaluators. Through experiments conducted on the special scenario dataset and five real-world datasets, we demonstrate the remarkable performance of OIPR in extreme and complex scenarios. It achieves a balance between point and event perspectives, overcoming their primary limitations and offering applicability to broader situations. + oai:arXiv.org:2503.01260v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Yuhan Jing, Jingyu Wang, Lei Zhang, Haifeng Sun, Bo He, Zirui Zhuang, Chengsen Wang, Qi Qi, Jianxin Liao - FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers - https://arxiv.org/abs/2512.07150 - arXiv:2512.07150v1 Announce Type: new -Abstract: Deep generative models have become powerful priors for solving inverse problems, and various training-free methods have been developed. However, when applied to latent flow models, existing methods often fail to converge to the posterior mode or suffer from manifold deviation within latent spaces. To mitigate this, here we introduce a novel training-free framework, FlowLPS, that solves inverse problems with pretrained flow models via a Langevin Proximal Sampling (LPS) strategy. Our method integrates Langevin dynamics for manifold-consistent exploration with proximal optimization for precise mode seeking, achieving a superior balance between reconstruction fidelity and perceptual quality across multiple inverse tasks on FFHQ and DIV2K, outperforming state of the art inverse solvers. - oai:arXiv.org:2512.07150v1 + ($\boldsymbol{\theta}_l, \boldsymbol{\theta}_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces + https://arxiv.org/abs/2503.08394 + arXiv:2503.08394v4 Announce Type: replace +Abstract: Multi-task optimization is typically characterized by a fixed and finite set of tasks. The present paper relaxes this condition by considering a non-fixed and potentially infinite set of optimization tasks defined in a parameterized, continuous and bounded task space. We refer to this unique problem setting as parametric multi-task optimization (PMTO). Assuming the bounds of the task parameters to be ($\boldsymbol{\theta}_l$, $\boldsymbol{\theta}_u$), a novel ($\boldsymbol{\theta}_l$, $\boldsymbol{\theta}_u$)-PMTO algorithm is crafted to operate in two complementary modes. In an offline optimization mode, a joint search over solution and task spaces is carried out with the creation of two approximation models: (1) for mapping points in a unified solution space to the objective spaces of all tasks, which provably accelerates convergence by acting as a conduit for inter-task knowledge transfers, and (2) for probabilistically mapping tasks to their corresponding solutions, which facilitates evolutionary exploration of under-explored regions of the task space. In the online mode, the derived models enable direct optimization of any task within the bounds without the need to search from scratch. This outcome is validated on both synthetic test problems and practical case studies, with the significant real-world applicability of PMTO shown towards fast reconfiguration of robot controllers under changing task conditions. The potential of PMTO to vastly speedup the search for solutions to minimax optimization problems is also demonstrated through an example in robust engineering design. + oai:arXiv.org:2503.08394v4 + cs.NE cs.LG - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Jonghyun Park, Jong Chul Ye + 10.1109/TEVC.2025.3598333 + Tingyang Wei, Jiao Liu, Abhishek Gupta, Puay Siew Tan, Yew-Soon Ong - A Structured Review of Fixed and Multimodal Sensing Techniques for Bat Monitoring - https://arxiv.org/abs/2512.07153 - arXiv:2512.07153v1 Announce Type: new -Abstract: Effective monitoring of mobile animal populations is crucial for ecological research, wildlife management, and agricultural applications. Monitoring of bats specifically can help understand the spread of disease as well as shine light on bat migration patterns, population dynamics, and the impacts of environmental changes on bat colonies. Fixed sensing modalities, such as infrared sensors, cameras, radar, and acoustic detectors, play a pivotal role in tracking and understanding animal behavior. This survey goes over context-informing details about bat biology, and then reviews these fixed sensing modalities, discussing the unique challenges and contributions of each approach. We highlight the coverage, applications, accuracy, and limitations associated with each of these sensing modalities. By synthesizing recent advances, we provide a comprehensive overview to guide future research in this area. - oai:arXiv.org:2512.07153v1 - eess.SY - cs.SY - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Maatla Sefawe, Sravya Ganti, Julianna Segalla, Erwei He, Isaac Tourner, Julia Gersey + Representation Retrieval Learning for Heterogeneous Data Integration + https://arxiv.org/abs/2503.09494 + arXiv:2503.09494v3 Announce Type: replace +Abstract: In the era of big data, large-scale, multi-source, multi-modality datasets are increasingly ubiquitous, offering unprecedented opportunities for predictive modeling and scientific discovery. However, these datasets often exhibit complex heterogeneity, such as covariates shift, posterior drift, and blockwise missingness, which worsen predictive performance of existing supervised learning algorithms. To address these challenges simultaneously, we propose a novel Representation Retrieval (R2) framework, which integrates a dictionary of representation learning modules (representer dictionary) with data source-specific sparsity-induced machine learning model (learners). Under the R2 framework, we introduce the notion of integrativeness for each representer, and propose a novel Selective Integration Penalty (SIP) to explicitly encourage more integrative representers to improve predictive performance. Theoretically, we show that the excess risk bound of the R2 framework is characterized by the integrativeness of representers, and SIP effectively improves the excess risk. Extensive simulation studies validate the superior performance of R2 framework and the effect of SIP. We further apply our method to two real-world datasets to confirm its empirical success. + oai:arXiv.org:2503.09494v3 + cs.LG + stat.ME + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Qi Xu, Annie Qu - CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics - https://arxiv.org/abs/2512.07155 - arXiv:2512.07155v1 Announce Type: new -Abstract: Diffusion models exhibit remarkable generative ability, yet achieving smooth and semantically consistent image morphing remains a challenge. Existing approaches often yield abrupt transitions or over-saturated appearances due to the lack of adaptive structural and semantic alignments. We propose CHIMERA, a zero-shot diffusion-based framework that formulates morphing as a cached inversion-guided denoising process. To handle large semantic and appearance disparities, we propose Adaptive Cache Injection and Semantic Anchor Prompting. Adaptive Cache Injection (ACI) caches down, mid, and up blocks features from both inputs during DDIM inversion and re-injects them adaptively during denoising, enabling spatial and semantic alignment in depth- and time-adaptive manners and enabling natural feature fusion and smooth transitions. Semantic Anchor Prompting (SAP) leverages a vision-language model to generate a shared anchor prompt that serves as a semantic anchor, bridging dissimilar inputs and guiding the denoising process toward coherent results. Finally, we introduce the Global-Local Consistency Score (GLCS), a morphing-oriented metric that simultaneously evaluates the global harmonization of the two inputs and the smoothness of the local morphing transition. Extensive experiments and user studies show that CHIMERA achieves smoother and more semantically aligned transitions than existing methods, establishing a new state of the art in image morphing. The code and project page will be publicly released. - oai:arXiv.org:2512.07155v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + CDKFormer: Contextual Deviation Knowledge-Based Transformer for Long-Tail Trajectory Prediction + https://arxiv.org/abs/2503.12695 + arXiv:2503.12695v2 Announce Type: replace +Abstract: Predicting the future movements of surrounding vehicles is essential for ensuring the safe operation and efficient navigation of autonomous vehicles (AVs) in urban traffic environments. Existing vehicle trajectory prediction methods primarily focus on improving overall performance, yet they struggle to address long-tail scenarios effectively. This limitation often leads to poor predictions in rare cases, significantly increasing the risk of safety incidents. Taking Argoverse 2 motion forecasting dataset as an example, we first investigate the long-tail characteristics in trajectory samples from two perspectives, individual motion and group interaction, and deriving deviation features to distinguish abnormal from regular scenarios. On this basis, we propose CDKFormer, a Contextual Deviation Knowledge-based Transformer model for long-tail trajectory prediction. CDKFormer integrates an attention-based scene context fusion module to encode spatiotemporal interaction and road topology. An additional deviation feature fusion module is proposed to capture the dynamic deviations in the target vehicle status. We further introduce a dual query-based decoder, supported by a multi-stream decoder block, to sequentially decode heterogeneous scene deviation features and generate multimodal trajectory predictions. Extensive experiments demonstrate that CDKFormer achieves state-of-the-art performance, significantly enhancing prediction accuracy and robustness for long-tailed trajectories compared to existing methods, thus advancing the reliability of AVs in complex real-world environments. + oai:arXiv.org:2503.12695v2 + cs.RO + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dahyeon Kye, Jeahun Sung, MinKyu Jeon, Jihyong Oh + 10.1016/j.trc.2025.105430 + Yuansheng Lian, Ke Zhang, Meng Li - MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation - https://arxiv.org/abs/2512.07165 - arXiv:2512.07165v1 Announce Type: new -Abstract: Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging pre-trained 3D priors have achieved impressive results, most of them rely on full fine-tuning of large Vision Transformer (ViT) backbones and incur substantial GPU costs. In this work, we introduce MuSASplat, a novel framework that dramatically reduces the computational burden of training pose-free feed-forward 3D Gaussian splats models with little compromise of rendering quality. Central to our approach is a lightweight Multi-Scale Adapter that enables efficient fine-tuning of ViT-based architectures with only a small fraction of training parameters. This design avoids the prohibitive GPU overhead associated with previous full-model adaptation techniques while maintaining high fidelity in novel view synthesis, even with very sparse input views. In addition, we introduce a Feature Fusion Aggregator that integrates features across input views effectively and efficiently. Unlike widely adopted memory banks, the Feature Fusion Aggregator ensures consistent geometric integration across input views and meanwhile mitigates the memory usage, training complexity, and computational costs significantly. Extensive experiments across diverse datasets show that MuSASplat achieves state-of-the-art rendering quality but has significantly reduced parameters and training resource requirements as compared with existing methods. - oai:arXiv.org:2512.07165v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Muyu Xu, Fangneng Zhan, Xiaoqin Zhang, Ling Shao, Shijian Lu + Dual-Source SPIR over a noiseless MAC without Data Replication or Shared Randomness + https://arxiv.org/abs/2503.14682 + arXiv:2503.14682v2 Announce Type: replace +Abstract: Information-theoretically secure Symmetric Private Information Retrieval (SPIR) is known to be infeasible over noiseless channels with a single server. Known solutions to overcome this infeasibility involve additional resources such as database replication, shared randomness, or noisy channels. In this paper, we propose an alternative approach for achieving SPIR with information-theoretic security guarantees, without relying on shared randomness, noisy channels, or data replication. Specifically, we demonstrate that it is sufficient to use a noiseless binary adder multiple-access channel, where inputs are controlled by two non-colluding servers and the output is observed by the client, alongside a public noiseless communication channel between the client and the servers. Furthermore, in this setting, we characterize the optimal file rates, i.e., the file lengths normalized by the number of channel uses, that can be transferred. + oai:arXiv.org:2503.14682v2 + cs.IT + cs.CR + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Remi A. Chou - When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing - https://arxiv.org/abs/2512.07166 - arXiv:2512.07166v1 Announce Type: new -Abstract: Privacy leakage in Multimodal Large Language Models (MLLMs) has long been an intractable problem. Existing studies, though effectively obscure private information in MLLMs, often overlook the evaluation of the authenticity and recovery quality of user privacy. To this end, this work uniquely focuses on the critical challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios. We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset, which includes a wide range of privacy categories and user instructions to simulate real MLLM applications. This dataset offers protected surrogates alongside their various MLLM-edited versions, thus enabling the direct assessment of privacy recovery quality. By formulating privacy recovery as a guided generation task conditioned on complementary multimodal signals, we further introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits. The experiments on both SPPE and InstructPix2Pix further show that our approach generalizes well across diverse visual content and editing tasks, achieving a strong balance between privacy protection and MLLM usability. - oai:arXiv.org:2512.07166v1 + Bezier Splatting for Fast and Differentiable Vector Graphics Rendering + https://arxiv.org/abs/2503.16424 + arXiv:2503.16424v4 Announce Type: replace +Abstract: Differentiable vector graphics (VGs) are widely used in image vectorization and vector synthesis, while existing representations are costly to optimize and struggle to achieve high-quality rendering results for high-resolution images. This work introduces a new differentiable VG representation, dubbed B\'ezier Splatting, that enables fast yet high-fidelity VG rasterization. B\'ezier Splatting samples 2D Gaussians along B\'ezier curves, which naturally provide positional gradients at object boundaries. Thanks to the efficient splatting-based differentiable rasterizer, B\'ezier Splatting achieves 30x and 150x faster per forward and backward rasterization step for open curves compared to DiffVG. Additionally, we introduce an adaptive pruning and densification strategy that dynamically adjusts the spatial distribution of curves to escape local minima, further improving VG quality. Furthermore, our new VG representation supports conversion to standard XML-based SVG format, enhancing interoperability with existing VG tools and pipelines. Experimental results show that B\'ezier Splatting significantly outperforms existing methods with better visual fidelity and significant optimization speedup. + oai:arXiv.org:2503.16424v4 + cs.GR cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Siyuan Xu, Yibing Liu, Peilin Chen, Yung-Hui Li, Shiqi Wang, Sam Kwong + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Xi Liu, Chaoyi Zhou, Nanxuan Zhao, Siyu Huang - JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention - https://arxiv.org/abs/2512.07168 - arXiv:2512.07168v1 Announce Type: new -Abstract: We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM to learn semantic audio features via masked prediction in latent space, fully decoupled from waveform reconstruction. Stage~2 leverages these representations for efficient tokenization using Finite Scalar Quantization (FSQ) and a mixed-radix packing scheme, followed by high-fidelity waveform reconstruction with a HiFi-GAN decoder. By integrating Gaussian mixture-based density-adaptive gating into the JEPA encoder, the model performs adaptive temporal feature selection and discovers hierarchical speech structure at a low frame rate of 2.5~Hz. The resulting tokens (47.5 tokens/sec) provide a reversible, highly compressed, and language-model-friendly representation that is competitive with, and often more efficient than, existing neural audio codecs. - oai:arXiv.org:2512.07168v1 - cs.SD - cs.AI + RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation + https://arxiv.org/abs/2503.18549 + arXiv:2503.18549v3 Announce Type: replace +Abstract: A CAD command sequence is a typical parametric design paradigm in 3D CAD systems where a model is constructed by overlaying 2D sketches with operations such as extrusion, revolution, and Boolean operations. Although there is growing academic interest in the automatic generation of command sequences, existing methods and datasets only support operations such as 2D sketching, extrusion,and Boolean operations. This limitation makes it challenging to represent more complex geometries. In this paper, we present a reinforcement learning (RL) training environment (gym) built on a CAD geometric engine. Given an input boundary representation (B-Rep) geometry, the policy network in the RL algorithm generates an action. This action, along with previously generated actions, is processed within the gym to produce the corresponding CAD geometry, which is then fed back into the policy network. The rewards, determined by the difference between the generated and target geometries within the gym, are used to update the RL network. Our method supports operations beyond sketches, Boolean, and extrusion, including revolution operations. With this training gym, we achieve state-of-the-art (SOTA) quality in generating command sequences from B-Rep geometries. + oai:arXiv.org:2503.18549v3 cs.LG - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Georgios Ioannides, Christos Constantinou, Aman Chadha, Aaron Elkins, Linsey Pang, Ravid Shwartz-Ziv, Yann LeCun + Xiaolong Yin, Xingyu Lu, Jiahang Shen, Jingzhe Ni, Hailong Li, Ruofeng Tong, Min Tang, Peng Du - Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach - https://arxiv.org/abs/2512.07170 - arXiv:2512.07170v1 Announce Type: new -Abstract: Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and lack the ability to flexibly incorporate user intent, especially in complex scenarios involving low-light degradation, color shifts, or exposure imbalance. Moreover, the absence of ground-truth fused images and the small scale of existing datasets make it difficult to train an end-to-end model that simultaneously understands high-level semantics and performs fine-grained multimodal alignment. We therefore present DiTFuse, instruction-driven Diffusion-Transformer (DiT) framework that performs end-to-end, semantics-aware fusion within a single model. By jointly encoding two images and natural-language instructions in a shared latent space, DiTFuse enables hierarchical and fine-grained control over fusion dynamics, overcoming the limitations of pre-fusion and post-fusion pipelines that struggle to inject high-level semantics. The training phase employs a multi-degradation masked-image modeling strategy, so the network jointly learns cross-modal alignment, modality-invariant restoration, and task-aware feature selection without relying on ground truth images. A curated, multi-granularity instruction dataset further equips the model with interactive fusion capabilities. DiTFuse unifies infrared-visible, multi-focus, and multi-exposure fusion-as well as text-controlled refinement and downstream tasks-within a single architecture. Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention. The model also supports multi-level user control and zero-shot generalization to other multi-image fusion scenarios, including instruction-conditioned segmentation. - oai:arXiv.org:2512.07170v1 + Shape and Texture Recognition in Large Vision-Language Models + https://arxiv.org/abs/2503.23062 + arXiv:2503.23062v5 Announce Type: replace +Abstract: Shapes and textures are the basic building blocks of visual perception. The ability to identify shapes regardless of orientation, texture, or context, and to recognize textures and materials independently of their associated objects, is essential for a general visual understanding of the world. This work introduces the Large Shapes and Textures dataset (LAS&T), a giant collection of highly diverse shapes and textures, created by unsupervised extraction of patterns from natural images. This dataset is used to benchmark how effectively leading Large Vision-Language Models (LVLM/VLM) recognize and represent shapes, textures, and materials in 2D and 3D scenes. For shape recognition, we test the models' ability to match images of identical shapes that differ in orientation, texture, color, or environment. Our results show that the shape-recognition capabilities of LVLMs remain well below human performance, especially when multiple transformations are applied. LVLMs rely predominantly on high-level and semantic features and struggle with abstract shapes lacking class associations. For texture and material recognition, we evaluated the models' ability to identify images with identical textures and materials across different objects and environments. Interestingly, leading LVLMs approach human-level performance in recognizing materials in 3D scenes, yet substantially underperform humans when identifying simpler, more abstract 2D textures and shapes. These results are consistent across a wide range of leading LVLMs (GPT/Gemini/LLama/Qwen) and foundation vision models (DINO/CLIP), exposing major deficiencies in the ability of VLMs to extract low-level visual features. In contrast, humans and simple nets trained directly for these tasks achieve high accuracy. The LAS&T dataset, featuring over 700,000 images for 2D/3D shape and textures recognition and retrieval, is freely available. + oai:arXiv.org:2503.23062v5 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Jiayang Li, Chengjie Jiang, Junjun Jiang, Pengwei Liang, Jiayi Ma, Liqiang Nie + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/publicdomain/zero/1.0/ + Sagi Eppel, Mor Bismut, Alona Faktor-Strugatski - TIDE: Two-Stage Inverse Degradation Estimation with Guided Prior Disentanglement for Underwater Image Restoration - https://arxiv.org/abs/2512.07171 - arXiv:2512.07171v1 Announce Type: new -Abstract: Underwater image restoration is essential for marine applications ranging from ecological monitoring to archaeological surveys, but effectively addressing the complex and spatially varying nature of underwater degradations remains a challenge. Existing methods typically apply uniform restoration strategies across the entire image, struggling to handle multiple co-occurring degradations that vary spatially and with water conditions. We introduce TIDE, a $\underline{t}$wo stage $\underline{i}$nverse $\underline{d}$egradation $\underline{e}$stimation framework that explicitly models degradation characteristics and applies targeted restoration through specialized prior decomposition. Our approach disentangles the restoration process into multiple specialized hypotheses that are adaptively fused based on local degradation patterns, followed by a progressive refinement stage that corrects residual artifacts. Specifically, TIDE decomposes underwater degradations into four key factors, namely color distortion, haze, detail loss, and noise, and designs restoration experts specialized for each. By generating specialized restoration hypotheses, TIDE balances competing degradation factors and produces natural results even in highly degraded regions. Extensive experiments across both standard benchmarks and challenging turbid water conditions show that TIDE achieves competitive performance on reference based fidelity metrics while outperforming state of the art methods on non reference perceptual quality metrics, with strong improvements in color correction and contrast enhancement. Our code is available at: https://rakesh-123-cryp.github.io/TIDE. - oai:arXiv.org:2512.07171v1 + ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation + https://arxiv.org/abs/2504.02316 + arXiv:2504.02316v2 Announce Type: replace +Abstract: Recent advances in zero-shot text-to-3D generation have revolutionized 3D content creation by enabling direct synthesis from textual descriptions. While state-of-the-art methods leverage 3D Gaussian Splatting with score distillation to enhance multi-view rendering through pre-trained text-to-image (T2I) models, they suffer from inherent prior view biases in T2I priors. These biases lead to inconsistent 3D generation, particularly manifesting as the multi-face Janus problem, where objects exhibit conflicting features across views. To address this fundamental challenge, we propose ConsDreamer, a novel method that mitigates view bias by refining both the conditional and unconditional terms in the score distillation process: (1) a View Disentanglement Module (VDM) that eliminates viewpoint biases in conditional prompts by decoupling irrelevant view components and injecting precise view control; and (2) a similarity-based partial order loss that enforces geometric consistency in the unconditional term by aligning cosine similarities with azimuth relationships. Extensive experiments demonstrate that ConsDreamer can be seamlessly integrated into various 3D representations and score distillation paradigms, effectively mitigating the multi-face Janus problem. + oai:arXiv.org:2504.02316v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shravan Venkatraman, Rakesh Raj Madavan, Pavan Kumar S, Muthu Subash Kavitha + Yuan Zhou, Shilong Jin, Litao Hua, Wanjun Lv, Haoran Duan, Jungong Han - Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration - https://arxiv.org/abs/2512.07173 - arXiv:2512.07173v1 Announce Type: new -Abstract: We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confidence across blocks and steps. Based on this observation, we present a lightweight adaptive approach that controls the generation block size, step size, and threshold based on the average confidence of unmasked tokens. We further reduce softmax overhead by dynamically leveraging a subset of the vocabulary to regulate sampling breadth. CadLLM is a plug-and-play, model-agnostic method compatible with KV-cache-based dLLMs. Extensive experiments on four popular tasks demonstrate that CadLLM yields up to 2.28x throughput improvement over the state-of-the-art baseline with competitive accuracy. - oai:arXiv.org:2512.07173v1 + Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agents + https://arxiv.org/abs/2504.02800 + arXiv:2504.02800v3 Announce Type: replace +Abstract: Mental disorders represent a critical global health challenge, and social media is increasingly viewed as a vital resource for real-time digital phenotyping and intervention. Large Language Models (LLMs) offer stronger semantic understanding and reasoning than traditional deep learning, but their use in high-stakes clinical settings is limited by hallucinations and the lack of persistent memory. However, existing literature has not sufficiently investigated how advanced enhancement techniques, specifically Retrieval-Augmented Generation (RAG) and Agentic systems, can address these reliability and reasoning limitations. Here, we systematically survey the evolving landscape of LLM-based methods for social media mental disorder analysis, spanning standard pretrained language models, RAG to mitigate hallucinations and contextual gaps, and agentic systems for autonomous reasoning and multi-step intervention. We organize existing work by technical paradigm and clinical target, extending beyond common internalizing disorders to include psychotic disorders and externalizing behaviors. Additionally, the paper comprehensively evaluates the performance of LLMs, including the impact of RAG, across various tasks. This work establishes a unified benchmark for the field, paving the way for the development of trustworthy, autonomous AI systems that can deliver precise and explainable mental health support. + oai:arXiv.org:2504.02800v3 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.1109/ICDEW67478.2025.00027 + Zhuohan Ge, Nicole Hu, Yubo Wang, Darian Li, Xinyi Zhu, Haoyang Li, Xin Zhang, Mingtao Zhang, Shihao Qi, Yuming Xu, Han Shi, Chen Jason Zhang, Qing Li + + + TabKAN: Advancing Tabular Data Analysis using Kolmogorov-Arnold Network + https://arxiv.org/abs/2504.06559 + arXiv:2504.06559v3 Announce Type: replace +Abstract: Tabular data analysis presents unique challenges that arise from heterogeneous feature types, missing values, and complex feature interactions. While traditional machine learning methods like gradient boosting often outperform deep learning, recent advancements in neural architectures offer promising alternatives. In this study, we introduce TabKAN, a novel framework for tabular data modeling based on Kolmogorov-Arnold Networks (KANs). Unlike conventional deep learning models, KANs use learnable activation functions on edges, which improves both interpretability and training efficiency. TabKAN incorporates modular KAN-based architectures designed for tabular analysis and proposes a transfer learning framework for knowledge transfer across domains. Furthermore, we develop a model-specific interpretability approach that reduces reliance on post hoc explanations. Extensive experiments on public datasets show that TabKAN achieves superior performance in supervised learning and significantly outperforms classical and Transformer-based models in binary and multi-class classification. The results demonstrate the potential of KAN-based architectures to bridge the gap between traditional machine learning and deep learning for structured data. + oai:arXiv.org:2504.06559v3 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.1007/s44379-025-00042-y + A. Eslamian, A. A. Aghaei, and Q. Cheng, "Tabkan: advancing tabular data analysis using Kolmogorov-Arnold network," Machine Learning for Computational Science and Engineering, 1(2): 40, 2025 + Ali Eslamian, Alireza Afzal Aghaei, Qiang Cheng - SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models - https://arxiv.org/abs/2512.07175 - arXiv:2512.07175v1 Announce Type: new -Abstract: Self-play fine-tuning has demonstrated promising abilities in adapting large language models (LLMs) to downstream tasks with limited real-world data. The basic principle is to iteratively refine the model with real samples and synthetic ones generated from itself. However, the existing methods primarily focus on the relative gaps between the rewards for two types of data, neglecting their absolute values. Through theoretical analysis, we identify that the gap-based methods suffer from unstable evolution, due to the potentially degenerated objectives. To address this limitation, we introduce a novel self-play fine-tuning method, namely Self-PlAy via Noise Contrastive Estimation (SPACE), which leverages noise contrastive estimation to capture the real-world data distribution. Specifically, SPACE treats synthetic samples as auxiliary components, and discriminates them from the real ones in a binary classification manner. As a result, SPACE independently optimizes the absolute reward values for each type of data, ensuring a consistently meaningful objective and thereby avoiding the instability issue. Theoretically, we show that the optimal solution of the objective in SPACE aligns with the underlying distribution of real-world data, and SPACE guarantees a provably stable convergence to the optimal distribution. Empirically, we show that SPACE significantly improves the performance of LLMs over various tasks, and outperforms supervised fine-tuning that employs much more real-world samples. Compared to gap-based self-play fine-tuning methods, SPACE exhibits remarkable superiority and stable evolution. - oai:arXiv.org:2512.07175v1 + Rethinking Few-Shot Image Fusion: Granular Ball Priors Enable General-Purpose Deep Fusion + https://arxiv.org/abs/2504.08937 + arXiv:2504.08937v4 Announce Type: replace +Abstract: In image fusion tasks, the absence of real fused images as priors forces most deep learning approaches to rely on large-scale paired datasets to extract global weighting features or to generate pseudo-supervised images through algorithmic constructions. Unlike previous methods, this work re-examines prior-guided learning under few-shot conditions by introducing rough set theory. We regard the traditional algorithm as a prior generator, while the network re-inferrs and adaptively optimizes the prior through a dynamic loss function, reducing the inference burden of the network and enabling effective few-shot learning.To provide the prior, we propose the Granular Ball Pixel Computation (GBPC) algorithm. GBPC models pixel pairs in a luminance subspace using meta-granular balls and mines intra-ball information at multiple granular levels. At the fine-grained level, sliding granular balls assign adaptive weights to individual pixels to produce pixel-level prior fusion. At the coarse-grained level, the algorithm performs split computation within a single image to estimate positive and boundary domain distributions, enabling modality awareness and prior confidence estimation, which dynamically guide the loss weighting.The network and the algorithmic prior are coupled through the loss function to form an integrated framework. Thanks to the dynamic weighting mechanism, the network can adaptively adjust to different priors during training, enhancing its perception and fusion capability across modalities. We name this framework GBFF (Granular Ball Fusion Framework). Experiments on four fusion tasks demonstrate that even with only ten training image pairs per task, GBFF achieves superior performance in both visual quality and model compactness. Code is available at: https://github.com/DMinjie/GBFF + oai:arXiv.org:2504.08937v4 + cs.GR + cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + eess.IV + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Minjie Deng, Yan Wei, An Wu, Yuncan Ouyang, Hao Zhai, Qianyao Peng + + + PinRec: Outcome-Conditioned, Multi-Token Generative Retrieval for Industry-Scale Recommendation Systems + https://arxiv.org/abs/2504.10507 + arXiv:2504.10507v4 Announce Type: replace +Abstract: Generative retrieval methods utilize generative sequential modeling techniques, such as transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models like two-tower architectures. However, current generative retrieval methods lack the scalability required for industrial recommender systems, and they are insufficiently flexible to satisfy the multiple metric requirements of modern systems. This paper introduces PinRec, a novel generative retrieval model developed for applications at Pinterest. PinRec utilizes outcome-conditioned generation, enabling modelers to specify how to balance various outcome metrics, such as the number of saves and clicks, to effectively align with business goals and user exploration. Additionally, PinRec incorporates multi-token generation to enhance output diversity while optimizing generation. Our experiments demonstrate that PinRec can successfully balance performance, diversity, and efficiency, delivering a significant positive impact to users using generative models. This paper marks a significant milestone in generative retrieval, as it presents, to our knowledge, the first rigorous study on implementing generative retrieval at the scale of Pinterest. + oai:arXiv.org:2504.10507v4 + cs.IR + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yibo Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang + Prabhat Agarwal, Anirudhan Badrinath, Laksh Bhasin, Jaewon Yang, Edoardo Botta, Jiajing Xu, Charles Rosenberg - Using Vision-Language Models as Proxies for Social Intelligence in Human-Robot Interaction - https://arxiv.org/abs/2512.07177 - arXiv:2512.07177v1 Announce Type: new -Abstract: Robots operating in everyday environments must often decide when and whether to engage with people, yet such decisions often hinge on subtle nonverbal cues that unfold over time and are difficult to model explicitly. Drawing on a five-day Wizard-of-Oz deployment of a mobile service robot in a university cafe, we analyze how people signal interaction readiness through nonverbal behaviors and how expert wizards use these cues to guide engagement. Motivated by these observations, we propose a two-stage pipeline in which lightweight perceptual detectors (gaze shifts and proxemics) are used to selectively trigger heavier video-based vision-language model (VLM) queries at socially meaningful moments. We evaluate this pipeline on replayed field interactions and compare two prompting strategies. Our findings suggest that selectively using VLMs as proxies for social reasoning enables socially responsive robot behavior, allowing robots to act appropriately by attending to the cues people naturally provide in real-world interactions. - oai:arXiv.org:2512.07177v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Verifiable Mission Planning For Space Operations + https://arxiv.org/abs/2504.11631 + arXiv:2504.11631v4 Announce Type: replace +Abstract: Spacecraft must operate under environmental and actuator uncertainties while meeting strict safety requirements. Traditional approaches rely on scenario-based heuristics that fail to account for stochastic influences, leading to suboptimal or unsafe plans. We propose a finite-horizon, chance-constrained Markov decision process for mission planning, where states represent mission and vehicle parameters, actions correspond to operational adjustments, and temporal logic specifications encode operational reach-avoid constraints. We synthesize policies that optimize mission objectives while ensuring constraints are met with high probability. Applied to the GRACE-FO mission, the approach accounts for stochastic solar activity and uncertain thrust performance, yielding maneuver schedules that maximize scientific return and provably satisfy safety requirements. We demonstrate how Markov decision processes can be applied to space missions, enabling autonomous operation with formal guarantees. + oai:arXiv.org:2504.11631v4 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Fanjun Bu, Melina Tsai, Audrey Tjokro, Tapomayukh Bhattacharjee, Jorge Ortiz, Wendy Ju + Quentin Rommel, Michael Hibbard, Pavan Shukla, Himanshu Save, Srinivas Bettadpur, Ufuk Topcu - ContextualSHAP : Enhancing SHAP Explanations Through Contextual Language Generation - https://arxiv.org/abs/2512.07178 - arXiv:2512.07178v1 Announce Type: new -Abstract: Explainable Artificial Intelligence (XAI) has become an increasingly important area of research, particularly as machine learning models are deployed in high-stakes domains. Among various XAI approaches, SHAP (SHapley Additive exPlanations) has gained prominence due to its ability to provide both global and local explanations across different machine learning models. While SHAP effectively visualizes feature importance, it often lacks contextual explanations that are meaningful for end-users, especially those without technical backgrounds. To address this gap, we propose a Python package that extends SHAP by integrating it with a large language model (LLM), specifically OpenAI's GPT, to generate contextualized textual explanations. This integration is guided by user-defined parameters (such as feature aliases, descriptions, and additional background) to tailor the explanation to both the model context and the user perspective. We hypothesize that this enhancement can improve the perceived understandability of SHAP explanations. To evaluate the effectiveness of the proposed package, we applied it in a healthcare-related case study and conducted user evaluations involving real end-users. The results, based on Likert-scale surveys and follow-up interviews, indicate that the generated explanations were perceived as more understandable and contextually appropriate compared to visual-only outputs. While the findings are preliminary, they suggest that combining visualization with contextualized text may support more user-friendly and trustworthy model explanations. - oai:arXiv.org:2512.07178v1 - cs.AI - cs.HC - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Haptic-based Complementary Filter for Rigid Body Rotations + https://arxiv.org/abs/2504.14570 + arXiv:2504.14570v2 Announce Type: replace +Abstract: The non-commutative nature of 3D rotations poses well-known challenges in generalizing planar problems to three-dimensional ones, even more so in contact-rich tasks where haptic information (i.e., forces/torques) is involved. In this sense, not all learning-based algorithms that are currently available generalize to 3D orientation estimation. Non-linear filters defined on $\mathbf{\mathbb{SO}(3)}$ are widely used with inertial measurement sensors; however, none of them have been used with haptic measurements. This paper presents a unique complementary filtering framework that interprets the geometric shape of objects in the form of superquadrics, exploits the symmetry of $\mathbf{\mathbb{SO}(3)}$, and uses force and vision sensors as measurements to provide an estimate of orientation. The framework's robustness and almost global stability are substantiated by a set of experiments on a dual-arm robotic setup. + oai:arXiv.org:2504.14570v2 + cs.RO + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Latifa Dwiyanti, Sergio Ryan Wibisono, Hidetaka Nambo + Amit Kumar, Domenico Campolo, Ravi N. Banavar - PICKT: Practical Interlinked Concept Knowledge Tracing for Personalized Learning using Knowledge Map Concept Relations - https://arxiv.org/abs/2512.07179 - arXiv:2512.07179v1 Announce Type: new -Abstract: With the recent surge in personalized learning, Intelligent Tutoring Systems (ITS) that can accurately track students' individual knowledge states and provide tailored learning paths based on this information are in demand as an essential task. This paper focuses on the core technology of Knowledge Tracing (KT) models that analyze students' sequences of interactions to predict their knowledge acquisition levels. However, existing KT models suffer from limitations such as restricted input data formats, cold start problems arising with new student enrollment or new question addition, and insufficient stability in real-world service environments. To overcome these limitations, a Practical Interlinked Concept Knowledge Tracing (PICKT) model that can effectively process multiple types of input data is proposed. Specifically, a knowledge map structures the relationships among concepts considering the question and concept text information, thereby enabling effective knowledge tracing even in cold start situations. Experiments reflecting real operational environments demonstrated the model's excellent performance and practicality. The main contributions of this research are as follows. First, a model architecture that effectively utilizes diverse data formats is presented. Second, significant performance improvements are achieved over existing models for two core cold start challenges: new student enrollment and new question addition. Third, the model's stability and practicality are validated through delicate experimental design, enhancing its applicability in real-world product environments. This provides a crucial theoretical and technical foundation for the practical implementation of next-generation ITS. - oai:arXiv.org:2512.07179v1 + Towards Task-Oriented Flying: Framework, Infrastructure, and Principles + https://arxiv.org/abs/2504.15129 + arXiv:2504.15129v2 Announce Type: replace +Abstract: Deploying robot learning methods to aerial robots in unstructured environments remains both challenging and promising. While recent advances in deep reinforcement learning (DRL) have enabled end-to-end flight control, the field still lacks systematic design guidelines and a unified infrastructure to support reproducible training and real-world deployment. We present a task-oriented framework for end-to-end DRL in quadrotors that integrates design principles for complex task specification and reveals the interdependencies among simulated task definition, training design principles, and physical deployment. Our framework involves software infrastructure, hardware platforms, and open-source firmware to support a full-stack learning infrastructure and workflow. Extensive empirical results demonstrate robust flight and sim-to-real generalization under real-world disturbances. By reducing the entry barrier for deploying learning-based controllers on aerial robots, our work lays a practical foundation for advancing autonomous flight in dynamic and unstructured environments. + oai:arXiv.org:2504.15129v2 + cs.RO cs.AI - cs.CL - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Wonbeen Lee, Channyoung Lee, Junho Sohn, Hansam Cho + cs.CV + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Kangyao Huang, Hao Wang, Jingyu Chen, Jintao Chen, Yu Luo, Di Guo, Xiangkui Zhang, Xiangyang Ji, Huaping Liu - Implementation of Honeynet and Honeypot in Network Infrastructure in Production Network - https://arxiv.org/abs/2512.07180 - arXiv:2512.07180v1 Announce Type: new -Abstract: Network infrastructure in a production environment is increasingly targeted by attackers every day. Many resources and services now rely on the internet, making network infrastructure one of the most critical parts to protect, as it hosts numerous company resources and services. Several solutions have already been proposed to prevent attacks, minimize damage, and divert hackers and intruders. Among these, the honeypot stands out as a highly effective tool; it is designed to mimic both a scanner and an attacker, diverting and misleading them within a simulated, production-level environment. This paper will demonstrate the use of a honeynet where a honeypot acts like a real resource to deceive the attacker and analyze their behavior. - oai:arXiv.org:2512.07180v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Using LLMs in Generating Design Rationale for Software Architecture Decisions + https://arxiv.org/abs/2504.20781 + arXiv:2504.20781v3 Announce Type: replace +Abstract: Design Rationale (DR) for software architecture decisions refers to the reasoning underlying architectural choices, which provides valuable insights into the different phases of the architecting process throughout software development. However, in practice, DR is often inadequately documented due to a lack of motivation and effort from developers. With the recent advancements in Large Language Models (LLMs), their capabilities in text comprehension, reasoning, and generation may enable the generation and recovery of DR for architecture decisions. In this study, we evaluated the performance of LLMs in generating DR for architecture decisions. First, we collected 50 Stack Overflow (SO) posts, 25 GitHub issues, and 25 GitHub discussions related to architecture decisions to construct a dataset of 100 architecture-related problems. Then, we selected five LLMs to generate DR for the architecture decisions with three prompting strategies, including zero-shot, chain of thought (CoT), and LLM-based agents. With the DR provided by human experts as ground truth, the Precision of LLM-generated DR with the three prompting strategies ranges from 0.267 to 0.278, Recall from 0.627 to 0.715, and F1-score from 0.351 to 0.389. Additionally, 64.45% to 69.42% of the arguments of DR not mentioned by human experts are also helpful, 4.12% to 4.87% of the arguments have uncertain correctness, and 1.59% to 3.24% of the arguments are potentially misleading. To further understand the trustworthiness and applicability of LLM-generated DR in practice, we conducted semi-structured interviews with six practitioners. Based on the experimental and interview results, we discussed the pros and cons of the three prompting strategies, the strengths and limitations of LLM-generated DR, and the implications for the practical use of LLM-generated DR. + oai:arXiv.org:2504.20781v3 + cs.SE + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Nawshad Ahmed Evan, Md Raihan Uddin + Xiyu Zhou, Ruiyin Li, Peng Liang, Beiqi Zhang, Mojtaba Shahin, Zengyang Li, Chen Yang - Coarse spaces for virtual element methods on irregular 3D subdomain decompositions - https://arxiv.org/abs/2512.07181 - arXiv:2512.07181v1 Announce Type: new -Abstract: We present a two-level overlapping Schwarz preconditioner for three-dimensional problems discretized with the Virtual Element Method. Our approach handles general polyhedral meshes and irregular subdomains, extending the applicability of previous methods. Numerical experiments show robust performance with respect to the number of subdomains and mesh parameters, with condition-number bound comparable to classical finite element results. While alternative methods such as FETI-DP and BDDC are available, the simplicity and competitiveness of overlapping additive Schwarz methods underscore the practical significance of our contribution. - oai:arXiv.org:2512.07181v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new + A Formalism for Optimal Search with Dynamic Heuristics (Extended Version) + https://arxiv.org/abs/2504.21131 + arXiv:2504.21131v3 Announce Type: replace +Abstract: While most heuristics studied in heuristic search depend only on the state, some accumulate information during search and thus also depend on the search history. Various existing approaches use such dynamic heuristics in $\mathrm{A}^*$-like algorithms and appeal to classic results for $\mathrm{A}^*$ to show optimality. However, doing so ignores the complexities of searching with a mutable heuristic. In this paper we formalize the idea of dynamic heuristics and use them in a generic algorithm framework. We study a particular instantiation that models $\mathrm{A}^*$ with dynamic heuristics and show general optimality results. Finally we show how existing approaches from classical planning can be viewed as special cases of this instantiation, making it possible to directly apply our optimality results. + oai:arXiv.org:2504.21131v3 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Ana Aguilar-Pineda, Luis F. Amey, Adrian Angulo-Paniagua, Juan G. Calvo + Remo Christen, Florian Pommerening, Clemens B\"uchner, Malte Helmert - UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting - https://arxiv.org/abs/2512.07184 - arXiv:2512.07184v1 Announce Type: new -Abstract: As multimodal data proliferates across diverse real-world applications, leveraging heterogeneous information such as texts and timestamps for accurate time series forecasting (TSF) has become a critical challenge. While diffusion models demonstrate exceptional performance in generation tasks, their application to TSF remains largely confined to modeling single-modality numerical sequences, overlooking the abundant cross-modal signals inherent in complex heterogeneous data. To address this gap, we propose UniDiff, a unified diffusion framework for multimodal time series forecasting. To process the numerical sequence, our framework first tokenizes the time series into patches, preserving local temporal dynamics by mapping each patch to an embedding space via a lightweight MLP. At its core lies a unified and parallel fusion module, where a single cross-attention mechanism adaptively weighs and integrates structural information from timestamps and semantic context from texts in one step, enabling a flexible and efficient interplay between modalities. Furthermore, we introduce a novel classifier-free guidance mechanism designed for multi-source conditioning, allowing for decoupled control over the guidance strength of textual and temporal information during inference, which significantly enhances model robustness. Extensive experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance. - oai:arXiv.org:2512.07184v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Da Zhang, Bingyu Li, Zhuyuan Zhao, Junyu Gao, Feiping Nie, Xuelong Li + Differentially Private Secure Multiplication with Erasures and Adversaries + https://arxiv.org/abs/2504.21178 + arXiv:2504.21178v2 Announce Type: replace +Abstract: We consider a private distributed multiplication problem involving N computation nodes and T colluding nodes. Shamir's secret sharing algorithm provides perfect information-theoretic privacy, while requiring an honest majority, i.e., N \ge 2T + 1. Recent work has investigated approximate computation and characterized privacy-accuracy trade-offs for the honest minority setting N \le 2T for real-valued data, quantifying privacy leakage via the differential privacy (DP) framework and accuracy via the mean squared error. However, it does not incorporate the error correction capabilities of Shamir's secret-sharing algorithm. This paper develops a new polynomial-based coding scheme for secure multiplication with an honest minority, and characterizes its achievable privacy-utility tradeoff, showing that the tradeoff can approach the converse bound as closely as desired. Unlike previous schemes, the proposed scheme inherits the capability of the Reed-Solomon (RS) code to tolerate erasures and adversaries. We utilize a modified Berlekamp-Welch algorithm over the real number field to detect adversarial nodes. + oai:arXiv.org:2504.21178v2 + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Haoyang Hu, Viveck R. Cadambe - START: Spatial and Textual Learning for Chart Understanding - https://arxiv.org/abs/2512.07186 - arXiv:2512.07186v1 Announce Type: new -Abstract: Chart understanding is crucial for deploying multimodal large language models (MLLMs) in real-world scenarios such as analyzing scientific papers and technical reports. Unlike natural images, charts pair a structured visual layout (spatial property) with an underlying data representation (textual property) -- grasping both is essential for precise, fine-grained chart reasoning. Motivated by this observation, we propose START, the Spatial and Textual learning for chART understanding. Specifically, we introduce (i) chart-element grounding and (ii) chart-to-code generation to strengthen an MLLM's understanding of both chart visual layout and data details. To facilitate spatial and textual learning, we propose the START-Dataset generated with a novel data-generation pipeline that first leverages an MLLM to translate real chart images into executable chart code, recovering the underlying data representation while preserving the visual distribution of real-world charts. We then evolve the code with a Large Language Model (LLM) to ascertain the positions of chart elements that capture the chart's visual structure, addressing challenges that existing methods cannot handle. To evaluate a model's ability to understand chart spatial structures, we propose the Chart Spatial understanding Benchmark (CS-Bench), filling a critical gap in comprehensive chart understanding evaluation. Leveraging spatial and textual learning, START delivers consistent gains across model sizes and benchmarks over the base models and surpasses prior state-of-the-art by a clear margin. Code, data and models will be publicly available. - oai:arXiv.org:2512.07186v1 - cs.CV + Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces + https://arxiv.org/abs/2505.03295 + arXiv:2505.03295v2 Announce Type: replace +Abstract: Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the development of a skill implementation conforming to a corresponding capability remains a time-consuming and challenging task. In this paper, we present a method that treats capabilities as contracts for skill implementations and leverages large language models to generate executable code based on natural language user input. A key feature of our approach is the integration of existing software libraries and interface technologies, enabling the generation of skill implementations across different target languages. We introduce a framework that allows users to incorporate their own libraries and resource interfaces into the code generation process through a retrieval-augmented generation architecture. The proposed method is evaluated using an autonomous mobile robot controlled via Python and ROS 2, demonstrating the feasibility and flexibility of the approach. + oai:arXiv.org:2505.03295v2 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.RO + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhuoming Liu, Xiaofeng Gao, Feiyang Niu, Qiaozi Gao, Liu Liu, Robinson Piramuthu + 10.1109/ETFA65518.2025.11205724 + Luis Miguel Vieira da Silva, Aljosha K\"ocher, Nicolas K\"onig, Felix Gehlhoff, Alexander Fay - PIR-DSN: A Decentralized Storage Network Supporting Private Information Retrieval - https://arxiv.org/abs/2512.07189 - arXiv:2512.07189v1 Announce Type: new -Abstract: Decentralized Storage Networks (DSNs) are emerging as a foundational infrastructure for Web 3.0, offering global peer-to-peer storage. However, a critical vulnerability persists: user privacy during file retrieval remains largely unaddressed, risking the exposure of sensitive information. To overcome this, we introduce PIR-DSN, the first DSN protocol to integrate Private Information Retrieval (PIR) for both single and multi-server settings. Our key innovations include a novel secure mapping method that transforms sparse file identifiers into compact integer indexes, enabling both public verifiability of file operations and efficient private retrieval. Furthermore, PIR-DSN guarantees Byzantine-robust private retrieval through file replication across multiple miners. We implement and rigorously evaluate PIR-DSN against three prominent industrial DSN systems. Experimental results demonstrate that PIR-DSN achieves comparable overhead for file upload and deletion. While PIR inherently introduces an additional computational cost leading to higher retrieval latency, PIR-DSN maintains comparable throughput. These findings underscore PIR-DSN's practical viability for privacy-sensitive applications within DSN environments. - oai:arXiv.org:2512.07189v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new + Fitts' List Revisited: An Empirical Study on Function Allocation in a Two-Agent Physical Human-Robot Collaborative Position/Force Task + https://arxiv.org/abs/2505.04722 + arXiv:2505.04722v2 Announce Type: replace +Abstract: In this letter, we investigate whether classical function allocation-the principle of assigning tasks to either a human or a machine-holds for physical Human-Robot Collaboration, which is important for providing insights for Industry 5.0 to guide how to best augment rather than replace workers. This study empirically tests the applicability of Fitts' List within physical Human-Robot Collaboration, by conducting a user study (N=26, within-subject design) to evaluate four distinct allocations of position/force control between human and robot in an abstract blending task. We hypothesize that the function in which humans control the position achieves better performance and receives higher user ratings. When allocating position control to the human and force control to the robot, compared to the opposite case, we observed a significant improvement in preventing overblending. This was also perceived better in terms of physical demand and overall system acceptance, while participants experienced greater autonomy, more engagement and less frustration. An interesting insight was that the supervisory role (when the robot controls both position and force) was rated second best in terms of subjective acceptance. Another surprising insight was that if position control was delegated to the robot, the participants perceived much lower autonomy than when the force control was delegated to the robot. These findings empirically support applying Fitts' principles to static function allocation for physical collaboration, while also revealing important nuanced user experience trade-offs, particularly regarding perceived autonomy when delegating position control. + oai:arXiv.org:2505.04722v2 + cs.RO + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Jiahao Zhang, Minghui Xu, Hechuan Guo, Xiuzhen Cheng + 10.1109/LRA.2025.3632607 + N. Mol, J. M. Prendergast, D. A. Abbink and L. Peternel, "Fitts' List Revisited: An Empirical Study on Function Allocation," in IEEE Robot. Autom. Lett., vol. 11, no. 1, pp. 202-209, Jan. 2026 + Nicky Mol, J. Micah Prendergast, David A. Abbink, Luka Peternel - Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification - https://arxiv.org/abs/2512.07190 - arXiv:2512.07190v1 Announce Type: new -Abstract: Modern deep neural networks have shown remarkable performance in medical image classification. However, such networks either emphasize pixel-intensity features instead of fundamental anatomical structures (e.g., those encoded by topological invariants), or they capture only simple topological features via single-parameter persistence. In this paper, we propose a new topology-guided classification framework that extracts multi-scale and multi-filtration persistent topological features and integrates them into vision classification backbones. For an input image, we first compute cubical persistence diagrams (PDs) across multiple image resolutions/scales. We then develop a ``vineyard'' algorithm that consolidates these PDs into a single, stable diagram capturing signatures at varying granularities, from global anatomy to subtle local irregularities that may indicate early-stage disease. To further exploit richer topological representations produced by multiple filtrations, we design a cross-attention-based neural network that directly processes the consolidated final PDs. The resulting topological embeddings are fused with feature maps from CNNs or Transformers. By integrating multi-scale and multi-filtration topologies into an end-to-end architecture, our approach enhances the model's capacity to recognize complex anatomical structures. Evaluations on three public datasets show consistent, considerable improvements over strong baselines and state-of-the-art methods, demonstrating the value of our comprehensive topological perspective for robust and interpretable medical image classification. - oai:arXiv.org:2512.07190v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Pengfei Gu (DK), Huimin Li (DK), Haoteng Tang (DK), Dongkuan (DK), Xu, Erik Enriquez, DongChul Kim, Bin Fu, Danny Z. Chen + Cross-Problem Solving for Network Optimization: Is Problem-Aware Learning the Key? + https://arxiv.org/abs/2505.05067 + arXiv:2505.05067v2 Announce Type: replace +Abstract: As intelligent network services continue to diversify, ensuring efficient and adaptive resource allocation in edge networks has become increasingly critical. Yet the wide functional variations across services often give rise to new and unforeseen optimization problems, rendering traditional manual modeling and solver design both time-consuming and inflexible. This limitation reveals a key gap between current methods and human solving - the inability to recognize and understand problem characteristics. It raises the question of whether problem-aware learning can bridge this gap and support effective cross-problem generalization. To answer this question, we propose a problem-aware diffusion (PAD) model, which leverages a problem-aware learning framework to enable cross-problem generalization. By explicitly encoding the mathematical formulations of optimization problems into token-level embeddings, PAD empowers the model to understand and adapt to problem structures. Extensive experiments across ten representative network optimization problems show that PAD generalizes well to unseen problems while avoiding the inefficiency of building new solvers from scratch, yet still delivering competitive solution quality. Meanwhile, an auxiliary constraint-aware module is designed to enforce solution validity further. The experiments indicate that problem-aware learning opens a promising direction toward general-purpose solvers for intelligent network operation and resource management. Our code is open source at https://github.com/qiyu3816/PAD. + oai:arXiv.org:2505.05067v2 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ruihuai Liang, Bo Yang, Pengyu Chen, Xuelin Cao, Zhiwen Yu, H. Vincent Poor, Chau Yuen - RefLSM: Linearized Structural-Prior Reflectance Model for Medical Image Segmentation and Bias-Field Correction - https://arxiv.org/abs/2512.07191 - arXiv:2512.07191v1 Announce Type: new -Abstract: Medical image segmentation remains challenging due to intensity inhomogeneity, noise, blurred boundaries, and irregular structures. Traditional level set methods, while effective in certain cases, often depend on approximate bias field estimations and therefore struggle under severe non-uniform imaging conditions. To address these limitations, we propose a novel variational Reflectance-based Level Set Model (RefLSM), which explicitly integrates Retinex-inspired reflectance decomposition into the segmentation framework. By decomposing the observed image into reflectance and bias field components, RefLSM directly segments the reflectance, which is invariant to illumination and preserves fine structural details. Building on this foundation, we introduce two key innovations for enhanced precision and robustness. First, a linear structural prior steers the smoothed reflectance gradients toward a data-driven reference, providing reliable geometric guidance in noisy or low-contrast scenes. Second, a relaxed binary level-set is embedded in RefLSM and enforced via convex relaxation and sign projection, yielding stable evolution and avoiding reinitialization-induced diffusion. The resulting variational problem is solved efficiently using an ADMM-based optimization scheme. Extensive experiments on multiple medical imaging datasets demonstrate that RefLSM achieves superior segmentation accuracy, robustness, and computational efficiency compared to state-of-the-art level set methods. - oai:arXiv.org:2512.07191v1 + Video Dataset Condensation with Diffusion Models + https://arxiv.org/abs/2505.06670 + arXiv:2505.06670v2 Announce Type: replace +Abstract: In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation has emerged as a promising solution to address this challenge by generating a compact synthetic dataset that retains the essential information from a large real dataset. However, existing methods often suffer from limited performance, particularly in the video domain. In this paper, we focus on video dataset distillation. We begin by employing a video diffusion model to generate synthetic videos. Since the videos are generated only once, this significantly reduces computational costs. Next, we introduce the Video Spatio-Temporal U-Net (VST-UNet), a model designed to select a diverse and informative subset of videos that effectively captures the characteristics of the original dataset. To further optimize computational efficiency, we explore a training-free clustering algorithm, Temporal-Aware Cluster-based Distillation (TAC-DT), to select representative videos without requiring additional training overhead. We validate the effectiveness of our approach through extensive experiments on four benchmark datasets, demonstrating performance improvements of up to \(10.61\%\) over the state-of-the-art. Our method consistently outperforms existing approaches across all datasets, establishing a new benchmark for video dataset distillation. + oai:arXiv.org:2505.06670v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Wenqi Zhao, Jiacheng Sang, Fenghua Cheng, Yonglu Shu, Dong Li, Xiaofeng Yang + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Zhe Li, Hadrien Reynaud, Mischa Dombrowski, Sarah Cechnicka, Franciskus Xaverius Erick, Bernhard Kainz - HVQ-CGIC: Enabling Hyperprior Entropy Modeling for VQ-Based Controllable Generative Image Compression - https://arxiv.org/abs/2512.07192 - arXiv:2512.07192v1 Announce Type: new -Abstract: Generative learned image compression methods using Vector Quantization (VQ) have recently shown impressive potential in balancing distortion and perceptual quality. However, these methods typically estimate the entropy of VQ indices using a static, global probability distribution, which fails to adapt to the specific content of each image. This non-adaptive approach leads to untapped bitrate potential and challenges in achieving flexible rate control. To address this challenge, we introduce a Controllable Generative Image Compression framework based on a VQ Hyperprior, termed HVQ-CGIC. HVQ-CGIC rigorously derives the mathematical foundation for introducing a hyperprior to the VQ indices entropy model. Based on this foundation, through novel loss design, to our knowledge, this framework is the first to introduce RD balance and control into vector quantization-based Generative Image Compression. Cooperating with a lightweight hyper-prior estimation network, HVQ-CGIC achieves a significant advantage in rate-distortion (RD) performance compared to current state-of-the-art (SOTA) generative compression methods. On the Kodak dataset, we achieve the same LPIPS as Control-GIC, CDC and HiFiC with an average of 61.3% fewer bits. We posit that HVQ-CGIC has the potential to become a foundational component for VQGAN-based image compression, analogous to the integral role of the HyperPrior framework in neural image compression. - oai:arXiv.org:2512.07192v1 + MELLM: A Flow-Guided Large Language Model for Micro-Expression Understanding + https://arxiv.org/abs/2505.07007 + arXiv:2505.07007v3 Announce Type: replace +Abstract: Micro-expressions (MEs), brief and low-intensity facial movements revealing concealed emotions, are crucial for affective computing. Despite notable progress in ME recognition, existing methods are largely confined to discrete emotion classification, lacking the capacity for comprehensive ME Understanding (MEU), particularly in interpreting subtle facial dynamics and underlying emotional cues. While Multimodal Large Language Models (MLLMs) offer potential for MEU with their advanced reasoning abilities, they still struggle to perceive such subtle facial affective behaviors. To bridge this gap, we propose a ME Large Language Model (MELLM) that integrates optical flow-based sensitivity to subtle facial motions with the powerful inference ability of LLMs. Specifically, an iterative, warping-based optical-flow estimator, named MEFlowNet, is introduced to precisely capture facial micro-movements. For its training and evaluation, we construct MEFlowDataset, a large-scale optical-flow dataset with 54,611 onset-apex image pairs spanning diverse identities and subtle facial motions. Subsequently, we design a Flow-Guided Micro-Expression Understanding paradigm. Under this framework, the optical flow signals extracted by MEFlowNet are leveraged to build MEU-Instruct, an instruction-tuning dataset for MEU. MELLM is then fine-tuned on MEU-Instruct, enabling it to translate subtle motion patterns into human-readable descriptions and generate corresponding emotional inferences. Experiments demonstrate that MEFlowNet significantly outperforms existing optical flow methods in facial and ME-flow estimation, while MELLM achieves state-of-the-art accuracy and generalization across multiple ME benchmarks. To the best of our knowledge, this work presents two key contributions: MEFlowNet as the first dedicated ME flow estimator, and MELLM as the first LLM tailored for MEU. + oai:arXiv.org:2505.07007v3 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Niu Yi, Xu Tianyi, Ma Mingming, Wang Xinkun + Sirui Zhao, Zhengye Zhang, Shifeng Liu, Xinglong Mao, Shukang Yin, Chaoyou Fu, Tong Xu, Enhong Chen - Towards Benchmarking Design Pattern Detection Under Obfuscation: Reproducing and Evaluating Attention-Based Detection Method - https://arxiv.org/abs/2512.07193 - arXiv:2512.07193v1 Announce Type: new -Abstract: This paper investigates the semantic robustness of attention-based classifiers for design pattern detection, particularly focusing on their reliance on structural and behavioral semantics. We reproduce the DPDAtt, an attention-based design pattern detection approach using learning-based classifiers, and evaluate its performance under obfuscation. To this end, we curate an obfuscated version of the DPDAtt Corpus, where the name identifiers in code such as class names, method names, etc., and string literals like print statements and comment blocks are replaced while preserving control flow, inheritance, and logic. Our findings reveal that these trained classifiers in DPDAtt depend significantly on superficial syntactic features, leading to substantial misclassification when such cues are removed through obfuscation. This work highlights the need for more robust detection tools capable of capturing deeper semantic meanings in source code. We propose our curated Obfuscated corpus (containing 34 Java source files) as a reusable proof-of-concept benchmark for evaluating state-of-the-art design pattern detectors on their true semantic generalization capabilities. - oai:arXiv.org:2512.07193v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - 10.1007/978-3-032-04403-7_13 - Lect. Notes Comput. Sci. 15982 (2026) 127-140 - Manthan Shenoy, Andreas Rausch + Leveraging Multi-Modal Information to Enhance Dataset Distillation + https://arxiv.org/abs/2505.08605 + arXiv:2505.08605v3 Announce Type: replace +Abstract: Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage and computational costs, related approaches offer a promising avenue for privacy preservation in computer vision by eliminating the need to store or share sensitive real-world images. Existing methods focus solely on optimizing visual representations, overlooking the potential of multi-modal information. In this work, we propose a multi-modal dataset distillation framework that incorporates two key enhancements: caption-guided supervision and object-centric masking. To leverage textual information, we introduce two strategies: caption concatenation, which fuses caption embeddings with visual features during classification, and caption matching, which enforces semantic alignment between real and synthetic data through a caption-based loss. To improve data utility and reduce unnecessary background noise, we employ segmentation masks to isolate target objects and introduce two novel losses: masked feature alignment and masked gradient matching, both aimed at promoting object-centric learning. Extensive evaluations demonstrate that our approach improves downstream performance while promoting privacy protection by minimizing exposure to real data. + oai:arXiv.org:2505.08605v3 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Zhe Li, Hadrien Reynaud, Bernhard Kainz - Synchrony-Gated Plasticity with Dopamine Modulation for Spiking Neural Networks - https://arxiv.org/abs/2512.07194 - arXiv:2512.07194v1 Announce Type: new -Abstract: While surrogate backpropagation proves useful for training deep spiking neural networks (SNNs), incorporating biologically inspired local signals on a large scale remains challenging. This difficulty stems primarily from the high memory demands of maintaining accurate spike-timing logs and the potential for purely local plasticity adjustments to clash with the supervised learning goal. To effectively leverage local signals derived from spiking neuron dynamics, we introduce Dopamine-Modulated Spike-Synchrony-Dependent Plasticity (DA-SSDP), a synchrony-based rule that is sensitive to loss and brings a synchrony-based local learning signal to the model. DA-SSDP condenses spike patterns into a synchrony metric at the batch level. An initial brief warm-up phase assesses its relationship to the task loss and sets a fixed gate that subsequently adjusts the local update's magnitude. In cases where synchrony proves unrelated to the task, the gate settles at one, simplifying DA-SSDP to a basic two-factor synchrony mechanism that delivers minor weight adjustments driven by concurrent spike firing and a Gaussian latency function. These small weight updates are only added to the network`s deeper layers following the backpropagation phase, and our tests showed this simplified version did not degrade performance and sometimes gave a small accuracy boost, serving as a regularizer during training. The rule stores only binary spike indicators and first-spike latencies with a Gaussian kernel. Without altering the model structure or optimization routine, evaluations on benchmarks like CIFAR-10 (+0.42\%), CIFAR-100 (+0.99\%), CIFAR10-DVS (+0.1\%), and ImageNet-1K (+0.73\%) demonstrated consistent accuracy gains, accompanied by a minor increase in computational overhead. Our code is available at https://github.com/NeuroSyd/DA-SSDP. - oai:arXiv.org:2512.07194v1 - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yuchen Tian, Samuel Tensingh, Jason Eshraghian, Nhan Duy Truong, Omid Kavehei + VoiceCloak: A Multi-Dimensional Defense Framework against Unauthorized Diffusion-based Voice Cloning + https://arxiv.org/abs/2505.12332 + arXiv:2505.12332v5 Announce Type: replace +Abstract: Diffusion Models (DMs) have achieved remarkable success in realistic voice cloning (VC), while they also increase the risk of malicious misuse. Existing proactive defenses designed for traditional VC models aim to disrupt the forgery process, but they have been proven incompatible with DMs due to the intricate generative mechanisms of diffusion. To bridge this gap, we introduce VoiceCloak, a multi-dimensional proactive defense framework with the goal of obfuscating speaker identity and degrading perceptual quality in potential unauthorized VC. To achieve these goals, we conduct a focused analysis to identify specific vulnerabilities within DMs, allowing VoiceCloak to disrupt the cloning process by introducing adversarial perturbations into the reference audio. Specifically, to obfuscate speaker identity, VoiceCloak first targets speaker identity by distorting representation learning embeddings to maximize identity variation, which is guided by auditory perception principles. Additionally, VoiceCloak disrupts crucial conditional guidance processes, particularly attention context, thereby preventing the alignment of vocal characteristics that are essential for achieving convincing cloning. Then, to address the second objective, VoiceCloak introduces score magnitude amplification to actively steer the reverse trajectory away from the generation of high-quality speech. Noise-guided semantic corruption is further employed to disrupt structural speech semantics captured by DMs, degrading output quality. Extensive experiments highlight VoiceCloak's outstanding defense success rate against unauthorized diffusion-based voice cloning. Audio samples of VoiceCloak are available at https://voice-cloak.github.io/VoiceCloak/. + oai:arXiv.org:2505.12332v5 + cs.SD + cs.AI + cs.CV + cs.MM + eess.AS + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Qianyue Hu, Junyan Wu, Wei Lu, Xiangyang Luo - MASim: Multilingual Agent-Based Simulation for Social Science - https://arxiv.org/abs/2512.07195 - arXiv:2512.07195v1 Announce Type: new -Abstract: Multi-agent role-playing has recently shown promise for studying social behavior with language agents, but existing simulations are mostly monolingual and fail to model cross-lingual interaction, an essential property of real societies. We introduce MASim, the first multilingual agent-based simulation framework that supports multi-turn interaction among generative agents with diverse sociolinguistic profiles. MASim offers two key analyses: (i) global public opinion modeling, by simulating how attitudes toward open-domain hypotheses evolve across languages and cultures, and (ii) media influence and information diffusion, via autonomous news agents that dynamically generate content and shape user behavior. To instantiate simulations, we construct the MAPS benchmark, which combines survey questions and demographic personas drawn from global population distributions. Experiments on calibration, sensitivity, consistency, and cultural case studies show that MASim reproduces sociocultural phenomena and highlights the importance of multilingual simulation for scalable, controlled computational social science. - oai:arXiv.org:2512.07195v1 + EEG-to-Text Translation: A Model for Deciphering Human Brain Activity + https://arxiv.org/abs/2505.13936 + arXiv:2505.13936v2 Announce Type: replace +Abstract: With the rapid advancement of large language models like Gemini, GPT, and others, bridging the gap between the human brain and language processing has become an important area of focus. To address this challenge, researchers have developed various models to decode EEG signals into text. However, these models still face significant performance limitations. To overcome these shortcomings, we propose a new model, R1 Translator, which aims to improve the performance of EEG-to-text decoding. The R1 Translator model combines a bidirectional LSTM encoder with a pretrained transformer-based decoder, utilizing EEG features to produce high-quality text outputs. The model processes EEG embeddings through the LSTM to capture sequential dependencies, which are then fed into the transformer decoder for effective text generation. The R1 Translator excels in ROUGE metrics, outperforming both T5 (previous research) and Brain Translator. Specifically, R1 achieves a ROUGE-1 score of 38.00% (P), which is up to 9% higher than T5 (34.89%) and 3% better than Brain (35.69%). It also leads in ROUGE-L, with a F1 score of 32.51%, outperforming T5 by 3% (29.67%) and Brain by 2% (30.38%). In terms of CER, R1 achieves a CER of 0.5795, which is 2% lower than T5 (0.5917) and 4% lower than Brain (0.6001). Additionally, R1 performs better in WER with a score of 0.7280, outperforming T5 by 4.3% (0.7610) and Brain by 3.6% (0.7553). Code is available at https://github.com/Mmurrad/EEG-To-text. + oai:arXiv.org:2505.13936v2 cs.CL cs.AI - cs.CY - cs.MA - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuan Zhang, Wenxuan Zhang, Anxu Wang, See-Kiong Ng, Yang Deng + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Saydul Akbar Murad, Ashim Dahal, Nick Rahimi - SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting - https://arxiv.org/abs/2512.07197 - arXiv:2512.07197v1 Announce Type: new -Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful explicit representation enabling real-time, high-fidelity 3D reconstruction and novel view synthesis. However, its practical use is hindered by the massive memory and computational demands required to store and render millions of Gaussians. These challenges become even more severe in 4D dynamic scenes. To address these issues, the field of Efficient Gaussian Splatting has rapidly evolved, proposing methods that reduce redundancy while preserving reconstruction quality. This survey provides the first unified overview of efficient 3D and 4D Gaussian Splatting techniques. For both 3D and 4D settings, we systematically categorize existing methods into two major directions, Parameter Compression and Restructuring Compression, and comprehensively summarize the core ideas and methodological trends within each category. We further cover widely used datasets, evaluation metrics, and representative benchmark comparisons. Finally, we discuss current limitations and outline promising research directions toward scalable, compact, and real-time Gaussian Splatting for both static and dynamic 3D scene representation. - oai:arXiv.org:2512.07197v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Seokhyun Youn, Soohyun Lee, Geonho Kim, Weeyoung Kwon, Sung-Ho Bae, Jihyong Oh + Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting + https://arxiv.org/abs/2505.15312 + arXiv:2505.15312v2 Announce Type: replace +Abstract: Multivariable time series forecasting methods can integrate information from exogenous variables, leading to significant prediction accuracy gains. The transformer architecture has been widely applied in various time series forecasting models due to its ability to capture long-range sequential dependencies. However, a na\"ive application of transformers often struggles to effectively model complex relationships among variables over time. To mitigate against this, we propose a novel architecture, termed Spectral Operator Neural Network (Sonnet). Sonnet applies learnable wavelet transformations to the input and incorporates spectral analysis using the Koopman operator. Its predictive skill relies on the Multivariable Coherence Attention (MVCA), an operation that leverages spectral coherence to model variable dependencies. Our empirical analysis shows that Sonnet yields the best performance on $34$ out of $47$ forecasting tasks with an average mean absolute error (MAE) reduction of $2.2\%$ against the most competitive baseline. We further show that MVCA can remedy the deficiencies of na\"ive attention in various deep learning models, reducing MAE by $10.7\%$ on average in the most challenging forecasting tasks. + oai:arXiv.org:2505.15312v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Yuxuan Shu, Vasileios Lampos - Generating Storytelling Images with Rich Chains-of-Reasoning - https://arxiv.org/abs/2512.07198 - arXiv:2512.07198v1 Announce Type: new -Abstract: An image can convey a compelling story by presenting rich, logically connected visual clues. These connections form Chains-of-Reasoning (CoRs) within the image, enabling viewers to infer events, causal relationships, and other information, thereby understanding the underlying story. In this paper, we focus on these semantically rich images and define them as Storytelling Images. Such images have diverse applications beyond illustration creation and cognitive screening, leveraging their ability to convey multi-layered information visually and inspire active interpretation. However, due to their complex semantic nature, Storytelling Images are inherently challenging to create, and thus remain relatively scarce. To address this challenge, we introduce the Storytelling Image Generation task, which explores how generative AI models can be leveraged to create such images. Specifically, we propose a two-stage pipeline, StorytellingPainter, which combines the creative reasoning abilities of Large Language Models (LLMs) with the visual synthesis capabilities of Text-to-Image (T2I) models to generate Storytelling Images. Alongside this pipeline, we develop a dedicated evaluation framework comprising three main evaluators: a Semantic Complexity Evaluator, a KNN-based Diversity Evaluator and a Story-Image Alignment Evaluator. Given the critical role of story generation in the Storytelling Image Generation task and the performance disparity between open-source and proprietary LLMs, we further explore tailored training strategies to reduce this gap, resulting in a series of lightweight yet effective models named Mini-Storytellers. Experimental results demonstrate the feasibility and effectiveness of our approaches. The code is available at https://github.com/xiujiesong/StorytellingImageGeneration. - oai:arXiv.org:2512.07198v1 + Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning + https://arxiv.org/abs/2505.17097 + arXiv:2505.17097v3 Announce Type: replace +Abstract: Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However, ICL performance remains unstable even when the in-context demonstrations (ICDs) are well matched, showing that LVLMs still struggle to make full use of the provided context. While existing work mainly focuses on prompt engineering or post-hoc logit calibration, we study the attention mechanisms inside LVLMs to address their inherent limitations. We identify two important weaknesses in their self-attention that hinder effective ICL. To address these weaknesses, we propose \textbf{Context-Aware Modulated Attention} (CAMA), a training-free and plug-and-play method that dynamically adjusts attention logits based on the input in-context sequence. CAMA uses a two-stage modulation process that strengthens attention to semantically important tokens, especially visual ones. Across four LVLMs and seven benchmarks, CAMA consistently outperforms vanilla models and baselines, showing clear effectiveness and generalization. It can also activate the intended benefits of prompt engineering methods and remains robust across different sequence configurations. Therefore, CAMA opens up new directions for improving multimodal reasoning through a deeper understanding of attention dynamics. + oai:arXiv.org:2505.17097v3 cs.CV cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiujie Song, Qi Jia, Shota Watanabe, Xiaoyi Pang, Ruijie Chen, Mengyue Wu, Kenny Q. Zhu + Yanshu Li, Jianjiang Yang, Ziteng Yang, Bozheng Li, Ligong Han, Hongyang He, Zhengtao Yao, Yingjie Victor Chen, Songlin Fei, Dongfang Liu, Ruixiang Tang - Less is More: Non-uniform Road Segments are Efficient for Bus Arrival Prediction - https://arxiv.org/abs/2512.07200 - arXiv:2512.07200v1 Announce Type: new -Abstract: In bus arrival time prediction, the process of organizing road infrastructure network data into homogeneous entities is known as segmentation. Segmenting a road network is widely recognized as the first and most critical step in developing an arrival time prediction system, particularly for auto-regressive-based approaches. Traditional methods typically employ a uniform segmentation strategy, which fails to account for varying physical constraints along roads, such as road conditions, intersections, and points of interest, thereby limiting prediction efficiency. In this paper, we propose a Reinforcement Learning (RL)-based approach to efficiently and adaptively learn non-uniform road segments for arrival time prediction. Our method decouples the prediction process into two stages: 1) Non-uniform road segments are extracted based on their impact scores using the proposed RL framework; and 2) A linear prediction model is applied to the selected segments to make predictions. This method ensures optimal segment selection while maintaining computational efficiency, offering a significant improvement over traditional uniform approaches. Furthermore, our experimental results suggest that the linear approach can even achieve better performance than more complex methods. Extensive experiments demonstrate the superiority of the proposed method, which not only enhances efficiency but also improves learning performance on large-scale benchmarks. The dataset and the code are publicly accessible at: https://github.com/pangjunbiao/Less-is-More. - oai:arXiv.org:2512.07200v1 + Understanding the Implicit Regularization of Gradient Descent in Over-parameterized Models + https://arxiv.org/abs/2505.17304 + arXiv:2505.17304v2 Announce Type: replace +Abstract: Implicit regularization refers to the tendency of local search algorithms to converge to low-dimensional solutions, even when such structures are not explicitly enforced. Despite its ubiquity, the mechanism underlying this behavior remains poorly understood, particularly in over-parameterized settings. We analyze gradient descent dynamics and identify three conditions under which it converges to second-order stationary points within an implicit low-dimensional region: (i) suitable initialization, (ii) efficient escape from saddle points, and (iii) sustained proximity to the region. We show that these can be achieved through infinitesimal perturbations and a small deviation rate. Building on this, we introduce Infinitesimally Perturbed Gradient Descent (IPGD), which satisfies these conditions under mild assumptions. We provide theoretical guarantees for IPGD in over-parameterized matrix sensing and empirical evidence of its broader applicability. + oai:arXiv.org:2505.17304v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhen Huang, Jiaxin Deng, Jiayu Xu, Junbiao Pang, Haitao Yu + Jianhao Ma, Geyu Liang, Salar Fattahi - Understanding Diffusion Models via Code Execution - https://arxiv.org/abs/2512.07201 - arXiv:2512.07201v1 Announce Type: new -Abstract: Diffusion models have achieved remarkable performance in generative modeling, yet their theoretical foundations are often intricate, and the gap between mathematical formulations in papers and practical open-source implementations can be difficult to bridge. Existing tutorials primarily focus on deriving equations, offering limited guidance on how diffusion models actually operate in code. To address this, we present a concise implementation of approximately 300 lines that explains diffusion models from a code-execution perspective. Our minimal example preserves the essential components -- including forward diffusion, reverse sampling, the noise-prediction network, and the training loop -- while removing unnecessary engineering details. This technical report aims to provide researchers with a clear, implementation-first understanding of how diffusion models work in practice and how code and theory correspond. Our code and pre-trained models are available at: https://github.com/disanda/GM/tree/main/DDPM-DDIM-ClassifierFree. - oai:arXiv.org:2512.07201v1 + The Missing Point in Vision Transformers for Universal Image Segmentation + https://arxiv.org/abs/2505.19795 + arXiv:2505.19795v2 Announce Type: replace +Abstract: Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately classifying these masks, especially in the presence of ambiguous boundaries and imbalanced class distributions, remains an open challenge. In this work, we introduce ViT-P, a novel two-stage segmentation framework that decouples mask generation from classification. The first stage employs a proposal generator to produce class-agnostic mask proposals, while the second stage utilizes a point-based classification model built on the Vision Transformer (ViT) to refine predictions by focusing on mask central points. ViT-P serves as a pre-training-free adapter, allowing the integration of various pre-trained vision transformers without modifying their architecture, ensuring adaptability to dense prediction tasks. Furthermore, we demonstrate that coarse and bounding box annotations can effectively enhance classification without requiring additional training on fine annotation datasets, reducing annotation costs while maintaining strong performance. Extensive experiments across COCO, ADE20K, and Cityscapes datasets validate the effectiveness of ViT-P, achieving state-of-the-art results with 54.0 PQ on ADE20K panoptic segmentation, 87.4 mIoU on Cityscapes semantic segmentation, and 63.6 mIoU on ADE20K semantic segmentation. The code and pretrained models are available at: https://github.com/sajjad-sh33/ViT-P}{https://github.com/sajjad-sh33/ViT-P. + oai:arXiv.org:2505.19795v2 cs.CV + cs.AI cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Cheng Yu + eess.IV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Sajjad Shahabodini, Mobina Mansoori, Farnoush Bayatmakou, Jamshid Abouei, Konstantinos N. Plataniotis, Arash Mohammadi - MMRPT: MultiModal Reinforcement Pre-Training via Masked Vision-Dependent Reasoning - https://arxiv.org/abs/2512.07203 - arXiv:2512.07203v1 Announce Type: new -Abstract: Multimodal pre-training remains constrained by the descriptive bias of image-caption pairs, leading models to favor surface linguistic cues over grounded visual understanding. We introduce MMRPT, a masked multimodal reinforcement pre-training framework that strengthens visual reasoning in MLLMs. We are the first to incorporate reinforcement learning directly into the pre-training of large vision-language models, enabling learning signals that reward visual grounding rather than caption imitation. MMRPT constructs masked multimodal data by estimating sentence-level visual dependency via attention over visual tokens and masking highly vision-dependent segments; the model reconstructs these spans through vision-grounded reasoning guided by a semantic-visual reward. Experiments show consistent zero-shot gains across diverse benchmarks and substantially improved robustness under supervised fine-tuning, demonstrating that reinforcement-driven masked reasoning provides a more reliable and generalizable pre-training objective for multimodal models. - oai:arXiv.org:2512.07203v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuhui Zheng, Kang An, Ziliang Wang, Yuhang Wang, Faqiang Qian, Yichao Wu + Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction + https://arxiv.org/abs/2505.20589 + arXiv:2505.20589v2 Announce Type: replace +Abstract: The diverse nature of protein prediction tasks has traditionally necessitated specialized models, hindering the development of broadly applicable and computationally efficient Protein Language Models (PLMs). In this work, we introduce Prot2Token, a unified framework that overcomes these challenges by converting a wide spectrum of protein-related predictions-from sequence-level properties and residue-specific attributes to complex inter-protein interactions-into a standardized next-token prediction format. At its core, Prot2Token employs an autoregressive decoder, conditioned on embeddings from pre-trained protein encoders and guided by learnable task tokens, to perform diverse predictions. This architecture uniquely facilitates multi-task learning, enabling general-purpose decoders to generalize across five distinct categories. We present extensive experimental validation across a variety of benchmarks, demonstrating Prot2Token's predictive power in different types of protein-prediction tasks. In 3D structure prediction, Prot2Token delivers substantial speedups (up to 1000x faster than AlphaFold2 with MSA on the same hardware) while, across other numerous tasks, matching or surpassing specialized methods. Beyond that, we introduce an auxiliary self-supervised decoder pre-training approach to improve spatially sensitive task performance. Prot2Token thus offers a step towards standardizing biological prediction into a generative interface, promising to accelerate biological discovery and the development of novel therapeutics. The code is available at https://github.com/mahdip72/prot2token . + oai:arXiv.org:2505.20589v2 + cs.LG + q-bio.QM + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Mahdi Pourmirzaei, Farzaneh Esmaili, Salhuldin Alqarghuli, Mohammadreza Pourmirzaei, Ye Han, Kai Chen, Mohsen Rezaei, Duolin Wang, Dong Xu - AutoLugano: A Deep Learning Framework for Fully Automated Lymphoma Segmentation and Lugano Staging on FDG-PET/CT - https://arxiv.org/abs/2512.07206 - arXiv:2512.07206v1 Announce Type: new -Abstract: Purpose: To develop a fully automated deep learning system, AutoLugano, for end-to-end lymphoma classification by performing lesion segmentation, anatomical localization, and automated Lugano staging from baseline FDG-PET/CT scans. Methods: The AutoLugano system processes baseline FDG-PET/CT scans through three sequential modules:(1) Anatomy-Informed Lesion Segmentation, a 3D nnU-Net model, trained on multi-channel inputs, performs automated lesion detection (2) Atlas-based Anatomical Localization, which leverages the TotalSegmentator toolkit to map segmented lesions to 21 predefined lymph node regions using deterministic anatomical rules; and (3) Automated Lugano Staging, where the spatial distribution of involved regions is translated into Lugano stages and therapeutic groups (Limited vs. Advanced Stage).The system was trained on the public autoPET dataset (n=1,007) and externally validated on an independent cohort of 67 patients. Performance was assessed using accuracy, sensitivity, specificity, F1-scorefor regional involvement detection and staging agreement. Results: On the external validation set, the proposed model demonstrated robust performance, achieving an overall accuracy of 88.31%, sensitivity of 74.47%, Specificity of 94.21% and an F1-score of 80.80% for regional involvement detection,outperforming baseline models. Most notably, for the critical clinical task of therapeutic stratification (Limited vs. Advanced Stage), the system achieved a high accuracy of 85.07%, with a specificity of 90.48% and a sensitivity of 82.61%.Conclusion: AutoLugano represents the first fully automated, end-to-end pipeline that translates a single baseline FDG-PET/CT scan into a complete Lugano stage. This study demonstrates its strong potential to assist in initial staging, treatment stratification, and supporting clinical decision-making. - oai:arXiv.org:2512.07206v1 - cs.CV + OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities + https://arxiv.org/abs/2505.23856 + arXiv:2505.23856v2 Announce Type: replace +Abstract: The emerging capabilities of large language models (LLMs) have sparked concerns about their immediate potential for harmful misuse. The core approach to mitigate these concerns is the detection of harmful queries to the model. Current detection approaches are fallible, and are particularly susceptible to attacks that exploit mismatched generalization of model capabilities (e.g., prompts in low-resource languages or prompts provided in non-text modalities such as image and audio). To tackle this challenge, we propose Omniguard, an approach for detecting harmful prompts across languages and modalities. Our approach (i) identifies internal representations of an LLM/MLLM that are aligned across languages or modalities and then (ii) uses them to build a language-agnostic or modality-agnostic classifier for detecting harmful prompts. Omniguard improves harmful prompt classification accuracy by 11.57\% over the strongest baseline in a multilingual setting, by 20.44\% for image-based prompts, and sets a new SOTA for audio-based prompts. By repurposing embeddings computed during generation, Omniguard is also very efficient ($\approx\!120 \times$ faster than the next fastest baseline). Code and data are available at: https://github.com/vsahil/OmniGuard. + oai:arXiv.org:2505.23856v2 + cs.CL + cs.AI + cs.HC cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Boyang Pan, Zeyu Zhang, Hongyu Meng, Bin Cui, Yingying Zhang, Wenli Hou, Junhao Li, Langdi Zhong, Xiaoxiao Chen, Xiaoyu Xu, Changjin Zuo, Chao Cheng, Nan-Jie Gong + Sahil Verma, Keegan Hines, Jeff Bilmes, Charlotte Siska, Luke Zettlemoyer, Hila Gonen, Chandan Singh + + + 50 Years of Automated Face Recognition + https://arxiv.org/abs/2505.24247 + arXiv:2505.24247v3 Announce Type: replace +Abstract: Over the past five decades, automated face recognition (FR) has progressed from handcrafted geometric and statistical approaches to advanced deep learning architectures that now approach, and in many cases exceed, human performance. This paper traces the historical and technological evolution of FR, encompassing early algorithmic paradigms through to contemporary neural systems trained on extensive real and synthetically generated datasets. We examine pivotal innovations that have driven this progression, including advances in dataset construction, loss function formulation, network architecture design, and feature fusion strategies. Furthermore, we analyze the relationship between data scale, diversity, and model generalization, highlighting how dataset expansion correlates with benchmark performance gains. Recent systems have achieved near-perfect large-scale identification accuracy, with the leading algorithm in the latest NIST FRTE 1:N benchmark reporting a FNIR of 0.15 percent at FPIR of 0.001 on a gallery of over 10 million identities. We delineate key open problems and emerging directions, including scalable training, multi-modal fusion, synthetic data, and interpretable recognition frameworks. + oai:arXiv.org:2505.24247v3 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Minchul Kim, Anil Jain, Xiaoming Liu - Geometric Prior-Guided Federated Prompt Calibration - https://arxiv.org/abs/2512.07208 - arXiv:2512.07208v1 Announce Type: new -Abstract: Federated Prompt Learning (FPL) offers a parameter-efficient solution for collaboratively training large models, but its performance is severely hindered by data heterogeneity, which causes locally trained prompts to become biased. Existing methods, focusing on aggregation or regularization, fail to address this root cause of local training bias. To this end, we propose Geometry-Guided Text Prompt Calibration (GGTPC), a novel framework that directly corrects this bias by providing clients with a global geometric prior. This prior, representing the shape of the global data distribution derived from the covariance matrix, is reconstructed on the server in a privacy-preserving manner. Clients then use a novel Geometry-Prior Calibration Layer (GPCL) to align their local feature distributions with this global prior during training. Extensive experiments show GGTPC's effectiveness. On the label-skewed CIFAR-100 dataset ($\beta$=0.1), it outperforms the state-of-the-art by 2.15\%. Under extreme skew ($\beta$=0.01), it improves upon the baseline by 9.17\%. Furthermore, as a plug-and-play module on the domain-skewed Office-Home dataset, it boosts FedAvg's performance by 4.60\%. These results demonstrate that GGTPC effectively mitigates data heterogeneity by correcting the fundamental local training bias, serving as a versatile module to enhance various FL algorithms. - oai:arXiv.org:2512.07208v1 + Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting + https://arxiv.org/abs/2505.24511 + arXiv:2505.24511v3 Announce Type: replace +Abstract: Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling. Despite their effectiveness, these methods often follow a fast thinking paradigm emphasizing pattern extraction and direct value mapping, while overlooking explicit reasoning over temporal dynamics and contextual dependencies. Meanwhile, emerging slow-thinking LLMs (e.g., ChatGPT-o1, DeepSeek-R1) have demonstrated impressive multi-step reasoning capabilities across diverse domains, suggesting a new opportunity for reframing TSF as a structured reasoning task. This motivates a key question: can slow-thinking LLMs effectively reason over temporal patterns to support time series forecasting, even in zero-shot manner? To investigate this, in this paper, we propose TimeReasoner, an extensive empirical study that formulates TSF as a conditional reasoning task. We design a series of prompting strategies to elicit inference-time reasoning from pretrained slow-thinking LLMs and evaluate their performance across diverse TSF benchmarks. Our findings reveal that slow-thinking LLMs exhibit non-trivial zero-shot forecasting capabilities, especially in capturing high-level trends and contextual shifts. While preliminary, our study surfaces important insights into the reasoning behaviors of LLMs in temporal domains highlighting both their potential and limitations. We hope this work catalyzes further research into reasoning-based forecasting paradigms and paves the way toward more interpretable and generalizable TSF frameworks. + oai:arXiv.org:2505.24511v3 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Fei Luo, Ziwei Zhao, Mingxuan Wang, Duoyang Li, Zhe Qian, Jiayi Tuo, Chenyue Zhou, Yanbiao Ma + Mingyue Cheng, Jiahao Wang, Daoyu Wang, Xiaoyu Tao, Qi Liu, Enhong Chen - Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits - https://arxiv.org/abs/2512.07209 - arXiv:2512.07209v1 Announce Type: new -Abstract: We introduce a novel pipeline for joint audio-visual editing that enhances the coherence between edited video and its accompanying audio. Our approach first applies state-of-the-art video editing techniques to produce the target video, then performs audio editing to align with the visual changes. To achieve this, we present a new video-to-audio generation model that conditions on the source audio, target video, and a text prompt. We extend the model architecture to incorporate conditional audio input and propose a data augmentation strategy that improves training efficiency. Furthermore, our model dynamically adjusts the influence of the source audio based on the complexity of the edits, preserving the original audio structure where possible. Experimental results demonstrate that our method outperforms existing approaches in maintaining audio-visual alignment and content integrity. - oai:arXiv.org:2512.07209v1 - cs.MM + Bench4KE: Benchmarking Automated Competency Question Generation + https://arxiv.org/abs/2505.24554 + arXiv:2505.24554v3 Announce Type: replace +Abstract: The availability of Large Language Models (LLMs) presents a unique opportunity to reinvigorate research on Knowledge Engineering (KE) automation. This trend is already evident in recent efforts developing LLM-based methods and tools for the automatic generation of Competency Questions (CQs), natural language questions used by ontology engineers to define the functional requirements of an ontology. However, the evaluation of these tools lacks standardization. This undermines the methodological rigor and hinders the replication and comparison of results. To address this gap, we introduce Bench4KE, an extensible API-based benchmarking system for KE automation. The presented release focuses on evaluating tools that generate CQs automatically. Bench4KE provides a curated gold standard consisting of CQ datasets from 17 real-world ontology engineering projects and uses a suite of similarity metrics to assess the quality of the CQs generated. We present a comparative analysis of 6 recent CQ generation systems, which are based on LLMs, establishing a baseline for future research. Bench4KE is also designed to accommodate additional KE automation tasks, such as SPARQL query generation, ontology testing and drafting. Code and datasets are publicly available under the Apache 2.0 license. + oai:arXiv.org:2505.24554v3 + cs.CL + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Anna Sofia Lippolis, Minh Davide Ragagni, Paolo Ciancarini, Andrea Giovanni Nuzzolese, Valentina Presutti + + + Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence + https://arxiv.org/abs/2506.04053 + arXiv:2506.04053v3 Announce Type: replace +Abstract: Sliced Mutual Information (SMI) is widely used as a scalable alternative to mutual information for measuring non-linear statistical dependence. Despite its advantages, such as faster convergence, robustness to high dimensionality, and nullification only under statistical independence, we demonstrate that SMI is highly susceptible to data manipulation and exhibits counterintuitive behavior. Through extensive benchmarking and theoretical analysis, we show that SMI saturates easily, fails to detect increases in statistical dependence, prioritizes redundancy over informative content, and in some cases, performs worse than correlation coefficient. + oai:arXiv.org:2506.04053v3 cs.LG - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Masato Ishii, Akio Hayakawa, Takashi Shibuya, Yuki Mitsufuji + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Alexander Semenenko, Ivan Butakov, Alexey Frolov, Ivan Oseledets - Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Clouds - https://arxiv.org/abs/2512.07211 - arXiv:2512.07211v1 Announce Type: new -Abstract: Object pose estimation is crucial to robotic perception and typically provides a single-pose estimate. However, a single estimate cannot capture pose uncertainty deriving from visual ambiguity, which can lead to unreliable behavior. Existing pose distribution methods rely heavily on color information, often unavailable in industrial settings. - We propose a novel neural network-based method for estimating object pose uncertainty using only 3D colorless data. To the best of our knowledge, this is the first approach that leverages deep learning for pose distribution estimation without relying on RGB input. We validate our method in a real-world bin picking scenario with objects of varying geometric ambiguity. Our current implementation focuses on symmetries in reflection and revolution, but the framework is extendable to full SE(3) pose distribution estimation. Source code available at opde3d.github.io - oai:arXiv.org:2512.07211v1 + Enabling Validation for Robust Few-Shot Recognition + https://arxiv.org/abs/2506.04713 + arXiv:2506.04713v3 Announce Type: replace +Abstract: Few-Shot Recognition (FSR) tackles classification tasks by training with minimal task-specific labeled data. Prevailing methods adapt or finetune a pretrained Vision-Language Model (VLM) and augment the scarce training data by retrieving task-relevant but noisy samples from open data sources. The finetuned VLM generalizes decently well to the task-specific in-distribution (ID) test data but struggles with out-of-distribution (OOD) test data. This motivates our study of robust FSR with VLM finetuning. The core challenge of FSR is data scarcity, extending beyond limited training data to a complete lack of validation data. We identify a key paradox as a potential solution: repurposing the retrieved open data for validation. As such retrieved data are inherently OOD compared with the task-specific ID training data, finetuned VLMs yield degraded performance on the retrieved data. This causes the validation logic to favor the pretrained model without any finetuning, hindering improvements w.r.t generalization. To resolve this dilemma, we introduce a novel validation strategy that harmonizes performance gain and degradation on the few-shot ID data and the retrieved data, respectively. Our validation enables parameter selection for partial finetuning and checkpoint selection, mitigating overfitting and improving test-data generalization. We unify this strategy with robust learning into a cohesive framework: Validation-Enabled Stage-wise Tuning (VEST). Extensive experiments on the established ImageNet OOD benchmarks show that VEST significantly outperforms existing VLM adaptation methods, achieving state-of-the-art FSR performance on both ID and OOD data. + oai:arXiv.org:2506.04713v3 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Frederik Hagelskj{\ae}r, Dimitrios Arapis, Steffen Madsen, Thorbj{\o}rn Mosekj{\ae}r Iversen - - - Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation - https://arxiv.org/abs/2512.07212 - arXiv:2512.07212v1 Announce Type: new -Abstract: Imitation learning with diffusion models has advanced robotic control by capturing multi-modal action distributions. However, existing approaches typically treat observations as high-level conditioning inputs to the denoising network, rather than integrating them into the stochastic dynamics of the diffusion process itself. As a result, sampling must begin from random Gaussian noise, weakening the coupling between perception and control and often yielding suboptimal performance. We introduce BridgePolicy, a generative visuomotor policy that explicitly embeds observations within the stochastic differential equation via a diffusion-bridge formulation. By constructing an observation-informed trajectory, BridgePolicy enables sampling to start from a rich, informative prior rather than random noise, substantially improving precision and reliability in control. A key challenge is that classical diffusion bridges connect distributions with matched dimensionality, whereas robotic observations are heterogeneous and multi-modal and do not naturally align with the action space. To address this, we design a multi-modal fusion module and a semantic aligner that unify visual and state inputs and align observation and action representations, making the bridge applicable to heterogeneous robot data. Extensive experiments across 52 simulation tasks on three benchmarks and five real-world tasks demonstrate that BridgePolicy consistently outperforms state-of-the-art generative policies. - oai:arXiv.org:2512.07212v1 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Zhaoyang Liu, Mokai Pan, Zhongyi Wang, Kaizhen Zhu, Haotao Lu, Jingya Wang, Ye Shi + Hanxin Wang, Tian Liu, Shu Kong - VFM-VLM: Vision Foundation Model and Vision Language Model based Visual Comparison for 3D Pose Estimation - https://arxiv.org/abs/2512.07215 - arXiv:2512.07215v1 Announce Type: new -Abstract: Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and DINOv2 based approaches for 3D pose estimation in hand object grasping scenarios. We evaluate both models on the task of 6D object pose estimation and demonstrate their complementary strengths: CLIP excels in semantic understanding through language grounding, while DINOv2 provides superior dense geometric features. Through extensive experiments on benchmark datasets, we show that CLIP based methods achieve better semantic consistency, while DINOv2 based approaches demonstrate competitive performance with enhanced geometric precision. Our analysis provides insights for selecting appropriate vision models for robotic manipulation and grasping, picking applications. - oai:arXiv.org:2512.07215v1 + Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection + https://arxiv.org/abs/2506.05872 + arXiv:2506.05872v2 Announce Type: replace +Abstract: Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel objects with only a handful of labeled samples from previously unseen domains. While data augmentation and generative methods have shown promise in few-shot learning, their effectiveness for CD-FSOD remains unclear due to the need for both visual realism and domain alignment. Existing strategies, such as copy-paste augmentation and text-to-image generation, often fail to preserve the correct object category or produce backgrounds coherent with the target domain, making them non-trivial to apply directly to CD-FSOD. To address these challenges, we propose Domain-RAG, a training-free, retrieval-guided compositional image generation framework tailored for CD-FSOD. Domain-RAG consists of three stages: domain-aware background retrieval, domain-guided background generation, and foreground-background composition. Specifically, the input image is first decomposed into foreground and background regions. We then retrieve semantically and stylistically similar images to guide a generative model in synthesizing a new background, conditioned on both the original and retrieved contexts. Finally, the preserved foreground is composed with the newly generated domain-aligned background to form the generated image. Without requiring any additional supervision or training, Domain-RAG produces high-quality, domain-consistent samples across diverse tasks, including CD-FSOD, remote sensing FSOD, and camouflaged FSOD. Extensive experiments show consistent improvements over strong baselines and establish new state-of-the-art results. Codes will be released upon acceptance. + oai:arXiv.org:2506.05872v2 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Md Selim Sarowar, Sungho Kim + Yu Li, Xingyu Qiu, Yuqian Fu, Jie Chen, Tianwen Qian, Xu Zheng, Danda Pani Paudel, Yanwei Fu, Xuanjing Huang, Luc Van Gool, Yu-Gang Jiang - MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling - https://arxiv.org/abs/2512.07216 - arXiv:2512.07216v1 Announce Type: new -Abstract: Lifelong user interest modeling is crucial for industrial recommender systems, yet existing approaches rely predominantly on ID-based features, suffering from poor generalization on long-tail items and limited semantic expressiveness. While recent work explores multimodal representations for behavior retrieval in the General Search Unit (GSU), they often neglect multimodal integration in the fine-grained modeling stage -- the Exact Search Unit (ESU). In this work, we present a systematic analysis of how to effectively leverage multimodal signals across both stages of the two-stage lifelong modeling framework. Our key insight is that simplicity suffices in the GSU: lightweight cosine similarity with high-quality multimodal embeddings outperforms complex retrieval mechanisms. In contrast, the ESU demands richer multimodal sequence modeling and effective ID-multimodal fusion to unlock its full potential. Guided by these principles, we propose MUSE, a simple yet effective multimodal search-based framework. MUSE has been deployed in Taobao display advertising system, enabling 100K-length user behavior sequence modeling and delivering significant gains in top-line metrics with negligible online latency overhead. To foster community research, we share industrial deployment practices and open-source the first large-scale dataset featuring ultra-long behavior sequences paired with high-quality multimodal embeddings. Our code and data is available at https://taobao-mm.github.io. - oai:arXiv.org:2512.07216v1 - cs.IR + Schauder Bases for $C[0, 1]$ Using ReLU, Softplus and Two Sigmoidal Functions + https://arxiv.org/abs/2506.07884 + arXiv:2506.07884v2 Announce Type: replace +Abstract: We construct four Schauder bases for the space $C[0,1]$, one using ReLU functions, another using Softplus functions, and two more using sigmoidal versions of the ReLU and Softplus functions. This establishes the existence of a basis using these functions for the first time, and improves on the universal approximation property associated with them. We also show an $O(\frac{1}{n})$ approximation bound based on our ReLU basis, and a negative result on constructing multivariate functions using finite combinations of ReLU functions. + oai:arXiv.org:2506.07884v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + math.FA + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Bin Wu, Feifan Yang, Zhangming Chan, Yu-Ran Gu, Jiawei Feng, Chao Yi, Xiang-Rong Sheng, Han Zhu, Jian Xu, Mang Ye, Bo Zheng + Transactions on Machine Learning Research, November 2025 + Anand Ganesh, Babhrubahan Bose, Anand Rajagopalan - NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models - https://arxiv.org/abs/2512.07218 - arXiv:2512.07218v1 Announce Type: new -Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, temporal reasoning, particularly under complex temporal constraints, remains a major challenge. To this end, existing approaches have explored symbolic methods, which encode temporal structure explicitly, and reflective mechanisms, which revise reasoning errors through multi-step inference. Nonetheless, symbolic approaches often underutilize the reasoning capabilities of LLMs, while reflective methods typically lack structured temporal representations, which can result in inconsistent or hallucinated reasoning. As a result, even when the correct temporal context is available, LLMs may still misinterpret or misapply time-related information, leading to incomplete or inaccurate answers. To address these limitations, in this work, we propose Neuro-Symbolic Temporal Reasoning (NeSTR), a novel framework that integrates structured symbolic representations with hybrid reflective reasoning to enhance the temporal sensitivity of LLM inference. NeSTR preserves explicit temporal relations through symbolic encoding, enforces logical consistency via verification, and corrects flawed inferences using abductive reflection. Extensive experiments on diverse temporal question answering benchmarks demonstrate that NeSTR achieves superior zero-shot performance and consistently improves temporal reasoning without any fine-tuning, showcasing the advantage of neuro-symbolic integration in enhancing temporal understanding in large language models. - oai:arXiv.org:2512.07218v1 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Feng Liang, Weixin Zeng, Runhao Zhao, Xiang Zhao + MBTModelGenerator: Automated Reverse Engineering of Test Models from Clickstream Data for Model-Based Testing of Web Applications + https://arxiv.org/abs/2506.08179 + arXiv:2506.08179v2 Announce Type: replace +Abstract: Context: Model-Based Testing (MBT) was first introduced in 1970's, and has the potential to improve efficiency and effectiveness of testing. However, its adoption-especially for web applications-has been hindered by the effort required to manually design MBT models, and keep them updated. -- Objective: Based on the above challenge in a real industrial context, this study introduces an automated approach to reduce that effort by reverse engineering MBT models from clickstream data captured during users' interaction with web applications. -- Method: We have developed and present in this paper an open-source tool, named MBTModelGenerator, which logs user interactions via a lightweight JavaScript module in the front-end, and transmits them to a REST API backend. These interactions are then transformed into directly executable MBT models in the input format of an open-source MBT tool named GraphWalker. -- Results: The tool was evaluated on two representative open-source web applications, Spring PetClinic and a Task Manager web app, and is under evaluation in several large-scale industrial testing projects. The generated MBT models accurately reflected user navigation flows and could be executed in the GraphWalker MBT tool without any manual changes. Using the tool has significantly reduced the effort of MBT model design by more than 90%, while still allowing test engineers to inspect and refine the generated models for completeness. -- Conclusion: Our approach facilitates lightweight adoption of MBT by automating model generation, which is the most effort intensive phase of MBT. To ensure correctness and completeness, the generated models should still be reviewed by test engineers -but that effort remains substantially lower than designing MBT models from scratch. The tool is in active industrial use and available as open-source for reuse and further development. + oai:arXiv.org:2506.08179v2 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Vahid Garousi, Alper Bu\u{g}ra Kele\c{s}, Yunus Balaman, Sasidhar Matta, Zafar Jafarov, Aytan M\"ovs\"umova, Atif Namazov - Characterizing Lane-Changing Behavior in Mixed Traffic - https://arxiv.org/abs/2512.07219 - arXiv:2512.07219v1 Announce Type: new -Abstract: Characterizing and understanding lane-changing behavior in the presence of automated vehicles (AVs) is crucial to ensuring safety and efficiency in mixed traffic. Accordingly, this study aims to characterize the interactions between the lane-changing vehicle (active vehicle) and the vehicle directly impacted by the maneuver in the target lane (passive vehicle). Utilizing real-world trajectory data from the Waymo Open Motion Dataset (WOMD), this study explores patterns in lane-changing behavior and provides insight into how these behaviors evolve under different AV market penetration rates (MPRs). In particular, we propose a game-theoretic framework to analyze cooperative and defective behaviors in mixed traffic, applied to the 7,636 observed lane-changing events in the WOMD. First, we utilize k-means clustering to classify vehicles as cooperative or defective, revealing that the proportions of cooperative AVs are higher than those of HDVs in both active and passive roles. Next, we jointly estimate the utilities of active and passive vehicles to model their behaviors using the quantal response equilibrium framework. Empirical payoff tables are then constructed based on these utilities. Using these payoffs, we analyze the presence of social dilemmas and examine the evolution of cooperative behaviors using evolutionary game theory. Our results reveal the presence of social dilemmas in approximately 4% and 11% of lane-changing events for active and passive vehicles, respectively, with most classified as Stag Hunt or Prisoner's Dilemma (Chicken Game rarely observed). Moreover, the Monte Carlo simulation results show that repeated lane-changing interactions consistently lead to increased cooperative behavior over time, regardless of the AV penetration rate. - oai:arXiv.org:2512.07219v1 - cs.MA - cs.GT - cs.RO + Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing + https://arxiv.org/abs/2506.11180 + arXiv:2506.11180v2 Announce Type: replace +Abstract: Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often results in representations that are not easily accessible to Large Language Models (LLMs). In this work-in-progress paper, we present an alternative approach based on the recently introduced Model Context Protocol (MCP). MCP allows systems to expose functionality through a standardized interface that is directly consumable by LLM-based agents. We conduct a prototypical evaluation on a laboratory-scale manufacturing system, where resource functions are made available via MCP. A general-purpose LLM is then tasked with planning and executing a multi-step process, including constraint handling and the invocation of resource functions via MCP. The results indicate that such an approach can enable flexible industrial automation without relying on explicit semantic models. This work lays the basis for further exploration of external tool integration in LLM-driven production systems. + oai:arXiv.org:2506.11180v2 + cs.SE + cs.AI + cs.ET cs.SY eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sungyong Chung, Alireza Talebpour, Samer H. Hamdar + 10.1109/ETFA65518.2025.11205601 + Luis Miguel Vieira da Silva, Aljosha K\"ocher, Felix Gehlhoff - Spatiotemporal Calibration and Ground Truth Estimation for High-Precision SLAM Benchmarking in Extended Reality - https://arxiv.org/abs/2512.07221 - arXiv:2512.07221v1 Announce Type: new -Abstract: Simultaneous localization and mapping (SLAM) plays a fundamental role in extended reality (XR) applications. As the standards for immersion in XR continue to increase, the demands for SLAM benchmarking have become more stringent. Trajectory accuracy is the key metric, and marker-based optical motion capture (MoCap) systems are widely used to generate ground truth (GT) because of their drift-free and relatively accurate measurements. However, the precision of MoCap-based GT is limited by two factors: the spatiotemporal calibration with the device under test (DUT) and the inherent jitter in the MoCap measurements. These limitations hinder accurate SLAM benchmarking, particularly for key metrics like rotation error and inter-frame jitter, which are critical for immersive XR experiences. This paper presents a novel continuous-time maximum likelihood estimator to address these challenges. The proposed method integrates auxiliary inertial measurement unit (IMU) data to compensate for MoCap jitter. Additionally, a variable time synchronization method and a pose residual based on screw congruence constraints are proposed, enabling precise spatiotemporal calibration across multiple sensors and the DUT. Experimental results demonstrate that our approach outperforms existing methods, achieving the precision necessary for comprehensive benchmarking of state-of-the-art SLAM algorithms in XR applications. Furthermore, we thoroughly validate the practicality of our method by benchmarking several leading XR devices and open-source SLAM algorithms. The code is publicly available at https://github.com/ylab-xrpg/xr-hpgt. - oai:arXiv.org:2512.07221v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new + PRO-V-R1: Reasoning Enhanced Programming Agent for RTL Verification + https://arxiv.org/abs/2506.12200 + arXiv:2506.12200v4 Announce Type: replace +Abstract: Register-Transfer Level (RTL) verification is a primary bottleneck, consuming 60-70% of development time. While Large Language Models (LLMs) show promise for RTL automation, their performance and research focus have overwhelmingly centered on RTL generation rather than verification. Current methods for RTL verification rely on large scale proprietary models (e.g., GPT-4o) to generate Python-based functional references, incurring a high cost and raising data-privacy risks. To date, an end-to-end open-source solution for autonomous verification remains absent. + We introduce PRO-V-R1, the first trainable open-source agentic framework for autonomous RTL verification. Our contributions are threefold: (1) we design PRO-V sys, a modular agentic system that couples LLM-based reasoning with programmatic tool use for RTL verification; (2) we establish a data construction pipeline that leverages existing RTL datasets to build simulation-validated, expert-level trajectories tailored for supervised fine-tuning (SFT) RTL verification agents; and (3) we implement an efficient reinforcement learning (RL) algorithm that uses verification-specific rewards derived from program-tool feedback to optimize the end-to-end verification workflow. Our empirical evaluation demonstrates PRO-V-R1 achieves a 57.7% functional correctness rate and 34.0% in robust fault detection, significantly outperforming the base model's 25.7% and 21.8% (respectively) from the state-of-the-art (SOTA) automatic verification system. This configuration also outperforms large-scale proprietary LLMs in functional correctness and shows comparable robustness for fault detection. + oai:arXiv.org:2506.12200v4 + cs.AI + cs.AR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Zichao Shu, Shitao Bei, Lijun Li, Zetao Chen + Yujie Zhao, Zhijing Wu, Boqin Yuan, Zhongming Yu, Hejia Zhang, Wentao Ni, Chia-Tung Ho, Haoxing Ren, Jishen Zhao - Pay Less Attention to Function Words for Free Robustness of Vision-Language Models - https://arxiv.org/abs/2512.07222 - arXiv:2512.07222v1 Announce Type: new -Abstract: To address the trade-off between robustness and performance for robust VLM, we observe that function words could incur vulnerability of VLMs against cross-modal adversarial attacks, and propose Function-word De-Attention (FDA) accordingly to mitigate the impact of function words. Similar to differential amplifiers, our FDA calculates the original and the function-word cross-attention within attention heads, and differentially subtracts the latter from the former for more aligned and robust VLMs. Comprehensive experiments include 2 SOTA baselines under 6 different attacks on 2 downstream tasks, 3 datasets, and 3 models. Overall, our FDA yields an average 18/13/53% ASR drop with only 0.2/0.3/0.6% performance drops on the 3 tested models on retrieval, and a 90% ASR drop with a 0.3% performance gain on visual grounding. We demonstrate the scalability, generalization, and zero-shot performance of FDA experimentally, as well as in-depth ablation studies and analysis. Code will be made publicly at https://github.com/michaeltian108/FDA. - oai:arXiv.org:2512.07222v1 + Knowledge Adaptation as Posterior Correction + https://arxiv.org/abs/2506.14262 + arXiv:2506.14262v3 Announce Type: replace +Abstract: Adaptation is the holy grail of intelligence, but even the best AI models lack the adaptability of toddlers. In spite of great progress, little is known about the mechanisms by which machines can learn to adapt as fast as humans and animals. Here, we cast adaptation as `correction' of old posteriors and show that a wide-variety of existing adaptation methods follow this very principle, including those used for continual learning, federated learning, unlearning, and model merging. In all these settings, more accurate posteriors often lead to smaller corrections and can enable faster adaptation. Posterior correction is derived by using the dual representation of the Bayesian Learning Rule of Khan and Rue (2023), where the interference between the old representation and new information is quantified by using the natural-gradient mismatch. We present many examples demonstrating how machines can learn to adapt quickly by using posterior correction. + oai:arXiv.org:2506.14262v3 cs.LG - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.AI + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen + Mohammad Emtiyaz Khan - Towards Robust Protective Perturbation against DeepFake Face Swapping - https://arxiv.org/abs/2512.07228 - arXiv:2512.07228v1 Announce Type: new -Abstract: DeepFake face swapping enables highly realistic identity forgeries, posing serious privacy and security risks. A common defence embeds invisible perturbations into images, but these are fragile and often destroyed by basic transformations such as compression or resizing. In this paper, we first conduct a systematic analysis of 30 transformations across six categories and show that protection robustness is highly sensitive to the choice of training transformations, making the standard Expectation over Transformation (EOT) with uniform sampling fundamentally suboptimal. Motivated by this, we propose Expectation Over Learned distribution of Transformation (EOLT), the framework to treat transformation distribution as a learnable component rather than a fixed design choice. Specifically, EOLT employs a policy network that learns to automatically prioritize critical transformations and adaptively generate instance-specific perturbations via reinforcement learning, enabling explicit modeling of defensive bottlenecks while maintaining broad transferability. Extensive experiments demonstrate that our method achieves substantial improvements over state-of-the-art approaches, with 26% higher average robustness and up to 30% gains on challenging transformation categories. - oai:arXiv.org:2512.07228v1 - cs.CV + Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models + https://arxiv.org/abs/2506.17114 + arXiv:2506.17114v4 Announce Type: replace +Abstract: Large reasoning models (e.g., R1, o3) have demonstrated remarkable mathematical problem-solving abilities. However, the high reported accuracy of these advanced models on popular datasets, reliance on purely numerical evaluation and potential benchmark leakage, often masks their true reasoning shortcomings. To address this, we propose leveraging the inherent rigor and methodological complexity of mathematical proofs as a diagnostic tool to expose these hidden failures. Specifically, we introduce the RFMDataset (Reveal Failure Modes), a collection of 200 diverse mathematical proof problems, and thoroughly evaluate advanced models' performance on it. Our in-depth analysis of their failures uncovers 10 fine-grained error types, which shows fundamental limitations in current large reasoning models: 1) large reasoning models grapple profoundly with mathematical proofs, with some generating entirely correct proofs for less than 20% of problems and failing even on basic ones; 2) models exhibit a diverse spectrum of reasoning failures, prominently demonstrating the lack of guarantees for the correctness and rigor of single-step reasoning; and 3) models show hallucination and incompleteness during the reasoning process. Our findings reveal that models' self-reflection is insufficient to resolve the current logical dilemmas, necessitating formalized and fine-grained logical training. + oai:arXiv.org:2506.17114v4 cs.AI - cs.CR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hengyang Yao, Lin Li, Ke Sun, Jianing Qiu, Huiping Chen + Dadi Guo, Jiayu Liu, Zhiyuan Fan, Zhitao He, Haoran Li, Yuxin Li, Yumeng Wang, Yi R. Fung - ReLKD: Inter-Class Relation Learning with Knowledge Distillation for Generalized Category Discovery - https://arxiv.org/abs/2512.07229 - arXiv:2512.07229v1 Announce Type: new -Abstract: Generalized Category Discovery (GCD) faces the challenge of categorizing unlabeled data containing both known and novel classes, given only labels for known classes. Previous studies often treat each class independently, neglecting the inherent inter-class relations. Obtaining such inter-class relations directly presents a significant challenge in real-world scenarios. To address this issue, we propose ReLKD, an end-to-end framework that effectively exploits implicit inter-class relations and leverages this knowledge to enhance the classification of novel classes. ReLKD comprises three key modules: a target-grained module for learning discriminative representations, a coarse-grained module for capturing hierarchical class relations, and a distillation module for transferring knowledge from the coarse-grained module to refine the target-grained module's representation learning. Extensive experiments on four datasets demonstrate the effectiveness of ReLKD, particularly in scenarios with limited labeled data. The code for ReLKD is available at https://github.com/ZhouF-ECNU/ReLKD. - oai:arXiv.org:2512.07229v1 + Co-Seg++: Mutual Prompt-Guided Collaborative Learning for Versatile Medical Segmentation + https://arxiv.org/abs/2506.17159 + arXiv:2506.17159v2 Announce Type: replace +Abstract: Medical image analysis is critical yet challenged by the need of jointly segmenting organs or tissues, and numerous instances for anatomical structures and tumor microenvironment analysis. Existing studies typically formulated different segmentation tasks in isolation, which overlooks the fundamental interdependencies between these tasks, leading to suboptimal segmentation performance and insufficient medical image understanding. To address this issue, we propose a Co-Seg++ framework for versatile medical segmentation. Specifically, we introduce a novel co-segmentation paradigm, allowing semantic and instance segmentation tasks to mutually enhance each other. We first devise a spatio-sequential prompt encoder (SSP-Encoder) to capture long-range spatial and sequential relationships between segmentation regions and image embeddings as prior spatial constraints. Moreover, we devise a multi-task collaborative decoder (MTC-Decoder) that leverages cross-guidance to strengthen the contextual consistency of both tasks, jointly computing semantic and instance segmentation masks. Extensive experiments on diverse CT and histopathology datasets demonstrate that the proposed Co-Seg++ outperforms state-of-the-arts in the semantic, instance, and panoptic segmentation of dental anatomical structures, histopathology tissues, and nuclei instances. The source code is available at https://github.com/xq141839/Co-Seg-Plus. + oai:arXiv.org:2506.17159v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fang Zhou, Zhiqiang Chen, Martin Pavlovski, Yizhong Zhang + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Qing Xu, Yuxiang Luo, Wenting Duan, Zhen Chen + + + Shrinking the Generation-Verification Gap with Weak Verifiers + https://arxiv.org/abs/2506.18203 + arXiv:2506.18203v2 Announce Type: replace +Abstract: Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM judges and reward models have become broadly useful as general-purpose verifiers, a significant performance gap remains between them and oracle verifiers (verifiers with perfect accuracy). To help close this gap, we introduce Weaver, a framework for designing a strong verifier by combining multiple weak, imperfect verifiers. We find weighted ensembles of verifiers, which typically require learning from labeled data, significantly outperform unweighted combinations due to differences in verifier accuracies. To reduce dependency on labeled data, Weaver leverages weak supervision to estimate each verifier's accuracy and combines outputs into a unified score that better reflects true response quality. However, directly applying weak supervision algorithms poses challenges, including inconsistent verifier output formats and handling low-quality verifiers. Weaver addresses these using dataset statistics to normalize outputs and filter specific verifiers. We study Weaver's effectiveness in test-time repeated sampling, where a model generates multiple candidate responses and selects one. Our evaluations show Weaver significantly improves over Pass@1-performance when selecting the first candidate-across reasoning and math tasks, achieving o3-mini-level accuracy with Llama 3.3 70B Instruct as generator, and an ensemble of 70B or smaller judge and reward models as verifiers (87.7% average). This gain mirrors the jump between GPT-4o and o3-mini (69.0% vs. 86.7%), which required extensive finetuning and post-training. To reduce computational costs of verifier ensembles, we train a 400M cross-encoder using Weaver's combined output scores. + oai:arXiv.org:2506.18203v2 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Jon Saad-Falcon, E. Kelly Buchanan, Mayee F. Chen, Tzu-Heng Huang, Brendan McLaughlin, Tanvir Bhathal, Shang Zhu, Ben Athiwaratkun, Frederic Sala, Scott Linderman, Azalia Mirhoseini, Christopher R\'e - STRinGS: Selective Text Refinement in Gaussian Splatting - https://arxiv.org/abs/2512.07230 - arXiv:2512.07230v1 Announce Type: new -Abstract: Text as signs, labels, or instructions is a critical element of real-world scenes as they can convey important contextual information. 3D representations such as 3D Gaussian Splatting (3DGS) struggle to preserve fine-grained text details, while achieving high visual fidelity. Small errors in textual element reconstruction can lead to significant semantic loss. We propose STRinGS, a text-aware, selective refinement framework to address this issue for 3DGS reconstruction. Our method treats text and non-text regions separately, refining text regions first and merging them with non-text regions later for full-scene optimization. STRinGS produces sharp, readable text even in challenging configurations. We introduce a text readability measure OCR Character Error Rate (CER) to evaluate the efficacy on text regions. STRinGS results in a 63.6% relative improvement over 3DGS at just 7K iterations. We also introduce a curated dataset STRinGS-360 with diverse text scenarios to evaluate text readability in 3D reconstruction. Our method and dataset together push the boundaries of 3D scene understanding in text-rich environments, paving the way for more robust text-aware reconstruction methods. - oai:arXiv.org:2512.07230v1 + End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards + https://arxiv.org/abs/2506.18331 + arXiv:2506.18331v4 Announce Type: replace +Abstract: While recent 3D generative models can produce high-quality texture images, they often fail to capture human preferences or meet task-specific requirements. Moreover, a core challenge in the 3D texture generation domain is that most existing approaches rely on repeated calls to 2D text-to-image generative models, which lack an inherent understanding of the 3D structure of the input 3D mesh object. To alleviate these issues, we propose an end-to-end differentiable, reinforcement-learning-free framework that embeds human feedback, expressed as differentiable reward functions, directly into the 3D texture synthesis pipeline. By back-propagating preference signals through both geometric and appearance modules of the proposed framework, our method generates textures that respect the 3D geometry structure and align with desired criteria. To demonstrate its versatility, we introduce three novel geometry-aware reward functions, which offer a more controllable and interpretable pathway for creating high-quality 3D content from natural language. By conducting qualitative, quantitative, and user-preference evaluations against state-of-the-art methods, we demonstrate that our proposed strategy consistently outperforms existing approaches. Our implementation code is publicly available at: https://github.com/AHHHZ975/Differentiable-Texture-Learning + oai:arXiv.org:2506.18331v4 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Abhinav Raundhal, Gaurav Behera, P J Narayanan, Ravi Kiran Sarvadevabhatla, Makarand Tapaswi + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + AmirHossein Zamani, Tianhao Xie, Amir G. Aghdam, Tiberiu Popa, Eugene Belilovsky - Cross-platform Product Matching Based on Entity Alignment of Knowledge Graph with RAEA model - https://arxiv.org/abs/2512.07232 - arXiv:2512.07232v1 Announce Type: new -Abstract: Product matching aims to identify identical or similar products sold on different platforms. By building knowledge graphs (KGs), the product matching problem can be converted to the Entity Alignment (EA) task, which aims to discover the equivalent entities from diverse KGs. The existing EA methods inadequately utilize both attribute triples and relation triples simultaneously, especially the interactions between them. This paper introduces a two-stage pipeline consisting of rough filter and fine filter to match products from eBay and Amazon. For fine filtering, a new framework for Entity Alignment, Relation-aware and Attribute-aware Graph Attention Networks for Entity Alignment (RAEA), is employed. RAEA focuses on the interactions between attribute triples and relation triples, where the entity representation aggregates the alignment signals from attributes and relations with Attribute-aware Entity Encoder and Relation-aware Graph Attention Networks. The experimental results indicate that the RAEA model achieves significant improvements over 12 baselines on EA task in the cross-lingual dataset DBP15K (6.59% on average Hits@1) and delivers competitive results in the monolingual dataset DWY100K. The source code for experiments on DBP15K and DWY100K is available at github (https://github.com/Mockingjay-liu/RAEA-model-for-Entity-Alignment). - oai:arXiv.org:2512.07232v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Towards an Oracle for Binary Decomposition Under Compilation Variance + https://arxiv.org/abs/2506.19425 + arXiv:2506.19425v2 Announce Type: replace +Abstract: Third-Party Library (TPL) detection, which identifies reused libraries in binary code, is critical for software security analysis. At its core, TPL detection depends on binary decomposition-the process of partitioning a monolithic binary into cohesive modules. Existing decomposition methods, whether anchor-based or clustering-based, fundamentally rely on the assumption that reused code exhibits similar function call relationships. However, this assumption is severely undermined by Function Call Graph (FCG) variations introduced by diverse compilation settings, particularly function inlining decisions that drastically alter FCG structures. In this work, we conduct the first systematic empirical study to establish the oracle for optimal binary decomposition under compilation variance. We first develop a labeling method to create precise FCG mappings on a comprehensive dataset compiled with 17 compilers, 6 optimizations, and 4 architectures; then, we identify the minimum semantic-equivalent function regions between FCG variants to derive the ground-truth decomposition. This oracle provides the first rigorous evaluation framework that quantitatively assesses decomposition algorithms under compilation variance. Using this oracle, we evaluate existing methods and expose their critical limitations: they either suffer from under-aggregation failure or over-aggregation failure. Our findings reveal that current decomposition techniques are inadequate for robust TPL detection, highlighting the urgent need for compilation-aware approaches. + oai:arXiv.org:2506.19425v2 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1007/s11280-022-01134-y - World Wide Web, vol. 26. no. 4, pp.2215-2235, 2023 - Wenlong Liu, Jiahua Pan, Xingyu Zhang, Xinxin Gong, Yang Ye, Xujin Zhao, Xin Wang, Kent Wu, Hua Xiang, Houmin Yan, Qingpeng Zhang + Ang Jia, He Jiang, Zhilei Ren, Xiaochen Li, Zhipeng Yang, Yaxin Duan, Ming Fan, Ting Liu - Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models - https://arxiv.org/abs/2512.07234 - arXiv:2512.07234v1 Announce Type: new -Abstract: Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the robustness of the vision-language models. Different from the vanilla dropout, we apply dropout on the tokens of the textual and visual branches, where we evaluate the token significance considering both intra-modal context and inter-modal alignment, enabling flexible dropout probabilities for each token. Moreover, to maintain semantic alignment for general knowledge transfer while encouraging the diverse representations that dropout introduces, we further propose residual entropy regularization. Experiments on 15 benchmarks show our method's effectiveness in challenging scenarios like low-shot learning, long-tail classification, and out-of-distribution generalization. Notably, our method surpasses regularization-based methods including KgCoOp by 5.10% and PromptSRC by 2.13% in performance on base-to-novel generalization. - oai:arXiv.org:2512.07234v1 - cs.CV + Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics + https://arxiv.org/abs/2506.20024 + arXiv:2506.20024v3 Announce Type: replace +Abstract: Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional complex systems predict future states individually. This approach struggles to model complex temporal dependencies and fails to explicitly account for the progressive growth of uncertainty inherent to the systems. While rolling diffusion frameworks, which apply increasing noise to forecasts at longer lead times, have been proposed to address this, their integration with state-of-the-art, high-fidelity diffusion techniques remains a significant challenge. We tackle this problem by introducing Elucidated Rolling Diffusion Models (ERDM), the first framework to successfully unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM). To do this, we adapt the core EDM components-its noise schedule, network preconditioning, and Heun sampler-to the rolling forecast setting. The success of this integration is driven by three key contributions: (i) a novel loss weighting scheme that focuses model capacity on the mid-range forecast horizons where determinism gives way to stochasticity; (ii) an efficient initialization strategy using a pre-trained EDM for the initial window; and (iii) a bespoke hybrid sequence architecture for robust spatiotemporal feature extraction under progressive denoising. On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5-degree resolution, ERDM consistently outperforms key diffusion-based baselines, including conditional autoregressive EDM. ERDM offers a flexible and powerful general framework for tackling diffusion-based dynamics forecasting problems where modeling uncertainty propagation is paramount. + oai:arXiv.org:2506.20024v3 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + physics.ao-ph + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Biao Chen, Lin Zuo, Mengmeng Jing, Kunbin He, Yuchen Wang + Advances in Neural Information Processing Systems (NeurIPS), 2025 + Salva R\"uhling Cachay, Miika Aittala, Karsten Kreis, Noah Brenowitz, Arash Vahdat, Morteza Mardani, Rose Yu - Unified Camera Positional Encoding for Controlled Video Generation - https://arxiv.org/abs/2512.07237 - arXiv:2512.07237v1 Announce Type: new -Abstract: Transformers have emerged as a universal backbone across 3D perception, video generation, and world models for autonomous driving and embodied AI, where understanding camera geometry is essential for grounding visual observations in three-dimensional space. However, existing camera encoding methods often rely on simplified pinhole assumptions, restricting generalization across the diverse intrinsics and lens distortions in real-world cameras. We introduce Relative Ray Encoding, a geometry-consistent representation that unifies complete camera information, including 6-DoF poses, intrinsics, and lens distortions. To evaluate its capability under diverse controllability demands, we adopt camera-controlled text-to-video generation as a testbed task. Within this setting, we further identify pitch and roll as two components effective for Absolute Orientation Encoding, enabling full control over the initial camera orientation. Together, these designs form UCPE (Unified Camera Positional Encoding), which integrates into a pretrained video Diffusion Transformer through a lightweight spatial attention adapter, adding less than 1% trainable parameters while achieving state-of-the-art camera controllability and visual fidelity. To facilitate systematic training and evaluation, we construct a large video dataset covering a wide range of camera motions and lens types. Extensive experiments validate the effectiveness of UCPE in camera-controllable video generation and highlight its potential as a general camera representation for Transformers across future multi-view, video, and 3D tasks. Code will be available at https://github.com/chengzhag/UCPE. - oai:arXiv.org:2512.07237v1 + Towards Explainable Bilingual Multimodal Misinformation Detection and Localization + https://arxiv.org/abs/2506.22930 + arXiv:2506.22930v3 Announce Type: replace +Abstract: The increasing realism of multimodal content has made misinformation more subtle and harder to detect, especially in news media where images are frequently paired with bilingual (e.g., Chinese-English) subtitles. Such content often includes localized image edits and cross-lingual inconsistencies that jointly distort meaning while remaining superficially plausible. We introduce BiMi, a bilingual multimodal framework that jointly performs region-level localization, cross-modal and cross-lingual consistency detection, and natural language explanation for misinformation analysis. To support generalization, BiMi integrates an online retrieval module that supplements model reasoning with up-to-date external context. We further release BiMiBench, a large-scale and comprehensive benchmark constructed by systematically editing real news images and subtitles, comprising 104,000 samples with realistic manipulations across visual and linguistic modalities. To enhance interpretability, we apply Group Relative Policy Optimization (GRPO) to improve explanation quality, marking the first use of GRPO in this domain. Extensive experiments demonstrate that BiMi outperforms strong baselines by up to +8.9 in classification accuracy, +15.9 in localization accuracy, and +2.5 in explanation BERTScore, advancing state-of-the-art performance in realistic, multilingual misinformation detection. Code, models, and datasets will be released. + oai:arXiv.org:2506.22930v3 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Cheng Zhang, Boying Li, Meng Wei, Yan-Pei Cao, Camilo Cruz Gambardella, Dinh Phung, Jianfei Cai + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yiwei He, Zhenglin Huang, Haiquan Wen, Tianxiao Li, Yi Dong, Hao Fei, Baoyuan Wu, Guangliang Cheng - A Diagrammatic Basis for Computer Programming - https://arxiv.org/abs/2512.07240 - arXiv:2512.07240v1 Announce Type: new -Abstract: Tape diagrams provide a convenient graphical notation for arrows of rig categories, i.e., categories equipped with two monoidal products, $\oplus$ and $\otimes$. In this work, we introduce Kleene-Cartesian rig categories, namely rig categories where $\otimes$ provides a Cartesian bicategory, while $\oplus$ a Kleene bicategory. We show that the associated tape diagrams can conveniently deal with imperative programs and various program logic. - oai:arXiv.org:2512.07240v1 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Filippo Bonchi, Alessandro Di Giorgio, Elena Di Lavore + Learning an Ensemble Token from Task-driven Priors in Facial Analysis + https://arxiv.org/abs/2507.01290 + arXiv:2507.01290v3 Announce Type: replace +Abstract: Facial analysis exhibits task-specific feature variations. While Convolutional Neural Networks (CNNs) have enabled the fine-grained representation of spatial information, Vision Transformers (ViTs) have facilitated the representation of semantic information at the patch level. While advances in backbone architectures have improved over the past decade, combining high-fidelity models often incurs computational costs on feature representation perspective. In this work, we introduce KT-Adapter, a novel methodology for learning knowledge token which enables the integration of high-fidelity feature representation in computationally efficient manner. Specifically, we propose a robust prior unification learning method that generates a knowledge token within a self-attention mechanism, sharing the mutual information across the pre-trained encoders. This knowledge token approach offers high efficiency with negligible computational cost. Our results show improved performance across facial analysis, with statistically significant enhancements observed in the feature representations. + oai:arXiv.org:2507.01290v3 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Sunyong Seo, Semin Kim, Jongha Lee - Squeezed-Eff-Net: Edge-Computed Boost of Tomography Based Brain Tumor Classification leveraging Hybrid Neural Network Architecture - https://arxiv.org/abs/2512.07241 - arXiv:2512.07241v1 Announce Type: new -Abstract: Brain tumors are one of the most common and dangerous neurological diseases which require a timely and correct diagnosis to provide the right treatment procedures. Even with the promotion of magnetic resonance imaging (MRI), the process of tumor delineation is difficult and time-consuming, which is prone to inter-observer error. In order to overcome these limitations, this work proposes a hybrid deep learning model based on SqueezeNet v1 which is a lightweight model, and EfficientNet-B0, which is a high-performing model, and is enhanced with handcrafted radiomic descriptors, including Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), Gabor filters and Wavelet transforms. The framework was trained and tested only on publicly available Nickparvar Brain Tumor MRI dataset, which consisted of 7,023 contrast-enhanced T1-weighted axial MRI slices which were categorized into four groups: glioma, meningioma, pituitary tumor, and no tumor. The testing accuracy of the model was 98.93% that reached a level of 99.08% with Test Time Augmentation (TTA) showing great generalization and power. The proposed hybrid network offers a compromise between computation efficiency and diagnostic accuracy compared to current deep learning structures and only has to be trained using fewer than 2.1 million parameters and less than 1.2 GFLOPs. The handcrafted feature addition allowed greater sensitivity in texture and the EfficientNet-B0 backbone represented intricate hierarchical features. The resulting model has almost clinical reliability in automated MRI-based classification of tumors highlighting its possibility of use in clinical decision-support systems. - oai:arXiv.org:2512.07241v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Scalable Differentially Private Sketches under Continual Observation + https://arxiv.org/abs/2507.03361 + arXiv:2507.03361v4 Announce Type: replace +Abstract: Linear sketches are fundamental tools in data stream analytics. They are notable for supporting both approximate frequency queries and heavy hitter detection with bounded trade-offs for error and memory. Importantly, on streams that contain sensitive information, linear sketches can be easily privatized with the injection of a suitable amount of noise. This process is efficient in the single release model, where the output is released only at the end of the stream. In this setting, it suffices to add noise to the sketch once. + In contrast, in the continual observation model, where the output is released at every time-step, fresh noise needs to be added to the sketch before each release. This creates an additional computational overhead. To address this, we introduce Lazy Sketch, a novel differentially private sketching method that employs lazy updates, perturbing and modifying only a small portion of the sketch at each step. Compared to prior work, we reduce the update complexity by a factor of $O(w)$, where $w$ is the width of the sketch. Experiments demonstrate that our method increases throughput by up to 250x over prior work, making continual observation differential privacy practical for high-speed streaming applications. + oai:arXiv.org:2507.03361v4 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Md. Srabon Chowdhury, Syeda Fahmida Tanzim, Sheekar Banerjee, Ishtiak Al Mamoon, AKM Muzahidul Islam + Rayne Holland - Function-Correcting Codes for Insertion-Deletion Channel - https://arxiv.org/abs/2512.07243 - arXiv:2512.07243v1 Announce Type: new -Abstract: In coding theory, handling errors that occur when symbols are inserted or deleted from a transmitted message is a long-standing challenge. Optimising redundancy for insertion and deletion channels remains a key open problem with significant importance for applications in DNA data storage and document exchange. Recently, a coding framework known as function-correcting codes has been proposed to address the challenge of minimising redundancy while preserving specific functions of the message. This framework has gained attention due to its potential applications in machine learning systems and long-term archival data storage. Motivated by the problem of redundancy optimisation for insertion and deletion channels, we propose a new framework called function-correcting codes for insdel channels. In this paper, we introduce the notions of function-correcting insertion codes, function-correcting deletion codes, and function-correcting insdel codes, and we show that these three formulations are equivalent. We then define insdel distance matrices and irregular insdel-distance codes, and derive lower and upper bounds on the optimal redundancy achievable by function-correcting codes for insdel channels. In addition, we establish Gilbert-Varshamov and Plotkin-like bounds on the length of irregular insdel-distance codes. Using the relation between optimal redundancy and the length of such codes, we obtain a simplified lower bound on optimal redundancy. Finally, we derive bounds on the optimal redundancy of function-correcting insdel codes for several classes of functions, including locally bounded functions, VT syndrome functions, the number-of-runs function, and the maximum-run-length function. - oai:arXiv.org:2512.07243v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new + Online Makespan Scheduling under Scenarios + https://arxiv.org/abs/2507.04016 + arXiv:2507.04016v2 Announce Type: replace +Abstract: We consider a natural extension of online makespan scheduling on identical parallel machines by introducing scenarios. A scenario is a subset of jobs, and the task of our problem is to find a global assignment of the jobs to machines so that the maximum makespan under a scenario, i.e., the maximum makespan of any schedule restricted to a scenario, is minimized. + For varying values of the number of scenarios and machines, we explore the competitiveness of online algorithms. We prove tight and near-tight bounds, several of which are achieved through novel constructions. In particular, we leverage the interplay between the unit processing time case of our problem and the hypergraph coloring problem both ways: We use hypergraph coloring techniques to steer an adversarial family of instances proving lower bounds, which in turn leads to lower bounds for several variants of online hypergraph coloring. + oai:arXiv.org:2507.04016v2 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Anamika Singh, Abhay Kumar Singh + Ekin Ergen - PINE: Pipeline for Important Node Exploration in Attributed Networks - https://arxiv.org/abs/2512.07244 - arXiv:2512.07244v1 Announce Type: new -Abstract: A graph with semantically attributed nodes are a common data structure in a wide range of domains. It could be interlinked web data or citation networks of scientific publications. The essential problem for such a data type is to determine nodes that carry greater importance than all the others, a task that markedly enhances system monitoring and management. Traditional methods to identify important nodes in networks introduce centrality measures, such as node degree or more complex PageRank. However, they consider only the network structure, neglecting the rich node attributes. Recent methods adopt neural networks capable of handling node features, but they require supervision. This work addresses the identified gap--the absence of approaches that are both unsupervised and attribute-aware--by introducing a Pipeline for Important Node Exploration (PINE). At the core of the proposed framework is an attention-based graph model that incorporates node semantic features in the learning process of identifying the structural graph properties. The PINE's node importance scores leverage the obtained attention distribution. We demonstrate the superior performance of the proposed PINE method on various homogeneous and heterogeneous attributed networks. As an industry-implemented system, PINE tackles the real-world challenge of unsupervised identification of key entities within large-scale enterprise graphs. - oai:arXiv.org:2512.07244v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving + https://arxiv.org/abs/2507.04049 + arXiv:2507.04049v3 Announce Type: replace +Abstract: Most end-to-end autonomous driving methods rely on imitation learning from single expert demonstrations, often leading to conservative and homogeneous behaviors that limit generalization in complex real-world scenarios. In this work, we propose DIVER, an end-to-end driving framework that integrates reinforcement learning with diffusion-based generation to produce diverse and feasible trajectories. At the core of DIVER lies a reinforced diffusion-based generation mechanism. First, the model conditions on map elements and surrounding agents to generate multiple reference trajectories from a single ground-truth trajectory, alleviating the limitations of imitation learning that arise from relying solely on single expert demonstrations. Second, reinforcement learning is employed to guide the diffusion process, where reward-based supervision enforces safety and diversity constraints on the generated trajectories, thereby enhancing their practicality and generalization capability. Furthermore, to address the limitations of L2-based open-loop metrics in capturing trajectory diversity, we propose a novel Diversity metric to evaluate the diversity of multi-mode predictions.Extensive experiments on the closed-loop NAVSIM and Bench2Drive benchmarks, as well as the open-loop nuScenes dataset, demonstrate that DIVER significantly improves trajectory diversity, effectively addressing the mode collapse problem inherent in imitation learning. + oai:arXiv.org:2507.04049v3 + cs.CV + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ziying Song, Lin Liu, Hongyu Pan, Bencheng Liao, Mingzhe Guo, Lei Yang, Yongchang Zhang, Shaoqing Xu, Caiyan Jia, Yadan Luo + + + The Prompt War: How AI Decides on a Military Intervention + https://arxiv.org/abs/2507.06277 + arXiv:2507.06277v3 Announce Type: replace +Abstract: Which factors determine AI's propensity to support military intervention? While the use of AI in high-stakes decision-making is growing exponentially, we still lack systematic analysis of the key drivers embedded in these models. This paper conducts a conjoint experiment in which large language models (LLMs) from leading providers (OpenAI, Anthropic, Google) are asked to decide on military intervention across 128 vignettes, with each vignette run 10 times. This design enables a systematic assessment of AI decision-making in military contexts. The results are remarkably consistent across models: all models place substantial weight on the probability of success and domestic support, prioritizing these factors over civilian casualties, economic shock, or international sanctions. The paper then tests whether LLMs are sensitive to context by introducing different motivations for intervention. The scoring is indeed context-dependent; however, probability of victory remains the most important factor in all scenarios. Finally, the paper evaluates numerical sensitivity and finds that models display some responsiveness to the scale of civilian casualties but no detectable sensitivity to the size of the economic shock. + oai:arXiv.org:2507.06277v3 + cs.CY + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Elizaveta Kovtun, Maksim Makarenko, Natalia Semenova, Alexey Zaytsev, Semen Budennyy + Maxim Chupilkin - Zero-Shot Textual Explanations via Translating Decision-Critical Features - https://arxiv.org/abs/2512.07245 - arXiv:2512.07245v1 Announce Type: new -Abstract: Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but are designed for general visual understanding, not classifier-specific reasoning. Existing zero-shot explanation methods align global image features with language, producing descriptions of what is visible rather than what drives the prediction. We propose TEXTER, which overcomes this limitation by isolating decision-critical features before alignment. TEXTER identifies the neurons contributing to the prediction and emphasizes the features encoded in those neurons -- i.e., the decision-critical features. It then maps these emphasized features into the CLIP feature space to retrieve textual explanations that reflect the model's reasoning. A sparse autoencoder further improves interpretability, particularly for Transformer architectures. Extensive experiments show that TEXTER generates more faithful and interpretable explanations than existing methods. The code will be publicly released. - oai:arXiv.org:2512.07245v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + FLoRA: An Advanced AI-Powered Engine to Facilitate Hybrid Human-AI Regulated Learning + https://arxiv.org/abs/2507.07362 + arXiv:2507.07362v3 Announce Type: replace +Abstract: Self-Regulated Learning (SRL), defined as learners' ability to systematically plan, monitor, and regulate their learning activities, is crucial for sustained academic achievement and lifelong learning competencies. Emerging AI developments profoundly influence SRL interactions by potentially either diminishing or strengthening learners' opportunities to exercise their own regulatory skills. Recent literature emphasizes a balanced approach termed Hybrid Human-AI Regulated Learning (HHAIRL), in which AI provides targeted, timely scaffolding while preserving the learners' role as active decision-makers and reflective monitors of their learning process. Central to HHAIRL is the integration of adaptive and personalized learning systems; by modelling each learner's knowledge and self-regulation patterns, AI can deliver contextually relevant scaffolds that support learners during all phases of the SRL process. Nevertheless, existing digital tools frequently fall short, lacking adaptability and personalisation, focusing narrowly on isolated SRL phases, and insufficiently supporting meaningful human-AI interactions. In response, this paper introduces the enhanced FLoRA Engine, which incorporates advanced generative AI features and state-of-the-art learning analytics, and grounds in solid educational theories. The FLoRA Engine offers tools such as collaborative writing, multi-agent chatbots, and detailed learning trace logging to support dynamic, adaptive scaffolding of self-regulation tailored to individual needs in real time. We further present a summary of several research studies that provide the validations for and illustrate how these tools can be utilized in real-world educational and experimental contexts. These studies demonstrate the effectiveness of FLoRA Engine in fostering SRL, providing both theoretical insights and practical solutions for the future of AI-enhanced learning contexts. + oai:arXiv.org:2507.07362v3 + cs.HC + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto + 10.1016/j.compedu.2025.105527 + Xinyu Li, Tongguang Li, Lixiang Yan, Yuheng Li, Linxuan Zhao, Mladen Rakovi\'c, Inge Molenaar, Dragan Ga\v{s}evi\'c, Yizhou Fan - Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection - https://arxiv.org/abs/2512.07246 - arXiv:2512.07246v1 Announce Type: new -Abstract: Error detection (ED), which aims to identify incorrect or inconsistent cell values in tabular data, is important for ensuring data quality. Recent state-of-the-art ED methods leverage the pre-trained knowledge and semantic capability embedded in large language models (LLMs) to directly label whether a cell is erroneous. However, this LLM-as-a-labeler pipeline (1) relies on the black box, implicit decision process, thus failing to provide explainability for the detection results, and (2) is highly sensitive to prompts, yielding inconsistent outputs due to inherent model stochasticity, therefore lacking robustness. To address these limitations, we propose an LLM-as-an-inducer framework that adopts LLM to induce the decision tree for ED (termed TreeED) and further ensembles multiple such trees for consensus detection (termed ForestED), thereby improving explainability and robustness. Specifically, based on prompts derived from data context, decision tree specifications and output requirements, TreeED queries the LLM to induce the decision tree skeleton, whose root-to-leaf decision paths specify the stepwise procedure for evaluating a given sample. Each tree contains three types of nodes: (1) rule nodes that perform simple validation checks (e.g., format or range), (2) Graph Neural Network (GNN) nodes that capture complex patterns (e.g., functional dependencies), and (3) leaf nodes that output the final decision types (error or clean). Furthermore, ForestED employs uncertainty-based sampling to obtain multiple row subsets, constructing a decision tree for each subset using TreeED. It then leverages an Expectation-Maximization-based algorithm that jointly estimates tree reliability and optimizes the consensus ED prediction. Extensive xperiments demonstrate that our methods are accurate, explainable and robust, achieving an average F1-score improvement of 16.1% over the best baseline. - oai:arXiv.org:2512.07246v1 + Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores + https://arxiv.org/abs/2507.08143 + arXiv:2507.08143v2 Announce Type: replace +Abstract: Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token importance. We show that Compactor can achieve the same performance as competing methods while retaining 20% fewer tokens in both synthetic and real-world context tasks, while being more task-robust. We further introduce a procedure for context-calibrated compression: inferring the maximum compression a given context supports before significant performance loss. Using context-calibrated compression, we show that Compactor achieves full KV performance on Longbench while reducing the KV memory burden by 68%, on average. To demonstrate the efficacy and generalizability of our approach, we apply Compactor to 27 synthetic and real-world tasks from RULER and Longbench, with models from both the Qwen 2.5 and Llama 3.1 families. Finally, we release compactor-vllm, an inference engine and suite of optimized Triton kernels designed to efficiently support the sparse, non-contiguous memory access patterns inherent to compressed KV caches. This work demonstrates that Compactor offers a practical, high-performance solution for alleviating the memory bottleneck in modern LLM deployment. + oai:arXiv.org:2507.08143v2 cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mengqi Wang (UNSW Sydney), Jianwei Wang (UNSW Sydney), Qing Liu (Data61, CSIRO), Xiwei Xu (Data61, CSIRO), Zhenchang Xing (Data61, CSIRO), Liming Zhu (Data61, CSIRO), Wenjie Zhang (UNSW Sydney) + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Vivek Chari, Benjamin Van Durme - AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing - https://arxiv.org/abs/2512.07247 - arXiv:2512.07247v1 Announce Type: new -Abstract: Recent studies have extended diffusion-based instruction-driven 2D image editing pipelines to 3D Gaussian Splatting (3DGS), enabling faithful manipulation of 3DGS assets and greatly advancing 3DGS content creation. However, it also exposes these assets to serious risks of unauthorized editing and malicious tampering. Although imperceptible adversarial perturbations against diffusion models have proven effective for protecting 2D images, applying them to 3DGS encounters two major challenges: view-generalizable protection and balancing invisibility with protection capability. In this work, we propose the first editing safeguard for 3DGS, termed AdLift, which prevents instruction-driven editing across arbitrary views and dimensions by lifting strictly bounded 2D adversarial perturbations into 3D Gaussian-represented safeguard. To ensure both adversarial perturbations effectiveness and invisibility, these safeguard Gaussians are progressively optimized across training views using a tailored Lifted PGD, which first conducts gradient truncation during back-propagation from the editing model at the rendered image and applies projected gradients to strictly constrain the image-level perturbation. Then, the resulting perturbation is backpropagated to the safeguard Gaussian parameters via an image-to-Gaussian fitting operation. We alternate between gradient truncation and image-to-Gaussian fitting, yielding consistent adversarial-based protection performance across different viewpoints and generalizes to novel views. Empirically, qualitative and quantitative results demonstrate that AdLift effectively protects against state-of-the-art instruction-driven 2D image and 3DGS editing. - oai:arXiv.org:2512.07247v1 - cs.CV + 3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models + https://arxiv.org/abs/2507.10733 + arXiv:2507.10733v2 Announce Type: replace +Abstract: Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is present. While existing studies have explored stealthy triggers in spatial and spectral domains, few incorporate the semantic domain. In this paper, we propose 3S-attack, a novel backdoor attack which is stealthy across the spatial, spectral, and semantic domains. The key idea is to exploit the semantic features of benign samples as triggers, using Gradient-weighted Class Activation Mapping (Grad-CAM) and a preliminary model for extraction. Then we embedded the trigger in the spectral domain, followed by pixel-level restrictions in the spatial domain. This process minimizes the distance between poisoned and benign samples, making the attack harder to detect by existing defenses and human inspection. And it exposes a vulnerability at the intersection of robustness and semantic interpretability, revealing that models can be manipulated to act in semantically consistent yet malicious ways. Extensive experiments on various datasets, along with theoretical analysis, demonstrate the stealthiness of 3S-attack and highlight the need for stronger defenses to ensure AI security. + oai:arXiv.org:2507.10733v2 cs.CR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ziming Hong, Tianyu Huang, Runnan Chen, Shanshan Ye, Mingming Gong, Bo Han, Tongliang Liu + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Jianyao Yin, Luca Arnaboldi, Honglong Chen, Pascal Berrang, Mark Ryan - Benchmarking Humanoid Imitation Learning with Motion Difficulty - https://arxiv.org/abs/2512.07248 - arXiv:2512.07248v1 Announce Type: new -Abstract: Physics-based motion imitation is central to humanoid control, yet current evaluation metrics (e.g., joint position error) only measure how well a policy imitates but not how difficult the motion itself is. This conflates policy performance with motion difficulty, obscuring whether failures stem from poor learning or inherently challenging motions. In this work, we address this gap with Motion Difficulty Score (MDS), a novel metric that defines and quantifies imitation difficulty independent of policy performance. Grounded in rigid-body dynamics, MDS interprets difficulty as the torque variation induced by small pose perturbations: larger torque-to-pose variation yields flatter reward landscapes and thus higher learning difficulty. MDS captures this through three properties of the perturbation-induced torque space: volume, variance, and temporal variability. We also use it to construct MD-AMASS, a difficulty-aware repartitioning of the AMASS dataset. Empirically, we rigorously validate MDS by demonstrating its explanatory power on the performance of state-of-the-art motion imitation policies. We further demonstrate the utility of MDS through two new MDS-based metrics: Maximum Imitable Difficulty (MID) and Difficulty-Stratified Joint Error (DSJE), providing fresh insights into imitation learning. - oai:arXiv.org:2512.07248v1 - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhaorui Meng, Lu Yin, Xinrui Chen, Anjun Chen, Shihui Guo, Yipeng Qin + Left Leaning Models: How AI Evaluates Economic Policy? + https://arxiv.org/abs/2507.15771 + arXiv:2507.15771v2 Announce Type: replace +Abstract: Would artificial intelligence (AI) cut interest rates or adopt conservative monetary policy? Would it deregulate or opt for a more controlled economy? As AI use by economic policymakers, academics, and market participants grows exponentially, it is becoming critical to understand AI preferences over economic policy. However, these preferences are not yet systematically evaluated and remain a black box. This paper makes a conjoint experiment on leading large language models (LLMs) from OpenAI, Anthropic, and Google, asking them to evaluate economic policy under multi-factor constraints. The results are remarkably consistent across models: most LLMs exhibit a strong preference for high growth, low unemployment, and low inequality over traditional macroeconomic concerns such as low inflation and low public debt. Scenario-specific experiments show that LLMs are sensitive to context but still display strong preferences for low unemployment and low inequality even in monetary-policy settings. Numerical sensitivity tests reveal intuitive responses to quantitative changes but also uncover non-linear patterns such as loss aversion. + oai:arXiv.org:2507.15771v2 + cs.CY + cs.AI + econ.GN + q-fin.EC + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Maxim Chupilkin + + + CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings + https://arxiv.org/abs/2507.17234 + arXiv:2507.17234v3 Announce Type: replace +Abstract: Automatic generation of radiology reports has the potential to alleviate radiologists' significant workload, yet current methods struggle to deliver clinically reliable conclusions. In particular, most prior approaches focus on producing fluent text without effectively ensuring the factual correctness of the reports and often rely on single-view images, limiting diagnostic comprehensiveness. We propose CLARIFID, a novel framework that directly optimizes diagnostic correctness by mirroring the two-step workflow of experts. Specifically, CLARIFID (1) learns the logical flow from Findings to Impression through section-aware pretraining, (2) is fine-tuned with Proximal Policy Optimization in which the CheXbert F1 score of the Impression section serves as the reward, (3) employs controlled decoding that completes "Findings" before synthesizing the "Impression", and (4) fuses multiple chest X-ray views via a vision-transformer-based multi-view encoder. During inference, we apply a next-token forcing strategy followed by report-level re-ranking, ensuring that the model first produces a comprehensive "Findings" section before synthesizing the "Impression" and thereby preserving coherent clinical reasoning. Experimental results on the MIMIC-CXR dataset demonstrate that our method achieves superior clinical efficacy and outperforms existing baselines on clinical efficacy scores. + oai:arXiv.org:2507.17234v3 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + 10.1016/j.eswa.2025.130633 + Kyeongkyu Lee, Seonghwan Yoon, Hongki Lim - IFFair: Influence Function-driven Sample Reweighting for Fair Classification - https://arxiv.org/abs/2512.07249 - arXiv:2512.07249v1 Announce Type: new -Abstract: Because machine learning has significantly improved efficiency and convenience in the society, it's increasingly used to assist or replace human decision-making. However, the data-based pattern makes related algorithms learn and even exacerbate potential bias in samples, resulting in discriminatory decisions against certain unprivileged groups, depriving them of the rights to equal treatment, thus damaging the social well-being and hindering the development of related applications. Therefore, we propose a pre-processing method IFFair based on the influence function. Compared with other fairness optimization approaches, IFFair only uses the influence disparity of training samples on different groups as a guidance to dynamically adjust the sample weights during training without modifying the network structure, data features and decision boundaries. To evaluate the validity of IFFair, we conduct experiments on multiple real-world datasets and metrics. The experimental results show that our approach mitigates bias of multiple accepted metrics in the classification setting, including demographic parity, equalized odds, equality of opportunity and error rate parity without conflicts. It also demonstrates that IFFair achieves better trade-off between multiple utility and fairness metrics compared with previous pre-processing methods. - oai:arXiv.org:2512.07249v1 + Language Models for Controllable DNA Sequence Design + https://arxiv.org/abs/2507.19523 + arXiv:2507.19523v2 Announce Type: replace +Abstract: We consider controllable DNA sequence design, where sequences are generated by conditioning on specific biological properties. While language models (LMs) such as GPT and BERT have achieved remarkable success in natural language generation, their application to DNA sequence generation remains largely underexplored. In this work, we introduce ATGC-Gen, an Automated Transformer Generator for Controllable Generation, which leverages cross-modal encoding to integrate diverse biological signals. ATGC-Gen is instantiated with both decoder-only and encoder-only transformer architectures, allowing flexible training and generation under either autoregressive or masked recovery objectives. We evaluate ATGC-Gen on representative tasks including promoter and enhancer sequence design, and further introduce a new dataset based on ChIP-Seq experiments for modeling protein binding specificity. Our experiments demonstrate that ATGC-Gen can generate fluent, diverse, and biologically relevant sequences aligned with the desired properties. Compared to prior methods, our model achieves notable improvements in controllability and functional relevance, highlighting the potential of language models in advancing programmable genomic design. The source code is released at (https://github.com/divelab/AIRS/blob/main/OpenBio/ATGC_Gen). + oai:arXiv.org:2507.19523v2 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jingran Yang, Min Zhang, Lingfeng Zhang, Zhaohui Wang, Yonggang Zhang + Xingyu Su, Xiner Li, Yuchao Lin, Ziqian Xie, Degui Zhi, Shuiwang Ji - See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement - https://arxiv.org/abs/2512.07251 - arXiv:2512.07251v1 Announce Type: new -Abstract: Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but current models often over-edit. This can distort organs, create false findings, and miss small tumors because these models do not understand anatomy or contrast dynamics. We propose SMILE, an anatomy-aware diffusion model that learns how organs are shaped and how they take up contrast. It enhances only clinically relevant regions while leaving all other areas unchanged. SMILE introduces three key ideas: (1) structure-aware supervision that follows true organ boundaries and contrast patterns; (2) registration-free learning that works directly with unaligned multi-phase CT scans; (3) unified inference that provides fast and consistent enhancement across all contrast phases. Across six external datasets, SMILE outperforms existing methods in image quality (14.2% higher SSIM, 20.6% higher PSNR, 50% better FID) and in clinical usefulness by producing anatomically accurate and diagnostically meaningful images. SMILE also improves cancer detection from non-contrast CT, raising the F1 score by up to 10 percent. - oai:arXiv.org:2512.07251v1 + CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding + https://arxiv.org/abs/2507.21888 + arXiv:2507.21888v3 Announce Type: replace +Abstract: We address Embodied Reference Understanding, the task of predicting the object a person in the scene refers to through pointing gesture and language. This requires multimodal reasoning over text, visual pointing cues, and scene context, yet existing methods often fail to fully exploit visual disambiguation signals. We also observe that while the referent often aligns with the head-to-fingertip direction, in many cases it aligns more closely with the wrist-to-fingertip direction, making a single-line assumption overly limiting. To address this, we propose a dual-model framework, where one model learns from the head-to-fingertip direction and the other from the wrist-to-fingertip direction. We introduce a Gaussian ray heatmap representation of these lines and use them as input to provide a strong supervisory signal that encourages the model to better attend to pointing cues. To fuse their complementary strengths, we present the CLIP-Aware Pointing Ensemble module, which performs a hybrid ensemble guided by CLIP features. We further incorporate an auxiliary object center prediction head to enhance referent localization. We validate our approach on YouRefIt, achieving 75.0 mAP at 0.25 IoU, alongside state-of-the-art CLIP and C_D scores, and demonstrate its generality on unseen CAESAR and ISL Pointing, showing robust performance across benchmarks. + oai:arXiv.org:2507.21888v3 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Junqi Liu, Zejun Wu, Pedro R. A. S. Bassi, Xinze Zhou, Wenxuan Li, Ibrahim E. Hamamci, Sezgin Er, Tianyu Lin, Yi Luo, Szymon P{\l}otka, Bjoern Menze, Daguang Xu, Kai Ding, Kang Wang, Yang Yang, Yucheng Tang, Alan L. Yuille, Zongwei Zhou + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Fevziye Irem Eyiokur, Dogucan Yaman, Haz{\i}m Kemal Ekenel, Alexander Waibel - DGGAN: Degradation Guided Generative Adversarial Network for Real-time Endoscopic Video Enhancement - https://arxiv.org/abs/2512.07253 - arXiv:2512.07253v1 Announce Type: new -Abstract: Endoscopic surgery relies on intraoperative video, making image quality a decisive factor for surgical safety and efficacy. Yet, endoscopic videos are often degraded by uneven illumination, tissue scattering, occlusions, and motion blur, which obscure critical anatomical details and complicate surgical manipulation. Although deep learning-based methods have shown promise in image enhancement, most existing approaches remain too computationally demanding for real-time surgical use. To address this challenge, we propose a degradation-aware framework for endoscopic video enhancement, which enables real-time, high-quality enhancement by propagating degradation representations across frames. In our framework, degradation representations are first extracted from images using contrastive learning. We then introduce a fusion mechanism that modulates image features with these representations to guide a single-frame enhancement model, which is trained with a cycle-consistency constraint between degraded and restored images to improve robustness and generalization. Experiments demonstrate that our framework achieves a superior balance between performance and efficiency compared with several state-of-the-art methods. These results highlight the effectiveness of degradation-aware modeling for real-time endoscopic video enhancement. Nevertheless, our method suggests that implicitly learning and propagating degradation representation offer a practical pathway for clinical application. - oai:arXiv.org:2512.07253v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Rational complex Bezier curves + https://arxiv.org/abs/2507.23485 + arXiv:2507.23485v3 Announce Type: replace +Abstract: In this paper we develop the formalism of rational complex Bezier curves. This framework is a simple extension of the CAD paradigm, since it describes arc of curves in terms of control polygons and weights, which are extended to complex values. One of the major advantages of this extension is that we may make use of two different groups of projective transformations. Besides the group of projective transformations of the real plane, we have the group of complex projective transformations. This allows us to apply useful transformations like the geometric inversion to curves in design. In addition to this, the use of the complex formulation allows to lower the degree of the curves in some cases. This can be checked using the resultant of two polynomials and provides a simple formula for determining whether a rational cubic curve is a conic or not. Examples of application of the formalism to classical curves are included. + oai:arXiv.org:2507.23485v3 + math.NA + cs.GR + cs.NA + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + A. Canton, L. Fernandez-Jambrina, M. J. Vazquez-Gallo + + + Fine-grained Spatiotemporal Grounding on Egocentric Videos + https://arxiv.org/abs/2508.00518 + arXiv:2508.00518v2 Announce Type: replace +Abstract: Spatiotemporal video grounding aims to localize target entities in videos based on textual queries. While existing research has made significant progress in exocentric videos, the egocentric setting remains relatively underexplored, despite its growing importance in applications such as augmented reality and robotics. In this work, we conduct a systematic analysis of the discrepancies between egocentric and exocentric videos, revealing key challenges such as shorter object durations, sparser trajectories, smaller object sizes, and larger positional shifts. To address these challenges, we introduce EgoMask, the first pixel-level benchmark for fine-grained spatiotemporal grounding in egocentric videos. It is constructed by our proposed automatic annotation pipeline, which annotates referring expressions and object masks across short-, medium-, and long-term videos. Additionally, we create EgoMask-Train, a large-scale training dataset to facilitate model development. Experiments demonstrate that the state-of-the-art spatiotemporal grounding models perform poorly on our benchmark EgoMask, but fine-tuning on EgoMask-Train yields significant improvements, while preserving performance on exocentric datasets. Our work thus provides essential resources and insights for advancing egocentric video understanding. Our code is available at https://github.com/LaVi-Lab/EgoMask . + oai:arXiv.org:2508.00518v2 + cs.CV + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Handing Xu, Zhenguo Nie, Tairan Peng, Huimin Pan, Xin-Jun Liu + Shuo Liang, Yiwu Zhong, Zi-Yuan Hu, Yeyao Tao, Liwei Wang - Improved bounds and optimal constructions of pure quantum locally recoverable codes - https://arxiv.org/abs/2512.07256 - arXiv:2512.07256v1 Announce Type: new -Abstract: By incorporating the concept of locality into quantum information theory, quantum locally recoverable codes (qLRCs) have been proposed, motivated by their potential applications in large-scale quantum data storage and their relevance to quantum LDPC codes. Despite the progress in optimal quantum error-correcting codes (QECCs), optimal constructions of qLRCs remain largely unexplored, partly due to the fact that the existing bounds for qLRCs are not sufficiently tight. In this paper, we focus on pure qLRCs derived from the Hermitian construction. We provide several new bounds for pure qLRCs and demonstrate that they are tighter than previously known bounds. Moreover, we show that a variety of classical QECCs, including quantum Hamming codes, quantum GRM codes, and quantum Solomon-Stiffler codes, give rise to pure qLRCs with explicit parameters. Based on these constructions, we further identify many infinite families of optimal qLRCs with respect to different bounds, achieving code lengths much larger than those of known optimal qLRCs. - oai:arXiv.org:2512.07256v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new + PRISM: Lightweight Multivariate Time-Series Classification through Symmetric Multi-Resolution Convolutional Layers + https://arxiv.org/abs/2508.04503 + arXiv:2508.04503v2 Announce Type: replace +Abstract: Multivariate time series classification supports applications from wearable sensing to biomedical monitoring and demands models that can capture both short-term patterns and longer-range temporal dependencies. Despite recent advances, Transformer and CNN models often remain computationally heavy and rely on many parameters. This work presents PRISM(Per-channel Resolution Informed Symmetric Module), a lightweight fully convolutional classifier. Operating in a channel-independent manner, in its early stage it applies a set of multi-resolution symmetric convolutional filters. This symmetry enforces structural constraints inspired by linear-phase FIR filters from classical signal processing, effectively halving the number of learnable parameters within the initial layers while preserving the full receptive field. Across the diverse UEA multivariate time-series archive as well as specific benchmarks in human activity recognition, sleep staging, and biomedical signals, PRISM matches or outperforms state-of-the-art CNN and Transformer models while using significantly fewer parameters and markedly lower computational cost. By bringing a principled signal processing prior into a modern neural architecture, PRISM offers an effective and computationally economical solution for multivariate time series classification. + oai:arXiv.org:2508.04503v2 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yang Li, Shitao Li, Gaojun Luo, San Ling + Federico Zucchi, Thomas Lampert - Automatic Syntax Error Repair for Discrete Controller Synthesis using Large Language Model - https://arxiv.org/abs/2512.07261 - arXiv:2512.07261v1 Announce Type: new -Abstract: Discrete Controller Synthesis (DCS) is a powerful formal method for automatically generating specifications of discrete event systems. However, its practical adoption is often hindered by the highly specialized nature of formal models written in languages such as FSP and FLTL. In practice, syntax errors in modeling frequently become an important bottleneck for developers-not only disrupting the workflow and reducing productivity, but also diverting attention from higher-level semantic design. To this end, this paper presents an automated approach that leverages Large Language Models (LLMs) to repair syntax errors in DCS models using a well-designed, knowledge-informed prompting strategy. Specifically, the prompting is derived from a systematic empirical study of common error patterns, identified through expert interviews and student workshops. It equips the LLM with DCS-specific domain knowledge, including formal grammar rules and illustrative examples, to guide accurate corrections. To evaluate our method, we constructed a new benchmark by systematically injecting realistic syntax errors into validated DCS models. The quantitative evaluation demonstrates the high effectiveness of the proposed approach in terms of repair accuracy and its practical utility regarding time, achieving a speedup of 3.46 times compared to human developers. The experimental replication suite, including the benchmark and prompts, is available at https://github.com/Uuusay1432/DCSModelRepair.git - oai:arXiv.org:2512.07261v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new + ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls + https://arxiv.org/abs/2508.06457 + arXiv:2508.06457v2 Announce Type: replace +Abstract: Large Language Models (LLMs) have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of LLMs, capable of generating highly realistic scam call scripts that simulate real-world fraud scenarios. Unlike prior work focused on single-shot prompt misuse, ScamAgent maintains dialogue memory, adapts dynamically to simulated user responses, and employs deceptive persuasion strategies across conversational turns. We show that current LLM safety guardrails, including refusal mechanisms and content filters, are ineffective against such agent-based threats. Even models with strong prompt-level safeguards can be bypassed when prompts are decomposed, disguised, or delivered incrementally within an agent framework. We further demonstrate the transformation of scam scripts into lifelike voice calls using modern text-to-speech systems, completing a fully automated scam pipeline. Our findings highlight an urgent need for multi-turn safety auditing, agent-level control frameworks, and new methods to detect and disrupt conversational deception powered by generative AI. + oai:arXiv.org:2508.06457v2 + cs.CR + cs.AI + cs.CL + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yusei Ishimizu, Takuto Yamauchi, Sinan Chen, Jinyu Cai, Jialong Li, Kenji Tei + Proceedings of Machine Learning Research 299, 2025 Conference on Applied Machine Learning for Information Security + Sanket Badhe - Escaping the native space of Sobolev kernels by interpolation - https://arxiv.org/abs/2512.07262 - arXiv:2512.07262v1 Announce Type: new -Abstract: Classical convergence analysis for kernel interpolation typically assumes that the target function $f$ lies in the reproducing kernel Hilbert space $\mathcal{H}_k\!\left(\Omega\right)$ induced by a kernel on a domain $\Omega\subset\mathbb{R}^N$. For many applications, however, this assumption is overly restrictive. We develop a general framework for analyzing the convergence of kernel interpolation {beyond the native space}. Let $A(\Omega)$ and $B(\Omega)$ be Banach spaces with continuous embeddings $\mathcal{H}_k\!\left(\Omega\right) \hookrightarrow A(\Omega)\hookrightarrow B(\Omega)$, assume point evaluation is continuous on $A(\Omega)$, and that $\mathcal{H}_k\!\left(\Omega\right)$ is dense in $A(\Omega)$. For a nested sequence of node sets $(X_n)_{n\ge1}\subset\Omega$ with $\bigcup_n X_n$ dense, we characterize convergence of the kernel interpolants in the $B(\Omega)$-norm for all target functions in $A(\Omega)$ via the uniform boundedness of the interpolation operators $\Pi^{\,n}_{A,B}:A(\Omega)\to B(\Omega)$. This yields a necessary and sufficient condition under which kernel interpolation extends beyond $\mathcal{H}_k\!\left(\Omega\right)$. Specializing to Sobolev kernels of order $\tau>N/2$ on bounded Lipschitz domains, we show that every $f \in C(\overline{\Omega})$ can be approximated in the $L^2(\Omega)$-norm by interpolation using quasi-uniform nested centers. Moreover, for a subclass of Sobolev kernels (including integer-order Mat\'ern kernels), we prove that the Lebesgue constant is uniformly bounded on $[a,b]\subset\mathbb{R}$ under quasi-uniform centers; within our framework this implies supremum norm convergence of the interpolants for every target functions $f \in C([a,b])$. - oai:arXiv.org:2512.07262v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new + CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning + https://arxiv.org/abs/2508.07871 + arXiv:2508.07871v2 Announce Type: replace +Abstract: Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image tokens contain sparse information, many contribute little to reasoning but greatly increase inference cost. Recent image token pruning methods address this issue by identifying important tokens and removing the rest. These methods improve efficiency with only small performance drops. However, most of them focus on single-image tasks and overlook multimodal in-context learning (ICL), where redundancy is higher and efficiency is more important. Redundant tokens weaken the advantage of multimodal ICL for rapid domain adaptation and lead to unstable performance. When existing pruning methods are applied in this setting, they cause large accuracy drops, which exposes a clear gap and the need for new approaches. To address this, we propose Contextually Adaptive Token Pruning (CATP), a training-free pruning method designed for multimodal ICL. CATP uses two stages of progressive pruning that fully reflect the complex cross-modal interactions in the input sequence. After removing 77.8% of the image tokens, CATP achieves an average performance gain of 0.6% over the vanilla model on four LVLMs and eight benchmarks, clearly outperforming all baselines. At the same time, it improves efficiency by reducing inference latency by an average of 10.78%. CATP strengthens the practical value of multimodal ICL and lays the foundation for future progress in interleaved image-text settings. + oai:arXiv.org:2508.07871v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tobias Ehring, Max-Paul Vogel, Bernard Haasdonk + Yanshu Li, Jianjiang Yang, Zhennan Shen, Ligong Han, Haoyan Xu, Ruixiang Tang - TeluguST-46: A Benchmark Corpus and Comprehensive Evaluation for Telugu-English Speech Translation - https://arxiv.org/abs/2512.07265 - arXiv:2512.07265v1 Announce Type: new -Abstract: Despite Telugu being spoken by over 80 million people, speech translation research for this morphologically rich language remains severely underexplored. We address this gap by developing a high-quality Telugu--English speech translation benchmark from 46 hours of manually verified CSTD corpus data (30h/8h/8h train/dev/test split). Our systematic comparison of cascaded versus end-to-end architectures shows that while IndicWhisper + IndicMT achieves the highest performance due to extensive Telugu-specific training data, finetuned SeamlessM4T models demonstrate remarkable competitiveness despite using significantly less Telugu-specific training data. This finding suggests that with careful hyperparameter tuning and sufficient parallel data (potentially less than 100 hours), end-to-end systems can achieve performance comparable to cascaded approaches in low-resource settings. Our metric reliability study evaluating BLEU, METEOR, ChrF++, ROUGE-L, TER, and BERTScore against human judgments reveals that traditional metrics provide better quality discrimination than BERTScore for Telugu--English translation. The work delivers three key contributions: a reproducible Telugu--English benchmark, empirical evidence of competitive end-to-end performance potential in low-resource scenarios, and practical guidance for automatic evaluation in morphologically complex language pairs. - oai:arXiv.org:2512.07265v1 - cs.CL - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - new + FedJam: Multimodal Federated Learning Framework for Jamming Detection + https://arxiv.org/abs/2508.09369 + arXiv:2508.09369v2 Announce Type: replace +Abstract: Jamming attacks pose a critical threat to wireless networks, yet existing detection methods remain largely unimodal, centralized and resource-intensive, limiting their performance, scalability, and deployment feasibility, respectively. To address these limitations, we present FedJam, a multimodal Federated Learning (FL) framework for on-device jamming detection and classification. FedJam locally fuses spectrograms and cross-layer network Key Performance Indicators (KPIs) using a lightweight dual-encoder architecture with an integrated fusion module and multimodal projection head, that enables privacy-preserving training and inference without transmitting raw data. We prototype and deploy FedJam on a wireless experimental testbed and evaluate it using the first, over-the-air multimodal dataset comprising synchronized samples across benign and three distinct jamming attack types. FedJam outperforms state-of-the-art unimodal baselines by up to 15% in accuracy, while requiring 60% fewer communication rounds to converge, and maintains low resource utilization. Its advantage is especially pronounced in realistic scenarios, where it remains extremely robust under heterogeneous data distributions across devices. + oai:arXiv.org:2508.09369v2 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Bhavana Akkiraju, Srihari Bandarupalli, Swathi Sambangi, Vasavi Ravuri, R Vijaya Saraswathi, Anil Kumar Vuppala + Ioannis Panitsas, Iason Ofeidis, Leandros Tassiulas - SINRL: Socially Integrated Navigation with Reinforcement Learning using Spiking Neural Networks - https://arxiv.org/abs/2512.07266 - arXiv:2512.07266v1 Announce Type: new -Abstract: Integrating autonomous mobile robots into human environments requires human-like decision-making and energy-efficient, event-based computation. Despite progress, neuromorphic methods are rarely applied to Deep Reinforcement Learning (DRL) navigation approaches due to unstable training. We address this gap with a hybrid socially integrated DRL actor-critic approach that combines Spiking Neural Networks (SNNs) in the actor with Artificial Neural Networks (ANNs) in the critic and a neuromorphic feature extractor to capture temporal crowd dynamics and human-robot interactions. Our approach enhances social navigation performance and reduces estimated energy consumption by approximately 1.69 orders of magnitude. - oai:arXiv.org:2512.07266v1 - cs.RO - cs.AI - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Florian Tretter, Daniel Fl\"ogel, Alexandru Vasilache, Max Grobbel, J\"urgen Becker, S\"oren Hohmann + MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training + https://arxiv.org/abs/2508.12522 + arXiv:2508.12522v2 Announce Type: replace +Abstract: Personalized expression recognition (ER) involves adapting a machine learning model to subject-specific data for improved recognition of expressions with considerable interpersonal variability. Subject-specific ER can benefit significantly from multi-source domain adaptation (MSDA) methods, where each domain corresponds to a specific subject to improve model accuracy and robustness. Despite promising results, state-of-the-art MSDA approaches often overlook multimodal information or blend sources into a single domain, limiting subject diversity and failing to explicitly capture unique subject-specific characteristics. To address these limitations, we introduce MuSACo, a multimodal subject-specific selection and adaptation method for ER based on co-training. It leverages complementary information across multiple modalities and multiple source domains for subject-specific adaptation. This makes MuSACo particularly relevant for affective computing applications in digital health, such as patient-specific assessment for stress or pain, where subject-level nuances are crucial. MuSACo selects source subjects relevant to the target and generates pseudo-labels using the dominant modality for class-aware learning, in conjunction with a class-agnostic loss to learn from less confident target samples. Finally, source features from each modality are aligned, while only confident target features are combined. Experimental results on challenging multimodal ER datasets: BioVid, StressID, and BAH show that MuSACo outperforms UDA (blending) and state-of-the-art MSDA methods. + oai:arXiv.org:2508.12522v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Muhammad Osama Zeeshan, Natacha Gillet, Alessandro Lameiras Koerich, Marco Pedersoli, Francois Bremond, Eric Granger - A graph generation pipeline for critical infrastructures based on heuristics, images and depth data - https://arxiv.org/abs/2512.07269 - arXiv:2512.07269v1 Announce Type: new -Abstract: Virtual representations of physical critical infrastructures, such as water or energy plants, are used for simulations and digital twins to ensure resilience and continuity of their services. These models usually require 3D point clouds from laser scanners that are expensive to acquire and require specialist knowledge to use. In this article, we present a graph generation pipeline based on photogrammetry. The pipeline detects relevant objects and predicts their relation using RGB images and depth data generated by a stereo camera. This more cost-effective approach uses deep learning for object detection and instance segmentation of the objects, and employs user-defined heuristics or rules to infer their relations. Results of two hydraulic systems show that this strategy can produce graphs close to the ground truth while its flexibility allows the method to be tailored to specific applications and its transparency qualifies it to be used in the high stakes decision-making that is required for critical infrastructures. - oai:arXiv.org:2512.07269v1 + DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples + https://arxiv.org/abs/2508.13309 + arXiv:2508.13309v2 Announce Type: replace +Abstract: Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to align well with human perception, and only recently have a few methods begun specifically exploring perceptually aligned adversarial examples. Moreover, it remains unclear whether insights from Lp-constrained attacks can be effectively leveraged to improve perceptual efficacy. In this paper, we introduce DAASH, a fully differentiable meta-attack framework that generates effective and perceptually aligned adversarial examples by strategically composing existing Lp-based attack methods. DAASH operates in a multi-stage fashion: at each stage, it aggregates candidate adversarial examples from multiple base attacks using learned, adaptive weights and propagates the result to the next stage. A novel meta-loss function guides this process by jointly minimizing misclassification loss and perceptual distortion, enabling the framework to dynamically modulate the contribution of each base attack throughout the stages. We evaluate DAASH on adversarially trained models across CIFAR-10, CIFAR-100, and ImageNet. Despite relying solely on Lp-constrained based methods, DAASH significantly outperforms state-of-the-art perceptual attacks such as AdvAD -- achieving higher attack success rates (e.g., 20.63\% improvement) and superior visual quality, as measured by SSIM, LPIPS, and FID (improvements $\approx$ of 11, 0.015, and 5.7, respectively). Furthermore, DAASH generalizes well to unseen defenses, making it a practical and strong baseline for evaluating robustness without requiring handcrafted adaptive attacks for each new defense. + oai:arXiv.org:2508.13309v2 cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Mike Diessner, Yannick Tarant + Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider, Tanzim Mahfuz, Fnu Suya, Swarup Bhunia, Prabuddha Chakraborty - RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translation - https://arxiv.org/abs/2512.07273 - arXiv:2512.07273v1 Announce Type: new -Abstract: Gloss-free sign language translation (SLT) is hindered by two key challenges: **inadequate sign representation** that fails to capture nuanced visual cues, and **sentence-level semantic misalignment** in current LLM-based methods, which limits translation quality. To address these issues, we propose a three-stage **r**einforcing **v**ision-**l**anguage **f**ramework (**RVLF**). We build a large vision-language model (LVLM) specifically designed for sign language, and then combine it with reinforcement learning (RL) to adaptively enhance translation performance. First, for a sufficient representation of sign language, RVLF introduces an effective semantic representation learning mechanism that fuses skeleton-based motion cues with semantically rich visual features extracted via DINOv2, followed by instruction tuning to obtain a strong SLT-SFT baseline. Then, to improve sentence-level semantic misalignment, we introduce a GRPO-based optimization strategy that fine-tunes the SLT-SFT model with a reward function combining translation fidelity (BLEU) and sentence completeness (ROUGE), yielding the optimized model termed SLT-GRPO. Our conceptually simple framework yields substantial gains under the gloss-free SLT setting without pre-training on any external large-scale sign language datasets, improving BLEU-4 scores by +5.1, +1.11, +1.4, and +1.61 on the CSL-Daily, PHOENIX-2014T, How2Sign, and OpenASL datasets, respectively. To the best of our knowledge, this is the first work to incorporate GRPO into SLT. Extensive experiments and ablation studies validate the effectiveness of GRPO-based optimization in enhancing both translation quality and semantic consistency. - oai:arXiv.org:2512.07273v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Incremental Generalized Hybrid A* + https://arxiv.org/abs/2508.13392 + arXiv:2508.13392v3 Announce Type: replace +Abstract: We address the problem of efficiently organizing search over very large trees, which arises in many applications ranging from autonomous driving to aerial vehicles. Here, we are motivated by off-road autonomy, where real-time planning is essential. Classical approaches use graphs of motion primitives and exploit dominance to mitigate the curse of dimensionality and prune expansions efficiently. However, for complex dynamics, repeatedly solving two-point boundary-value problems makes graph construction too slow for fast kinodynamic planning. Hybrid A* (HA*) addressed this challenge by searching over a tree of motion primitives and introducing approximate pruning using a grid-based dominance check. However, choosing the grid resolution is difficult: too coarse risks failure, while too fine leads to excessive expansions and slow planning. We propose Incremental Generalized Hybrid A* (IGHA*), an anytime tree-search framework that dynamically organizes vertex expansions without rigid pruning. IGHA* provably matches or outperforms HA*. For both on-road kinematic and off-road kinodynamic planning queries for a car-like robot, variants of IGHA* use 6x fewer expansions to the best solution compared to an optimized version of HA* (HA*M, an internal baseline). In simulated off- road experiments in a high-fidelity simulator, IGHA* outper- forms HA*M when both are used in the loop with a model predictive controller. We demonstrate real-time performance both in simulation and on a small-scale off-road vehicle, enabling fast, robust planning under complex dynamics. Website: https://personalrobotics.github.io/IGHAStar/ + oai:arXiv.org:2508.13392v3 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhi Rao, Yucheng Zhou, Benjia Zhou, Yiqing Huang, Sergio Escalera, Jun Wan + Sidharth Talia, Oren Salzman, Siddhartha Srinivasa - Effective Attention-Guided Multi-Scale Medical Network for Skin Lesion Segmentation - https://arxiv.org/abs/2512.07275 - arXiv:2512.07275v1 Announce Type: new -Abstract: In the field of healthcare, precise skin lesion segmentation is crucial for the early detection and accurate diagnosis of skin diseases. Despite significant advances in deep learning for image processing, existing methods have yet to effectively address the challenges of irregular lesion shapes and low contrast. To address these issues, this paper proposes an innovative encoder-decoder network architecture based on multi-scale residual structures, capable of extracting rich feature information from different receptive fields to effectively identify lesion areas. By introducing a Multi-Resolution Multi-Channel Fusion (MRCF) module, our method captures cross-scale features, enhancing the clarity and accuracy of the extracted information. Furthermore, we propose a Cross-Mix Attention Module (CMAM), which redefines the attention scope and dynamically calculates weights across multiple contexts, thus improving the flexibility and depth of feature capture and enabling deeper exploration of subtle features. To overcome the information loss caused by skip connections in traditional U-Net, an External Attention Bridge (EAB) is introduced, facilitating the effective utilization of information in the decoder and compensating for the loss during upsampling. Extensive experimental evaluations on several skin lesion segmentation datasets demonstrate that the proposed model significantly outperforms existing transformer and convolutional neural network-based models, showcasing exceptional segmentation accuracy and robustness. - oai:arXiv.org:2512.07275v1 + FLAIR: Frequency- and Locality-Aware Implicit Neural Representations + https://arxiv.org/abs/2508.13544 + arXiv:2508.13544v5 Announce Type: replace +Abstract: Implicit Neural Representations (INRs) leverage neural networks to map coordinates to corresponding signals, enabling continuous and compact representations. This paradigm has driven significant advances in various vision tasks. However, existing INRs lack frequency selectivity and spatial localization, leading to an over-reliance on redundant signal components. Consequently, they exhibit spectral bias, tending to learn low-frequency components early while struggling to capture fine high-frequency details. To address these issues, we propose FLAIR (Frequency- and Locality-Aware Implicit Neural Representations), which incorporates two key innovations. The first is Band-Localized Activation (BLA), a novel activation designed for joint frequency selection and spatial localization under the constraints of the time-frequency uncertainty principle (TFUP). Through structured frequency control and spatially localized responses, BLA effectively mitigates spectral bias and enhances training stability. The second is Wavelet-Energy-Guided Encoding (WEGE), which leverages the discrete wavelet transform to compute energy scores and explicitly guide frequency information to the network, enabling precise frequency selection and adaptive band control. Our method consistently outperforms existing INRs in 2D image representation, as well as 3D shape reconstruction and novel view synthesis. + oai:arXiv.org:2508.13544v5 cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Siyu Wang, Hua Wang, Huiyu Li, Fan Zhang - - - Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery - https://arxiv.org/abs/2512.07276 - arXiv:2512.07276v1 Announce Type: new -Abstract: Three-dimensional geospatial analysis is critical to applications in urban planning, climate adaptation, and environmental assessment. Current methodologies depend on costly, specialized sensors (e.g., LiDAR and multispectral), which restrict global accessibility. Existing sensor-based and rule-driven methods further struggle with tasks requiring the integration of multiple 3D cues, handling diverse queries, and providing interpretable reasoning. We hereby present Geo3DVQA, a comprehensive benchmark for evaluating vision-language models (VLMs) in height-aware, 3D geospatial reasoning using RGB-only remote sensing imagery. Unlike conventional sensor-based frameworks, Geo3DVQA emphasizes realistic scenarios that integrate elevation, sky view factors, and land cover patterns. The benchmark encompasses 110k curated question-answer pairs spanning 16 task categories across three complexity levels: single-feature inference, multi-feature reasoning, and application-level spatial analysis. The evaluation of ten state-of-the-art VLMs highlights the difficulty of RGB-to-3D reasoning. GPT-4o and Gemini-2.5-Flash achieved only 28.6% and 33.0% accuracy respectively, while domain-specific fine-tuning of Qwen2.5-VL-7B achieved 49.6% (+24.8 points). These results reveal both the limitations of current VLMs and the effectiveness of domain adaptation. Geo3DVQA introduces new challenge frontiers for scalable, accessible, and holistic 3D geospatial analysis. The dataset and code will be released upon publication at https://github.com/mm1129/Geo3DVQA. - oai:arXiv.org:2512.07276v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Mai Tsujimoto, Junjue Wang, Weihao Xuan, Naoto Yokoya - - - Efficient ASR for Low-Resource Languages: Leveraging Cross-Lingual Unlabeled Data - https://arxiv.org/abs/2512.07277 - arXiv:2512.07277v1 Announce Type: new -Abstract: Automatic speech recognition for low-resource languages remains fundamentally constrained by the scarcity of labeled data and computational resources required by state-of-the-art models. We present a systematic investigation into cross-lingual continuous pretraining for low-resource languages, using Perso-Arabic languages (Persian, Arabic, and Urdu) as our primary case study. Our approach demonstrates that strategic utilization of unlabeled speech data can effectively bridge the resource gap without sacrificing recognition accuracy. We construct a 3,000-hour multilingual corpus through a scalable unlabeled data collection pipeline and employ targeted continual pretraining combined with morphologically-aware tokenization to develop a 300M parameter model that achieves performance comparable to systems 5 times larger. Our model outperforms Whisper Large v3 (1.5B parameters) on Persian and achieves competitive results on Arabic and Urdu despite using significantly fewer parameters and substantially less labeled data. These findings challenge the prevailing assumption that ASR quality scales primarily with model size, revealing instead that data relevance and strategic pretraining are more critical factors for low-resource scenarios. This work provides a practical pathway toward inclusive speech technology, enabling effective ASR for underrepresented languages without dependence on massive computational infrastructure or proprietary datasets. - oai:arXiv.org:2512.07277v1 - cs.CL - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Srihari Bandarupalli, Bhavana Akkiraju, Charan Devarakonda, Vamsiraghusimha Narsinga, Anil Kumar Vuppala - - - ContinuumConductor : Decentralized Process Mining on the Edge-Cloud Continuum - https://arxiv.org/abs/2512.07280 - arXiv:2512.07280v1 Announce Type: new -Abstract: Process mining traditionally assumes centralized event data collection and analysis. However, modern Industrial Internet of Things systems increasingly operate over distributed, resource-constrained edge-cloud infrastructures. This paper proposes a structured approach for decentralizing process mining by enabling event data to be mined directly within the IoT systems edge-cloud continuum. We introduce ContinuumConductor a layered decision framework that guides when to perform process mining tasks such as preprocessing, correlation, and discovery centrally or decentrally. Thus, enabling privacy, responsive and resource-efficient process mining. For each step in the process mining pipeline, we analyze the trade-offs of decentralization versus centralization across these layers and propose decision criteria. We demonstrate ContinuumConductor at a real-world use-case of process optimazition in inland ports. Our contributions lay the foundation for computing-aware process mining in cyber-physical and IIoT systems. - oai:arXiv.org:2512.07280v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Hendrik Reiter, Janick Edinger, Martin Kabierski, Agnes Koschmider, Olaf Landsiedel, Arvid Lepsien, Xixi Lu, Andrea Marrella, Estefania Serral, Stefan Schulte, Florian Tschorsch, Matthias Weidlich, Wilhelm Hasselbring + Sukhun Ko, Seokhyun Yoon, Dahyeon Kye, Kyle Min, Chanho Eom, Jihyong Oh - SIT-Graph: State Integrated Tool Graph for Multi-Turn Agents - https://arxiv.org/abs/2512.07287 - arXiv:2512.07287v1 Announce Type: new -Abstract: Despite impressive advances in agent systems, multi-turn tool-use scenarios remain challenging. It is mainly because intent is clarified progressively and the environment evolves with each tool call. While reusing past experience is natural, current LLM agents either treat entire trajectories or pre-defined subtasks as indivisible units, or solely exploit tool-to-tool dependencies, hindering adaptation as states and information evolve across turns. In this paper, we propose a State Integrated Tool Graph (SIT-Graph), which enhances multi-turn tool use by exploiting partially overlapping experience. Inspired by human decision-making that integrates episodic and procedural memory, SIT-Graph captures both compact state representations (episodic-like fragments) and tool-to-tool dependencies (procedural-like routines) from historical trajectories. Specifically, we first build a tool graph from accumulated tool-use sequences, and then augment each edge with a compact state summary of the dialog and tool history that may shape the next action. At inference time, SIT-Graph enables a human-like balance between episodic recall and procedural execution: when the next decision requires recalling prior context, the agent retrieves the state summaries stored on relevant edges and uses them to guide its next action; when the step is routine, it follows high-confidence tool dependencies without explicit recall. Experiments across multiple stateful multi-turn tool-use benchmarks show that SIT-Graph consistently outperforms strong memory- and graph-based baselines, delivering more robust tool selection and more effective experience transfer. - oai:arXiv.org:2512.07287v1 + Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models + https://arxiv.org/abs/2508.14285 + arXiv:2508.14285v2 Announce Type: replace +Abstract: Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, it is often unclear how well the fine-tuned LLM will generalize, i.e., how well it will perform on unseen datasets. Methods have been proposed to improve generalization by optimizing in-context prompts, or by using meta-learning to fine-tune LLMs. However, these methods are expensive in memory and computation, requiring either long-context prompts or saving copies of parameters and using second-order gradient updates. To address these challenges, we propose Amortized Bayesian Meta-Learning for LoRA (ABMLL). This method builds on amortized Bayesian meta-learning for smaller models, adapting this approach to LLMs while maintaining its computational efficiency. We reframe task-specific and global parameters in the context of LoRA and use a new hyperparameter to balance reconstruction accuracy and the fidelity of task-specific parameters to the global ones. ABMLL provides effective generalization and scales to large models such as LLAMA3-8B. Furthermore, as a result of using a Bayesian framework, ABMLL provides improved uncertainty quantification. We test ABMLL on CrossFit and Unified-QA datasets and find that it outperforms existing methods on these benchmarks in terms of both accuracy and expected calibration error. + oai:arXiv.org:2508.14285v2 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sijia Li, Yuchen Huang, Zifan Liu, Zijian Li, Jingjing fu, Lei Song, Jiang Bian, Jun Zhang, Rui Wang + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Liyi Zhang, Jake Snell, Thomas L. Griffiths - Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models - https://arxiv.org/abs/2512.07288 - arXiv:2512.07288v1 Announce Type: new -Abstract: Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models' actual behavior and has found that they often lack faithfulness. However, the question of how to improve faithfulness remains underexplored. Moreover, because different explanation styles have superficially distinct characteristics, it is unclear whether improvements observed in one style also arise when using other styles. This study analyzes the effects of training for faithful self-explanations and the extent to which these effects generalize, using three classification tasks and three explanation styles. We construct one-word constrained explanations that are likely to be faithful using a feature attribution method, and use these pseudo-faithful self-explanations for continual learning on instruction-tuned models. Our experiments demonstrate that training can improve self-explanation faithfulness across all classification tasks and explanation styles, and that these improvements also show signs of generalization to the multi-word settings and to unseen tasks. Furthermore, we find consistent cross-style generalization among three styles, suggesting that training may contribute to a broader improvement in faithful self-explanation ability. - oai:arXiv.org:2512.07288v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tomoki Doi, Masaru Isonuma, Hitomi Yanaka + A statistical test for network similarity + https://arxiv.org/abs/2508.14399 + arXiv:2508.14399v2 Announce Type: replace +Abstract: In this article, we revisit and expand our prior work on graph similarity. As with our earlier work, we focus on a view of similarity which does not require node correspondence between graphs under comparison. Our work is suited to the temporal study of networks, change-point and anomaly detection and simple comparisons of static graphs. It provides a similarity metric for the study of (weakly) connected graphs. Our work proposes a metric designed to compare networks and assess the (dis)similarity between them. For example, given three different graphs with possibly different numbers of nodes, $G_1$, $G_2$ and $G_3$, we aim to answer two questions: a) "How different is $G_1 $ from $G_2$?" and b) "Is graph $G_3$ more similar to $G_1$ or to $G_2$?". We illustrate the value of our test and its accuracy through several new experiments, using synthetic and real-world graphs. + oai:arXiv.org:2508.14399v2 + cs.DM + stat.AP + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Pierre Miasnikof, Alexander Y. Shetopaloff - Breaking ECDSA with Electromagnetic Side-Channel Attacks: Challenges and Practicality on Modern Smartphones - https://arxiv.org/abs/2512.07292 - arXiv:2512.07292v1 Announce Type: new -Abstract: Smartphones handle sensitive tasks such as messaging and payment and may soon support critical electronic identification through initiatives such as the European Digital Identity (EUDI) wallet, currently under development. Yet the susceptibility of modern smartphones to physical side-channel analysis (SCA) is underexplored, with recent work limited to pre-2019 hardware. Since then, smartphone system on chip (SoC) platforms have grown more complex, with heterogeneous processor clusters, sub 10 nm nodes, and frequencies over 2 GHz, potentially complicating SCA. In this paper, we assess the feasibility of electromagnetic (EM) SCA on a Raspberry Pi 4, featuring a Broadcom BCM2711 SoC and a Fairphone 4 featuring a Snapdragon 750G 5G SoC. Using new attack methodologies tailored to modern SoCs, we recover ECDSA secrets from OpenSSL by mounting the Nonce@Once attack of Alam et al. (Euro S&P 2021) and show that the libgcrypt countermeasure does not fully mitigate it. We present case studies illustrating how hardware and software stacks impact EM SCA feasibility. Motivated by use cases such as the EUDI wallet, we survey Android cryptographic implementations and define representative threat models to assess the attack. Our findings show weaknesses in ECDSA software implementations and underscore the need for independently certified secure elements (SEs) in all smartphones. - oai:arXiv.org:2512.07292v1 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - new + SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass + https://arxiv.org/abs/2508.15769 + arXiv:2508.15769v2 Announce Type: replace +Abstract: 3D content generation has recently attracted significant research interest, driven by its critical applications in VR/AR and embodied AI. In this work, we tackle the challenging task of synthesizing multiple 3D assets within a single scene image. Concretely, our contributions are fourfold: (i) we present SceneGen, a novel framework that takes a scene image and corresponding object masks as input, simultaneously producing multiple 3D assets with geometry and texture. Notably, SceneGen operates with no need for extra optimization or asset retrieval; (ii) we introduce a novel feature aggregation module that integrates local and global scene information from visual and geometric encoders within the feature extraction module. Coupled with a position head, this enables the generation of 3D assets and their relative spatial positions in a single feedforward pass; (iii) we demonstrate SceneGen's direct extensibility to multi-image input scenarios. Despite being trained solely on single-image inputs, our architecture yields improved generation performance when multiple images are provided; and (iv) extensive quantitative and qualitative evaluations confirm the efficiency and robustness of our approach. We believe this paradigm offers a novel solution for high-quality 3D content generation, potentially advancing its practical applications in downstream tasks. The code and model will be publicly available at: https://mengmouxu.github.io/SceneGen. + oai:arXiv.org:2508.15769v2 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Felix Oberhansl, Marc Schink, Nisha Jacob Kabakci, Michael Gruber, Dominik Klein, Sven Freud, Tobias Damm, Michael Hartmeier, Ivan Gavrilan, Silvan Streit, Jonas Stappenbeck, Andreas Seelos Zankl + Yanxu Meng, Haoning Wu, Ya Zhang, Weidi Xie - The Human Need for Storytelling: Reflections on Qualitative Software Engineering Research With a Focus Group of Experts - https://arxiv.org/abs/2512.07293 - arXiv:2512.07293v1 Announce Type: new -Abstract: From its first adoption in the late 80s, qualitative research has slowly but steadily made a name for itself in what was, and perhaps still is, the predominantly quantitative software engineering (SE) research landscape. As part of our regular column on empirical software engineering (ACM SIGSOFT SEN-ESE), we reflect on the state of qualitative SE research with a focus group of experts. Among other things, we discuss why qualitative SE research is important, how it evolved over time, common impediments faced while practicing it today, and what the future of qualitative SE research might look like. Joining the conversation are Rashina Hoda (Monash University, Australia), Carolyn Seaman (University of Maryland, United States), and Klaas Stol (University College Cork, Ireland). The content of this paper is a faithful account of our conversation from October 25, 2025, which we moderated and edited for our column. - oai:arXiv.org:2512.07293v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new + Not Just for Archiving: Provable Benefits of Reusing the Archive in Evolutionary Multi-objective Optimization + https://arxiv.org/abs/2508.16993 + arXiv:2508.16993v2 Announce Type: replace +Abstract: Evolutionary Algorithms (EAs) have become the most popular tool for solving widely-existed multi-objective optimization problems. In Multi-Objective EAs (MOEAs), there is increasing interest in using an archive to store non-dominated solutions generated during the search. This approach can 1) mitigate the effects of population oscillation, a common issue in many MOEAs, and 2) allow for the use of smaller, more practical population sizes. In this paper, we analytically show that the archive can even further help MOEAs through reusing its solutions during the process of new solution generation. We first prove that using a small population size alongside an archive (without incorporating archived solutions in the generation process) may fail on certain problems, as the population may remove previously discovered but promising solutions. We then prove that reusing archive solutions can overcome this limitation, resulting in at least a polynomial speedup on the expected running time. Our analysis focuses on the well-established SMS-EMOA algorithm applied to the commonly studied OneJumpZeroJump problem as well as one of its variants. We also show that reusing archive solutions can be better than using a large population size directly. Finally, we show that our theoretical findings can generally hold in practice by experiments on well-known practical optimization problems -- multi-objective 0-1 Knapsack, TSP, QAP and NK-landscape problems -- with realistic settings. + oai:arXiv.org:2508.16993v2 + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Roberto Verdecchia, Justus Bogner + Shengjie Ren, Zimin Liang, Miqing Li, Chao Qian - PIP: Making Andersen's Points-to Analysis Sound and Practical for Incomplete C Programs - https://arxiv.org/abs/2512.07299 - arXiv:2512.07299v1 Announce Type: new -Abstract: Compiling files individually lends itself well to parallelization, but forces the compiler to operate on incomplete programs. State-of-the-art points-to analyses guarantee sound solutions only for complete programs, requiring summary functions to describe any missing program parts. Summary functions are rarely available in production compilers, however, where soundness and efficiency are non-negotiable. This paper presents an Andersen-style points-to analysis that efficiently produces sound solutions for incomplete C programs. The analysis accomplishes soundness by tracking memory locations and pointers that are accessible from external modules, and efficiency by performing this tracking implicitly in the constraint graph. We show that implicit pointee tracking makes the constraint solver 15$\times$ faster than any combination of five different state-of-the-art techniques using explicit pointee tracking. We also present the Prefer Implicit Pointees (PIP) technique that further reduces the use of explicit pointees. PIP gives an additional speedup of 1.9$\times$, compared to the fastest solver configuration not benefiting from PIP. The precision of the analysis is evaluated in terms of an alias-analysis client, where it reduces the number of MayAlias-responses by 40% compared to LLVM's BasicAA pass alone. Finally, we show that the analysis is scalable in terms of memory, making it suitable for optimizing compilers in practice. - oai:arXiv.org:2512.07299v1 - cs.PL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Random-phase Wave Splatting of Translucent Primitives for Computer-generated Holography + https://arxiv.org/abs/2508.17480 + arXiv:2508.17480v2 Announce Type: replace +Abstract: Holographic near-eye displays offer ultra-compact form factors for VR/AR systems but rely on advanced computer-generated holography (CGH) algorithms to convert 3D scenes into interference patterns on spatial light modulators (SLMs). Conventional CGH typically generates smooth-phase holograms, limiting view-dependent effects and realistic defocus blur, while severely under-utilizing the SLM space-bandwidth product. + We propose Random-phase Wave Splatting (RPWS), a unified wave optics rendering framework that converts arbitrary 3D representations based on 2D translucent primitives into random-phase holograms. RPWS is fully compatible with modern 3D representations such as Gaussians and triangles, improves bandwidth utilization which effectively enlarges eyebox size, reconstructs accurate defocus blur and parallax, and leverages time-multiplexed rendering not as a heuristic for speckle suppression, but as a mathematically exact alpha-blending mechanism derived from first principles in statistics. At the core of RPWS are (1) a new wavefront compositing procedure and (2) an alpha-blending scheme for random-phase geometric primitives, ensuring correct color reconstruction and robust occlusion when compositing millions of primitives. + RPWS departs substantially from the recent primitive-based CGH algorithm, Gaussian Wave Splatting (GWS). Because GWS uses smooth-phase primitives, it struggles to capture view-dependent effects and realistic defocus blur and under-utilizes the SLM space-bandwidth product; moreover, naively extending GWS to random-phase primitives fails to reconstruct accurate colors. In contrast, RPWS is designed from the ground up for arbitrary random-phase translucent primitives, and through simulations and experimental validations we demonstrate state-of-the-art image quality and perceptually faithful 3D holograms for next-generation near-eye displays. + oai:arXiv.org:2508.17480v2 + cs.GR + cs.AR + eess.IV + eess.SP + physics.optics + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - H{\aa}vard Rognebakke Krogstie, Helge Bahmann, Magnus Sj\"alander, Nico Reissmann + Brian Chao, Jacqueline Yang, Suyeon Choi, Manu Gopakumar, Ryota Koiso, Gordon Wetzstein - Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts - https://arxiv.org/abs/2512.07302 - arXiv:2512.07302v1 Announce Type: new -Abstract: Existing image perception methods based on VLMs generally follow a paradigm wherein models extract and analyze image content based on user-provided textual task prompts. However, such methods face limitations when applied to UAV imagery, which presents challenges like target confusion, scale variations, and complex backgrounds. These challenges arise because VLMs' understanding of image content depends on the semantic alignment between visual and textual tokens. When the task prompt is simplistic and the image content is complex, achieving effective alignment becomes difficult, limiting the model's ability to focus on task-relevant information. To address this issue, we introduce AerialVP, the first agent framework for task prompt enhancement in UAV image perception. AerialVP proactively extracts multi-dimensional auxiliary information from UAV images to enhance task prompts, overcoming the limitations of traditional VLM-based approaches. Specifically, the enhancement process includes three stages: (1) analyzing the task prompt to identify the task type and enhancement needs, (2) selecting appropriate tools from the tool repository, and (3) generating enhanced task prompts based on the analysis and selected tools. To evaluate AerialVP, we introduce AerialSense, a comprehensive benchmark for UAV image perception that includes Aerial Visual Reasoning, Aerial Visual Question Answering, and Aerial Visual Grounding tasks. AerialSense provides a standardized basis for evaluating model generalization and performance across diverse resolutions, lighting conditions, and both urban and natural scenes. Experimental results demonstrate that AerialVP significantly enhances task prompt guidance, leading to stable and substantial performance improvements in both open-source and proprietary VLMs. Our work will be available at https://github.com/lostwolves/AerialVP. - oai:arXiv.org:2512.07302v1 - cs.CV + LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions + https://arxiv.org/abs/2508.18321 + arXiv:2508.18321v3 Announce Type: replace +Abstract: Large language models (LLMs) are increasingly integrated into multi-agent systems (MAS), where peer interactions shape individual decisions. While prior work has mainly examined conformity bias, we broaden the view to include how LLMs build rapport from prior interactions, discern and integrate high-quality peer information, and resist misleading inputs-abilities essential for achieving collective intelligence under complex social dynamics. We introduce KAIROS, a benchmark that simulates quiz-style collaboration with peer agents whose rapport levels and behaviours can be precisely controlled in both historical interactions and the current round. This unified setup enables systematic analysis of how rapport, peer actions, and the model's self-confidence jointly influence decision-making. Using KAIROS, we evaluate prompting, supervised fine-tuning, and reinforcement learning via Group Relative Policy Optimisation (GRPO). Results show that model scale is a primary factor moderating susceptibility to social influence: larger models are more resilient and benefit from prompting-based mitigation, whereas smaller models remain vulnerable. Only carefully configured GRPO training yields consistent robustness and performance gains for small models. + oai:arXiv.org:2508.18321v3 + cs.CL cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mingning Guo, Mengwei Wu, Shaoxian Li, Haifeng Li, Chao Tao + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Maojia Song, Tej Deep Pala, Ruiwen Zhou, Weisheng Jin, Amir Zadeh, Chuan Li, Dorien Herremans, Soujanya Poria - Efficient Computation of a Continuous Topological Model of the Configuration Space of Tethered Mobile Robots - https://arxiv.org/abs/2512.07303 - arXiv:2512.07303v1 Announce Type: new -Abstract: Despite the attention that the problem of path planning for tethered robots has garnered in the past few decades, the approaches proposed to solve it typically rely on a discrete representation of the configuration space and do not exploit a model that can simultaneously capture the topological information of the tether and the continuous location of the robot. In this work, we explicitly build a topological model of the configuration space of a tethered robot starting from a polygonal representation of the workspace where the robot moves. To do so, we first establish a link between the configuration space of the tethered robot and the universal covering space of the workspace, and then we exploit this link to develop an algorithm to compute a simplicial complex model of the configuration space. We show how this approach improves the performances of existing algorithms that build other types of representations of the configuration space. The proposed model can be computed in a fraction of the time required to build traditional homotopy-augmented graphs, and is continuous, allowing to solve the path planning task for tethered robots using a broad set of path planning algorithms. - oai:arXiv.org:2512.07303v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Gianpietro Battocletti, Dimitris Boskos, Bart De Schutter + A Unifying Framework for Global Optimization: From Theory to Formalization + https://arxiv.org/abs/2508.20671 + arXiv:2508.20671v2 Announce Type: replace +Abstract: We introduce an abstract measure___theoretic framework that serves as a tool to rigorously study stochastic iterative global optimization algorithms as a unified class. The framework is formulated in terms of probability kernels, which, via the Ionescu--Tulcea theorem, induce probability measures on the space of sequences of algorithm iterations, endowed with two intuitive properties. This framework answers the need for a general, implementation___independent formalism in the analysis of such algorithms, providing a starting point for formalizing general results in proof-assistants. To illustrate the relevance of our tool, we show that common algorithms fit naturally in the framework, and we also use it to give a rigorous proof of a general consistency theorem for stochastic iterative global optimization algorithms (Proposition 3 of (Malherbe, et al., 2017). This proof and the entire framework are formalized in the Lean proof assistant. This formalization both ensures the correctness of the definitions and proofs, and provides a basis for future machine-assisted formalizations in the field. + oai:arXiv.org:2508.20671v2 + cs.FL + cs.LO + math.OC + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Ga\"etan Serr\'e (ENS Paris Saclay, CB), Argyris Kalogeratos (CB, ENS Paris Saclay), Nicolas Vayatis (CB, ENS Paris Saclay) - Reevaluating Automated Wildlife Species Detection: A Reproducibility Study on a Custom Image Dataset - https://arxiv.org/abs/2512.07305 - arXiv:2512.07305v1 Announce Type: new -Abstract: This study revisits the findings of Carl et al., who evaluated the pre-trained Google Inception-ResNet-v2 model for automated detection of European wild mammal species in camera trap images. To assess the reproducibility and generalizability of their approach, we reimplemented the experiment from scratch using openly available resources and a different dataset consisting of 900 images spanning 90 species. After minimal preprocessing, we obtained an overall classification accuracy of 62%, closely aligning with the 71% reported in the original work despite differences in datasets. As in the original study, per-class performance varied substantially, as indicated by a macro F1 score of 0.28,highlighting limitations in generalization when labels do not align directly with ImageNet classes. Our results confirm that pretrained convolutional neural networks can provide a practical baseline for wildlife species identification but also reinforce the need for species-specific adaptation or transfer learning to achieve consistent, high-quality predictions. - oai:arXiv.org:2512.07305v1 + Mixture of Contexts for Long Video Generation + https://arxiv.org/abs/2508.21058 + arXiv:2508.21058v3 Announce Type: replace +Abstract: Long video generation is fundamentally a long context memory problem: models must retain and retrieve salient events across a long range without collapsing or drifting. However, scaling diffusion transformers to generate long-context videos is fundamentally limited by the quadratic cost of self-attention, which makes memory and computation intractable and difficult to optimize for long sequences. We recast long-context video generation as an internal information retrieval task and propose a simple, learnable sparse attention routing module, Mixture of Contexts (MoC), as an effective long-term memory retrieval engine. In MoC, each query dynamically selects a few informative chunks plus mandatory anchors (caption, local windows) to attend to, with causal routing that prevents loop closures. As we scale the data and gradually sparsify the routing, the model allocates compute to salient history, preserving identities, actions, and scenes over minutes of content. Efficiency follows as a byproduct of retrieval (near-linear scaling), which enables practical training and synthesis, and the emergence of memory and consistency at the scale of minutes. + oai:arXiv.org:2508.21058v3 + cs.GR + cs.AI cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/publicdomain/zero/1.0/ - Tobias Abraham Haider + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-sa/4.0/ + Shengqu Cai, Ceyuan Yang, Lvmin Zhang, Yuwei Guo, Junfei Xiao, Ziyan Yang, Yinghao Xu, Zhenheng Yang, Alan Yuille, Leonidas Guibas, Maneesh Agrawala, Lu Jiang, Gordon Wetzstein - Zero Carbon V2X Tariffs for Non-Domestic Customers - https://arxiv.org/abs/2512.07308 - arXiv:2512.07308v1 Announce Type: new -Abstract: With the aim of meeting the worlds net-zero objectives, electricity trading through contractual agreements is becoming increasingly relevant in global and local energy markets. We develop contracts enabling efficient energy trading using Vehicle to Everything technology which can be applied to regulate energy markets and reduce costs and carbon emissions by using electric vehicles with bidirectional batteries to store energy during offpeak hours for export during peak hours. We introduce a contract based on the VCG mechanism which enables fleets of electric vehicles to export electricity to the grid efficiently throughout the day, where each electric vehicle has its energy consumption and exporting schedules and costs. - oai:arXiv.org:2512.07308v1 - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 - new + Locus: Agentic Predicate Synthesis for Directed Fuzzing + https://arxiv.org/abs/2508.21302 + arXiv:2508.21302v3 Announce Type: replace +Abstract: Directed fuzzing aims to find program inputs that lead to specified target program states. It has broad applications, such as debugging system crashes, confirming reported bugs, and generating exploits for potential vulnerabilities. This task is inherently challenging because target states are often deeply nested in the program, while the search space manifested by numerous possible program inputs is prohibitively large. Existing approaches rely on branch distances or manually-specified constraints to guide the search; however, the branches alone are often insufficient to precisely characterize progress toward reaching the target states, while the manually specified constraints are often tailored for specific bug types and thus difficult to generalize to diverse target states and programs. + We present Locus, a novel framework to improve the efficiency of directed fuzzing. Our key insight is to synthesize predicates to capture fuzzing progress as semantically meaningful intermediate states, serving as milestones towards reaching the target states. When used to instrument the program under fuzzing, they can reject executions unlikely to reach the target states, while providing additional coverage guidance. To automate this task and generalize to diverse programs, Locus features an agentic framework with program analysis tools to synthesize and iteratively refine the candidate predicates, while ensuring the predicates strictly relax the target states to prevent false rejections via symbolic execution. Our evaluation shows that Locus substantially improves the efficiency of eight state-of-the-art fuzzers in discovering real-world vulnerabilities, achieving an average speedup of 41.6x. So far, Locus has found nine previously unpatched bugs, with three already acknowledged with draft patches. + oai:arXiv.org:2508.21302v3 + cs.CR + cs.AI + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Elisheva S Shamash, Zhong Fan + 10.1145/3744916.3773102 + Jie Zhu, Chihao Shen, Ziyang Li, Jiahao Yu, Yizheng Chen, Kexin Pei - Radiance-Field Reinforced Pretraining: Scaling Localization Models with Unlabeled Wireless Signals - https://arxiv.org/abs/2512.07309 - arXiv:2512.07309v1 Announce Type: new -Abstract: Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learning has greatly enhanced localization accuracy and robustness, existing localization models still face major challenges in cross-scene generalization due to their reliance on scene-specific labeled data. To address this, we introduce Radiance-Field Reinforced Pretraining (RFRP). This novel self-supervised pretraining framework couples a large localization model (LM) with a neural radio-frequency radiance field (RF-NeRF) in an asymmetrical autoencoder architecture. In this design, the LM encodes received RF spectra into latent, position-relevant representations, while the RF-NeRF decodes them to reconstruct the original spectra. This alignment between input and output enables effective representation learning using large-scale, unlabeled RF data, which can be collected continuously with minimal effort. To this end, we collected RF samples at 7,327,321 positions across 100 diverse scenes using four common wireless technologies--RFID, BLE, WiFi, and IIoT. Data from 75 scenes were used for training, and the remaining 25 for evaluation. Experimental results show that the RFRP-pretrained LM reduces localization error by over 40% compared to non-pretrained models and by 21% compared to those pretrained using supervised learning. - oai:arXiv.org:2512.07309v1 + AoI-based Scheduling of Correlated Sources for Timely Inference + https://arxiv.org/abs/2509.01926 + arXiv:2509.01926v2 Announce Type: replace +Abstract: We investigate a real-time remote inference system where multiple correlated sources transmit observations over a communication channel to a receiver. The receiver utilizes these observations to infer multiple time-varying targets. Due to limited communication resources, the delivered observations may not be fresh. To quantify data freshness, we employ the Age of Information (AoI) metric. To minimize the inference error, we aim to design a signal-agnostic scheduling policy that leverages AoI without requiring knowledge of the actual target values or the source observations. This scheduling problem is a restless multi-armed bandit (RMAB) problem with a non-separable penalty function. Unlike traditional RMABs, the correlation among sources introduces a unique challenge: the penalty function of each source depends on the AoI of other correlated sources, preventing the problem from decomposing into multiple independent Markov Decision Processes (MDPs), a key step in applying traditional RMAB solutions. To address this, we propose a novel approach that approximates the penalty function for each source and establishes an analytical bound on the approximation error. We then develop scheduling policies for two scenarios: (i) full knowledge of the penalty functions and (ii) no knowledge of the penalty functions. For the case of known penalty functions, we present an upper bound on the optimality gap that highlights the impact of the correlation parameter and the system size. For the case of unknown penalty functions and signal distributions, we develop an online learning approach that utilizes bandit feedback to learn an online Maximum Gain First policy. Simulation results demonstrate the effectiveness of our proposed policies in minimizing inference error and achieving scalability in the number of sources. + oai:arXiv.org:2509.01926v2 + cs.NI cs.IT - cs.AI math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Guosheng Wang, Shen Wang, Lei Yang - - - Towards a Relationship-Aware Transformer for Tabular Data - https://arxiv.org/abs/2512.07310 - arXiv:2512.07310v1 Announce Type: new -Abstract: Deep learning models for tabular data typically do not allow for imposing a graph of external dependencies between samples, which can be useful for accounting for relatedness in tasks such as treatment effect estimation. Graph neural networks only consider adjacent nodes, making them difficult to apply to sparse graphs. This paper proposes several solutions based on a modified attention mechanism, which accounts for possible relationships between data points by adding a term to the attention matrix. Our models are compared with each other and the gradient boosting decision trees in a regression task on synthetic and real-world datasets, as well as in a treatment effect estimation task on the IHDP dataset. - oai:arXiv.org:2512.07310v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Andrei V. Konstantinov, Valerii A. Zuev, Lev V. Utkin + Md Kamran Chowdhury Shisher, Vishrant Tripathi, Mung Chiang, Christopher G. Brinton - DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Management - https://arxiv.org/abs/2512.07312 - arXiv:2512.07312v1 Announce Type: new -Abstract: The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and their asynchronous management, we investigate the opposite point of the design spectrum: a multi-core AI accelerator equipped with a shared system-level cache and application-aware management policies, which keeps the programming effort modest. Our approach exploits dataflow information available in the software stack to guide cache replacement (including dead-block prediction), in concert with bypass decisions and mechanisms that alleviate cache thrashing. - We assess the proposal using a cycle-accurate simulator and observe substantial performance gains (up to 1.80x speedup) compared with conventional cache architectures. In addition, we build and validate an analytical model that takes into account the actual overlapping behaviors to extend the measurement results of our policies to real-world larger-scale workloads. Experiment results show that when functioning together, our bypassing and thrashing mitigation strategies can handle scenarios both with and without inter-core data sharing and achieve remarkable speedups. - Finally, we implement the design in RTL and the area of our design is $\mathbf{0.064mm^2}$ with 15nm process, which can run at 2 GHz clock frequency. Our findings explore the potential of the shared cache design to assist the development of future AI accelerator systems. - oai:arXiv.org:2512.07312v1 - cs.AR + Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning + https://arxiv.org/abs/2509.03817 + arXiv:2509.03817v2 Announce Type: replace +Abstract: Multi-agent systems of large language models (LLMs) show promise for complex reasoning, but their effectiveness is often limited by fixed collaboration protocols. These frameworks typically focus on macro-level orchestration while overlooking agents' internal deliberative capabilities. This critical meta-cognitive blindspot treats agents as passive executors unable to adapt their strategy based on internal cognitive states like uncertainty or confidence. We introduce the Meta-Policy Deliberation Framework (MPDF), where agents learn a decentralized policy over a set of high-level meta-cognitive actions: Persist, Refine, and Concede. To overcome the instability of traditional policy gradients in this setting, we develop SoftRankPO, a novel reinforcement learning algorithm. SoftRankPO stabilizes training by shaping advantages based on the rank of rewards mapped through smooth normal quantiles, making the learning process robust to reward variance. Experiments show that MPDF with SoftRankPO achieves a a 4-5% absolute gain in average accuracy across five mathematical and general reasoning benchmarks compared to six state-of-the-art heuristic and learning-based multi-agent reasoning algorithms. Our work presents a paradigm for learning adaptive, meta-cognitive policies for multi-agent LLM systems, shifting the focus from designing fixed protocols to learning dynamic, deliberative strategies. + oai:arXiv.org:2509.03817v2 cs.AI - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhongchun Zhou, Chengtao Lai, Yuhang Gu, Wei Zhang - - - Learning-Augmented Ski Rental with Discrete Distributions: A Bayesian Approach - https://arxiv.org/abs/2512.07313 - arXiv:2512.07313v1 Announce Type: new -Abstract: We revisit the classic ski rental problem through the lens of Bayesian decision-making and machine-learned predictions. While traditional algorithms minimize worst-case cost without assumptions, and recent learning-augmented approaches leverage noisy forecasts with robustness guarantees, our work unifies these perspectives. We propose a discrete Bayesian framework that maintains exact posterior distributions over the time horizon, enabling principled uncertainty quantification and seamless incorporation of expert priors. Our algorithm achieves prior-dependent competitive guarantees and gracefully interpolates between worst-case and fully-informed settings. Our extensive experimental evaluation demonstrates superior empirical performance across diverse scenarios, achieving near-optimal results under accurate priors while maintaining robust worst-case guarantees. This framework naturally extends to incorporate multiple predictions, non-uniform priors, and contextual information, highlighting the practical advantages of Bayesian reasoning in online decision problems with imperfect predictions. - oai:arXiv.org:2512.07313v1 - cs.LG - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Bosun Kang, Hyejun Park, Chenglin Fan + Wei Yang, Jesse Thomason - M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling - https://arxiv.org/abs/2512.07314 - arXiv:2512.07314v1 Announce Type: new -Abstract: Modeling human mobility is vital for extensive applications such as transportation planning and epidemic modeling. With the rise of the Artificial Intelligence Generated Content (AIGC) paradigm, recent works explore synthetic trajectory generation using autoregressive and diffusion models. While these methods show promise for generating single-day trajectories, they remain limited by inefficiencies in long-term generation (e.g., weekly trajectories) and a lack of explicit spatiotemporal multi-scale modeling. This study proposes Multi-Scale Spatio-Temporal AutoRegression (M-STAR), a new framework that generates long-term trajectories through a coarse-to-fine spatiotemporal prediction process. M-STAR combines a Multi-scale Spatiotemporal Tokenizer that encodes hierarchical mobility patterns with a Transformer-based decoder for next-scale autoregressive prediction. Experiments on two real-world datasets show that M-STAR outperforms existing methods in fidelity and significantly improves generation speed. The data and codes are available at https://github.com/YuxiaoLuo0013/M-STAR. - oai:arXiv.org:2512.07314v1 - cs.AI + Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Families + https://arxiv.org/abs/2509.04622 + arXiv:2509.04622v5 Announce Type: replace +Abstract: Representational similarity metrics are fundamental tools in neuroscience and AI, yet we lack systematic comparisons of their discriminative power across model families. We introduce a quantitative framework to evaluate representational similarity measures based on their ability to separate model families-across architectures (CNNs, Vision Transformers, Swin Transformers, ConvNeXt) and training regimes (supervised vs. self-supervised). Using three complementary separability measures-dprime from signal detection theory, silhouette coefficients and ROC-AUC, we systematically assess the discriminative capacity of commonly used metrics including RSA, linear predictivity, Procrustes, and soft matching. We show that separability systematically increases as metrics impose more stringent alignment constraints. Among mapping-based approaches, soft-matching achieves the highest separability, followed by Procrustes alignment and linear predictivity. Non-fitting methods such as RSA also yield strong separability across families. These results provide the first systematic comparison of similarity metrics through a separability lens, clarifying their relative sensitivity and guiding metric choice for large-scale model and brain comparisons. + oai:arXiv.org:2509.04622v5 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuxiao Luo, Songming Zhang, Sijie Ruan, Siran Chen, Kang Liu, Yang Xu, Yu Zheng, Ling Yin - - - On the Orbits of Similarity Classes of Tetrahedra Generated by the Longest-Edge Bisection Algorithm - https://arxiv.org/abs/2512.07315 - arXiv:2512.07315v1 Announce Type: new -Abstract: In this work, we study the dynamics of similarity classes of tetrahedra generated by the longest-edge bisection (LEB) algorithm. Building on the normalization strategy introduced by Perdomo and Plaza for triangles, we construct a canonical representation of tetrahedra in a normalized space embedded in the product of the hyperbolic half-plane and the hyperbolic half-space model. This representation allows us to define the left and right refinement maps, $\Phi_L$ and $\Phi_R$, acting on the space of normalized tetrahedral shapes, and to study their iterative orbits as discrete dynamical systems. Using these maps, we show that the orbit of the space-filling Sommerville tetrahedron contains only 4 similarity classes, 3 of which form an attractive cycle corresponding to the orbit of the path tetrahedron. We also show that small perturbations of elements in those orbits still lead to finite orbits. In addition, we study small perturbations of the regular tetrahedron and show that their orbits are also finite. Extensive numerical exploration of orbits for the other types of tetrahedra suggests that the LEB algorithm does not produce degenerating tetrahedra. Our framework provides a geometric and dynamical foundation for analyzing the shape evolution of tetrahedral meshes and offers a possible route toward an analytic proof of the non-degeneracy property for the tetrahedral partitions generated by the LEB refinements. This property is highly desired in e.g. the finite element methods (FEMs). - oai:arXiv.org:2512.07315v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - J\'er\^ome Michaud, Sergey Korotov - - - Model Predictive Control for Cooperative Docking Between Autonomous Surface Vehicles with Disturbance Rejection - https://arxiv.org/abs/2512.07316 - arXiv:2512.07316v1 Announce Type: new -Abstract: Uncrewed Surface Vehicles (USVs) are a popular and efficient type of marine craft that find application in a large number of water-based tasks. When multiple USVs operate in the same area, they may be required to dock to each other to perform a shared task. Existing approaches for the docking between autonomous USVs generally consider one USV as a stationary target, while the second one is tasked to reach the required docking pose. In this work, we propose a cooperative approach for USV-USV docking, where two USVs work together to dock at an agreed location. We use a centralized Model Predictive Control (MPC) approach to solve the control problem, obtaining feasible trajectories that also guarantee constraint satisfaction. Owing to its model-based nature, this approach allows the rejection of disturbances, inclusive of exogenous inputs, by anticipating their effect on the USVs through the MPC prediction model. This is particularly effective in case of almost-stationary disturbances such as water currents. In simulations, we demonstrate how the proposed approach allows for a faster and more efficient docking with respect to existing approaches. - oai:arXiv.org:2512.07316v1 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.AI + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Gianpietro Battocletti, Dimitris Boskos, Bart De Schutter + Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla - DBMC-aNOMAly: Asynchronous NOMA with Pilot-Symbol Optimization Protocol for Diffusion-Based Molecular Communication Networks - https://arxiv.org/abs/2512.07317 - arXiv:2512.07317v1 Announce Type: new -Abstract: Multiple access (MA) schemes can enable cooperation between multiple nodes in future diffusion-based molecular communication (DBMC) networks. Non-orthogonal MA for DBMC networks (DBMC-NOMA) is a promising option for efficient simultaneous MA using a single molecule type. Expanding significantly upon previous work on the topic, this paper addresses the question of parameter optimization and bit error probability (BEP) reduction in an asynchronous network using DBMC-NOMA. First, we analytically derive the associated BEP and use the result for a thorough comparison with other MA schemes like time-division and molecule-division MA. We show that the asynchronous nature of the system can be exploited for performance gain, and the upper-bound performance can be achieved in all circumstances by avoiding a few worst-case offset configurations. Subsequently, we propose DBMC-aNOMAly, a pilot-symbol-based optimization protocol for asynchronous DBMC-NOMA, and extensively evaluate it using Monte-Carlo simulations. DBMC-aNOMAly is shown to provide robust BEP reduction for different network sizes, noise levels, subjected to sampling jitter, as well as for changing conditions during runtime, particularly, compared to protocols in previous work. DBMC-aNOMAly consists of a set of simple operations such as comparisons and additions, deliberately designed to be implementable with chemical reaction networks, setting up future work on the realistic modeling of the protocol. - oai:arXiv.org:2512.07317v1 - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 - new + Harnessing Object Grounding for Time-Sensitive Video Understanding + https://arxiv.org/abs/2509.06335 + arXiv:2509.06335v2 Announce Type: replace +Abstract: We propose to improve the time-sensitive video understanding (TSV) capability of video large language models (Video-LLMs) with grounded objects (GO). We hypothesize that TSV tasks can benefit from GO within frames, which is supported by our preliminary experiments on LITA, a state-of-the-art Video-LLM for reasoning temporal localization. While augmenting prompts with textual descriptions of these object annotations improves the performance of LITA, it also introduces extra token length and susceptibility to the noise in object-level information. To address this, we propose GO-Tokenizer, a lightweight add-on module for Video-LLMs leveraging off-the-shelf object detectors to encode compact object information on the fly. Experimental results demonstrate that pretraining with GO-Tokenizer outperforms the vanilla Video-LLM and its counterpart, utilizing textual descriptions of objects in the prompt. The gain generalizes across different models, datasets, and video understanding tasks, such as reasoning temporal localization and dense captioning. + oai:arXiv.org:2509.06335v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alexander Wietfeld, Wolfgang Kellerer + Tz-Ying Wu, Sharath Nittur Sridhar, Subarna Tripathi - ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation - https://arxiv.org/abs/2512.07328 - arXiv:2512.07328v1 Announce Type: new -Abstract: Text-to-video (T2V) generation has advanced rapidly, yet maintaining consistent character identities across scenes remains a major challenge. Existing personalization methods often focus on facial identity but fail to preserve broader contextual cues such as hairstyle, outfit, and body shape, which are critical for visual coherence. We propose \textbf{ContextAnyone}, a context-aware diffusion framework that achieves character-consistent video generation from text and a single reference image. Our method jointly reconstructs the reference image and generates new video frames, enabling the model to fully perceive and utilize reference information. Reference information is effectively integrated into a DiT-based diffusion backbone through a novel Emphasize-Attention module that selectively reinforces reference-aware features and prevents identity drift across frames. A dual-guidance loss combines diffusion and reference reconstruction objectives to enhance appearance fidelity, while the proposed Gap-RoPE positional embedding separates reference and video tokens to stabilize temporal modeling. Experiments demonstrate that ContextAnyone outperforms existing reference-to-video methods in identity consistency and visual quality, generating coherent and context-preserving character videos across diverse motions and scenes. Project page: \href{https://github.com/ziyang1106/ContextAnyone}{https://github.com/ziyang1106/ContextAnyone}. - oai:arXiv.org:2512.07328v1 + Zo3T: Zero-Shot 3D-Aware Trajectory-Guided Image-to-Video Generation via Test-Time Training + https://arxiv.org/abs/2509.06723 + arXiv:2509.06723v3 Announce Type: replace +Abstract: Trajectory-Guided image-to-video (I2V) generation aims to synthesize videos that adhere to user-specified motion instructions. Existing methods typically rely on computationally expensive fine-tuning on scarce annotated datasets. Although some zero-shot methods attempt to trajectory control in the latent space, they may yield unrealistic motion by neglecting 3D perspective and creating a misalignment between the manipulated latents and the network's noise predictions. To address these challenges, we introduce Zo3T, a novel zero-shot test-time-training framework for trajectory-guided generation with three core innovations: First, we incorporate a 3D-Aware Kinematic Projection, leveraging inferring scene depth to derive perspective-correct affine transformations for target regions. Second, we introduce Trajectory-Guided Test-Time LoRA, a mechanism that dynamically injects and optimizes ephemeral LoRA adapters into the denoising network alongside the latent state. Driven by a regional feature consistency loss, this co-adaptation effectively enforces motion constraints while allowing the pre-trained model to locally adapt its internal representations to the manipulated latent, thereby ensuring generative fidelity and on-manifold adherence. Finally, we develop Guidance Field Rectification, which refines the denoising evolutionary path by optimizing the conditional guidance field through a one-step lookahead strategy, ensuring efficient generative progression towards the target trajectory. Zo3T significantly enhances 3D realism and motion accuracy in trajectory-controlled I2V generation, demonstrating superior performance over existing training-based and zero-shot approaches. + oai:arXiv.org:2509.06723v3 cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ziyang Mai, Yu-Wing Tai + Ruicheng Zhang, Jun Zhou, Zunnan Xu, Zihao Liu, Jiehui Huang, Mingyang Zhang, Yu Sun, Xiu Li - The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers - https://arxiv.org/abs/2512.07331 - arXiv:2512.07331v1 Announce Type: new -Abstract: Vision Transformers (ViTs) lack the hierarchical inductive biases inherent to Convolutional Neural Networks (CNNs), theoretically allowing them to maintain high-dimensional representations throughout all layers. However, recent observations suggest ViTs often spontaneously manifest a "U-shaped" entropy profile-compressing information in middle layers before expanding it for the final classification. In this work, we demonstrate that this "Inductive Bottleneck" is not an architectural artifact, but a data-dependent adaptation. By analyzing the layer-wise Effective Encoding Dimension (EED) of DINO-trained ViTs across datasets of varying compositional complexity (UC Merced, Tiny ImageNet, and CIFAR-100), we show that the depth of the bottleneck correlates strongly with the semantic abstraction required by the task. We find that while texture-heavy datasets preserve high-rank representations throughout, object-centric datasets drive the network to dampen high-frequency information in middle layers, effectively "learning" a bottleneck to isolate semantic features. - oai:arXiv.org:2512.07331v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Knowledge Distillation Driven Semantic NOMA for Image Transmission with Diffusion Model + https://arxiv.org/abs/2509.07363 + arXiv:2509.07363v2 Announce Type: replace +Abstract: As a promising 6G enabler beyond conventional bit-level transmission, semantic communication can considerably reduce required bandwidth resources, while its combination with multiple access requires further exploration. This paper proposes a knowledge distillation-driven and diffusion-enhanced (KDD) semantic non-orthogonal multiple access (NOMA), named KDD-SemNOMA, for multi-user uplink wireless image transmission. Specifically, to ensure robust feature transmission across diverse transmission conditions, we firstly develop a ConvNeXt-based deep joint source and channel coding architecture with enhanced adaptive feature module. This module incorporates signal-to-noise ratio and channel state information to dynamically adapt to additive white Gaussian noise and Rayleigh fading channels. Furthermore, to improve image restoration quality without inference overhead, we introduce a two-stage knowledge distillation strategy, i.e., a teacher model, trained on interference-free orthogonal transmission, guides a student model via feature affinity distillation and cross-head prediction distillation. Moreover, a diffusion model-based refinement stage leverages generative priors to transform initial SemNOMA outputs into high-fidelity images with enhanced perceptual quality. Extensive experiments on CIFAR-10 and FFHQ-256 datasets demonstrate superior performance over state-of-the-art methods, delivering satisfactory reconstruction performance even at extremely poor channel conditions. These results highlight the advantages in both pixel-level accuracy and perceptual metrics, effectively mitigating interference and enabling high-quality image recovery. + oai:arXiv.org:2509.07363v2 + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Kanishk Awadhiya + Qifei Wang, Zhen Gao, Shuo Sun, Zhijin Qin, Xiaodong Xu, Meixia Tao - Local-Curvature-Aware Knowledge Graph Embedding: An Extended Ricci Flow Approach - https://arxiv.org/abs/2512.07332 - arXiv:2512.07332v1 Announce Type: new -Abstract: Knowledge graph embedding (KGE) relies on the geometry of the embedding space to encode semantic and structural relations. Existing methods place all entities on one homogeneous manifold, Euclidean, spherical, hyperbolic, or their product/multi-curvature variants, to model linear, symmetric, or hierarchical patterns. Yet a predefined, homogeneous manifold cannot accommodate the sharply varying curvature that real-world graphs exhibit across local regions. Since this geometry is imposed a priori, any mismatch with the knowledge graph's local curvatures will distort distances between entities and hurt the expressiveness of the resulting KGE. To rectify this, we propose RicciKGE to have the KGE loss gradient coupled with local curvatures in an extended Ricci flow such that entity embeddings co-evolve dynamically with the underlying manifold geometry towards mutual adaptation. Theoretically, when the coupling coefficient is bounded and properly selected, we rigorously prove that i) all the edge-wise curvatures decay exponentially, meaning that the manifold is driven toward the Euclidean flatness; and ii) the KGE distances strictly converge to a global optimum, which indicates that geometric flattening and embedding optimization are promoting each other. Experimental improvements on link prediction and node classification benchmarks demonstrate RicciKGE's effectiveness in adapting to heterogeneous knowledge graph structures. - oai:arXiv.org:2512.07332v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Zhengquan Luo, Guy Tadmor, Or Amar, David Zeevi, Zhiqiang Xu + Dynamic read & write optimization with TurtleKV + https://arxiv.org/abs/2509.10714 + arXiv:2509.10714v2 Announce Type: replace +Abstract: High read and write performance is important for generic key/value stores, which are fundamental to modern applications and databases. Yet, achieving high performance for both reads and writes is challenging due to traditionally limited memory and the pick-any-two-out-of-three tradeoff between memory use, read performance, and write performance. Existing state-of-the-art approaches limit memory usage and chose a primary dimension (reads or writes) for which to optimize their on-disk structures. They recover performance in the remaining dimension by other mechanisms. This approach limits databases' maximum performance in the remaining dimension and their dynamic (online) tunability to respond to changing workloads. We explore a different approach that dynamically trades memory for read or write performance as needed. We present TurtleKV, which includes a novel unbiased data structure for on-disk storage. It includes a knob that dynamically increases memory reserved for increasing read or write performance. When evaluated on YCSB, TurtleKV achieves up to 8x the write throughput of industry-leader RocksDB and up to 5x the read throughput while incurring similar space amplification. Compared to the state-of-the-art system SplinterDB, TurtleKV runs up to 40% better on point queries, up to 6x better on range scans and achieves similar write performance, while incurring 50% less space amplification. + oai:arXiv.org:2509.10714v2 + cs.DB + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Tony Astolfi, Vidya Silai, Darby Huye, Lan Liu, Raja R. Sambasivan, Johes Bater - IyaCare: An Integrated AI-IoT-Blockchain Platform for Maternal Health in Resource-Constrained Settings - https://arxiv.org/abs/2512.07333 - arXiv:2512.07333v1 Announce Type: new -Abstract: Maternal mortality in Sub-Saharan Africa remains critically high, accounting for 70% of global deaths despite representing only 17% of the world population. Current digital health interventions typically deploy artificial intelligence (AI), Internet of Things (IoT), and blockchain technologies in isolation, missing synergistic opportunities for transformative healthcare delivery. This paper presents IyaCare, a proof-of-concept integrated platform that combines predictive risk assessment, continuous vital sign monitoring, and secure health records management specifically designed for resource-constrained settings. We developed a web-based system with Next.js frontend, Firebase backend, Ethereum blockchain architecture, and XGBoost AI models trained on maternal health datasets. Our feasibility study demonstrates 85.2% accuracy in high-risk pregnancy prediction and validates blockchain data integrity, with key innovations including offline-first functionality and SMS-based communication for community health workers. While limitations include reliance on synthetic validation data and simulated healthcare environments, results confirm the technical feasibility and potential impact of converged digital health solutions. This work contributes a replicable architectural model for integrated maternal health platforms in low-resource settings, advancing progress toward SDG 3.1 targets. - oai:arXiv.org:2512.07333v1 - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - new + Generative AI in Game Development: A Qualitative Research Synthesis + https://arxiv.org/abs/2509.11898 + arXiv:2509.11898v2 Announce Type: replace +Abstract: Generative Artificial Intelligence (GenAI) is currently reshaping game development practices, production pipelines, and value networks in an unprecedentedly pervasive manner with cascading consequences remaining unclear. In the last five years since GenAI's inception, a growing body of qualitative research has explored these early transformations from different settings and demographic angles. However, these studies often contextualise and consolidate their findings weakly with related work; for research to keep up with and support stakeholders in this development, the current moment calls for a synthesis of the findings emerged thus far. Here, we address this need through a qualitative research synthesis via meta-ethnography. We followed PRISMA-S to systematically search the relevant literature from 2020-2025, including major HCI and games research databases. We then synthesised the ten eligible studies, conducting reciprocal translation and line-of-argument synthesis guided by eMERGe, informed by CASP quality appraisal. We identified nine overarching themes, provide recommendations, and contextualise our insights in wider game production trajectories. With this work, we seek to provide practitioners, researchers and policy-makers with grounded insights to guide practice, research and governance. + oai:arXiv.org:2509.11898v2 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Oche D. Ankeli, Marvin M. Ogore + Alexandru Ternar, Alena Denisova, Jo\~ao M. Cunha, Annakaisa Kultima, Christian Guckelsberger - Generalized Referring Expression Segmentation on Aerial Photos - https://arxiv.org/abs/2512.07338 - arXiv:2512.07338v1 Announce Type: new -Abstract: Referring expression segmentation is a fundamental task in computer vision that integrates natural language understanding with precise visual localization of target regions. Considering aerial imagery (e.g., modern aerial photos collected through drones, historical photos from aerial archives, high-resolution satellite imagery, etc.) presents unique challenges because spatial resolution varies widely across datasets, the use of color is not consistent, targets often shrink to only a few pixels, and scenes contain very high object densities and objects with partial occlusions. This work presents Aerial-D, a new large-scale referring expression segmentation dataset for aerial imagery, comprising 37,288 images with 1,522,523 referring expressions that cover 259,709 annotated targets, spanning across individual object instances, groups of instances, and semantic regions covering 21 distinct classes that range from vehicles and infrastructure to land coverage types. The dataset was constructed through a fully automatic pipeline that combines systematic rule-based expression generation with a Large Language Model (LLM) enhancement procedure that enriched both the linguistic variety and the focus on visual details within the referring expressions. Filters were additionally used to simulate historic imaging conditions for each scene. We adopted the RSRefSeg architecture, and trained models on Aerial-D together with prior aerial datasets, yielding unified instance and semantic segmentation from text for both modern and historical images. Results show that the combined training achieves competitive performance on contemporary benchmarks, while maintaining strong accuracy under monochrome, sepia, and grainy degradations that appear in archival aerial photography. The dataset, trained models, and complete software pipeline are publicly available at https://luispl77.github.io/aerial-d . - oai:arXiv.org:2512.07338v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + SENSE models: an open source solution for multilingual and multimodal semantic-based tasks + https://arxiv.org/abs/2509.12093 + arXiv:2509.12093v2 Announce Type: replace +Abstract: This paper introduces SENSE (Shared Embedding for N-lingual Speech and tExt), an open-source solution inspired by the SAMU-XLSR framework and conceptually similar to Meta AI's SONAR models. These approaches rely on a teacher-student framework to align a self-supervised speech encoder with the language-agnostic continuous representations of a text encoder at the utterance level. We describe how the original SAMU-XLSR method has been updated by selecting a stronger teacher text model and a better initial speech encoder. The source code for training and using SENSE models has been integrated into the SpeechBrain toolkit, and the first SENSE model we trained has been publicly released. We report experimental results on multilingual and multimodal semantic tasks, where our SENSE model achieves highly competitive performance. Finally, this study offers new insights into how semantics are captured in such semantically aligned speech encoders. + oai:arXiv.org:2509.12093v2 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Salima Mdhaffar, Haroun Elleuch, Chaimae Chellaf, Ha Nguyen, Yannick Est\`eve + + + Funding AI for Good: A Call for Meaningful Engagement + https://arxiv.org/abs/2509.12455 + arXiv:2509.12455v2 Announce Type: replace +Abstract: Artificial Intelligence for Social Good (AI4SG) is a growing area that explores AI's potential to address social issues, such as public health. Yet prior work has shown limited evidence of its tangible benefits for intended communities, and projects frequently face inadequate community engagement and sustainability challenges. While existing HCI literature on AI4SG initiatives primarily focuses on the mechanisms of funded projects and their outcomes, much less attention has been given to the funding agenda and rhetoric that influences downstream approaches. Through a thematic analysis of 35 funding documents -- representing about $410 million USD in total investments, we reveal dissonances between AI4SG's stated intentions for positive social impact and the techno-centric approaches that some funding agendas promoted, while also identifying funding documents that scaffolded community-collaborative approaches for applicants. Drawing on our findings, we offer recommendations for funders to embed approaches that balance both contextual understanding and technical capacities in future funding call designs. We further discuss how the HCI community can positively shape AI4SG funding design processes. + oai:arXiv.org:2509.12455v2 + cs.CY + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by-nc-nd/4.0/ - Lu\'is Marnoto, Alexandre Bernardino, Bruno Martins + Hongjin Lin, Anna Kawakami, Catherine D'Ignazio, Kenneth Holstein, Krzysztof Gajos - PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning - https://arxiv.org/abs/2512.07342 - arXiv:2512.07342v1 Announce Type: new -Abstract: Recently, offline reinforcement learning (RL) has become a popular RL paradigm. In offline RL, data providers share pre-collected datasets -- either as individual transitions or sequences of transitions forming trajectories -- to enable the training of RL models (also called agents) without direct interaction with the environments. Offline RL saves interactions with environments compared to traditional RL, and has been effective in critical areas, such as navigation tasks. Meanwhile, concerns about privacy leakage from offline RL datasets have emerged. - To safeguard private information in offline RL datasets, we propose the first differential privacy (DP) offline dataset synthesis method, PrivORL, which leverages a diffusion model and diffusion transformer to synthesize transitions and trajectories, respectively, under DP. The synthetic dataset can then be securely released for downstream analysis and research. PrivORL adopts the popular approach of pre-training a synthesizer on public datasets, and then fine-tuning on sensitive datasets using DP Stochastic Gradient Descent (DP-SGD). Additionally, PrivORL introduces curiosity-driven pre-training, which uses feedback from the curiosity module to diversify the synthetic dataset and thus can generate diverse synthetic transitions and trajectories that closely resemble the sensitive dataset. Extensive experiments on five sensitive offline RL datasets show that our method achieves better utility and fidelity in both DP transition and trajectory synthesis compared to baselines. The replication package is available at the GitHub repository. - oai:arXiv.org:2512.07342v1 - cs.CR + Do Natural Language Descriptions of Model Activations Convey Privileged Information? + https://arxiv.org/abs/2509.13316 + arXiv:2509.13316v3 Announce Type: replace +Abstract: Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illuminate how the target model represents and operates on inputs. But do such activation verbalization approaches actually provide privileged knowledge about the internal workings of the target model, or do they merely convey information about its inputs? We critically evaluate popular verbalization methods across datasets used in prior work and find that they can succeed at benchmarks without any access to target model internals, suggesting that these datasets may not be ideal for evaluating verbalization methods. We then run controlled experiments which reveal that verbalizations often reflect the parametric knowledge of the verbalizer LLM which generated them, rather than the knowledge of the target LLM whose activations are decoded. Taken together, our results indicate a need for targeted benchmarks and experimental controls to rigorously assess whether verbalization methods provide meaningful insights into the operations of LLMs. + oai:arXiv.org:2509.13316v3 + cs.CL cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chen Gong, Zheng Liu, Kecen Li, Tianhao Wang + Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra, Byron C. Wallace + + + The Groupoid-Syntax of Type Theory is a Set + https://arxiv.org/abs/2509.14988 + arXiv:2509.14988v2 Announce Type: replace +Abstract: Categories with families (CwFs) have been used to define the semantics of type theory in type theory. In the setting of Homotopy Type Theory (HoTT), one of the limitations of the traditional notion of CwFs is the requirement to set-truncate types, which excludes models based on univalent categories, such as the standard set model. To address this limitation, we introduce the concept of a Groupoid Category with Families (GCwF). This framework truncates types at the groupoid level and incorporates coherence equations, providing a natural extension of the CwF framework when starting from a 1-category. + We demonstrate that the initial GCwF for a type theory with a base family of sets and Pi-types (groupoid-syntax) is set-truncated. Consequently, this allows us to utilize the conventional intrinsic syntax of type theory while enabling interpretations in semantically richer and more natural models. All constructions in this paper were formalised in Cubical Agda. + oai:arXiv.org:2509.14988v2 + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Thorsten Altenkirch, Ambrus Kaposi, Szumi Xie - Linear codes over $\frac{\mathbb{F}_q[u]}{\langle u^2 \rangle}$ with mixed-alphabet defining sets and their Gray images: Constructions of projective few-weight, distance-optimal and minimal codes - https://arxiv.org/abs/2512.07343 - arXiv:2512.07343v1 Announce Type: new -Abstract: Let $\mathcal{R}=\frac{\mathbb{F}_q[u]}{\langle u^2 \rangle}\times \mathbb{F}_q$ be the mixed alphabet ring. In this paper, we construct four infinite families of linear codes over the ring $\frac{\mathbb{F}_q[u]}{\langle u^2 \rangle}$ whose defining sets are certain nonempty subsets of $\mathcal{R}^m$ associated with three simplicial complexes of $\mathbb{F}_q^m,$ each possessing a single maximal element. We explicitly determine the parameters and Lee weight distributions of these codes. We also study their Gray images and obtain three infinite families of few weight, near Griesmer, distance optimal and minimal codes over $\mathbb{F}_q$ with new parameters. We also provide two constructions of infinite families of projective few weight codes over $\mathbb{F}_q$ with new parameters, and observe that these codes are self orthogonal for $q=2$ or $3.$ Additionally, we obtain two infinite families of binary distance optimal projective codes and an infinite family of dimension optimal projective codes over $\mathbb{F}_q$ with new parameters. Apart from this, we construct an infinite family of quaternary projective $3$-weight codes whose non zero Hamming weights sum to $\frac{9}{4}$ times the code length, which give rise to strongly walk regular graphs. As an application of our newly constructed minimal codes over $\mathbb{F}_q$, we examine the minimal access structures of Massey's secret sharing schemes based on their duals and determine the number of dictatorial participants in these schemes. Finally, we investigate the locality properties of our newly constructed projective codes. - oai:arXiv.org:2512.07343v1 + Indoor Fluid Antenna Systems Enabled by Layout-Specific Modeling and Group Relative Policy Optimization + https://arxiv.org/abs/2509.15006 + arXiv:2509.15006v4 Announce Type: replace +Abstract: Fluid antenna system (FAS) revolutionizes wireless communications via utilizing position-flexible antennas that dynamically optimize channel conditions and mitigate multipath fading. This innovation is particularly valuable in indoor environments, in which signal propagation is severely degraded due to structural obstructions and complex multipath reflections. In this paper, we investigate the channel modeling and the joint optimization of antenna positioning, beamforming, and power allocation for indoor FAS. In particular, we propose a layout-specific channel model, and employ the novel group relative policy optimization (GRPO) algorithm for tackling the optimization problem. Compared to the state-of-the-art Sionna model, our model achieves an 83.3% reduction in computation time with an approximately 3 dB increase in root-mean-square error (RMSE). When simplified to a two-ray model, our model allows for a closed-form antenna position solution with near-optimal performance. For the joint optimization problem, our GRPO algorithm outperforms proximal policy optimization (PPO) and other baselines in sum-rate, while requiring only 50.8% computational resources of PPO, thanks to its group advantage estimation. Simulation results show that increasing either the group size or trajectory length in GRPO does not yield significant improvements in sum-rate, suggesting that these parameters can be selected conservatively without sacrificing performance. + oai:arXiv.org:2509.15006v4 cs.IT math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Leijo Jose, Lavanya G., Anuradha Sharma + Tong Zhang, Qianren Li, Shuai Wang, Wanli Ni, Jiliang Zhang, Rui Wang, Kai-Kit Wong, Chan-Byoung Chae - Venus: An Efficient Edge Memory-and-Retrieval System for VLM-based Online Video Understanding - https://arxiv.org/abs/2512.07344 - arXiv:2512.07344v1 Announce Type: new -Abstract: Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing VLMs' reasoning power in these cases, deployment constraints are overlooked, leading to overwhelming system overhead in real-world deployments. To address that, we propose Venus, an on-device memory-and-retrieval system for efficient online video understanding. Venus proposes an edge-cloud disaggregated architecture that sinks memory construction and keyframe retrieval from cloud to edge, operating in two stages. In the ingestion stage, Venus continuously processes streaming edge videos via scene segmentation and clustering, where the selected keyframes are embedded with a multimodal embedding model to build a hierarchical memory for efficient storage and retrieval. In the querying stage, Venus indexes incoming queries from memory, and employs a threshold-based progressive sampling algorithm for keyframe selection that enhances diversity and adaptively balances system cost and reasoning accuracy. Our extensive evaluation shows that Venus achieves a 15x-131x speedup in total response latency compared to state-of-the-art methods, enabling real-time responses within seconds while maintaining comparable or even superior reasoning accuracy. - oai:arXiv.org:2512.07344v1 - cs.DC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shengyuan Ye, Bei Ouyang, Tianyi Qian, Liekang Zeng, Mu Yuan, Xiaowen Chu, Weijie Hong, Xu Chen + Beyond Community Notes: A Framework for Understanding and Building Crowdsourced Context Systems for Social Media + https://arxiv.org/abs/2509.15434 + arXiv:2509.15434v2 Announce Type: replace +Abstract: Social media platforms are increasingly developing features that display crowdsourced context alongside posts, modeled after X's Community Notes. These systems, which we term Crowdsourced Context Systems (CCS), have the potential to reshape our information ecosystem as major platforms embrace them as alternatives to top-down fact-checking. To deeply understand the features and implications of such systems, we perform a systematic literature review of existing CCS research and analyze several real-world CCS implementations. Based on our analysis, we develop a framework with two distinct components. First, we present a theoretical model to help conceptualize and define CCS. Second, we identify a design space encompassing six key aspects of CCS: participation, inputs, curation, presentation, platform treatment, and transparency. We discuss key normative implications of different CCS design and implementation choices. Our paper integrates these theoretical, design, and ethical perspectives to establish a foundation for future human-centered research on Crowdsourced Context Systems. + oai:arXiv.org:2509.15434v2 + cs.HC + cs.CY + cs.SI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Travis Lloyd, Tung Nguyen, Karen Levy, Mor Naaman - Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splatting - https://arxiv.org/abs/2512.07345 - arXiv:2512.07345v1 Announce Type: new -Abstract: Versatile 3D tasks (e.g., generation or editing) that distill from Text-to-Image (T2I) diffusion models have attracted significant research interest for not relying on extensive 3D training data. However, T2I models exhibit limitations resulting from prior view bias, which produces conflicting appearances between different views of an object. This bias causes subject-words to preferentially activate prior view features during cross-attention (CA) computation, regardless of the target view condition. To overcome this limitation, we conduct a comprehensive mathematical analysis to reveal the root cause of the prior view bias in T2I models. Moreover, we find different UNet layers show different effects of prior view in CA. Therefore, we propose a novel framework, TD-Attn, which addresses multi-view inconsistency via two key components: (1) the 3D-Aware Attention Guidance Module (3D-AAG) constructs a view-consistent 3D attention Gaussian for subject-words to enforce spatial consistency across attention-focused regions, thereby compensating for the limited spatial information in 2D individual view CA maps; (2) the Hierarchical Attention Modulation Module (HAM) utilizes a Semantic Guidance Tree (SGT) to direct the Semantic Response Profiler (SRP) in localizing and modulating CA layers that are highly responsive to view conditions, where the enhanced CA maps further support the construction of more consistent 3D attention Gaussians. Notably, HAM facilitates semantic-specific interventions, enabling controllable and precise 3D editing. Extensive experiments firmly establish that TD-Attn has the potential to serve as a universal plugin, significantly enhancing multi-view consistency across 3D tasks. - oai:arXiv.org:2512.07345v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shilong Jin, Haoran Duan, Litao Hua, Wentao Huang, Yuan Zhou + Omni-LIVO: Robust RGB-Colored Multi-Camera Visual-Inertial-LiDAR Odometry via Photometric Migration and ESIKF Fusion + https://arxiv.org/abs/2509.15673 + arXiv:2509.15673v2 Announce Type: replace +Abstract: Wide field-of-view (FoV) LiDAR sensors provide dense geometry across large environments, but existing LiDAR-inertial-visual odometry (LIVO) systems generally rely on a single camera, limiting their ability to fully exploit LiDAR-derived depth for photometric alignment and scene colorization. We present Omni-LIVO, a tightly coupled multi-camera LIVO system that leverages multi-view observations to comprehensively utilize LiDAR geometric information across extended spatial regions. Omni-LIVO introduces a Cross-View direct alignment strategy that maintains photometric consistency across non-overlapping views, and extends the Error-State Iterated Kalman Filter (ESIKF) with multi-view updates and adaptive covariance. The system is evaluated on public benchmarks and our custom dataset, showing improved accuracy and robustness over state-of-the-art LIVO, LIO, and visual-inertial SLAM baselines. Code and dataset will be released upon publication. + oai:arXiv.org:2509.15673v2 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Yinong Cao, Xin He, Yuwei Chen, Chenyang Zhang, Chengyu Pu, Bingtao Wang, Kaile Wu, Shouzheng Zhu, Fei Han, Shijie Liu, Chunlai Li, Jianyu Wang - MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition - https://arxiv.org/abs/2512.07348 - arXiv:2512.07348v1 Announce Type: new -Abstract: In controllable image generation, synthesizing coherent and consistent images from multiple reference inputs, i.e., Multi-Image Composition (MICo), remains a challenging problem, partly hindered by the lack of high-quality training data. To bridge this gap, we conduct a systematic study of MICo, categorizing it into 7 representative tasks and curate a large-scale collection of high-quality source images and construct diverse MICo prompts. Leveraging powerful proprietary models, we synthesize a rich amount of balanced composite images, followed by human-in-the-loop filtering and refinement, resulting in MICo-150K, a comprehensive dataset for MICo with identity consistency. We further build a Decomposition-and-Recomposition (De&Re) subset, where 11K real-world complex images are decomposed into components and recomposed, enabling both real and synthetic compositions. To enable comprehensive evaluation, we construct MICo-Bench with 100 cases per task and 300 challenging De&Re cases, and further introduce a new metric, Weighted-Ref-VIEScore, specifically tailored for MICo evaluation. Finally, we fine-tune multiple models on MICo-150K and evaluate them on MICo-Bench. The results show that MICo-150K effectively equips models without MICo capability and further enhances those with existing skills. Notably, our baseline model, Qwen-MICo, fine-tuned from Qwen-Image-Edit, matches Qwen-Image-2509 in 3-image composition while supporting arbitrary multi-image inputs beyond the latter's limitation. Our dataset, benchmark, and baseline collectively offer valuable resources for further research on Multi-Image Composition. - oai:arXiv.org:2512.07348v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Graph Coloring for Multi-Task Learning + https://arxiv.org/abs/2509.16959 + arXiv:2509.16959v4 Announce Type: replace +Abstract: When different objectives conflict with each other in multi-task learning, gradients begin to interfere and slow convergence, thereby potentially reducing the final model's performance. To address this, we introduce SON-GOKU, a scheduler that computes gradient interference, constructs an interference graph, and then applies greedy graph-coloring to partition tasks into groups that align well with each other. At each training step, only one group (color class) of tasks are activated, and the grouping partition is constantly recomputed as task relationships evolve throughout training. By ensuring that each mini-batch contains only tasks that pull the model in the same direction, our method improves the effectiveness of any underlying multi-task learning optimizer without additional tuning. Since tasks within these groups will update in compatible directions, multi-task learning will improve model performance rather than impede it. Empirical results on six different datasets show that this interference-aware graph-coloring approach consistently outperforms baselines and state-of-the-art multi-task optimizers. We provide extensive theory showing why grouping and sequential updates improve multi-task learning, with guarantees on descent, convergence, and accurately identifying what tasks conflict or align. + oai:arXiv.org:2509.16959v4 + cs.LG + cs.AI + cs.NE + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xinyu Wei, Kangrui Cen, Hongyang Wei, Zhen Guo, Bairui Li, Zeqing Wang, Jinrui Zhang, Lei Zhang + Santosh Patapati - Symmetries in Sorting - https://arxiv.org/abs/2512.07349 - arXiv:2512.07349v1 Announce Type: new -Abstract: Sorting algorithms are fundamental to computer science, and their correctness criteria are well understood as rearranging elements of a list according to a specified total order on the underlying set of elements. As mathematical functions, they are functions on lists that perform combinatorial operations on the representation of the input list. In this paper, we study sorting algorithms conceptually as abstract sorting functions. - There is a canonical surjection from the free monoid on a set (lists of elements) to the free commutative monoid on the same set (multisets of elements). We show that sorting functions determine a section (right inverse) to this surjection satisfying two axioms, that do not presuppose a total order on the underlying set. Then, we establish an equivalence between (decidable) total orders on the underlying set and correct sorting functions. - The first part of the paper develops concepts from universal algebra from the point of view of functorial signatures, and gives constructions of free monoids and free commutative monoids in (univalent) type theory. Using these constructions, the second part of the paper develops the axiomatisation of sorting functions. The paper uses informal mathematical language, and comes with an accompanying formalisation in Cubical Agda. - oai:arXiv.org:2512.07349v1 - cs.LO - math.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Vikraman Choudhury, Wind Wong + Enhancing the NAO: Extending Capabilities of Legacy Robots for Long-Term Research + https://arxiv.org/abs/2509.17760 + arXiv:2509.17760v3 Announce Type: replace +Abstract: Legacy (unsupported) robotic platforms often lose research utility when manufacturer support ends, preventing integration of modern sensing, speech, and interaction capabilities. We present the Enhanced NAO, a revitalized version of Aldebaran's NAO robot featuring upgraded beamforming microphones, RGB-D and thermal cameras, and additional compute resources in a fully self-contained package. This system combines cloud-based and local models for perception and dialogue, while preserving the NAO's expressive body and behaviors. In a pilot user study validating conversational performance, the Enhanced NAO delivered significantly higher conversational quality and elicited stronger user preference compared to the NAO AI Edition, without increasing response latency. The added visual and thermal sensing modalities established a foundation for future perception-driven interaction. Beyond this implementation, our framework provides a platform-agnostic strategy for extending the lifespan and research utility of legacy robots, ensuring they remain valuable tools for human-robot interaction. + oai:arXiv.org:2509.17760v3 + cs.RO + cs.HC + eess.AS + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Austin Wilson, Sahar Kapasi, Zane Greene, Alexis E. Block - Communication-Efficient Serving for Video Diffusion Models with Latent Parallelism - https://arxiv.org/abs/2512.07350 - arXiv:2512.07350v1 Announce Type: new -Abstract: Video diffusion models (VDMs) perform attention computation over the 3D spatio-temporal domain. Compared to large language models (LLMs) processing 1D sequences, their memory consumption scales cubically, necessitating parallel serving across multiple GPUs. Traditional parallelism strategies partition the computational graph, requiring frequent high-dimensional activation transfers that create severe communication bottlenecks. To tackle this issue, we exploit the local spatio-temporal dependencies inherent in the diffusion denoising process and propose Latent Parallelism (LP), the first parallelism strategy tailored for VDM serving. \textcolor{black}{LP decomposes the global denoising problem into parallelizable sub-problems by dynamically rotating the partitioning dimensions (temporal, height, and width) within the compact latent space across diffusion timesteps, substantially reducing the communication overhead compared to prevailing parallelism strategies.} To ensure generation quality, we design a patch-aligned overlapping partition strategy that matches partition boundaries with visual patches and a position-aware latent reconstruction mechanism for smooth stitching. Experiments on three benchmarks demonstrate that LP reduces communication overhead by up to 97\% over baseline methods while maintaining comparable generation quality. As a non-intrusive plug-in paradigm, LP can be seamlessly integrated with existing parallelism strategies, enabling efficient and scalable video generation services. - oai:arXiv.org:2512.07350v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhiyuan Wu, Shuai Wang, Li Chen, Kaihui Gao, Dan Li, Yanyu Ren, Qiming Zhang, Yong Wang + SlicePilot: Demystifying Network Slice Placement in Heterogeneous Cloud Infrastructures + https://arxiv.org/abs/2509.18545 + arXiv:2509.18545v2 Announce Type: replace +Abstract: Cellular networks are comprised of software-based entities, with main functions encapsulated as Virtual Network Functions (VNFs) deployed on Commercial-off-the-Shelf (COTS) hardware. As a key enabler of 5G, network slicing offers logically isolated Quality of Service (QoS) for diverse use cases. With the transition to cloud-native infrastructures, optimizing network slice placement across multi-cloud environments remains challenging due to heterogeneous resource capabilities and varying slice-specific demands. This paper presents SlicePilot, a modular framework that enables autonomous and near-optimal VNF placement using a disaggregated Multi-Agent Reinforcement Learning (MARL) approach. SlicePilot collects real-world traffic profiles to estimate resource needs for each slice type. These estimates guide a MARL-based scheduler that minimizes deployment costs while satisfying QoS constraints. We evaluate SlicePilot on a multi-cloud testbed and demonstrate a 19x speed-up over combinatorial optimization methods, while keeping deployment costs within 7.8% of the optimal. Although SlicePilot results in 2.42x more QoS violations under high-load conditions, this trade-off is offset by faster decision-making and reduced computational overhead. Overall, SlicePilot delivers a scalable, cost-efficient solution for network slice placement, making it suitable for real-time deployments where responsiveness and efficiency are critical. + oai:arXiv.org:2509.18545v2 + cs.NI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Ioannis Panitsas, Tolga O. Atalay, Dragoslav Stojadinovic, Angelos Stavrou, Leandros Tassiulas - DeepAgent: A Dual Stream Multi Agent Fusion for Robust Multimodal Deepfake Detection - https://arxiv.org/abs/2512.07351 - arXiv:2512.07351v1 Announce Type: new -Abstract: The increasing use of synthetic media, particularly deepfakes, is an emerging challenge for digital content verification. Although recent studies use both audio and visual information, most integrate these cues within a single model, which remains vulnerable to modality mismatches, noise, and manipulation. To address this gap, we propose DeepAgent, an advanced multi-agent collaboration framework that simultaneously incorporates both visual and audio modalities for the effective detection of deepfakes. DeepAgent consists of two complementary agents. Agent-1 examines each video with a streamlined AlexNet-based CNN to identify the symbols of deepfake manipulation, while Agent-2 detects audio-visual inconsistencies by combining acoustic features, audio transcriptions from Whisper, and frame-reading sequences of images through EasyOCR. Their decisions are fused through a Random Forest meta-classifier that improves final performance by taking advantage of the different decision boundaries learned by each agent. This study evaluates the proposed framework using three benchmark datasets to demonstrate both component-level and fused performance. Agent-1 achieves a test accuracy of 94.35% on the combined Celeb-DF and FakeAVCeleb datasets. On the FakeAVCeleb dataset, Agent-2 and the final meta-classifier attain accuracies of 93.69% and 81.56%, respectively. In addition, cross-dataset validation on DeepFakeTIMIT confirms the robustness of the meta-classifier, which achieves a final accuracy of 97.49%, and indicates a strong capability across diverse datasets. These findings confirm that hierarchy-based fusion enhances robustness by mitigating the weaknesses of individual modalities and demonstrate the effectiveness of a multi-agent approach in addressing diverse types of manipulations in deepfakes. - oai:arXiv.org:2512.07351v1 - cs.CV + The Cream Rises to the Top: Efficient Reranking Method for Verilog Code Generation + https://arxiv.org/abs/2509.20215 + arXiv:2509.20215v2 Announce Type: replace +Abstract: LLMs face significant challenges in Verilog generation due to limited domain-specific knowledge. While sampling techniques improve pass@k metrics, hardware engineers need one trustworthy solution rather than uncertain candidates. To bridge this gap, we formulate it as a semantic alignment problem between requirements and Verilog implementations, and propose VCD-RNK, a discriminator model tailored for efficient Verilog code reranking. Specifically, VCD-RNKincorporates Verilog-specific reasoning by distilling expert knowledge across three dimensions: code semantic analysis, test case generation, and functional correctness assessment. By explicitly simulating the above reasoning processes during inference, VCD-RNK effectively avoids computationally intensive test execution in existing methods. + oai:arXiv.org:2509.20215v2 + cs.AR cs.AI - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Sayeem Been Zaman, Wasimul Karim, Arefin Ittesafun Abian, Reem E. Mohamed, Md Rafiqul Islam, Asif Karim, Sami Azam + Guang Yang, Wei Zheng, Xiang Chen, Yifan Sun, Fengji Zhang, Terry Yue Zhuo - MultiAPI Spoof: A Multi-API Dataset and Local-Attention Network for Speech Anti-spoofing Detection - https://arxiv.org/abs/2512.07352 - arXiv:2512.07352v1 Announce Type: new -Abstract: Existing speech anti-spoofing benchmarks rely on a narrow set of public models, creating a substantial gap from real-world scenarios in which commercial systems employ diverse, often proprietary APIs. To address this issue, we introduce MultiAPI Spoof, a multi-API audio anti-spoofing dataset comprising about 230 hours of synthetic speech generated by 30 distinct APIs, including commercial services, open-source models, and online platforms. Based on this dataset, we define the API tracing task, enabling fine-grained attribution of spoofed audio to its generation source. We further propose Nes2Net-LA, a local-attention enhanced variant of Nes2Net that improves local context modeling and fine-grained spoofing feature extraction. Experiments show that Nes2Net-LA achieves state-of-the-art performance and offers superior robustness, particularly under diverse and unseen spoofing conditions. Code \footnote{https://github.com/XuepingZhang/MultiAPI-Spoof} and dataset \footnote{https://xuepingzhang.github.io/MultiAPI-Spoof-Dataset/} have released. - oai:arXiv.org:2512.07352v1 - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Xueping Zhang, Zhenshan Zhang, Yechen Wang, Linxi Li, Liwei Jin, Ming Li - - - Off-grid solar energy storage system with hybrid lithium iron phosphate (LFP) and lead-acid batteries in high mountains: a case report of Jiujiu Cabins in Taiwan - https://arxiv.org/abs/2512.07353 - arXiv:2512.07353v1 Announce Type: new -Abstract: Mountain huts are buildings located at high altitude, offering a place for hikers and providing shelter. Energy supply on mountain huts is still an open issue. Using renewable energies could be an appropriate solution. Jiujiu Cabins, a famous mountain hut in Shei-Pa National Park, Taiwan, has operated an off-grid solar energy storage system (ESS) with lead-acid batteries. In 2021, a serious system failures took place, leading to no electricity. After an detailed on-site survey, a reorganization and repair project implemented, the energy system came back to operate normally. Meanwhile, a eco-friendly lithium iron phosphate battery (LFP battery) ESS replaces part of the lead-acid battery ESS, forming a hybrid ESS, making a better and green off-grid solar ESS. In this case report, the energy architecture, detailed descriptions, and historical status of the system are provided. An on-site survey of the failed energy system, a system improvement project, and future plan are listed. - oai:arXiv.org:2512.07353v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hsien-Ching Chung - - - Dualities of dihedral and generalised quaternion codes and applications to quantum codes - https://arxiv.org/abs/2512.07354 - arXiv:2512.07354v1 Announce Type: new -Abstract: Let $\mathbb{F}_q$ be a finite field of $q$ elements, for some prime power $q$, and let $G$ be a finite group. A (left) group code, or simply a $G$-code, is a (left) ideal of the group algebra $\mathbb{F}_q[G]$. In this paper, we provide a complete algebraic description for the hermitian dual code of any $D_n$-code over $\mathbb{F}_{q^2}$, where $D_n$ is a dihedral group of order $2n$ with $\gcd(q,n)=1$, through a suitable Wedderburn-Artin's decomposition of the group algebra $\mathbb{F}_{q^2}[D_n]$, and we determine all distinct hermitian self-orthogonal $D_n$-codes over $\mathbb{F}_{q^2}$. We also present a thorough representation of the euclidean dual code of any $Q_n$-code over $\mathbb{F}_q$, where $Q_n$ is a generalised quaternion group of order $4n$ with $\gcd(q,4n)=1$, via the Wedderburn-Artin's decomposition of the group algebra $\mathbb{F}_q[Q_n]$. In particular, since the semisimple group algebras $\mathbb{F}_{q^2}[Q_n]$ and $\mathbb{F}_{q^2}[D_{2n}]$ are isomorphic, then the hermitian dual code of any $Q_n$-code has also been fully described. As application of the hermitian dualities computed, we give a systematic construction, via the structure of the group algebra, to obtain quantum error-correcting codes, and in fact we rebuild some already known optimal quantum codes with this methodical approach. - oai:arXiv.org:2512.07354v1 - cs.IT - math.IT - math.QA - math.RA - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Miguel Sales-Cabrera, Xaro Soler-Escriv\`a, V\'ictor Sotomayor + A Data-driven Typology of Vision Models from Integrated Representational Metrics + https://arxiv.org/abs/2509.21628 + arXiv:2509.21628v2 Announce Type: replace +Abstract: Large vision models differ widely in architecture and training paradigm, yet we lack principled methods to determine which aspects of their representations are shared across families and which reflect distinctive computational strategies. We leverage a suite of representational similarity metrics, each capturing a different facet-geometry, unit tuning, or linear decodability-and assess family separability using multiple complementary measures. Metrics preserving geometry or tuning (e.g., RSA, Soft Matching) yield strong family discrimination, whereas flexible mappings such as Linear Predictivity show weaker separation. These findings indicate that geometry and tuning carry family-specific signatures, while linearly decodable information is more broadly shared. To integrate these complementary facets, we adapt Similarity Network Fusion (SNF), a method inspired by multi-omics integration. SNF achieves substantially sharper family separation than any individual metric and produces robust composite signatures. Clustering of the fused similarity matrix recovers both expected and surprising patterns: supervised ResNets and ViTs form distinct clusters, yet all self-supervised models group together across architectural boundaries. Hybrid architectures (ConvNeXt, Swin) cluster with masked autoencoders, suggesting convergence between architectural modernization and reconstruction-based training. This biology-inspired framework provides a principled typology of vision models, showing that emergent computational strategies-shaped jointly by architecture and training objective-define representational structure beyond surface design categories. + oai:arXiv.org:2509.21628v2 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla - A Geometric Unification of Concept Learning with Concept Cones - https://arxiv.org/abs/2512.07355 - arXiv:2512.07355v1 Announce Type: new -Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge. While CBMs use supervision to align activations with human-labeled concepts, SAEs rely on sparse coding to uncover emergent ones. We show that both paradigms instantiate the same geometric structure: each learns a set of linear directions in activation space whose nonnegative combinations form a concept cone. Supervised and unsupervised methods thus differ not in kind but in how they select this cone. Building on this view, we propose an operational bridge between the two paradigms. CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs. This containment framework yields quantitative metrics linking inductive biases -- such as SAE type, sparsity, or expansion ratio -- to emergence of plausible\footnote{We adopt the terminology of \citet{jacovi2020towards}, who distinguish between faithful explanations (accurately reflecting model computations) and plausible explanations (aligning with human intuition and domain knowledge). CBM concepts are plausible by construction -- selected or annotated by humans -- though not necessarily faithful to the true latent factors that organise the data manifold.} concepts. Using these metrics, we uncover a ``sweet spot'' in both sparsity and expansion factor that maximizes both geometric and semantic alignment with CBM concepts. Overall, our work unifies supervised and unsupervised concept discovery through a shared geometric framework, providing principled metrics to measure SAE progress and assess how well discovered concept align with plausible human concepts. - oai:arXiv.org:2512.07355v1 - cs.AI - cs.CV + Nonlinear Optimization with GPU-Accelerated Neural Network Constraints + https://arxiv.org/abs/2509.22462 + arXiv:2509.22462v2 Announce Type: replace +Abstract: We propose a reduced-space formulation for optimizing over trained neural networks where the network's outputs and derivatives are evaluated on a GPU. To do this, we treat the neural network as a "gray box" where intermediate variables and constraints are not exposed to the optimization solver. Compared to the full-space formulation, in which intermediate variables and constraints are exposed to the optimization solver, the reduced-space formulation leads to faster solves and fewer iterations in an interior point method. We demonstrate the benefits of this method on two optimization problems: Adversarial generation for a classifier trained on MNIST images and security-constrained optimal power flow with transient feasibility enforced using a neural network surrogate. + oai:arXiv.org:2509.22462v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Alexandre Rocchi--Henry, Thomas Fel, Gianni Franchi + Robert Parker, Oscar Dowson, Nicole LoGiudice, Manuel Garcia, Russell Bent - Size Matters: The Impact of Avatar Size on User Experience in Healthcare Applications - https://arxiv.org/abs/2512.07357 - arXiv:2512.07357v1 Announce Type: new -Abstract: The usage of virtual avatars in healthcare applications has become widely popular; however, certain critical aspects, such as social distancing and avatar size, remain insufficiently explored. This research investigates user experience and preferences when interacting with a healthcare application utilizing virtual avatars displayed in different sizes. For our study, we had 23 participants interacting with five different avatars (a human-size avatar followed by four smaller avatars in a randomized order) varying in size, projected on a wall in front of them. The avatars were fully integrated with an artificial intelligence chatbot to make them conversational. Users were asked to rate the usability of the system after interacting with each avatar and complete a survey regarding trust and an additional questionnaire on social presence. The results of this study show that avatar size significantly influences the perceived attractiveness and perspicuity, with the medium-sized avatars receiving the highest ratings. Social presence correlated strongly with stimulation and attractiveness, suggesting that an avatar's visual appeal and interactivity influenced user engagement more than its physical size. Additionally, we observed a tendency for gender-specific differences on some of the UEQ+ scales, with male participants tending to prefer human-sized representations, while female participants slightly favored smaller avatars. These findings highlight the importance of avatar design and representation in optimizing user experience and trust in virtual healthcare environments. - oai:arXiv.org:2512.07357v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Navid Ashrafi, Francesco Vona, Sina Hinzmann, Juliane Henning, Maurizio Vergari, Maximilian Warsinke, Catarina Pinto Moreira, Jan-Niklas Voigt-Antons + Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions + https://arxiv.org/abs/2509.23782 + arXiv:2509.23782v2 Announce Type: replace +Abstract: Large Language Models (LLMs) often fail on multiple-choice questions (MCQs) despite demonstrating correct knowledge in other contexts, such as free-form generation. To investigate the mechanism underlying this knowledge-prediction gap on MCQs and alleviate it, we conduct a probing analysis and find that residual streams in certain layers contain a subspace spanned by two important bases: a \emph{knowledge basis} that encodes the probability of the ground-truth answer for a given MCQ and a \emph{prediction basis} that encodes the probability of the answer choice predicted by the model. We observe that incorrect predictions arise from a misalignment of the model's hidden states along these two bases. Hence, we introduce \textbf{KAPPA} (Knowledge-Aligned Prediction through Projection-based Adjustment), a parameter-free intervention that transforms the hidden states to align the prediction coordinate with the knowledge coordinate within this subspace. Experiments on binary-choice reformulations of Big-Bench-Hard and ARC-Challenge show that KAPPA substantially improves accuracy and consistently outperforms baselines. While optimal subspaces differ across tasks, subspaces generalize to some extent, as supported by cross-dataset experiments. Moreover, KAPPA extends its effectiveness to free-form questions beyond MCQs. Our work provides a new geometric understanding of the knowledge-prediction gap and offers a practical method for better aligning model behavior with its latent knowledge. + oai:arXiv.org:2509.23782v2 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Yoonah Park, Haesung Pyun, Yohan Jo - Multi-Rigid-Body Approximation of Human Hands with Application to Digital Twin - https://arxiv.org/abs/2512.07359 - arXiv:2512.07359v1 Announce Type: new -Abstract: Human hand simulation plays a critical role in digital twin applications, requiring models that balance anatomical fidelity with computational efficiency. We present a complete pipeline for constructing multi-rigid-body approximations of human hands that preserve realistic appearance while enabling real-time physics simulation. Starting from optical motion capture of a specific human hand, we construct a personalized MANO (Multi-Abstracted hand model with Neural Operations) model and convert it to a URDF (Unified Robot Description Format) representation with anatomically consistent joint axes. The key technical challenge is projecting MANO's unconstrained SO(3) joint rotations onto the kinematically constrained joints of the rigid-body model. We derive closed-form solutions for single degree-of-freedom joints and introduce a Baker-Campbell-Hausdorff (BCH)-corrected iterative method for two degree-of-freedom joints that properly handles the non-commutativity of rotations. We validate our approach through digital twin experiments where reinforcement learning policies control the multi-rigid-body hand to replay captured human demonstrations. Quantitative evaluation shows sub-centimeter reconstruction error and successful grasp execution across diverse manipulation tasks. - oai:arXiv.org:2512.07359v1 + Control Your Robot: A Unified System for Robot Control and Policy Deployment + https://arxiv.org/abs/2509.23823 + arXiv:2509.23823v2 Announce Type: replace +Abstract: Cross-platform robot control remains difficult because hardware interfaces, data formats, and control paradigms vary widely, which fragments toolchains and slows deployment. To address this, we present Control Your Robot, a modular, general-purpose framework that unifies data collection and policy deployment across diverse platforms. The system reduces fragmentation through a standardized workflow with modular design, unified APIs, and a closed-loop architecture. It supports flexible robot registration, dual-mode control with teleoperation and trajectory playback, and seamless integration from multimodal data acquisition to inference. Experiments on single-arm and dual-arm systems show efficient, low-latency data collection and effective support for policy learning with imitation learning and vision-language-action models. Policies trained on data gathered by Control Your Robot match expert demonstrations closely, indicating that the framework enables scalable and reproducible robot learning across platforms. + oai:arXiv.org:2509.23823v2 cs.RO - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Bin Zhao, Yiwen Lu, Haohua Zhu, Xiao Li, Sheng Yi + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Tian Nian, Weijie Ke, Shaolong Zhu, Bingshan Hu - Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentation - https://arxiv.org/abs/2512.07360 - arXiv:2512.07360v1 Announce Type: new -Abstract: Benefiting from the inductive biases learned from large-scale datasets, open-vocabulary semantic segmentation (OVSS) leverages the power of vision-language models, such as CLIP, to achieve remarkable progress without requiring task-specific training. However, due to CLIP's pre-training nature on image-text pairs, it tends to focus on global semantic alignment, resulting in suboptimal performance when associating fine-grained visual regions with text. This leads to noisy and inconsistent predictions, particularly in local areas. We attribute this to a dispersed bias stemming from its contrastive training paradigm, which is difficult to alleviate using CLIP features alone. To address this, we propose a structure-aware feature rectification approach that incorporates instance-specific priors derived directly from the image. Specifically, we construct a region adjacency graph (RAG) based on low-level features (e.g., colour and texture) to capture local structural relationships and use it to refine CLIP features by enhancing local discrimination. Extensive experiments show that our method effectively suppresses segmentation noise, improves region-level consistency, and achieves strong performance on multiple open-vocabulary segmentation benchmarks. - oai:arXiv.org:2512.07360v1 - cs.CV + Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in LLMs + https://arxiv.org/abs/2509.24319 + arXiv:2509.24319v2 Announce Type: replace +Abstract: Large language models (LLMs) can express different values in two distinct ways: (1) intrinsic expression, reflecting the model's inherent values learned during training, and (2) prompted expression, elicited by explicit prompts. Given their widespread use in value alignment and persona steering, it is paramount to clearly understand their underlying mechanisms, particularly whether they mostly overlap (as one might expect) or rely on substantially different mechanisms, but this remains largely understudied. We analyze this at the mechanistic level using two approaches: (1) value vectors, feature directions representing value mechanisms extracted from the residual stream, and (2) value neurons, MLP neurons that contribute to value expressions. We demonstrate that intrinsic and prompted value mechanisms partly share common components that are crucial for inducing value expression, but also possess unique elements that manifest in different ways. As a result, these mechanisms lead to different degrees of value steerability (prompted > intrinsic) and response diversity (intrinsic > prompted). In particular, components unique to the intrinsic mechanism seem to promote lexical diversity in responses, whereas those specific to the prompted mechanism primarily strengthen instruction following, taking effect even in distant tasks like jailbreaking. + oai:arXiv.org:2509.24319v2 + cs.CL cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Qiming Huang, Hao Ai, Jianbo Jiao + Jongwook Han, Jongwon Lim, Injin Kong, Yohan Jo - The Impact of Spatial Misalignment and Time Delay on Collaborative Presence in Augmented Reality - https://arxiv.org/abs/2512.07363 - arXiv:2512.07363v1 Announce Type: new -Abstract: Precise temporal and spatial alignment is critical in collaborative Augmented Reality (AR) where users rely on shared visual information to coordinate actions. System latency and object misalignment can disrupt communication, reduce task efficiency, and negatively impact the overall user experience. While previous research has primarily focused on individual AR interactions, the impact of these inconsistencies on collaboration remains underexplored. This article investigates how user experience and task load are affected by object misalignment and time delay in a shared AR space. To examine these factors, we conducted an experiment with 32 participants, organized into 16 pairs, who collaboratively completed a spatial placement task. Within each condition, both participants alternated roles, taking turns as the leader-providing verbal placement instructions-and the builder-executing the placement. Six conditions were tested, manipulating object alignment (perfectly aligned vs. randomly misaligned) and time delay (0s, 0.1s, 0.4s). The misalignment was applied randomly to each virtual object with a shift of +-20 cm on every axis to create a clear distinction in spatial perception. User experience and task load were assessed to evaluate how these factors influence collaboration and interaction in AR environments. Results showed that spatial misalignment significantly increased perceived workload (NASA-TLX) and lowered user ratings in Pragmatic quality and Attractiveness (UEQ), while time delay had a more limited effect. These findings highlight the critical role of spatial accuracy in maintaining collaboration quality in AR. - oai:arXiv.org:2512.07363v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Michael Stern, Maurizio Vergari, Julia Schorlemmer, Francesco Vona, David Grieshammer, Jan-Niklas Voigt-Antons + Short window attention enables long-term memorization + https://arxiv.org/abs/2509.24552 + arXiv:2509.24552v2 Announce Type: replace +Abstract: Recent works show that hybrid architectures combining sliding window softmax attention layers with linear recurrent neural network (RNN) layers outperform both of these architectures taken separately. However, the impact of the window length and the interplay between softmax attention and linear RNN layers remain under-studied. In this work, we introduce SWAX, a hybrid architecture consisting of sliding-window attention and xLSTM linear RNN layers. + A counter-intuitive finding with SWAX is that larger sliding windows do not improve the long-context performance. In fact, short window attention encourages the model to better train the long-term memory of the xLSTM, by relying less on the softmax attention mechanism for long context-retrieval. + The issue with small sliding windows is that they are detrimental for short-context tasks, which could be solved with information from moderately larger sliding windows otherwise. Therefore, we train SWAX by stochastically changing the sliding window size, forcing the model to leverage both a longer context window and the xLSTM memory. SWAX trained with stochastic window sizes significantly outperforms regular window attention both on short and long-context problems. + oai:arXiv.org:2509.24552v2 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Lo\"ic Cabannes, Maximilian Beck, Gergely Szilvasy, Matthijs Douze, Maria Lomeli, Jade Copet, Pierre-Emmanuel Mazar\'e, Gabriel Synnaeve, Herv\'e J\'egou - On semi-separability and differentiation matrices - https://arxiv.org/abs/2512.07365 - arXiv:2512.07365v1 Announce Type: new -Abstract: The theory of spectral methods for partial differential equations leads to infinite-dimensional matrices which represent the derivative operator with respect to an underlying orthonormal basis. Favourable properties of such differentiation matrices are crucial in the design of good spectral methods. It is known that bases using Laguerre and ultraspherical polynomials lead to semi-separable differentiation matrices of rank 1. In this paper we consider orthonormal bases constructed from Jacobi polynomials and prove that the underlying differentiation matrices are semi-separable of rank 2. This requires new results on semi-separable matrices which might be interesting in a wider context. - oai:arXiv.org:2512.07365v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new + MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources + https://arxiv.org/abs/2509.25531 + arXiv:2509.25531v2 Announce Type: replace +Abstract: We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong model performance. MixtureVitae follows a risk-mitigated sourcing strategy that combines public-domain and permissively licensed text (e.g., CC-BY/Apache) with carefully justified low-risk additions (e.g., government works and EU TDM-eligible sources), alongside targeted instruction, reasoning and synthetic data with documented provenance. We detail a transparent, multi-stage pipeline for license-aware filtering, safety and quality screening, and domain-aware mixing, and we release the dataset and curation recipes to support reproducible research. In controlled experiments using the open-sci-ref training protocol (fixed architectures at 130M/400M/1.3B/1.7B parameters; training budgets of 50B and 300B tokens), models trained on MixtureVitae consistently outperform other permissive datasets across a suite of standard benchmarks, and at the 1.7B/300B setting they surpass FineWeb-Edu and approach DCLM in the later stages of training. Performance is particularly strong on math/code and competitive on QA tasks. These results demonstrate that permissive-first, risk-mitigated data provides a practical and legally mitigated foundation for training capable LLMs, reducing reliance on indiscriminate web scraping without sacrificing competitiveness. Code: https://github.com/ontocord/mixturevitae + oai:arXiv.org:2509.25531v2 + cs.CL + cs.AI + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Arieh Iserles + Huu Nguyen (Sonny), Victor May (Sonny), Harsh Raj (Sonny), Marianna Nezhurina (Sonny), Yishan Wang (Sonny), Yanqi Luo (Sonny), Minh Chien Vu (Sonny), Taishi Nakamura (Sonny), Ken Tsui (Sonny), Van Khue Nguyen (Sonny), David Salinas (Sonny), Aleksandra Krasnod\k{e}bska (Sonny), Christoph Schuhmann (Sonny), Mats Leon Richter (Sonny), Xuan-Son (Sonny), Vu, Jenia Jitsev + + + SOCK: A Benchmark for Measuring Self-Replication in Large Language Models + https://arxiv.org/abs/2509.25643 + arXiv:2509.25643v3 Announce Type: replace +Abstract: We introduce SOCK, a benchmark command line interface (CLI) that measures large language models' (LLMs) ability to self-replicate without human intervention. In this benchmark, self-replication is defined not only as an LLM's ability to create a functioning and running copy of itself, but also the ability for that self-replication to persist and occur across different computational contexts. Accordingly, we've developed a system to categorize LLMs based on broad self-replication capabilities in two general classes, Replication-Capability Levels (RCL) and Persistence-Capability Levels (PCL). Using a five-task suite based on practically manipulable modern CLI utilities and computer processes, experiments are orchestrated in a controlled environment with an LLM acting agentically. The performance of the LLM on agent tasks is then computed to produce an R-score (a quantitative evaluation of overall self-replication ability) and data used to categorize LLMs into specific RCL-PCL matrices. SOCK offers two primary contributions: (1) Provides the first formalized definitions and benchmark suite for evaluating LLM self-replication, with the goal of establishing a standard for future research, to our knowledge; (2) Allows the industry to track the effectiveness of future multi-agent systems and mitigate potential self-replication threat vectors within them. The results compiled from evaluating a variety of open-weight and proprietary frontier models reveal significant obstacles to persistent self-replication and multi-agent systems, including context retention and multi-agent decision-making. We propose future research directions to safely reduce the severity of these obstacles, potentially lowering future risk of more functional multi-agent systems. + oai:arXiv.org:2509.25643v3 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Justin Chavarria, Rohan Raizada, Justin White, Eyad Alhetairshi - Non-Intrusive Data-Free Parametric Reduced Order Model for Geometrically Nonlinear Structures - https://arxiv.org/abs/2512.07366 - arXiv:2512.07366v1 Announce Type: new -Abstract: We present a fully non-intrusive parametric reduced-order modeling (PROM) framework for geometrically nonlinear structures subject to geometric variations. The method builds upon equation-driven Galerkin ROMs constructed from vibration modes and modal-derivative companion vectors, while nonlinear reduced tensors are identified from standard finite element outputs. A database of such ROMs is generated over a set of training samples, and all reduced operators-including the linear stiffness matrix, the quadratic and cubic nonlinear tensors, the Rayleigh damping parameters, and the reduction basis-are interpolated using Radial Basis Functions (RBFs). A global reduced basis is obtained through a two-level POD compression, combined with a MAC-guided reordering strategy to ensure parametric smoothness. The resulting PROM preserves the symmetry and polynomial structure of the reduced equations, enabling robust and efficient adaptation to new parameter values. Analytical parameter sensitivities follow directly from the interpolation model. The approach is demonstrated on a parametrically curved panel and a wing-box with geometric variations, showing excellent agreement with high-fidelity simulations and enabling substantial reductions in computational cost for parametric analyses. - oai:arXiv.org:2512.07366v1 + Numerical approximations to invariant measures of hybrid stochastic differential equations with superlinear coefficients via the backward Euler-Maruyama method + https://arxiv.org/abs/2509.25799 + arXiv:2509.25799v2 Announce Type: replace +Abstract: For stochastic differential equations (SDEs) with Markovian switching, whose drift and diffusion coefficients are allowed to contain superlinear terms, the backward Euler-Maruyama (BEM) method is proposed to approximate the invariant measure. The existence and uniqueness of the invariant measure of the numerical solution generated by the BEM method is proved. Then the convergence of the numerical invariant measure to its underlying counterpart is shown. Those results obtained in this work release the requirement of the global Lipschitz condition on the diffusion coefficient in [X. Li et al. SIAM J. Numer. Anal. 56(3)(2018), pp. 1435-1455] and can also be regarded as a non-trivial extension of [W. Liu et al. Appl. Numer. Math. 184(2023), pp. 137-150] to the case of hybrid SDEs. + oai:arXiv.org:2509.25799v2 math.NA cs.NA - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Alexander Saccani, Paolo Tiso + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Wei Liu, Jie Xu - Multilingual corpora for the study of new concepts in the social sciences and humanities: - https://arxiv.org/abs/2512.07367 - arXiv:2512.07367v1 Announce Type: new -Abstract: This article presents a hybrid methodology for building a multilingual corpus designed to support the study of emerging concepts in the humanities and social sciences (HSS), illustrated here through the case of ``non-technological innovation''. The corpus relies on two complementary sources: (1) textual content automatically extracted from company websites, cleaned for French and English, and (2) annual reports collected and automatically filtered according to documentary criteria (year, format, duplication). The processing pipeline includes automatic language detection, filtering of non-relevant content, extraction of relevant segments, and enrichment with structural metadata. From this initial corpus, a derived dataset in English is created for machine learning purposes. For each occurrence of a term from the expert lexicon, a contextual block of five sentences is extracted (two preceding and two following the sentence containing the term). Each occurrence is annotated with the thematic category associated with the term, enabling the construction of data suitable for supervised classification tasks. This approach results in a reproducible and extensible resource, suitable both for analyzing lexical variability around emerging concepts and for generating datasets dedicated to natural language processing applications. - oai:arXiv.org:2512.07367v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects + https://arxiv.org/abs/2510.02069 + arXiv:2510.02069v2 Announce Type: replace +Abstract: Accurate reconstruction and relighting of glossy objects remains a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disentangle. Existing neural rendering approaches often rely on simplified BRDF models or parameterizations that couple diffuse and specular components, which restrict faithful material recovery and limit relighting fidelity. We propose a relightable framework that integrates a microfacet BRDF with the specular-glossiness parameterization into 2D Gaussian Splatting with deferred shading. This formulation enables more physically consistent material decomposition, while diffusion-based priors for surface normals and diffuse color guide early-stage optimization and mitigate ambiguity. A coarse-to-fine environment map optimization accelerates convergence, and negative-only environment map clipping preserves high-dynamic-range specular reflections. Extensive experiments on complex, glossy scenes demonstrate that our method achieves high-quality geometry and material reconstruction, delivering substantially more realistic and consistent relighting under novel illumination compared to existing Gaussian splatting methods. + oai:arXiv.org:2510.02069v2 + cs.GR + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Revekka Kyriakoglou (LIASD), Anna Pappa (LIASD) + Georgios Kouros, Minye Wu, Tinne Tuytelaars - Challenges in Developing Secure Software -- Results of an Interview Study in the German Software Industry - https://arxiv.org/abs/2512.07368 - arXiv:2512.07368v1 Announce Type: new -Abstract: The damage caused by cybercrime makes the development of secure software inevitable. Although many tools and frameworks exist to support the development of secure software, statistics on cybercrime show no improvement in recent years. To understand the challenges software companies face in developing secure software, we conducted an interview study with 19 industry experts from 12 cross-industry companies. The results of our study show that the challenges are mainly due to high complexity, a lack of security awareness, and unsuitable processes, which are further exacerbated by an immediate lack of skilled personnel. This article presents our study and the challenges we identified, and derives potential research directions from them. - oai:arXiv.org:2512.07368v1 - cs.SE - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - new + LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL + https://arxiv.org/abs/2510.02350 + arXiv:2510.02350v2 Announce Type: replace +Abstract: Converting natural language questions into SQL queries enables non-expert users to interact with relational databases and has long been a central task for natural language interfaces to data. While the WikiSQL dataset played a key role in early text-to-SQL research, its usage has declined due to structural and annotation issues, including case sensitivity inconsistencies, data type mismatches, syntax errors, and unanswered questions. We present LLMSQL, a systematic revision and transformation of WikiSQL designed for the large language model era. We classify these errors and implement automated methods for cleaning and re-annotation. To assess the impact of these improvements, we evaluated multiple large language models, including Gemma 3, LLaMA 3.2, Mistral 7B, gpt-oss 20B, Phi-3.5 Mini, Qwen 2.5, OpenAI o4-mini, DeepSeek-R1, and others. Notably, DeepSeek-R1 achieves 88.40% accuracy in a zero-shot setting, and models under 10B parameters surpass 90% accuracy after fine-tuning. Rather than serving as an update, LLMSQL is introduced as an LLM-ready benchmark. Unlike the original WikiSQL, which was tailored for pointer-network models selecting tokens from input, LLMSQL provides clean natural language questions and full SQL queries as plain text, enabling straightforward generation and evaluation for modern natural-language-to-SQL models. + oai:arXiv.org:2510.02350v2 + cs.CL + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Alex R. Mattukat, Timo Langstrof, Horst Lichter + Dzmitry Pihulski, Karol Charchut, Viktoria Novogrodskaia, Jan Koco\'n - ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning - https://arxiv.org/abs/2512.07371 - arXiv:2512.07371v1 Announce Type: new -Abstract: Behavior-cloning based visuomotor policies enable precise manipulation but often inherit the slow, cautious tempo of human demonstrations, limiting practical deployment. However, prior studies on acceleration methods mainly rely on statistical or heuristic cues that ignore task semantics and can fail across diverse manipulation settings. We present ESPADA, a semantic and spatially aware framework that segments demonstrations using a VLM-LLM pipeline with 3D gripper-object relations, enabling aggressive downsampling only in non-critical segments while preserving precision-critical phases, without requiring extra data or architectural modifications, or any form of retraining. To scale from a single annotated episode to the full dataset, ESPADA propagates segment labels via Dynamic Time Warping (DTW) on dynamics-only features. Across both simulation and real-world experiments with ACT and DP baselines, ESPADA achieves approximately a 2x speed-up while maintaining success rates, narrowing the gap between human demonstrations and efficient robot control. - oai:arXiv.org:2512.07371v1 - cs.RO + UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs + https://arxiv.org/abs/2510.03291 + arXiv:2510.03291v2 Announce Type: replace +Abstract: Large Language Models (LLMs) achieve strong performance across diverse tasks but face prohibitive computational and memory costs. Pruning offers a promising path by inducing sparsity while preserving architectural flexibility. However, existing methods struggle to balance efficiency and robustness: local metric approaches prune layer by layer but often collapse under high sparsity, whereas global feedback methods enforce consistency at the cost of expensive weight updates or restrictive semi-structured formats. We present UniPruning, a unified post-training pruning framework that combines the speed of local saliency metrics with the stability of global coordination, enabled by a mirror descent based optimization, all without updating model weights. UniPruning leverages fast layer-wise scoring and a lightweight global controller to allocate a single sparsity budget, supporting both unstructured and semi-structured N :M pruning within one framework. After a brief calibration, it can generate pruning masks for arbitrary sparsity levels in one shot, and adapts seamlessly to hardware-aware constraints. Extensive experiments on multiple pretrained LLM families and standard benchmarks show that UniPruning consistently delivers competitive or superior perplexity and zero-shot accuracy. Ablation studies further highlight the importance of mirror descent and local saliency anchoring. Overall, UniPruning provides an efficient, principled, and scalable solution for sparsifying large-scale LLMs. Our code is available at: https://github.com/RainbowQTT/UniPruning. + oai:arXiv.org:2510.03291v2 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Byungju Kim, Jinu Pahk, Chungwoo Lee, Jaejoon Kim, Jangha Lee, Theo Taeyeong Kim, Kyuhwan Shim, Jun Ki Lee, Byoung-Tak Zhang + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Yizhuo Ding, Wanying Qu, Jiawei Geng, Wenqi Shao, Yanwei Fu - Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning - https://arxiv.org/abs/2512.07374 - arXiv:2512.07374v1 Announce Type: new -Abstract: Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, existing unlearning methods often require full-model fine-tuning or access to the original training data, which limits their scalability and practicality. In this work, we introduce Recover-to-Forget (R2F), a novel framework for efficient unlearning in LLMs based on reconstructing full-model gradient directions from low-rank LoRA adapter updates. Rather than performing backpropagation through the full model, we compute gradients with respect to LoRA parameters using multiple paraphrased prompts and train a gradient decoder to approximate the corresponding full-model gradients. To ensure applicability to larger or black-box models, the decoder is trained on a proxy model and transferred to target models. We provide a theoretical analysis of cross-model generalization and demonstrate that our method achieves effective unlearning while preserving general model performance. Experimental results demonstrate that R2F offers a scalable and lightweight alternative for unlearning in pretrained LLMs without requiring full retraining or access to internal parameters. - oai:arXiv.org:2512.07374v1 - cs.LG - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + From Patchwork to Network: A Comprehensive Framework for Demand Analysis and Fleet Optimization of Urban Air Mobility + https://arxiv.org/abs/2510.04186 + arXiv:2510.04186v3 Announce Type: replace +Abstract: Urban Air Mobility (UAM) presents a transformative vision for metropolitan transportation, but its practical implementation is hindered by substantial infrastructure costs and operational complexities. We address these challenges by modeling a UAM network that leverages existing regional airports and operates with an optimized, heterogeneous fleet of aircraft. We introduce LPSim, a Large-Scale Parallel Simulation framework that utilizes multi-GPU computing to co-optimize UAM demand, fleet operations, and ground transportation interactions simultaneously. + Our equilibrium search algorithm is extended to accurately forecast demand and determine the most efficient fleet composition. Applied to a case study of the San Francisco Bay Area, our results demonstrate that this UAM model can yield over 20 minutes' travel time savings for 230,000 selected trips. However, the analysis also reveals that system-wide success is critically dependent on seamless integration with ground access and dynamic scheduling. + oai:arXiv.org:2510.04186v3 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni, Mohsen Imani + Xuan Jiang, Xuanyu Zhou, Yibo Zhao, Shangqing Cao, Dingyi Zhuang, Jinhua Zhao, Haris Koutsopoulos, Shenhao Wang, Mark Hansen, Raja Sengupta - LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples - https://arxiv.org/abs/2512.07375 - arXiv:2512.07375v1 Announce Type: new -Abstract: Large language models (LLMs) possess vast knowledge acquired from extensive training corpora, but they often cannot remove specific pieces of information when needed, which makes it hard to handle privacy, bias mitigation, and knowledge correction. Traditional model unlearning approaches require computationally expensive fine-tuning or direct weight editing, making them impractical for real-world deployment. In this work, we introduce LoRA-based Unlearning with Negative Examples (LUNE), a lightweight framework that performs negative-only unlearning by updating only low-rank adapters while freezing the backbone, thereby localizing edits and avoiding disruptive global changes. Leveraging Low-Rank Adaptation (LoRA), LUNE targets intermediate representations to suppress (or replace) requested knowledge with an order-of-magnitude lower compute and memory than full fine-tuning or direct weight editing. Extensive experiments on multiple factual unlearning tasks show that LUNE: (I) achieves effectiveness comparable to full fine-tuning and memory-editing methods, and (II) reduces computational cost by about an order of magnitude. - oai:arXiv.org:2512.07375v1 - cs.LG - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + NERVIS: An Interactive System for Graph-Based Exploration and Editing of Named Entities + https://arxiv.org/abs/2510.04971 + arXiv:2510.04971v2 Announce Type: replace +Abstract: We present an interactive visualization system for exploring named entities and their relationships across document collections. The system is designed around a graph-based representation that integrates three types of nodes: documents, entity mentions, and entities. Connections capture two key relationship types: (i) identical entities across contexts, and (ii) co-locations of mentions within documents. Multiple coordinated views enable users to examine entity occurrences, discover clusters of related mentions, and explore higher-level entity group relationships. To support flexible and iterative exploration, the interface offers fuzzy views with approximate connections, as well as tools for interactively editing the graph by adding or removing links, entities, and mentions, as well as editing entity terms. Additional interaction features include filtering, mini-map navigation, and export options to JSON or image formats for downstream analysis and reporting. This approach contributes to human-centered exploration of entity-rich text data by combining graph visualization, interactive refinement, and adaptable perspectives on relationships. + oai:arXiv.org:2510.04971v2 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yezi Liu, Hanning Chen, Wenjun Huang, Yang Ni, Mohsen Imani + Uro\v{s} \v{S}majdek, Ciril Bohak - Enhancing Small Object Detection with YOLO: A Novel Framework for Improved Accuracy and Efficiency - https://arxiv.org/abs/2512.07379 - arXiv:2512.07379v1 Announce Type: new -Abstract: This paper investigates and develops methods for detecting small objects in large-scale aerial images. Current approaches for detecting small objects in aerial images often involve image cropping and modifications to detector network architectures. Techniques such as sliding window cropping and architectural enhancements, including higher-resolution feature maps and attention mechanisms, are commonly employed. Given the growing importance of aerial imagery in various critical and industrial applications, the need for robust frameworks for small object detection becomes imperative. To address this need, we adopted the base SW-YOLO approach to enhance speed and accuracy in small object detection by refining cropping dimensions and overlap in sliding window usage and subsequently enhanced it through architectural modifications. we propose a novel model by modifying the base model architecture, including advanced feature extraction modules in the neck for feature map enhancement, integrating CBAM in the backbone to preserve spatial and channel information, and introducing a new head to boost small object detection accuracy. Finally, we compared our method with SAHI, one of the most powerful frameworks for processing large-scale images, and CZDet, which is also based on image cropping, achieving significant improvements in accuracy. The proposed model achieves significant accuracy gains on the VisDrone2019 dataset, outperforming baseline YOLOv5L detection by a substantial margin. Specifically, the final proposed model elevates the mAP .5.5 accuracy on the VisDrone2019 dataset from the base accuracy of 35.5 achieved by the YOLOv5L detector to 61.2. Notably, the accuracy of CZDet, which is another classic method applied to this dataset, is 58.36. This research demonstrates a significant improvement, achieving an increase in accuracy from 35.5 to 61.2. - oai:arXiv.org:2512.07379v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs + https://arxiv.org/abs/2510.05154 + arXiv:2510.05154v3 Announce Type: replace +Abstract: Large-scale public deliberations generate thousands of free-form contributions that must be synthesized into representative and neutral summaries for policy use. While LLMs have been shown as a promising tool to generate summaries for large-scale deliberations, they also risk underrepresenting minority perspectives and exhibiting bias with respect to the input order, raising fairness concerns in high-stakes contexts. Studying and fixing these issues requires a comprehensive evaluation at a large scale, yet current practice often relies on LLMs as judges, which show weak alignment with human judgments. To address this, we present DeliberationBank, a large-scale human-grounded dataset with (1) opinion data spanning ten deliberation questions created by 3,000 participants and (2) summary judgment data annotated by 4,500 participants across four dimensions (representativeness, informativeness, neutrality, policy approval). Using these datasets, we train DeliberationJudge, a fine-tuned DeBERTa model that can rate deliberation summaries from individual perspectives. DeliberationJudge is more efficient and more aligned with human judgements compared to a wide range of LLM judges. With DeliberationJudge, we evaluate 18 LLMs and reveal persistent weaknesses in deliberation summarization, especially underrepresentation of minority positions. Our framework provides a scalable and reliable way to evaluate deliberation summarization, helping ensure AI systems are more representative and equitable for policymaking. + oai:arXiv.org:2510.05154v3 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Mahila Moghadami, Mohammad Ali Keyvanrad, Melika Sabaghian + Shenzhe Zhu, Shu Yang, Michiel A. Bakker, Alex Pentland, Jiaxin Pei - Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects - https://arxiv.org/abs/2512.07381 - arXiv:2512.07381v1 Announce Type: new -Abstract: 3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly in sparse-view and dynamic scene reconstruction. We propose Tessellation GS, a structured 2D GS approach anchored on mesh faces, to reconstruct dynamic scenes from a single continuously moving or static camera. Our method constrains 2D Gaussians to localized regions and infers their attributes via hierarchical neural features on mesh faces. Gaussian subdivision is guided by an adaptive face subdivision strategy driven by a detail-aware loss function. Additionally, we leverage priors from a reconstruction foundation model to initialize Gaussian deformations, enabling robust reconstruction of general dynamic objects from a single static camera, previously extremely challenging for optimization-based methods. Our method outperforms previous SOTA method, reducing LPIPS by 29.1% and Chamfer distance by 49.2% on appearance and mesh reconstruction tasks. - oai:arXiv.org:2512.07381v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment + https://arxiv.org/abs/2510.05526 + arXiv:2510.05526v2 Announce Type: replace +Abstract: Reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) are important techniques to align large language models (LLM) with human preference. However, the quality of RLHF and DPO training is seriously compromised by \textit{\textbf{C}orrupted} preference, reward \textit{\textbf{O}veroptimization}, and bias towards \textit{\textbf{V}erbosity}. To our knowledge, most existing works tackle only one of these important issues, and the few other works require much computation to estimate multiple reward models and lack theoretical guarantee of generalization ability. In this work, we propose RLHF-\textbf{COV} and DPO-\textbf{COV} algorithms that can simultaneously mitigate these three issues, in both offline and online settings. This ability is theoretically demonstrated by obtaining length-regularized generalization error rates for our DPO-COV algorithms trained on corrupted data, which match the best-known rates for simpler cases with clean data and without length regularization. Moreover, our DPO-COV algorithm is simple to implement without reward estimation, and is proved to be equivalent to our RLHF-COV algorithm, which directly implies the equivalence between the vanilla RLHF and DPO algorithms. Experiments demonstrate the effectiveness of our DPO-COV algorithms under both offline and online settings. + oai:arXiv.org:2510.05526v2 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shuohan Tao, Boyao Zhou, Hanzhang Tu, Yuwang Wang, Yebin Liu + Ziyi Chen, Junyi Li, Peiran Yu, Heng Huang - LogicCBMs: Logic-Enhanced Concept-Based Learning - https://arxiv.org/abs/2512.07383 - arXiv:2512.07383v1 Announce Type: new -Abstract: Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring predictions as a linear combination of semantic concepts. However, a linear combination is inherently limiting. So we propose the enhancement of concept-based learning models through propositional logic. We introduce a logic module that is carefully designed to connect the learned concepts from CBMs through differentiable logic operations, such that our proposed LogicCBM can go beyond simple weighted combinations of concepts to leverage various logical operations to yield the final predictions, while maintaining end-to-end learnability. Composing concepts using a set of logic operators enables the model to capture inter-concept relations, while simultaneously improving the expressivity of the model in terms of logic operations. Our empirical studies on well-known benchmarks and synthetic datasets demonstrate that these models have better accuracy, perform effective interventions and are highly interpretable. - oai:arXiv.org:2512.07383v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection + https://arxiv.org/abs/2510.05535 + arXiv:2510.05535v2 Announce Type: replace +Abstract: Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse application scenarios. Recent advances employ generative intelligence to alleviate these drawbacks. However, these methods remain constrained by permutation sensitivity in embedding and reliance on convexity assumptions in gradient-based search. To address these limitations, our initial work introduces a novel framework that integrates permutation-invariant embedding with policy-guided search. Although effective, it still left opportunities to adapt to realistic distributed scenarios. In practice, data across local clients is highly imbalanced, heterogeneous and constrained by strict privacy regulations, limiting direct sharing. These challenges highlight the need for a framework that can integrate feature selection knowledge across clients without exposing sensitive information. In this extended journal version, we advance the framework from two perspectives: 1) developing a privacy-preserving knowledge fusion strategy to derive a unified representation space without sharing sensitive raw data. 2) incorporating a sample-aware weighting strategy to address distributional imbalance among heterogeneous local clients. Extensive experiments validate the effectiveness, robustness, and efficiency of our framework. The results further demonstrate its strong generalization ability in federated learning scenarios. The code and data are publicly available: https://anonymous.4open.science/r/FedCAPS-08BF. + oai:arXiv.org:2510.05535v2 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Deepika SN Vemuri, Gautham Bellamkonda, Aditya Pola, Vineeth N Balasubramanian + Rui Liu, Tao Zhe, Yanjie Fu, Feng Xia, Ted Senator, Dongjie Wang - On the Impact of Graph Neural Networks in Recommender Systems: A Topological Perspective - https://arxiv.org/abs/2512.07384 - arXiv:2512.07384v1 Announce Type: new -Abstract: In recommender systems, user-item interactions can be modeled as a bipartite graph, where user and item nodes are connected by undirected edges. This graph-based view has motivated the rapid adoption of graph neural networks (GNNs), which often outperform collaborative filtering (CF) methods such as latent factor models, deep neural networks, and generative strategies. Yet, despite their empirical success, the reasons why GNNs offer systematic advantages over other CF approaches remain only partially understood. This monograph advances a topology-centered perspective on GNN-based recommendation. We argue that a comprehensive understanding of these models' performance should consider the structural properties of user-item graphs and their interaction with GNN architectural design. To support this view, we introduce a formal taxonomy that distills common modeling patterns across eleven representative GNN-based recommendation approaches and consolidates them into a unified conceptual pipeline. We further formalize thirteen classical and topological characteristics of recommendation datasets and reinterpret them through the lens of graph machine learning. Using these definitions, we analyze the considered GNN-based recommender architectures to assess how and to what extent they encode such properties. Building on this analysis, we derive an explanatory framework that links measurable dataset characteristics to model behavior and performance. Taken together, this monograph re-frames GNN-based recommendation through its topological underpinnings and outlines open theoretical, data-centric, and evaluation challenges for the next generation of topology-aware recommender systems. - oai:arXiv.org:2512.07384v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Daniele Malitesta, Claudio Pomo, Vito Walter Anelli, Alberto Carlo Maria Mancino, Alejandro Bellog\'in, Tommaso Di Noia + NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents + https://arxiv.org/abs/2510.07172 + arXiv:2510.07172v2 Announce Type: replace +Abstract: Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive exploration of complex model systems. To address these critical gaps, we introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains. Our design mitigates the evaluation trilemma by using counterfactual law shifts - systematic alterations of canonical laws - to generate a vast suite of problems that are scalable, scientifically relevant, and memorization-resistant. Moreover, we elevate the evaluation from static function fitting to interactive model discovery, requiring agents to experimentally probe simulated complex systems to uncover hidden principles. Our extensive experiment reveals a clear but fragile capability for discovery in frontier LLMs: this ability degrades precipitously with increasing system complexity and exhibits extreme sensitivity to observational noise. Notably, we uncover a paradoxical effect of tool assistance: providing a code interpreter can hinder more capable models by inducing a premature shift from exploration to exploitation, causing them to satisfice on suboptimal solutions. These results demonstrate that robust, generalizable discovery in complex, interactive environments remains the core challenge. By providing a scalable, robust, and scientifically authentic testbed, NewtonBench offers a crucial tool for measuring true progress and guiding the development of next-generation AI agents capable of genuine scientific discovery. + oai:arXiv.org:2510.07172v2 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen, Baixuan Xu, Zhaowei Wang, Jiayang Cheng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See - How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline - https://arxiv.org/abs/2512.07385 - arXiv:2512.07385v1 Announce Type: new -Abstract: Unmanned Aerial Vehicles (UAVs) offer wide-ranging applications but also pose significant safety and privacy violation risks in areas like airport and infrastructure inspection, spurring the rapid development of Anti-UAV technologies in recent years. However, current Anti-UAV research primarily focuses on RGB, infrared (IR), or RGB-IR videos captured by fixed ground cameras, with little attention to tracking target UAVs from another moving UAV platform. To fill this gap, we propose a new multi-modal visual tracking task termed UAV-Anti-UAV, which involves a pursuer UAV tracking a target adversarial UAV in the video stream. Compared to existing Anti-UAV tasks, UAV-Anti-UAV is more challenging due to severe dual-dynamic disturbances caused by the rapid motion of both the capturing platform and the target. To advance research in this domain, we construct a million-scale dataset consisting of 1,810 videos, each manually annotated with bounding boxes, a language prompt, and 15 tracking attributes. Furthermore, we propose MambaSTS, a Mamba-based baseline method for UAV-Anti-UAV tracking, which enables integrated spatial-temporal-semantic learning. Specifically, we employ Mamba and Transformer models to learn global semantic and spatial features, respectively, and leverage the state space model's strength in long-sequence modeling to establish video-level long-term context via a temporal token propagation mechanism. We conduct experiments on the UAV-Anti-UAV dataset to validate the effectiveness of our method. A thorough experimental evaluation of 50 modern deep tracking algorithms demonstrates that there is still significant room for improvement in the UAV-Anti-UAV domain. The dataset and codes will be available at {\color{magenta}https://github.com/983632847/Awesome-Multimodal-Object-Tracking}. - oai:arXiv.org:2512.07385v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval + https://arxiv.org/abs/2510.08935 + arXiv:2510.08935v2 Announce Type: replace +Abstract: Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies that overlook user-specific semantics, ignoring individual expression styles, preferences, and historical context. In practice, identical queries in text can express vastly different intentions across users. This representational rigidity limits the ability of current RAG systems to generalize effectively in personalized settings. Specifically, we identify two core challenges for personalization: 1) user expression styles are inherently diverse, making it difficult for standard expansions to preserve personalized intent. 2) user corpora induce heterogeneous semantic structures-varying in topical focus and lexical organization-which hinders the effective anchoring of expanded queries within the user's corpora space. To address these challenges, we propose Personalize Before Retrieve (PBR), a framework that incorporates user-specific signals into query expansion prior to retrieval. PBR consists of two components: P-PRF, which generates stylistically aligned pseudo feedback using user history for simulating user expression style, and P-Anchor, which performs graph-based structure alignment over user corpora to capture its structure. Together, they produce personalized query representations tailored for retrieval. Experiments on two personalized benchmarks show that PBR consistently outperforms strong baselines, with up to 10% gains on PersonaBench across retrievers. Our findings demonstrate the value of modeling personalization before retrieval to close the semantic gap in user-adaptive RAG systems. + oai:arXiv.org:2510.08935v2 + cs.IR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chunhui Zhang, Li Liu, Zhipeng Zhang, Yong Wang, Hao Wen, Xi Zhou, Shiming Ge, Yanfeng Wang + Yingyi Zhang, Pengyue Jia, Derong Xu, Yi Wen, Xianneng Li, Yichao Wang, Wenlin Zhang, Xiaopeng Li, Weinan Gan, Huifeng Guo, Yong Liu, Xiangyu Zhao - Breaking Players' expectations: the Role of Non-player Characters' coherence and Consistency - https://arxiv.org/abs/2512.07388 - arXiv:2512.07388v1 Announce Type: new -Abstract: In video games, non-player characters (NPCs) play a pivotal role in shaping players' experiences. The design of these characters, encompassing their appearance and behaviors, can be manipulated in terms of coherence and consistency to maintain players' expectations or, on the contrary, to surprise them. The extent to which NPCs' coherence and consistency influence players' evaluation of them remains to be unveiled. To address this knowledge gap, two experiments were conducted in the context of a military shooter game. Players' evaluations of NPCs' perceived intelligence and believability were measured, as these two dimensions are fundamental to players' adoption of NPCs and subsequent commitment to them. The first experiment investigated the impact of disrupting players' initial expectations on their evaluations of NPCs. The second experiment focused on the influence of NPCs' coherence and consistency on both players' expectations and evaluation of NPCs, using a combination of questionnaires and behavioral and physiological measures. The results of our study show that disrupting players' initial expectations influences their assessment of NPCs, with coherent and consistent design reinforcing expectations and incoherent design challenging them. - oai:arXiv.org:2512.07388v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Remi Poivet (ISIR), Catherine Pelachaud (ISIR ACIDE, CNRS), Malika Auvray (ISIR ACIDE, CNRS) + Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers + https://arxiv.org/abs/2510.09017 + arXiv:2510.09017v2 Announce Type: replace +Abstract: Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model performance, quantization fidelity, and interpretability, arise from a problematic mutual reinforcement mechanism where the model learns an inefficient 'no-op' behavior by focusing attention on tokens with near-zero value states. In this paper, we propose Value-State Gated Attention (VGA), a simple, dedicated, and stable architectural mechanism for performing 'no-op' attention efficiently by directly breaking this cycle. VGA introduces a learnable, data-dependent gate, computed directly from the value vectors (V), to modulate the output. Through a theoretical analysis of the underlying gradients, we show that gating the value-state with a function of itself is more effective at decoupling value and attention score updates than prior methods that gate on input embeddings. This creates a direct regulatory pathway that allows the model to suppress a token's contribution based on its emergent value representation. Our experiments demonstrate that VGA significantly mitigates the formation of attention sinks and stabilizes value-state norms, leading to improved performance, robust quantization fidelity, and enhanced model interpretability. + oai:arXiv.org:2510.09017v2 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Rui Bu, Haofeng Zhong, Wenzheng Chen, Yangyan Li - Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood - https://arxiv.org/abs/2512.07390 - arXiv:2512.07390v1 Announce Type: new -Abstract: Test-time adaptation (TTA) enables efficient adaptation of deployed models, yet it often leads to poorly calibrated predictive uncertainty - a critical issue in high-stakes domains such as autonomous driving, finance, and healthcare. Existing calibration methods typically assume fixed models or static distributions, resulting in degraded performance under real-world, dynamic test conditions. To address these challenges, we introduce Style Invariance as a Correctness Likelihood (SICL), a framework that leverages style-invariance for robust uncertainty estimation. SICL estimates instance-wise correctness likelihood by measuring prediction consistency across style-altered variants, requiring only the model's forward pass. This makes it a plug-and-play, backpropagation-free calibration module compatible with any TTA method. Comprehensive evaluations across four baselines, five TTA methods, and two realistic scenarios with three model architecture demonstrate that SICL reduces calibration error by an average of 13 percentage points compared to conventional calibration approaches. - oai:arXiv.org:2512.07390v1 - cs.LG - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Gilhyun Nam, Taewon Kim, Joonhyun Jeong, Eunho Yang + On the Relationship between Space-Time Accessibility and Leisure Activity Participation + https://arxiv.org/abs/2510.10307 + arXiv:2510.10307v2 Announce Type: replace +Abstract: Understanding how accessibility shapes participation in leisure activities is central to promoting inclusive and vibrant urban life. Conventional accessibility measures often focus on potential access from fixed home locations, overlooking the constraints and opportunities embedded in daily routines. In this study, we apply a space-time accessibility (STA) metric rooted in the capability approach, capturing feasible leisure opportunities between home and work given a certain time budget, individual transport modes, and urban infrastructure. Using high-resolution GPS data from 2,415 residents in the Paris region, we assess how STA influences total travel time and leisure participation, measured as the diversity of leisure locations visited. Our analysis shows that most individuals, especially active transport users, choose destinations aligned with their STA-defined opportunity sets, underscoring the metric's validity in capturing capability sets. Structural equation modeling reveals that STA directly fosters leisure diversity but also reduces travel time, which in turn is associated with lower diversity of visited leisure locations. These findings highlight the value of person-centered, capability-informed accessibility metrics for understanding inequalities in urban mobility and informing transport planning strategies that expand real freedoms to participate in social life across diverse population groups. + oai:arXiv.org:2510.10307v2 + cs.SI + cs.CE + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-sa/4.0/ + Yuan Liao, Rafael H. M. Pereira, Jorge Gil, Silvia De Sojo Caso, Laura Alessandretti - GlimmerNet: A Lightweight Grouped Dilated Depthwise Convolutions for UAV-Based Emergency Monitoring - https://arxiv.org/abs/2512.07391 - arXiv:2512.07391v1 Announce Type: new -Abstract: Convolutional Neural Networks (CNNs) have proven highly effective for edge and mobile vision tasks due to their computational efficiency. While many recent works seek to enhance CNNs with global contextual understanding via self-attention-based Vision Transformers, these approaches often introduce significant computational overhead. In this work, we demonstrate that it is possible to retain strong global perception without relying on computationally expensive components. We present GlimmerNet, an ultra-lightweight convolutional network built on the principle of separating receptive field diversity from feature recombination. GlimmerNet introduces Grouped Dilated Depthwise Convolutions(GDBlocks), which partition channels into groups with distinct dilation rates, enabling multi-scale feature extraction at no additional parameter cost. To fuse these features efficiently, we design a novel Aggregator module that recombines cross-group representations using grouped pointwise convolution, significantly lowering parameter overhead. With just 31K parameters and 29% fewer FLOPs than the most recent baseline, GlimmerNet achieves a new state-of-the-art weighted F1-score of 0.966 on the UAV-focused AIDERv2 dataset. These results establish a new accuracy-efficiency trade-off frontier for real-time emergency monitoring on resource-constrained UAV platforms. Our implementation is publicly available at https://github.com/djordjened92/gdd-cnn. - oai:arXiv.org:2512.07391v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + ADiP: Adaptive Precision Systolic Array for Matrix Multiplication Acceleration + https://arxiv.org/abs/2510.10623 + arXiv:2510.10623v2 Announce Type: replace +Abstract: Transformers are at the core of modern AI nowadays. They rely heavily on matrix multiplication and require efficient acceleration due to their substantial memory and computational requirements. Quantization plays a vital role in reducing memory usage, and can be exploited for computations by designing reconfigurable architectures that enhance matrix multiplication by dynamically adjusting the precision. This paper proposes ADiP, a novel adaptive-precision systolic array architecture designed for efficient matrix multiplication acceleration.The proposed architecture consists of NxN adaptive-precision processing elements (PEs) and shared accumulators. ADiP supports multiple computation modes, including symmetric single-matrix multiplication as well as asymmetric multi-matrix multiplication with a shared input matrix, thereby improving data-reuse and PE utilization. In addition, ADiP maximizes the computational density by adapting to different precisions, such as 8bitx8bit, 8bitx4bit, and 8bitx2bit. Analytical models are developed for ADiP architecture, including latency and throughput for versatile architecture configurations. A comprehensive hardware design space exploration is demonstrated using 22nm commercial technology, achieving up to a 4x higher computational throughput. Furthermore, ADiP is evaluated on different transformer workloads from GPT-2 Medium, BERT Large, and BitNet-1.58B models, delivering latency improvement up to 53.6%, and energy improvement up to 24.4% for BitNet-1.58B MHA workloads. At a 64x64 size with 4096 PEs, ADiP achieves a peak throughput of 8.192 TOPS, 16.384 TOPS, and 32.768 TOPS for 8bitx8bit, 8bitx4bit, and 8bitx2bit operations, respectively. + oai:arXiv.org:2510.10623v2 + cs.AR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - {\DJ}or{\dj}e Nedeljkovi\'c + Ahmed J. Abdelmaksoud, Cristian Sestito, Shiwei Wang, Themis Prodromakis - Empirical Results for Adjusting Truncated Backpropagation Through Time while Training Neural Audio Effects - https://arxiv.org/abs/2512.07393 - arXiv:2512.07393v1 Announce Type: new -Abstract: This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT hyperparameters -- sequence number, batch size, and sequence length -- and their influence on model performance. Using a convolutional-recurrent architecture, we conduct extensive experiments across datasets with and without conditionning by user controls. Results demonstrate that carefully tuning these parameters enhances model accuracy and training stability, while also reducing computational demands. Objective evaluations confirm improved performance with optimized settings, while subjective listening tests indicate that the revised TBPTT configuration maintains high perceptual quality. - oai:arXiv.org:2512.07393v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation + https://arxiv.org/abs/2510.11000 + arXiv:2510.11000v2 Announce Type: replace +Abstract: Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address these limitations, we introduce ContextGen, a novel Diffusion Transformer framework for multi-instance generation that is guided by both layout and reference images. Our approach integrates two key technical contributions: a Contextual Layout Anchoring (CLA) mechanism that incorporates the composite layout image into the generation context to robustly anchor the objects in their desired positions, and Identity Consistency Attention (ICA), an innovative attention mechanism that leverages contextual reference images to ensure the identity consistency of multiple instances. Recognizing the lack of large-scale, hierarchically-structured datasets for this task, we introduce IMIG-100K, the first dataset with detailed layout and identity annotations. Extensive experiments demonstrate that ContextGen sets a new state-of-the-art, outperforming existing methods in control precision, identity fidelity, and overall visual quality. + oai:arXiv.org:2510.11000v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 28th International Conference on Digital Audio Effects (DAFx25), Sep 2025, Ancona, Italy - Yann Bourdin (ASTRAL), Pierrick Legrand (ASTRAL, ENSC, IMS), Fanny Roche + Ruihang Xu, Dewei Zhou, Fan Ma, Yi Yang - Reconstructing Objects along Hand Interaction Timelines in Egocentric Video - https://arxiv.org/abs/2512.07394 - arXiv:2512.07394v1 Announce Type: new -Abstract: We introduce the task of Reconstructing Objects along Hand Interaction Timelines (ROHIT). We first define the Hand Interaction Timeline (HIT) from a rigid object's perspective. In a HIT, an object is first static relative to the scene, then is held in hand following contact, where its pose changes. This is usually followed by a firm grip during use, before it is released to be static again w.r.t. to the scene. We model these pose constraints over the HIT, and propose to propagate the object's pose along the HIT enabling superior reconstruction using our proposed Constrained Optimisation and Propagation (COP) framework. Importantly, we focus on timelines with stable grasps - i.e. where the hand is stably holding an object, effectively maintaining constant contact during use. This allows us to efficiently annotate, study, and evaluate object reconstruction in videos without 3D ground truth. We evaluate our proposed task, ROHIT, over two egocentric datasets, HOT3D and in-the-wild EPIC-Kitchens. In HOT3D, we curate 1.2K clips of stable grasps. In EPIC-Kitchens, we annotate 2.4K clips of stable grasps including 390 object instances across 9 categories from videos of daily interactions in 141 environments. Without 3D ground truth, we utilise 2D projection error to assess the reconstruction. Quantitatively, COP improves stable grasp reconstruction by 6.2-11.3% and HIT reconstruction by up to 24.5% with constrained pose propagation. - oai:arXiv.org:2512.07394v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Zhifan Zhu, Siddhant Bansal, Shashank Tripathi, Dima Damen + COINS: SemantiC Ids Enhanced COLd Item RepresentatioN for Click-through Rate Prediction in E-commerce Sarch + https://arxiv.org/abs/2510.12604 + arXiv:2510.12604v2 Announce Type: replace +Abstract: With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding issue. Existing methods align items' side content with collaborative information to transfer collaborative signals from high-popularity items to cold-start items. However, these methods fail to account for the asymmetry between collaboration and content, nor the fine-grained differences among items. To address these issues, we propose SMILE, an item representation enhancement approach based on fused alignment of semantic IDs. Specifically, we use RQ-OPQ encoding to quantize item content and collaborative information, followed by a two-step alignment: RQ encoding transfers shared collaborative signals across items, while OPQ encoding learns differentiated information of items. Comprehensive offline experiments on large-scale industrial datasets demonstrate superiority of SMILE, and rigorous online A/B tests confirm statistically significant improvements: item CTR +1.66%, buyers +1.57%, and order volume +2.17%. + oai:arXiv.org:2510.12604v2 + cs.IR + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Qihang Zhao, Zhongbo Sun, Xiaoyang Zheng, Xian Guo, Siyuan Wang, Zihan Liang, Mingcan Peng, Ben Chen, Chenyi Lei - Safety-Critical Control on Lie Groups Using Energy-Augmented Zeroing Control Barrier Functions - https://arxiv.org/abs/2512.07395 - arXiv:2512.07395v1 Announce Type: new -Abstract: We study safety-critical control on fully actuated mechanical systems by means of Zeroing Control Barrier Functions (ZCBFs) defined on Lie Groups. Specifically, we introduce and theoretically validate two classes of ZCBFs. The first enforces kinematic constraints, suitable for implementing obstacle avoidance algorithms. The second enforces kinetic energy limits along prescribed inertial-frame translational and rotational directions, relevant for ensuring safe physical interaction. Numerical simulations involving slit traversal and safe landing scenarios are presented to validate the effectiveness and versatility of the proposed methodology. - oai:arXiv.org:2512.07395v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new + You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction + https://arxiv.org/abs/2510.14885 + arXiv:2510.14885v2 Announce Type: replace +Abstract: Despite the renewed interest in zero-shot visual classification due to the rise of Multimodal Large Language Models (MLLMs), the problem of evaluating free-form responses of auto-regressive models remains a persistent challenge. Most existing works focus on language-only tasks or don't consider Multiple Choice Questions (MCQs) beyond 5-way options, both of which are critical capabilities to solve tasks in Fine-Grained Visual Classification (FGVC) where choice counts are in the hundreds to thousands and the choices are highly related. Furthermore, in this highly multi-way MCQ setting it is not clear how to extend LLM choice extraction to retrieval-based problems, where computing probabilities over the choice set is computationally costly. In this work we investigate nlg2choice, a simple two-stage method which first asks the MLLM an open-ended question for the task with minimal constraints, then uses text-only constrained decoding to predict the most likely choice. In retrieval settings, we compute the probability of the constrained response taking that choice with an early stopping method to significantly improve throughput. Our results show improvement over a suite of seven fine-grained visual datasets when evaluating in terms of classification and retrieval, and show that this performance holds over the various ways that users of LLMs can implement tasks in natural language. + oai:arXiv.org:2510.14885v2 + cs.CV + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Alessandro Letti, Riccardo Zanella, Alessandro Macchelli, Federico Califano + Logan Lawrence, Oindrila Saha, Megan Wei, Chen Sun, Subhransu Maji, Grant Van Horn - Asymptotic analysis of shallow and deep forgetting in replay with Neural Collapse - https://arxiv.org/abs/2512.07400 - arXiv:2512.07400v1 Announce Type: new -Abstract: A persistent paradox in continual learning (CL) is that neural networks often retain linearly separable representations of past tasks even when their output predictions fail. We formalize this distinction as the gap between deep feature-space and shallow classifier-level forgetting. We reveal a critical asymmetry in Experience Replay: while minimal buffers successfully anchor feature geometry and prevent deep forgetting, mitigating shallow forgetting typically requires substantially larger buffer capacities. To explain this, we extend the Neural Collapse framework to the sequential setting. We characterize deep forgetting as a geometric drift toward out-of-distribution subspaces and prove that any non-zero replay fraction asymptotically guarantees the retention of linear separability. Conversely, we identify that the "strong collapse" induced by small buffers leads to rank-deficient covariances and inflated class means, effectively blinding the classifier to true population boundaries. By unifying CL with out-of-distribution detection, our work challenges the prevailing reliance on large buffers, suggesting that explicitly correcting these statistical artifacts could unlock robust performance with minimal replay. - oai:arXiv.org:2512.07400v1 - cs.LG + When Many-Shot Prompting Fails: An Empirical Study of LLM Code Translation + https://arxiv.org/abs/2510.16809 + arXiv:2510.16809v2 Announce Type: replace +Abstract: Large Language Models (LLMs) with vast context windows offer new avenues for in-context learning (ICL), where providing many examples ("many-shot" prompting) is often assumed to enhance performance. We investigate this assumption for the complex task of code translation. Through a large-scale empirical study of over 90,000 translations, we systematically evaluate the impact of scaling in-context examples from zero-shot to many-shot configurations of up to 625 examples, with prompts spanning from approximately 100,000 to 800,000 tokens. Our findings reveal a "many-shot paradox": while static similarity metrics may modestly improve with more examples, functional correctness consistently peaks with few-shot prompting (5-25 examples). Providing substantially more examples often degrades this crucial functional performance. This study highlights that for code translation, the quality of a few well-chosen examples outweighs sheer quantity, challenging the universal efficacy of "more is better" for ICL and underscoring the task-dependent nature of optimal prompting strategies. Our results have significant implications for effectively leveraging LLMs in software engineering. + oai:arXiv.org:2510.16809v2 + cs.SE cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.CL + cs.PL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Giulia Lanzillotta, Damiano Meier, Thomas Hofmann + Amirkia Rafiei Oskooei, Kaan Baturalp Cosdan, Husamettin Isiktas, Mehmet S. Aktas - Otus Supercomputer - https://arxiv.org/abs/2512.07401 - arXiv:2512.07401v1 Announce Type: new -Abstract: Otus is a high-performance computing cluster that was launched in 2025 and is operated by the Paderborn Center for Parallel Computing (PC2) at Paderborn University in Germany. The system is part of the National High Performance Computing (NHR) initiative. Otus complements the previous supercomputer Noctua 2, offering approximately twice the computing power while retaining the three node types that were characteristic of Noctua 2: 1) CPU compute nodes with different memory capacities, 2) high-end GPU nodes, and 3) HPC-grade FPGA nodes. On the Top500 list, which ranks the 500 most powerful supercomputers in the world, Otus is in position 164 with the CPU partition and in position 255 with the GPU partition (June 2025). On the Green500 list, ranking the 500 most energy-efficient supercomputers in the world, Otus is in position 5 with the GPU partition (June 2025). - This article provides a comprehensive overview of the system in terms of its hardware, software, system integration, and its overall integration into the data center building to ensure energy-efficient operation. The article aims to provide unique insights for scientists using the system and for other centers operating HPC clusters. The article will be continuously updated to reflect the latest system setup and measurements. - oai:arXiv.org:2512.07401v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sadaf Ehtesabi, Manoar Hossain, Tobias Kenter, Andreas Krawinkel, Holger Nitsche, Lukas Ostermann, Christian Plessl, Heinrich Riebler, Stefan Rohde, Robert Schade, Michael Schwarz, Jens Simon, Nils Winnwa, Alex Wiens, Xin Wu + On the Credibility of Deniable Communication in Court + https://arxiv.org/abs/2510.16873 + arXiv:2510.16873v2 Announce Type: replace +Abstract: Over time, cryptographically deniable systems have come to be associated in computer-science literature with the idea of "denying" evidence in court - specifically, with the ability to convincingly forge evidence in courtroom scenarios and an inability to authenticate evidence in such contexts. Evidentiary processes in courts, however, have been developed over centuries to account for the reality that evidence has always been forgeable, and relies on factors outside of cryptographic models to seek the truth "as well as possible" while acknowledging that all evidence is imperfect. We argue that deniability does not and need not change this paradigm. + Our analysis highlights a gap between technical deniability notions and their application to the real world. There will always be factors outside a cryptographic model that influence perceptions of a message's authenticity, in realistic situations. We propose the broader concept of credibility to capture these factors. The credibility of a system is determined by (1) a threshold of quality that a forgery must pass to be "believable" as an original communication, which varies based on sociotechnical context and threat model, (2) the ease of creating a forgery that passes this threshold, which is also context- and threat-model-dependent, and (3) default system retention policy and retention settings. All three aspects are important for designing secure communication systems for real-world threat models, and some aspects of (2) and (3) may be incorporated directly into technical system design. We hope that our model of credibility will facilitate system design and deployment that addresses threats that are not and cannot be captured by purely technical definitions and existing cryptographic models, and support more nuanced discourse on the strengths and limitations of cryptographic guarantees within specific legal and sociotechnical contexts. + oai:arXiv.org:2510.16873v2 + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Jacob Leiken, Sunoo Park - Do LLMs Trust the Code They Write? - https://arxiv.org/abs/2512.07404 - arXiv:2512.07404v1 Announce Type: new -Abstract: Despite the effectiveness of large language models (LLMs) for code generation, they often output incorrect code. One reason is that model output probabilities are often not well-correlated with correctness, and reflect only the final output of the generation process. Inspired by findings that LLMs internally encode concepts like truthfulness, this paper explores if LLMs similarly represent code correctness. Specifically, we identify a correctness representation inside LLMs by contrasting the hidden states between pairs of correct and incorrect code for the same programming tasks. By experimenting on four LLMs, we show that exploiting this extracted correctness representation outperforms standard log-likelihood ranking, as well as verbalized model confidence. Furthermore, we explore how this internal correctness signal can be used to select higher-quality code samples, without requiring test execution. Ultimately, this work demonstrates how leveraging internal representations can enhance code generation systems and make LLMs more reliable, thus improving confidence in automatically generated code. - oai:arXiv.org:2512.07404v1 - cs.SE - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + StreamingThinker: Large Language Models Can Think While Reading + https://arxiv.org/abs/2510.17238 + arXiv:2510.17238v2 Announce Type: replace +Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in chain of thought (CoT) reasoning. However, the current LLM reasoning paradigm initiates thinking only after the entire input is available, which introduces unnecessary latency and weakens attention to earlier information in dynamic scenarios. Inspired by human cognition of thinking while reading, we first design a \textit{\textbf{streaming thinking}} paradigm for LLMs, where reasoning unfolds in the order of input and further adjusts its depth once reading is complete. We instantiate this paradigm with \textit{StreamingThinker}, a framework that enables LLMs to think while reading through the integration of streaming CoT generation, streaming-constraint training, and streaming parallel inference. Specifically, StreamingThinker employs streaming reasoning units with quality control for CoT generation, enforces order-preserving reasoning through streaming attention masks and position encoding, and leverages parallel KV caches that decouple input encoding from reasoning generation, thereby ensuring alignment and enabling true concurrency. We evaluate StreamingThinker on the Qwen3 model family across math reasoning, logical reasoning, and context-based QA reasoning tasks. Experimental results show that the StreamingThinker preserves performance comparable to batch thinking, while yielding an 80\% reduction in token waiting before the onset of reasoning and a more than 60\% reduction in time-level latency for producing the final answer, demonstrating the effectiveness of the streaming paradigm for LLM reasoning. Code will be released at https://github.com/EIT-NLP/StreamingLLM/tree/main/StreamingThinker. + oai:arXiv.org:2510.17238v2 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Francisco Ribeiro, Claudio Spiess, Prem Devanbu, Sarah Nadi + Junlong Tong, Yingqi Fan, Anhao Zhao, Yunpu Ma, Xiaoyu Shen - Orbit recovery under the rigid motions group - https://arxiv.org/abs/2512.07405 - arXiv:2512.07405v1 Announce Type: new -Abstract: We study the orbit recovery problem under the rigid-motion group SE(n), where the objective is to reconstruct an unknown signal from multiple noisy observations subjected to unknown rotations and translations. This problem is fundamental in signal processing, computer vision, and structural biology. - Our main theoretical contribution is bounding the sample complexity of this problem. We show that if the d-th order moment under the rotation group SO(n) uniquely determines the signal orbit, then orbit recovery under SE(n) is achievable with $N\gtrsim \sigma^{2d+4}$ samples as the noise variance $\sigma^2 \to \infty$. The key technical insight is that the d-th order SO(n) moments can be explicitly recovered from (d+2)-order SE(n) autocorrelations, enabling us to transfer known results from the rotation-only setting to the rigid-motion case. We further harness this result to derive a matching bound to the sample complexity of the multi-target detection model that serves as an abstract framework for electron-microscopy-based technologies in structural biology, such as single-particle cryo-electron microscopy (cryo-EM) and cryo-electron tomography (cryo-ET). - Beyond theory, we present a provable computational pipeline for rigid-motion orbit recovery in three dimensions. Starting from rigid-motion autocorrelations, we extract the SO(3) moments and demonstrate successful reconstruction of a 3-D macromolecular structure. Importantly, this algorithmic approach is valid at any noise level, suggesting that even very small macromolecules, long believed to be inaccessible using structural biology electron-microscopy-based technologies, may, in principle, be reconstructed given sufficient data. - oai:arXiv.org:2512.07405v1 - cs.IT - eess.SP - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new + PAGE-4D: Disentangled Pose and Geometry Estimation for VGGT-4D Perception + https://arxiv.org/abs/2510.17568 + arXiv:2510.17568v3 Announce Type: replace +Abstract: Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction, and point cloud reconstruction -- all without post-processing. A central challenge in multi-task 4D reconstruction is the inherent conflict between tasks: accurate camera pose estimation requires suppressing dynamic regions, while geometry reconstruction requires modeling them. To resolve this tension, we propose a dynamics-aware aggregator that disentangles static and dynamic information by predicting a dynamics-aware mask -- suppressing motion cues for pose estimation while amplifying them for geometry reconstruction. Extensive experiments show that PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction. + oai:arXiv.org:2510.17568v3 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Amnon Balanov, Tamir Bendory, Dan Edidin + Kaichen Zhou, Yuhan Wang, Grace Chen, Xinhai Chang, Gaspard Beaudouin, Fangneng Zhan, Paul Pu Liang, Mengyu Wang - Structure preserving discretization method for 1D and 2D port-Hamiltonian systems using finite differences on staggered grids - https://arxiv.org/abs/2512.07406 - arXiv:2512.07406v1 Announce Type: new -Abstract: This paper extends previous work on finitedifference schemes over staggered grids for infinite-dimensional port-Hamiltonian systems. In the one-dimensional setting, it generalizes the discretization approach originally developed for the wave equation to a broader class of systems characterized by interconnection operators that include both differential and non-differential terms, such as the Timoshenko beam equation. The paper then introduces a discretization strategy for the two-dimensional case that requires only two grids, thereby accommodating a wider range of systems, including those whose interconnection operators contain non-differential components, such as the Mindlin plate model. - oai:arXiv.org:2512.07406v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new + Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning + https://arxiv.org/abs/2510.17923 + arXiv:2510.17923v4 Announce Type: replace +Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods face a fundamental scalability bottleneck due to their heavy reliance on human-curated preference data or labeled datasets for reward modeling. To overcome this limitation, we explore RL on unlabeled data where models learn autonomously from continuous experience streams. The core challenge in this setting lies in reliable reward estimation without ground-truth supervision. Existing approaches like Test-Time RL address this through self-consistent consensus, but risk reinforcing incorrect pseudo-labels derived from majority voting. We introduce COMPASS (Composite Path and Answer Self-Scoring), a novel test-time reward mechanism that operates without external supervision. COMPASS integrates two complementary components: the Dual-Calibration Answer Reward (DCAR), which stabilizes training by establishing trustworthy pseudo-labels through confidence and credibility calibration, and the Decisive Path Reward (DPR), which directly optimizes the reasoning process quality beyond mere outcome supervision. By jointly reinforcing trustworthy consensus answers and highly decisive reasoning chains, the COMPASS systematically enhances the model's analytical capabilities. Extensive experiments show that COMPASS achieves significant and consistent performance gains across diverse reasoning tasks and model architectures, advancing a more scalable direction for LLMs to learn from continuous experience. + oai:arXiv.org:2510.17923v4 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ignacio Diaz Alastuey (UMLP, ENSMM, FEMTO-ST), Yann Le Gorrec (UMLP, ENSMM, FEMTO-ST), Yongxin Wu (UMLP, ENSMM, FEMTO-ST) + Jingyu Xing, Chenwei Tang, Xinyu Liu, Deng Xiong, Shudong Huang, Wei Ju, Jiancheng Lv, Ziyue Qiao - Training Language Models to Use Prolog as a Tool - https://arxiv.org/abs/2512.07407 - arXiv:2512.07407v1 Announce Type: new -Abstract: Ensuring reliable tool use is critical for safe agentic AI systems. Language models frequently produce unreliable reasoning with plausible but incorrect solutions that are difficult to verify. To address this, we investigate fine-tuning models to use Prolog as an external tool for verifiable computation. Using Group Relative Policy Optimization (GRPO), we fine-tune Qwen2.5-3B-Instruct on a cleaned GSM8K-Prolog-Prover dataset while varying (i) prompt structure, (ii) reward composition (execution, syntax, semantics, structure), and (iii) inference protocol: single-shot, best-of-N, and two agentic modes where Prolog is invoked internally or independently. Our reinforcement learning approach outperforms supervised fine-tuning, with our 3B model achieving zero-shot MMLU performance comparable to 7B few-shot results. Our findings reveal that: 1) joint tuning of prompt, reward, and inference shapes program syntax and logic; 2) best-of-N with external Prolog verification maximizes accuracy on GSM8K; 3) agentic inference with internal repair yields superior zero-shot generalization on MMLU-Stem and MMLU-Pro. These results demonstrate that grounding model reasoning in formal verification systems substantially improves reliability and auditability for safety-critical applications. The source code for reproducing our experiments is available under https://github.com/niklasmellgren/grpo-prolog-inference - oai:arXiv.org:2512.07407v1 + Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation + https://arxiv.org/abs/2510.20812 + arXiv:2510.20812v3 Announce Type: replace +Abstract: Large Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet they struggle when reasoning over information-intensive images that densely interleave textual annotations with fine-grained graphical elements. The main challenges lie in precisely localizing critical cues in dense layouts and multi-hop reasoning to integrate dispersed evidence. We propose Speculative Verdict (SV), a training-free framework inspired by speculative decoding that combines multiple lightweight draft experts with a large verdict model. In the draft stage, small VLMs act as draft experts to generate reasoning paths that provide diverse localization candidates; in the verdict stage, a strong VLM synthesizes these paths to produce the final answer, minimizing computational cost while recovering correct answers. To further improve efficiency and accuracy, SV introduces a consensus expert selection mechanism that forwards only high-agreement reasoning paths to the verdict. Empirically, SV achieves consistent gains on challenging information-intensive and high-resolution visual question answering benchmarks, including InfographicVQA, ChartMuseum, ChartQAPro, and HR-Bench 4K. By synthesizing correct insights from multiple partially accurate reasoning paths, SV achieves both error correction and cost-efficiency compared to large proprietary models or training pipelines. Code is available at https://github.com/Tinaliu0123/speculative-verdict. + oai:arXiv.org:2510.20812v3 + cs.CV + cs.AI cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Niklas Mellgren, Peter Schneider-Kamp, Lukas Galke Poech + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Yuhan Liu, Lianhui Qin, Shengjie Wang - WaggleNet: A LoRa and MQTT-Based Monitoring System for Internal and External Beehive Conditions - https://arxiv.org/abs/2512.07408 - arXiv:2512.07408v1 Announce Type: new -Abstract: Bee populations are declining globally due to habitat loss, pesticide exposure, and climate change, threatening agricultural productivity and food security. While existing smart beehive systems monitor internal conditions, they typically overlook external environmental factors that significantly influence colony health, and are constrained by high cost, limited scalability, and inadequate contextual analysis. We present WaggleNet, a novel dual-scope monitoring system that simultaneously captures both internal hive conditions and external environmental parameters using a cost-effective LoRa-MQTT architecture. Our system deploys modular worker nodes ($\sim$\$15 each) equipped with temperature, humidity, light, and GPS sensors both inside and around beehives. A master node functions as a LoRa-MQTT gateway, forwarding data to a cloud server with a mobile application interface. Field experiments confirmed reliable operation with 100\% packet delivery over 110 meters in line-of-sight conditions and 95 meters in obstructed environments, including successful deployment inside wooden hive structures. Our system demonstrated stable end-to-end latency under 5 seconds and continuous operation over a two-month period across diverse environmental conditions. By bridging the gap between internal and external monitoring, WaggleNet enables contextual anomaly detection and supports data-driven precision beekeeping in resource-constrained settings. - oai:arXiv.org:2512.07408v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Shift Bribery over Social Networks + https://arxiv.org/abs/2510.21200 + arXiv:2510.21200v2 Announce Type: replace +Abstract: In shift bribery, a briber seeks to promote his preferred candidate by paying voters to raise their ranking. Classical models of shift bribery assume voters act independently, overlooking the role of social influence. However, in reality, individuals are social beings and are often represented as part of a social network, where bribed voters may influence their neighbors, thereby amplifying the effect of persuasion. We study Shift bribery over Networks, where voters are modeled as nodes in a directed weighted graph, and arcs represent social influence between them. In this setting, bribery is not confined to directly targeted voters its effects can propagate through the network, influencing neighbors and amplifying persuasion. Given a budget and individual cost functions for shifting each voter's preference toward a designated candidate, the goal is to determine whether a shift strategy exists within budget that ensures the preferred candidate wins after both direct and network-propagated influence takes effect. We show that the problem is NP-Complete even with two candidates and unit costs, and W[2]-hard when parameterized by budget or maximum degree. On the positive side, we design polynomial-time algorithms for complete graphs under plurality and majority rules and path graphs for uniform edge weights, linear-time algorithms for transitive tournaments for two candidates, linear cost functions and uniform arc weights, and pseudo-polynomial algorithms for cluster graphs. We further prove the existence of fixed-parameter tractable algorithms with treewidth as parameter for two candidates, linear cost functions and uniform arc weights and pseudo-FPT with cluster vertex deletion number for two candidates and uniform arc weights. Together, these results give a detailed complexity landscape for shift bribery in social networks. + oai:arXiv.org:2510.21200v2 + cs.GT + cs.CY + cs.MA + cs.SI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Minju Jeon, Jiyun Kim, Sewon Kim, Seongmin Park, Bo Zhang, Anthony H. Smith + Ashlesha Hota, Susobhan Bandopadhyay, Palash Dey - InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs - https://arxiv.org/abs/2512.07410 - arXiv:2512.07410v1 Announce Type: new -Abstract: Humanoid agents are expected to emulate the complex coordination inherent in human social behaviors. However, existing methods are largely confined to single-agent scenarios, overlooking the physically plausible interplay essential for multi-agent interactions. To bridge this gap, we propose InterAgent, the first end-to-end framework for text-driven physics-based multi-agent humanoid control. At its core, we introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to mitigate cross-modal interference while enabling synergistic coordination. We further propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies to facilitate network learning. Additionally, within it we devise a sparse edge-based attention mechanism that dynamically prunes redundant connections and emphasizes critical inter-agent spatial relations, thereby enhancing the robustness of interaction modeling. Extensive experiments demonstrate that InterAgent consistently outperforms multiple strong baselines, achieving state-of-the-art performance. It enables producing coherent, physically plausible, and semantically faithful multi-agent behaviors from only text prompts. Our code and data will be released to facilitate future research. - oai:arXiv.org:2512.07410v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production + https://arxiv.org/abs/2510.23856 + arXiv:2510.23856v2 Announce Type: replace +Abstract: Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business value. This path is complicated by fragmented frameworks, slow development, and the absence of standardized evaluation practices. Generalist agents have emerged as a promising direction, excelling on academic benchmarks and offering flexibility across task types, applications, and modalities. Yet, evidence of their use in production enterprise settings remains limited. This paper reports IBM's experience developing and piloting the Computer Using Generalist Agent (CUGA), which has been open-sourced for the community (https://github.com/cuga-project/cuga-agent). CUGA adopts a hierarchical planner--executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was evaluated in a pilot within the Business-Process-Outsourcing talent acquisition domain, addressing enterprise requirements for scalability, auditability, safety, and governance. To support assessment, we introduce BPO-TA, a 26-task benchmark spanning 13 analytics endpoints. In preliminary evaluations, CUGA approached the accuracy of specialized agents while indicating potential for reducing development time and cost. Our contribution is twofold: presenting early evidence of generalist agents operating at enterprise scale, and distilling technical and organizational lessons from this initial pilot. We outline requirements and next steps for advancing research-grade architectures like CUGA into robust, enterprise-ready systems. + oai:arXiv.org:2510.23856v2 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by-nc-sa/4.0/ - Bin Li, Ruichi Zhang, Han Liang, Jingyan Zhang, Juze Zhang, Xin Chen, Lan Xu, Jingyi Yu, Jingya Wang + Segev Shlomov, Alon Oved, Sami Marreed, Ido Levy, Offer Akrabi, Avi Yaeli, {\L}ukasz Str\k{a}k, Elizabeth Koumpan, Yinon Goldshtein, Eilam Shapira, Nir Mashkif, Asaf Adi - Data-driven Exploration of Mobility Interaction Patterns - https://arxiv.org/abs/2512.07415 - arXiv:2512.07415v1 Announce Type: new -Abstract: Understanding the movement behaviours of individuals and the way they react to the external world is a key component of any problem that involves the modelling of human dynamics at a physical level. In particular, it is crucial to capture the influence that the presence of an individual can have on the others. Important examples of applications include crowd simulation and emergency management, where the simulation of the mass of people passes through the simulation of the individuals, taking into consideration the others as part of the general context. While existing solutions basically start from some preconceived behavioural model, in this work we propose an approach that starts directly from the data, adopting a data mining perspective. Our method searches the mobility events in the data that might be possible evidences of mutual interactions between individuals, and on top of them looks for complex, persistent patterns and time evolving configurations of events. The study of these patterns can provide new insights on the mechanics of mobility interactions between individuals, which can potentially help in improving existing simulation models. We instantiate the general methodology on two real case studies, one on cars and one on pedestrians, and a full experimental evaluation is performed, both in terms of performances, parameter sensitivity and interpretation of sample results. - oai:arXiv.org:2512.07415v1 - cs.CV + OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows + https://arxiv.org/abs/2510.24411 + arXiv:2510.24411v2 Announce Type: replace +Abstract: Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their potential for unsafe operations, such as system compromise and privacy leakage, is raising significant concerns. Detecting these safety concerns across the vast and complex operational space of mobile environments presents a formidable challenge that remains critically underexplored. To establish a foundation for mobile agent safety research, we introduce MobileRisk-Live, a dynamic sandbox environment accompanied by a safety detection benchmark comprising realistic trajectories with fine-grained annotations. Built upon this, we propose OS-Sentinel, a novel hybrid safety detection framework that synergistically combines a Formal Verifier for detecting explicit system-level violations with a VLM-based Contextual Judge for assessing contextual risks and agent actions. Experiments show that OS-Sentinel achieves 10%-30% improvements over existing approaches across multiple metrics. Further analysis provides critical insights that foster the development of safer and more reliable autonomous mobile agents. Our code and data are available at https://github.com/OS-Copilot/OS-Sentinel. + oai:arXiv.org:2510.24411v2 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Gabriele Galatolo, Mirco Nanni - - - Adaptive Tuning of Parameterized Traffic Controllers via Multi-Agent Reinforcement Learning - https://arxiv.org/abs/2512.07417 - arXiv:2512.07417v1 Announce Type: new -Abstract: Effective traffic control is essential for mitigating congestion in transportation networks. Conventional traffic management strategies, including route guidance, ramp metering, and traffic signal control, often rely on state feedback controllers, used for their simplicity and reactivity; however, they lack the adaptability required to cope with complex and time-varying traffic dynamics. This paper proposes a multi-agent reinforcement learning framework in which each agent adaptively tunes the parameters of a state feedback traffic controller, combining the reactivity of state feedback controllers with the adaptability of reinforcement learning. By tuning parameters at a lower frequency rather than directly determining control actions at a high frequency, the reinforcement learning agents achieve improved training efficiency while maintaining adaptability to varying traffic conditions. The multi-agent structure further enhances system robustness, as local controllers can operate independently in the event of partial failures. The proposed framework is evaluated on a simulated multi-class transportation network under varying traffic conditions. Results show that the proposed multi-agent framework outperforms the no control and fixed-parameter state feedback control cases, while performing on par with the single-agent RL-based adaptive state feedback control, with a much better resilience to partial failures. - oai:arXiv.org:2512.07417v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Giray \"On\"ur, Azita Dabiri, Bart De Schutter - - - Revolutionizing Mixed Precision Quantization: Towards Training-free Automatic Proxy Discovery via Large Language Models - https://arxiv.org/abs/2512.07419 - arXiv:2512.07419v1 Announce Type: new -Abstract: Mixed-Precision Quantization (MPQ) liberates the Deep Neural Networks (DNNs) from the Out-Of-Memory (OOM) bottleneck, which garnered increasing research attention. However, conventional methods either searched from costly differentiable optimization, which is neither efficient nor flexible, or learned a quantized DNN from the proxy (i.e., HAWQ) manually designed by human experts, which is labor-intensive and requires huge expert knowledge. Can we design a proxy without involving any human experts and training? In this paper, we provide an affirmative answer by proposing a novel Large Language Models (LLMs)-driven Training-free Automatic Proxy (dubbed TAP) discovery framework, which reforms the design paradigm of MPQ by utilizing LLMs to find superior TAP tailored for MPQ, automatically. In addition, to bridge the gap between black-box LLMs and the tough MPQ task, we ingeniously propose simple Direct Policy Optimization (DPO) based reinforcement learning to enhance LLMs' reasoning by optimizing prompts, which can construct a positive feedback loop between the LLM and the MPQ task, enabling LLMs to generate better TAP in the next evolution. Extensive experiments on mainstream benchmarks demonstrate that TAP achieves state-of-the-art performance. Finally, we truly believe that our TAP will significantly contribute to the MPQ community by providing a new perspective on LLM-driven design algorithms. - oai:arXiv.org:2512.07419v1 - cs.LG + cs.CL cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Haidong Kang, Jun Du, Lihong Lin + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong - OnePiece: The Great Route to Generative Recommendation -- A Case Study from Tencent Algorithm Competition - https://arxiv.org/abs/2512.07424 - arXiv:2512.07424v1 Announce Type: new -Abstract: In past years, the OpenAI's Scaling-Laws shows the amazing intelligence with the next-token prediction paradigm in neural language modeling, which pointing out a free-lunch way to enhance the model performance by scaling the model parameters. In RecSys, the retrieval stage is also follows a 'next-token prediction' paradigm, to recall the hunderds of items from the global item set, thus the generative recommendation usually refers specifically to the retrieval stage (without Tree-based methods). This raises a philosophical question: without a ground-truth next item, does the generative recommendation also holds a potential scaling law? In retrospect, the generative recommendation has two different technique paradigms: (1) ANN-based framework, utilizing the compressed user embedding to retrieve nearest other items in embedding space, e.g, Kuaiformer. (2) Auto-regressive-based framework, employing the beam search to decode the item from whole space, e.g, OneRec. In this paper, we devise a unified encoder-decoder framework to validate their scaling-laws at same time. Our empirical finding is that both of their losses strictly adhere to power-law Scaling Laws ($R^2$>0.9) within our unified architecture. - oai:arXiv.org:2512.07424v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new + Using Copilot Agent Mode to Automate Library Migration: A Quantitative Assessment + https://arxiv.org/abs/2510.26699 + arXiv:2510.26699v2 Announce Type: replace +Abstract: Keeping software systems up to date is essential to avoid technical debt, security vulnerabilities, and the rigidity typical of legacy systems. However, updating libraries and frameworks remains a time consuming and error-prone process. Recent advances in Large Language Models (LLMs) and agentic coding systems offer new opportunities for automating such maintenance tasks. In this paper, we evaluate the update of a well-known Python library, SQLAlchemy, across a dataset of ten client applications. For this task, we use the Github's Copilot Agent Mode, an autonomous AI systema capable of planning and executing multi-step migration workflows. To assess the effectiveness of the automated migration, we also introduce Migration Coverage, a metric that quantifies the proportion of API usage points correctly migrated. The results of our study show that the LLM agent was capable of migrating functionalities and API usages between SQLAlchemy versions (migration coverage: 100%, median), but failed to maintain the application functionality, leading to a low test-pass rate (39.75%, median). + oai:arXiv.org:2510.26699v2 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiangxia Cao, Shuo Yang, Zijun Wang, Qinghai Tan + Aylton Almeida, Laerte Xavier, Marco Tulio Valente - When normalization hallucinates: unseen risks in AI-powered whole slide image processing - https://arxiv.org/abs/2512.07426 - arXiv:2512.07426v1 Announce Type: new -Abstract: Whole slide image (WSI) normalization remains a vital preprocessing step in computational pathology. Increasingly driven by deep learning, these models learn to approximate data distributions from training examples. This often results in outputs that gravitate toward the average, potentially masking diagnostically important features. More critically, they can introduce hallucinated content, artifacts that appear realistic but are not present in the original tissue, posing a serious threat to downstream analysis. These hallucinations are nearly impossible to detect visually, and current evaluation practices often overlook them. In this work, we demonstrate that the risk of hallucinations is real and underappreciated. While many methods perform adequately on public datasets, we observe a concerning frequency of hallucinations when these same models are retrained and evaluated on real-world clinical data. To address this, we propose a novel image comparison measure designed to automatically detect hallucinations in normalized outputs. Using this measure, we systematically evaluate several well-cited normalization methods retrained on real-world data, revealing significant inconsistencies and failures that are not captured by conventional metrics. Our findings underscore the need for more robust, interpretable normalization techniques and stricter validation protocols in clinical deployment. - oai:arXiv.org:2512.07426v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Online Energy Storage Arbitrage under Imperfect Predictions: A Conformal Risk-Aware Approach + https://arxiv.org/abs/2511.01032 + arXiv:2511.01032v2 Announce Type: replace +Abstract: This work proposes a conformal approach for energy storage arbitrage to control the downside risk arising from imperfect price forecasts. Energy storage arbitrage relies solely on predictions of future market prices, while inaccurate price predictions may lead to significant profit losses. Based on conformal decision theory, we describe a controller that dynamically adjusts decision conservativeness through prediction sets without distributional assumptions. To enable online calibration when online profit loss feedback is unobservable, we establish that a temporal difference error serves as a measurable proxy. Building on this insight, we develop two online calibration strategies: prediction error-based adaptation targeting forecast accuracy, and value error-based calibration focusing on decision quality. Analysis of the conformal controller proves bounded long-term risk with convergence guarantees in temporal difference error, which further effectively manages risk exposure in potential profit losses. Case studies demonstrate superior performance in balancing risk and opportunity compared to benchmarks under varying forecast conditions. + oai:arXiv.org:2511.01032v2 + eess.SY + cs.SY + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by-nc-nd/4.0/ - Karel Moens, Matthew B. Blaschko, Tinne Tuytelaars, Bart Diricx, Jonas De Vylder, Mustafa Yousif + Yiqian Wu, Ming Yi, Bolun Xu, James Anderson - MIDG: Mixture of Invariant Experts with knowledge injection for Domain Generalization in Multimodal Sentiment Analysis - https://arxiv.org/abs/2512.07430 - arXiv:2512.07430v1 Announce Type: new -Abstract: Existing methods in domain generalization for Multimodal Sentiment Analysis (MSA) often overlook inter-modal synergies during invariant features extraction, which prevents the accurate capture of the rich semantic information within multimodal data. Additionally, while knowledge injection techniques have been explored in MSA, they often suffer from fragmented cross-modal knowledge, overlooking specific representations that exist beyond the confines of unimodal. To address these limitations, we propose a novel MSA framework designed for domain generalization. Firstly, the framework incorporates a Mixture of Invariant Experts model to extract domain-invariant features, thereby enhancing the model's capacity to learn synergistic relationships between modalities. Secondly, we design a Cross-Modal Adapter to augment the semantic richness of multimodal representations through cross-modal knowledge injection. Extensive domain experiments conducted on three datasets demonstrate that the proposed MIDG achieves superior performance. - oai:arXiv.org:2512.07430v1 + Test-driven Reinforcement Learning in Continuous Control + https://arxiv.org/abs/2511.07904 + arXiv:2511.07904v3 Announce Type: replace +Abstract: Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose of defining the optimal goal and guiding learning, it is challenging to design the reward function manually, which often results in a suboptimal task representation. To tackle the reward design challenge in RL, inspired by the satisficing theory, we propose a Test-driven Reinforcement Learning (TdRL) framework. In the TdRL framework, multiple test functions are used to represent the task objective rather than a single reward function. Test functions can be categorized as pass-fail tests and indicative tests, each dedicated to defining the optimal objective and guiding the learning process, respectively, thereby making defining tasks easier. Building upon such a task definition, we first prove that if a trajectory return function assigns higher returns to trajectories closer to the optimal trajectory set, maximum entropy policy optimization based on this return function will yield a policy that is closer to the optimal policy set. Then, we introduce a lexicographic heuristic approach to compare the relative distance relationship between trajectories and the optimal trajectory set for learning the trajectory return function. Furthermore, we develop an algorithm implementation of TdRL. Experimental results on the DeepMind Control Suite benchmark demonstrate that TdRL matches or outperforms handcrafted reward methods in policy training, with greater design simplicity and inherent support for multi-objective optimization. We argue that TdRL offers a novel perspective for representing task objectives, which could be helpful in addressing the reward design challenges in RL applications. + oai:arXiv.org:2511.07904v3 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yangle Li, Danli Luo, Haifeng Hu + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-sa/4.0/ + Zhao Yu, Xiuping Wu, Liangjun Ke - Mitigating Bias in Graph Hyperdimensional Computing - https://arxiv.org/abs/2512.07433 - arXiv:2512.07433v1 Announce Type: new -Abstract: Graph hyperdimensional computing (HDC) has emerged as a promising paradigm for cognitive tasks, emulating brain-like computation with high-dimensional vectors known as hypervectors. While HDC offers robustness and efficiency on graph-structured data, its fairness implications remain largely unexplored. In this paper, we study fairness in graph HDC, where biases in data representation and decision rules can lead to unequal treatment of different groups. We show how hypervector encoding and similarity-based classification can propagate or even amplify such biases, and we propose a fairness-aware training framework, FairGHDC, to mitigate them. FairGHDC introduces a bias correction term, derived from a gap-based demographic-parity regularizer, and converts it into a scalar fairness factor that scales the update of the class hypervector for the ground-truth label. This enables debiasing directly in the hypervector space without modifying the graph encoder or requiring backpropagation. Experimental results on six benchmark datasets demonstrate that FairGHDC substantially reduces demographic-parity and equal-opportunity gaps while maintaining accuracy comparable to standard GNNs and fairness-aware GNNs. At the same time, FairGHDC preserves the computational advantages of HDC, achieving up to about one order of magnitude ($\approx 10\times$) speedup in training time on GPU compared to GNN and fairness-aware GNN baselines. - oai:arXiv.org:2512.07433v1 + Decomposition of Small Transformer Models + https://arxiv.org/abs/2511.08854 + arXiv:2511.08854v2 Announce Type: replace +Abstract: Recent work in mechanistic interpretability has shown that decomposing models in parameter space may yield clean handles for analysis and intervention. Previous methods have demonstrated successful applications on a wide range of toy models, but the gap to "real models" has not yet been bridged. In this work, we extend Stochastic Parameter Decomposition (SPD) to Transformer models, proposing an updated causal importance function suited for sequential data and a new loss function. We demonstrate that SPD can successfully decompose a toy induction-head model and recover the expected 2-step circuit. We also show that applying SPD to GPT-2-small can successfully locate subcomponents corresponding to interpretable concepts like "golf" and "basketball". These results take the first step in the direction of extending SPD to modern models, and show that we can use the method to surface interpretable parameter-space mechanisms. + oai:arXiv.org:2511.08854v2 cs.LG - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yezi Liu, William Youngwoo Chung, Yang Ni, Hanning Chen, Mohsen Imani + Casper L. Christensen, Logan Riggs - Systematic Evaluation of Black-Box Checking for Fast Bug Detection - https://arxiv.org/abs/2512.07434 - arXiv:2512.07434v1 Announce Type: new -Abstract: Combinations of active automata learning, model-based testing and model checking have been successfully used in numerous applications, e.g., for spotting bugs in implementations of major network protocols and to support refactoring of embedded controllers. However, in the large majority of these applications, model checking is only used at the very end, when no counterexample can be found anymore for the latest hypothesis model. This contrasts with the original proposal of black-box checking (BBC) by Peled, Vardi & Yannakakis, which applies model checking for all hypotheses, also the intermediate ones. In this article, we present the first systematic evaluation of the ability of BBC to find bugs quickly, based on 77 benchmarks models from real protocol implementations and controllers for which specifications of safety properties are available. Our main finding are: (a) In cases where the full model can be learned, BBC detects violations of the specifications with just 3.4% of the queries needed by an approach in which model checking is only used for the full model. (b) Even when the full model cannot be learned, BBC is still able to detect many violations of the specification. In particular, BBC manages to detect 94% of the safety properties violations in the challenging RERS 2019 industrial LTL benchmarks. (c) Our results also confirm that BBC is way more effective than existing MBT algorithms in finding deep bugs in implementations. - oai:arXiv.org:2512.07434v1 - cs.SE - cs.FL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Bram Pellen, Mar\'ia Bel\'en Rodr\'iguez, Frits Vaandrager, Petra van den Bos + Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis for Large Reasoning Models + https://arxiv.org/abs/2511.09907 + arXiv:2511.09907v2 Announce Type: replace +Abstract: Data synthesis for training large reasoning models offers a scalable alternative to limited, human-curated datasets, enabling the creation of high-quality data. However, existing approaches face several challenges: (i) indiscriminate generation that ignores the solver's ability and yields low-value problems, or reliance on complex data pipelines to balance problem difficulty; and (ii) a lack of reasoning in problem generation, leading to shallow problem variants. In this paper, we develop a problem generator that reasons explicitly to plan problem directions before synthesis and adapts difficulty to the solver's ability. Specifically, we construct related problem pairs and augment them with intermediate problem-design CoT produced by a reasoning model. These data bootstrap problem-design strategies from the generator. Then, we treat the solver's feedback on synthetic problems as a reward signal, enabling the generator to calibrate difficulty and produce complementary problems near the edge of the solver's competence. Extensive experiments on 10 mathematical and general reasoning benchmarks show that our method achieves an average improvement of 2.5% and generalizes to both language and vision-language models. Moreover, a solver trained on the synthesized data provides improved rewards for continued generator training, enabling co-evolution and yielding a further 0.7% performance gain. Our code will be made publicly available here. + oai:arXiv.org:2511.09907v2 + cs.AI + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Yongxian Wei, Yilin Zhao, Li Shen, Xinrui Chen, Runxi Cheng, Sinan Du, Hao Yu, Gang Liu, Jiahong Yan, Chun Yuan, Dian Li - LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services - https://arxiv.org/abs/2512.07436 - arXiv:2512.07436v1 Announce Type: new -Abstract: Recent advances in large reasoning models (LRMs) have enabled agentic search systems to perform complex multi-step reasoning across multiple sources. However, most studies focus on general information retrieval and rarely explores vertical domains with unique challenges. In this work, we focus on local life services and introduce LocalSearchBench, which encompass diverse and complex business scenarios. Real-world queries in this domain are often ambiguous and require multi-hop reasoning across merchants and products, remaining challenging and not fully addressed. As the first comprehensive benchmark for agentic search in local life services, LocalSearchBench includes over 150,000 high-quality entries from various cities and business types. We construct 300 multi-hop QA tasks based on real user queries, challenging agents to understand questions and retrieve information in multiple steps. We also developed LocalPlayground, a unified environment integrating multiple tools for agent interaction. Experiments show that even state-of-the-art LRMs struggle on LocalSearchBench: the best model (DeepSeek-V3.1) achieves only 34.34% correctness, and most models have issues with completeness (average 77.33%) and faithfulness (average 61.99%). This highlights the need for specialized benchmarks and domain-specific agent training in local life services. Code, Benchmark, and Leaderboard are available at localsearchbench.github.io. - oai:arXiv.org:2512.07436v1 + Do Language Models Associate Sound with Meaning? A Multimodal Study of Sound Symbolism + https://arxiv.org/abs/2511.10045 + arXiv:2511.10045v3 Announce Type: replace +Abstract: Sound symbolism is a linguistic concept that refers to non-arbitrary associations between phonetic forms and their meanings. We suggest that this can be a compelling probe into how Multimodal Large Language Models (MLLMs) interpret auditory information in human languages. We investigate MLLMs' performance on phonetic iconicity across textual (orthographic and IPA) and auditory forms of inputs with up to 25 semantic dimensions (e.g., sharp vs. round), observing models' layer-wise information processing by measuring phoneme-level attention fraction scores. To this end, we present LEX-ICON, an extensive mimetic word dataset consisting of 8,052 words from four natural languages (English, French, Japanese, and Korean) and 2,930 systematically constructed pseudo-words, annotated with semantic features applied across both text and audio modalities. Our key findings demonstrate (1) MLLMs' phonetic intuitions that align with existing linguistic research across multiple semantic dimensions and (2) phonosemantic attention patterns that highlight models' focus on iconic phonemes. These results bridge domains of artificial intelligence and cognitive linguistics, providing the first large-scale, quantitative analyses of phonetic iconicity in terms of MLLMs' interpretability. + oai:arXiv.org:2511.10045v3 + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jinhong Jeong, Sunghyun Lee, Jaeyoung Lee, Seonah Han, Youngjae Yu + + + ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs + https://arxiv.org/abs/2511.10240 + arXiv:2511.10240v2 Announce Type: replace +Abstract: Large Language Models (LLMs) demonstrate strong reasoning capabilities but struggle with hallucinations and limited transparency. Recently, KG-enhanced LLMs that integrate knowledge graphs (KGs) have been shown to improve reasoning performance, particularly for complex, knowledge-intensive tasks. However, these methods still face significant challenges, including inaccurate retrieval and reasoning failures, often exacerbated by long input contexts that obscure relevant information or by context constructions that struggle to capture the richer logical directions required by different question types. Furthermore, many of these approaches rely on LLMs to directly retrieve evidence from KGs, and to self-assess the sufficiency of this evidence, which often results in premature or incorrect reasoning. To address the retrieval and reasoning failures, we propose ProgRAG, a multi-hop knowledge graph question answering (KGQA) framework that decomposes complex questions into sub-questions, and progressively extends partial reasoning paths by answering each sub-question. At each step, external retrievers gather candidate evidence, which is then refined through uncertainty-aware pruning by the LLM. Finally, the context for LLM reasoning is optimized by organizing and rearranging the partial reasoning paths obtained from the sub-question answers. Experiments on three well-known datasets demonstrate that ProgRAG outperforms existing baselines in multi-hop KGQA, offering improved reliability and reasoning quality. + oai:arXiv.org:2511.10240v2 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Hang He, Chuhuai Yue, Chengqi Dong, Mingxue Tian, Zhenfeng Liu, Jiajun Chai, Xiaohan Wang, Yufei Zhang, Qun Liao, Guojun Yin, Wei Lin, Chengcheng Wan, Haiying Sun, Ting Su + Minbae Park, Hyemin Yang, Jeonghyun Kim, Kunsoo Park, Hyunjoon Kim - KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models - https://arxiv.org/abs/2512.07437 - arXiv:2512.07437v1 Announce Type: new -Abstract: DreamerV3 is a state-of-the-art online model-based reinforcement learning (MBRL) algorithm known for remarkable sample efficiency. Concurrently, Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-Layer Perceptrons (MLPs), offering superior parameter efficiency and interpretability. To mitigate KANs' computational overhead, variants like FastKAN leverage Radial Basis Functions (RBFs) to accelerate inference. In this work, we investigate integrating KAN architectures into the DreamerV3 framework. We introduce KAN-Dreamer, replacing specific MLP and convolutional components of DreamerV3 with KAN and FastKAN layers. To ensure efficiency within the JAX-based World Model, we implement a tailored, fully vectorized version with simplified grid management. We structure our investigation into three subsystems: Visual Perception, Latent Prediction, and Behavior Learning. Empirical evaluations on the DeepMind Control Suite (walker_walk) analyze sample efficiency, training time, and asymptotic performance. Experimental results demonstrate that utilizing our adapted FastKAN as a drop-in replacement for the Reward and Continue predictors yields performance on par with the original MLP-based architecture, maintaining parity in both sample efficiency and training speed. This report serves as a preliminary study for future developments in KAN-based world models. - oai:arXiv.org:2512.07437v1 - cs.LG - cs.AI - cs.CV - cs.NE + Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning + https://arxiv.org/abs/2511.11218 + arXiv:2511.11218v2 Announce Type: replace +Abstract: Humanoid robots have demonstrated strong capabilities for interacting with static scenes across locomotion, manipulation, and more challenging loco-manipulation tasks. Yet the real world is dynamic, and quasi-static interactions are insufficient to cope with diverse environmental conditions. As a step toward more dynamic interaction scenarios, we present a reinforcement-learning-based training pipeline that produces a unified whole-body controller for humanoid badminton, enabling coordinated lower-body footwork and upper-body striking without motion priors or expert demonstrations. Training follows a three-stage curriculum: first footwork acquisition, then precision-guided racket swing generation, and finally task-focused refinement, yielding motions in which both legs and arms serve the hitting objective. For deployment, we incorporate an Extended Kalman Filter (EKF) to estimate and predict shuttlecock trajectories for target striking. We also introduce a prediction-free variant that dispenses with EKF and explicit trajectory prediction. To validate the framework, we conduct five sets of experiments in both simulation and the real world. In simulation, two robots sustain a rally of 21 consecutive hits. Moreover, the prediction-free variant achieves successful hits with comparable performance relative to the target-known policy. In real-world tests, both prediction and controller modules exhibit high accuracy, and on-court hitting achieves an outgoing shuttle speed up to 19.1 m/s with a mean return landing distance of 4 m. These experimental results show that our proposed training scheme can deliver highly dynamic while precise goal striking in badminton, and can be adapted to more dynamics-critical domains. + oai:arXiv.org:2511.11218v2 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chenwei Shi, Xueyu Luan + Chenhao Liu, Leyun Jiang, Yibo Wang, Kairan Yao, Jinchen Fu, Xiaoyu Ren - Scalable Formal Verification of Incremental Stability in Large-Scale Systems Using Graph Neural Networks - https://arxiv.org/abs/2512.07448 - arXiv:2512.07448v1 Announce Type: new -Abstract: This work proposes a novel distributed framework for verifying the incremental stability of large-scale systems with unknown dynamics and known interconnection structures using graph neural networks. Our proposed approach relies on the construction of local incremental Lyapunov functions for subsystems, which are then composed together to obtain a suitable Lyapunov function for the interconnected system. Graph neural networks are used to synthesize these functions in a data-driven fashion. The formal correctness guarantee is then obtained by leveraging Lipschitz bounds of the trained neural networks. Finally, the effectiveness of our approach is validated through two nonlinear case studies. - oai:arXiv.org:2512.07448v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Ahan Basu, Mahathi Anand, Pushpak Jagtap + SynBullying: A Multi LLM Synthetic Conversational Dataset for Cyberbullying Detection + https://arxiv.org/abs/2511.11599 + arXiv:2511.11599v2 Announce Type: replace +Abstract: We introduce SynBullying, a synthetic multi-LLM conversational dataset for studying and detecting cyberbullying (CB). SynBullying provides a scalable and ethically safe alternative to human data collection by leveraging large language models (LLMs) to simulate realistic bullying interactions. The dataset offers (i) conversational structure, capturing multi-turn exchanges rather than isolated posts; (ii) context-aware annotations, where harmfulness is assessed within the conversational flow considering context, intent, and discourse dynamics; and (iii) fine-grained labeling, covering various CB categories for detailed linguistic and behavioral analysis. We evaluate SynBullying across five dimensions, including conversational structure, lexical patterns, sentiment/toxicity, role dynamics, harm intensity, and CB-type distribution. We further examine its utility by testing its performance as standalone training data and as an augmentation source for CB classification. + oai:arXiv.org:2511.11599v2 + cs.AI + cs.CL + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Arefeh Kazemi, Hamza Qadeer, Joachim Wagner, Hossein Hosseini, Sri Balaaji Natarajan Kalaivendan, Brian Davis - AFarePart: Accuracy-aware Fault-resilient Partitioner for DNN Edge Accelerators - https://arxiv.org/abs/2512.07449 - arXiv:2512.07449v1 Announce Type: new -Abstract: Deep Neural Networks (DNNs) are increasingly deployed across distributed and resource-constrained platforms, such as System-on-Chip (SoC) accelerators and edge-cloud systems. DNNs are often partitioned and executed across heterogeneous processing units to optimize latency and energy. However, the reliability of these partitioned models under hardware faults and communication errors remains a critical yet underexplored topic, especially in safety-critical applications. In this paper, we propose an accuracy-aware, fault-resilient DNN partitioning framework targeting multi-objective optimization using NSGA-II, where accuracy degradation under fault conditions is introduced as a core metric alongside energy and latency. Our framework performs runtime fault injection during optimization and utilizes a feedback loop to prioritize fault-tolerant partitioning. We evaluate our approach on benchmark CNNs including AlexNet, SqueezeNet and ResNet18 on hardware accelerators, and demonstrate up to 27.7% improvement in fault tolerance with minimal increase in performance overhead. Our results highlight the importance of incorporating resilience into DNN partitioning, and thereby paving the way for robust AI inference in error-prone environments. - oai:arXiv.org:2512.07449v1 - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Mukta Debnath (University of Calcutta, India), Krishnendu Guha (University College Cork, Ireland), Debasri Saha (University of Calcutta, India), Amlan Chakrabarti (University of Calcutta, India), Susmita Sur-Kolay (Indian Statistical Institute, India) + No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding + https://arxiv.org/abs/2511.12083 + arXiv:2511.12083v2 Announce Type: replace +Abstract: High-quality information set abstraction remains a core challenge in solving large-scale imperfect-information extensive-form games (IIEFGs)--such as no-limit Texas Hold'em--where the finite nature of spatial resources hinders solving strategies for the full game. State-of-the-art AI methods rely on pre-trained discrete clustering for abstraction, yet their hard classification irreversibly discards critical information: specifically, the quantifiable subtle differences between information sets--vital for strategy solving--thus compromising the quality of such solving. Inspired by the word embedding paradigm in natural language processing, this paper proposes the Embedding CFR algorithm, a novel approach for solving strategies in IIEFGs within an embedding space. The algorithm pre-trains and embeds the features of individual information sets into an interconnected low-dimensional continuous space, where the resulting vectors more precisely capture both the distinctions and connections between information sets. Embedding CFR introduces a strategy-solving process driven by regret accumulation and strategy updates in this embedding space, with supporting theoretical analysis verifying its ability to reduce cumulative regret. Experiments on poker show that with the same spatial overhead, Embedding CFR achieves significantly faster exploitability convergence compared to cluster-based abstraction algorithms, confirming its effectiveness. Furthermore, to our knowledge, it is the first algorithm in poker AI that pre-trains information set abstractions via low-dimensional embedding for strategy solving. + oai:arXiv.org:2511.12083v2 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yanchang Fu, Shengda Liu, Pei Xu, Kaiqi Huang - Forget and Explain: Transparent Verification of GNN Unlearning - https://arxiv.org/abs/2512.07450 - arXiv:2512.07450v1 Announce Type: new -Abstract: Graph neural networks (GNNs) are increasingly used to model complex patterns in graph-structured data. However, enabling them to "forget" designated information remains challenging, especially under privacy regulations such as the GDPR. Existing unlearning methods largely optimize for efficiency and scalability, yet they offer little transparency, and the black-box nature of GNNs makes it difficult to verify whether forgetting has truly occurred. We propose an explainability-driven verifier for GNN unlearning that snapshots the model before and after deletion, using attribution shifts and localized structural changes (for example, graph edit distance) as transparent evidence. The verifier uses five explainability metrics: residual attribution, heatmap shift, explainability score deviation, graph edit distance, and a diagnostic graph rule shift. We evaluate two backbones (GCN, GAT) and four unlearning strategies (Retrain, GraphEditor, GNNDelete, IDEA) across five benchmarks (Cora, Citeseer, Pubmed, Coauthor-CS, Coauthor-Physics). Results show that Retrain and GNNDelete achieve near-complete forgetting, GraphEditor provides partial erasure, and IDEA leaves residual signals. These explanation deltas provide the primary, human-readable evidence of forgetting; we also report membership-inference ROC-AUC as a complementary, graph-wide privacy signal. - oai:arXiv.org:2512.07450v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Collusion-proof Auction Design using Side Information + https://arxiv.org/abs/2511.12456 + arXiv:2511.12456v2 Announce Type: replace +Abstract: We study the problem of auction design in the presence of bidder collusion. Specifically, we consider a multi-unit auction of identical items with single-minded bidders, where a subset of bidders may collude by coordinating bids and transferring payments and items among themselves. The classical Vickrey-Clarke-Groves(VCG) mechanism is highly vulnerable to collusion and fully collusion-proof mechanisms are limited to posted-price formats, which fail to guarantee even approximate efficiency. This paper aims to bridge this gap by designing auctions that achieve good welfare and revenue guarantees even when some bidders collude. We first characterize the strategic behavior of colluding bidders under VCG and prove that such bidders optimally bid shade: they never overbid or take additional items, but instead reduce the auction price. This characterization enables a Bulow-Klemperer type result: adding colluding bidders can only improve welfare and revenue relative to running VCG on the non-colluding group alone. We next consider a setting where black-box collusion detection algorithm is available to label bidders as being colluding or non-colluding, and we propose a VCG-Posted Price(V-PoP) mechanism that combines VCG applied to non-colluding bidders with a posted-price mechanism for colluding bidders. We show that V-PoP is ex-post dominant-strategy incentive compatible(DSIC) and derive probabilistic guarantees on expected welfare and revenue under both known and unknown valuation distributions. Numerical experiments across several distributions demonstrate that V-PoP consistently outperforms VCG restricted to non-colluding bidders and approaches the performance of the ideal VCG mechanism assuming universal truthfulness. Our results provide a principled framework for incorporating collusion detection into mechanism design, offering a step toward collusion-resistant auctions. + oai:arXiv.org:2511.12456v2 + cs.GT + econ.TH + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Imran Ahsan (Department of Smart Cities, Chung-Ang University), Hyunwook Yu (Department of Computer Science and Engineering, Chung-Ang University), Jinsung Kim (Department of Computer Science and Engineering, Chung-Ang University), Mucheol Kim (Department of Computer Science and Engineering, Chung-Ang University) + Sukanya Kudva, Anil Aswani - From Show Programmes to Data: Designing a Workflow to Make Performing Arts Ephemera Accessible Through Language Models - https://arxiv.org/abs/2512.07452 - arXiv:2512.07452v1 Announce Type: new -Abstract: Many heritage institutions hold extensive collections of theatre programmes, which remain largely underused due to their complex layouts and lack of structured metadata. In this paper, we present a workflow for transforming such documents into structured data using a combination of multimodal large language models (LLMs), an ontology-based reasoning model, and a custom extension of the Linked Art framework. We show how vision-language models can accurately parse and transcribe born-digital and digitised programmes, achieving over 98% of correct extraction. To overcome the challenges of semantic annotation, we train a reasoning model (POntAvignon) using reinforcement learning with both formal and semantic rewards. This approach enables automated RDF triple generation and supports alignment with existing knowledge graphs. Through a case study based on the Festival d'Avignon corpus, we demonstrate the potential for large-scale, ontology-driven analysis of performing arts data. Our results open new possibilities for interoperable, explainable, and sustainable computational theatre historiography. - oai:arXiv.org:2512.07452v1 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Clarisse Bardiot, Pierre-Carl Langlais, Bernard Jacquemin, Jacob Hart, Antonios Lagarias, Nicolas Foucault, Aur\'elie Lema\^itre-Legargeant, Jeanne Fras + Botany Meets Robotics in Alpine Scree Monitoring + https://arxiv.org/abs/2511.12526 + arXiv:2511.12526v2 Announce Type: replace +Abstract: According to the European Union's Habitat Directive, habitat monitoring plays a critical role in response to the escalating problems posed by biodiversity loss and environmental degradation. Scree habitats, hosting unique and often endangered species, face severe threats from climate change due to their high-altitude nature. Traditionally, their monitoring has required highly skilled scientists to conduct extensive fieldwork in remote, potentially hazardous locations, making the process resource-intensive and time-consuming. This paper presents a novel approach for scree habitat monitoring using a legged robot to assist botanists in data collection and species identification. Specifically, we deployed the ANYmal C robot in the Italian Alpine bio-region in two field campaigns spanning two years and leveraged deep learning to detect and classify key plant species of interest. Our results demonstrate that agile legged robots can navigate challenging terrains and increase the frequency and efficiency of scree monitoring. When paired with traditional phytosociological surveys performed by botanists, this robotics-assisted protocol not only streamlines field operations but also enhances data acquisition, storage, and usage. The outcomes of this research contribute to the evolving landscape of robotics in environmental science, paving the way for a more comprehensive and sustainable approach to habitat monitoring and preservation. + oai:arXiv.org:2511.12526v2 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.1109/TFR.2025.3632773 + IEEE Transactions on Field Robotics, vol. 2, pp. 920-936, 2025 + Davide De Benedittis, Giovanni Di Lorenzo, Franco Angelini, Barbara Valle, Marina Serena Borgatti, Paolo Remagnino, Marco Caccianiga, Manolo Garabini - Persian-Phi: Efficient Cross-Lingual Adaptation of Compact LLMs via Curriculum Learning - https://arxiv.org/abs/2512.07454 - arXiv:2512.07454v1 Announce Type: new -Abstract: The democratization of AI is currently hindered by the immense computational costs required to train Large Language Models (LLMs) for low-resource languages. This paper presents Persian-Phi, a 3.8B parameter model that challenges the assumption that robust multilingual capabilities require massive model sizes or multilingual baselines. We demonstrate how Microsoft Phi-3 Mini -- originally a monolingual English model -- can be effectively adapted to Persian through a novel, resource-efficient curriculum learning pipeline. Our approach employs a unique "warm-up" stage using bilingual narratives (Tiny Stories) to align embeddings prior to heavy training, followed by continual pretraining and instruction tuning via Parameter-Efficient Fine-Tuning (PEFT). Despite its compact size, Persian-Phi achieves competitive results on Open Persian LLM Leaderboard in HuggingFace. Our findings provide a validated, scalable framework for extending the reach of state-of-the-art LLMs to underrepresented languages with minimal hardware resources. The Persian-Phi model is publicly available at https://huggingface.co/amirakhlaghiqqq/PersianPhi. - oai:arXiv.org:2512.07454v1 - cs.CL + Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation + https://arxiv.org/abs/2511.12779 + arXiv:2511.12779v2 Announce Type: replace +Abstract: We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$ groups, where each group comprises related objectives that can be trained together. This problem arises in applications such as robotics, control, and preference optimization in language models, where learning a single policy for all $n$ objectives is suboptimal as $n$ grows. We introduce a two-stage procedure -- meta-training followed by fine-tuning -- to address this problem. We first learn a meta-policy for all objectives using multitask learning. Then, we adapt the meta-policy to multiple randomly sampled subsets of objectives. The adaptation step leverages a first-order approximation property of well-trained policy networks, which is empirically verified to be accurate within a 2% error margin across various RL environments. The resulting algorithm, PolicyGradEx, efficiently estimates an aggregate task-affinity score matrix given a policy evaluation algorithm. Based on the estimated affinity score matrix, we cluster the $n$ objectives into $k$ groups by maximizing the intra-cluster affinity scores. Experiments on three robotic control and the Meta-World benchmarks demonstrate that our approach outperforms state-of-the-art baselines by 16% on average, while delivering up to $26\times$ faster speedup relative to performing full training to obtain the clusters. Ablation studies validate each component of our approach. For instance, compared with random grouping and gradient-similarity-based grouping, our loss-based clustering yields an improvement of 19%. Finally, we analyze the generalization error of policy networks by measuring the Hessian trace of the loss surface, which gives non-vacuous measures relative to the observed generalization errors. + oai:arXiv.org:2511.12779v2 + cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Amir Mohammad Akhlaghi, Amirhossein Shabani, Mostafa Abdolmaleki, Saeed Reza Kheradpisheh + Zhenshuo Zhang, Minxuan Duan, Youran Ye, Hongyang R. Zhang - Human Geometry Distribution for 3D Animation Generation - https://arxiv.org/abs/2512.07459 - arXiv:2512.07459v1 Announce Type: new -Abstract: Generating realistic human geometry animations remains a challenging task, as it requires modeling natural clothing dynamics with fine-grained geometric details under limited data. To address these challenges, we propose two novel designs. First, we propose a compact distribution-based latent representation that enables efficient and high-quality geometry generation. We improve upon previous work by establishing a more uniform mapping between SMPL and avatar geometries. Second, we introduce a generative animation model that fully exploits the diversity of limited motion data. We focus on short-term transitions while maintaining long-term consistency through an identity-conditioned design. These two designs formulate our method as a two-stage framework: the first stage learns a latent space, while the second learns to generate animations within this latent space. We conducted experiments on both our latent space and animation model. We demonstrate that our latent space produces high-fidelity human geometry surpassing previous methods ($90\%$ lower Chamfer Dist.). The animation model synthesizes diverse animations with detailed and natural dynamics ($2.2 \times$ higher user study score), achieving the best results across all evaluation metrics. - oai:arXiv.org:2512.07459v1 - cs.GR - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Xiangjun Tang, Biao Zhang, Peter Wonka + Batch Acquisition Function Evaluations and Decouple Optimizer Updates for Faster Bayesian Optimization + https://arxiv.org/abs/2511.13625 + arXiv:2511.13625v3 Announce Type: replace +Abstract: Bayesian optimization (BO) efficiently finds high-performing parameters by maximizing an acquisition function, which models the promise of parameters. A major computational bottleneck arises in acquisition function optimization, where multi-start optimization (MSO) with quasi-Newton (QN) methods is required due to the non-convexity of the acquisition function. BoTorch, a widely used BO library, currently optimizes the summed acquisition function over multiple points, leading to the speedup of MSO owing to PyTorch batching. Nevertheless, this paper empirically demonstrates the suboptimality of this approach in terms of off-diagonal approximation errors in the inverse Hessian of a QN method, slowing down its convergence. To address this problem, we propose to decouple QN updates using a coroutine while batching the acquisition function calls. Our approach not only yields the theoretically identical convergence to the sequential MSO but also drastically reduces the wall-clock time compared to the previous approaches. Our approach is available in GPSampler in Optuna, effectively reducing its computational overhead. + oai:arXiv.org:2511.13625v3 + cs.LG + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Kaichi Irie, Shuhei Watanabe, Masaki Onishi - Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning - https://arxiv.org/abs/2512.07461 - arXiv:2512.07461v1 Announce Type: new -Abstract: We introduce Native Parallel Reasoner (NPR), a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transforms the model from sequential emulation to native parallel cognition through three key innovations: 1) a self-distilled progressive training paradigm that transitions from ``cold-start'' format discovery to strict topological constraints without external supervision; 2) a novel Parallel-Aware Policy Optimization (PAPO) algorithm that optimizes branching policies directly within the execution graph, allowing the model to learn adaptive decomposition via trial and error; and 3) a robust NPR Engine that refactors memory management and flow control of SGLang to enable stable, large-scale parallel RL training. Across eight reasoning benchmarks, NPR trained on Qwen3-4B achieves performance gains of up to 24.5% and inference speedups up to 4.6x. Unlike prior baselines that often fall back to autoregressive decoding, NPR demonstrates 100% genuine parallel execution, establishing a new standard for self-evolving, efficient, and scalable agentic reasoning. - oai:arXiv.org:2512.07461v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Tractable Probabilistic Models for Investment Planning + https://arxiv.org/abs/2511.13888 + arXiv:2511.13888v2 Announce Type: replace +Abstract: Investment planning in power utilities, such as generation and transmission expansion, requires decade-long forecasts under profound uncertainty. Forecasting of energy mix and energy use decades ahead is nontrivial. Classical approaches focus on generating a finite number of scenarios (modeled as a mixture of Diracs in statistical theory terms), which limits insight into scenario-specific volatility and hinders robust decision-making. We propose an alternative using tractable probabilistic models (TPMs), particularly sum-product networks (SPNs). These models enable exact, scalable inference of key quantities such as scenario likelihoods, marginals, and conditional probabilities, supporting robust scenario expansion and risk assessment. + This framework enables direct embedding of chance-constrained optimization into investment planning, enforcing safety or reliability with prescribed confidence levels. TPMs allow both scenario analysis and volatility quantification by compactly representing high-dimensional uncertainties. We demonstrate the effectiveness of the approach through a representative power system planning case study, illustrating its computational and reliability advantages over traditional scenario-based models. + oai:arXiv.org:2511.13888v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Tong Wu, Yang Liu, Jun Bai, Zixia Jia, Shuyi Zhang, Ziyong Lin, Yanting Wang, Song-Chun Zhu, Zilong Zheng + Nicolas M. Cuadrado A., Mohannad Takrouri, Ji\v{r}\'i N\v{e}me\v{c}ek, Martin Tak\'a\v{c}, Jakub Mare\v{c}ek - Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics - https://arxiv.org/abs/2512.07462 - arXiv:2512.07462v1 Announce Type: new -Abstract: As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behaviour has profound implications for safety, coordination, and the design of AI-driven social and economic infrastructures. Assessing such behaviour requires methods that capture not only what LLMs output, but the underlying intentions that guide their decisions. In this work, we extend the FAIRGAME framework to systematically evaluate LLM behaviour in repeated social dilemmas through two complementary advances: a payoff-scaled Prisoners Dilemma isolating sensitivity to incentive magnitude, and an integrated multi-agent Public Goods Game with dynamic payoffs and multi-agent histories. These environments reveal consistent behavioural signatures across models and languages, including incentive-sensitive cooperation, cross-linguistic divergence and end-game alignment toward defection. To interpret these patterns, we train traditional supervised classification models on canonical repeated-game strategies and apply them to FAIRGAME trajectories, showing that LLMs exhibit systematic, model- and language-dependent behavioural intentions, with linguistic framing at times exerting effects as strong as architectural differences. Together, these findings provide a unified methodological foundation for auditing LLMs as strategic agents and reveal systematic cooperation biases with direct implications for AI governance, collective decision-making, and the design of safe multi-agent systems. - oai:arXiv.org:2512.07462v1 - cs.MA + AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models + https://arxiv.org/abs/2511.14295 + arXiv:2511.14295v2 Announce Type: replace +Abstract: We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language understanding. Evaluating 35 Arabic and bilingual LLMs reveals that current models demonstrate strong surface level proficiency but struggle with deeper grammatical and syntactic reasoning. AraLingBench highlights a persistent gap between high scores on knowledge-based benchmarks and true linguistic mastery, showing that many models succeed through memorization or pattern recognition rather than authentic comprehension. By isolating and measuring fundamental linguistic skills, AraLingBench provides a diagnostic framework for developing Arabic LLMs. The full evaluation code is publicly available on GitHub. + oai:arXiv.org:2511.14295v2 + cs.CL cs.AI - cs.GT cs.LG - math.DS - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Trung-Kiet Huynh, Duy-Minh Dao-Sy, Thanh-Bang Cao, Phong-Hao Le, Hong-Dan Nguyen, Phu-Quy Nguyen-Lam, Minh-Luan Nguyen-Vo, Hong-Phat Pham, Phu-Hoa Pham, Thien-Kim Than, Chi-Nguyen Tran, Huy Tran, Gia-Thoai Tran-Le, Alessio Buscemi, Le Hong Trang, The Anh Han + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Sina Mukalled, Nadine Rizk, Fatima Karnib, Issam Lakkis, Ammar Mohanna, Bernard Ghanem - Parallel Algorithms for Combined Regularized Support Vector Machines: Application in Music Genre Classification - https://arxiv.org/abs/2512.07463 - arXiv:2512.07463v1 Announce Type: new -Abstract: In the era of rapid development of artificial intelligence, its applications span across diverse fields, relying heavily on effective data processing and model optimization. Combined Regularized Support Vector Machines (CR-SVMs) can effectively handle the structural information among data features, but there is a lack of efficient algorithms in distributed-stored big data. To address this issue, we propose a unified optimization framework based on consensus structure. This framework is not only applicable to various loss functions and combined regularization terms but can also be effectively extended to non-convex regularization terms, showing strong scalability. Based on this framework, we develop a distributed parallel alternating direction method of multipliers (ADMM) algorithm to efficiently compute CR-SVMs when data is stored in a distributed manner. To ensure the convergence of the algorithm, we also introduce the Gaussian back-substitution method. Meanwhile, for the integrity of the paper, we introduce a new model, the sparse group lasso support vector machine (SGL-SVM), and apply it to music information retrieval. Theoretical analysis confirms that the computational complexity of the proposed algorithm is not affected by different regularization terms and loss functions, highlighting the universality of the parallel algorithm. Experiments on synthetic and free music archiv datasets demonstrate the reliability, stability, and efficiency of the algorithm. - oai:arXiv.org:2512.07463v1 - cs.LG - stat.AP - stat.CO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Robust H-infinity control and worst-case search in constrained parametric space + https://arxiv.org/abs/2511.15480 + arXiv:2511.15480v3 Announce Type: replace +Abstract: Standard H-infinity/H2 robust control and analysis tools operate on uncertain parameters assumed to vary independently within prescribed bounds. This paper extends their capabilities in the presence of constraints coupling these parameters and restricting the parametric space. Focusing on the worst-case search, we demonstrate - based on the theory of upper-C1 functions - the validity of using standard, readily available smooth optimization algorithms to address this nonsmooth constrained optimization problem. In particular, we prove that the sequential quadratic programming algorithm converges to Karush-Kuhn-Tucker points, and that such conditions are satisfied by any subgradient at a local minimum. This worst-case search then enables robust controller synthesis: as in the state-of-art algorithm for standard robust control, identified worst-case configurations are iteratively added to an active set on which a non-smooth multi-models optimization of the controller is performed. The methodology is illustrated on a satellite benchmark with flexible appendages, of order 50 with 43 uncertain parameters. From a practical point of view, we combine the local exploitation proposed above with a global exploration using either Monte-Carlo sampling or particle swarm optimization. We show that the proposed constrained optimization effectively complements Monte-Carlo sampling by enabling fast detection of rare worst-case configurations, and that the robust controller optimization converges with less than 10 active configurations. + oai:arXiv.org:2511.15480v3 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Rongmei Liang, Zizheng Liu, Xiaofei Wu, Jingwen Tu + Ervan Kassarian, Francesco Sanfedino, Daniel Alazard, Andrea Marrazza - Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction - https://arxiv.org/abs/2512.07464 - arXiv:2512.07464v1 Announce Type: new -Abstract: For full-size humanoid robots, even with recent advances in reinforcement learning-based control, achieving reliable locomotion on complex terrains, such as long staircases, remains challenging. In such settings, limited perception, ambiguous terrain cues, and insufficient adaptation of gait timing can cause even a single misplaced or mistimed step to result in rapid loss of balance. We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy. A downward-facing depth camera mounted under the base observes the support region around the feet, and a compact U-Net reconstructs a dense egocentric height map from each frame in real time, operating at the same frequency as the control loop. The perceptual height map, together with proprioceptive observations, is processed by a unified policy that produces joint commands and a global stepping-phase signal, allowing gait timing and whole-body posture to be adapted jointly to the commanded motion and local terrain geometry. We further adopt a single-stage successive teacher-student training scheme for efficient policy learning and knowledge transfer. Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings, including forward and backward stair ascent and descent, as well as crossing a 46 cm gap. Project Page:https://ga-phl.github.io/ - oai:arXiv.org:2512.07464v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new + What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity + https://arxiv.org/abs/2511.15593 + arXiv:2511.15593v2 Announce Type: replace +Abstract: AI research agents offer the promise to accelerate scientific progress by automating the design, implementation, and training of machine learning models. However, the field is still in its infancy, and the key factors driving the success or failure of agent trajectories are not fully understood. We examine the role that ideation diversity plays in agent performance. First, we analyse agent trajectories on MLE-bench, a well-known benchmark to evaluate AI research agents, across different models and agent scaffolds. Our analysis reveals that different models and agent scaffolds yield varying degrees of ideation diversity, and that higher-performing agents tend to have increased ideation diversity. Further, we run a controlled experiment where we modify the degree of ideation diversity, demonstrating that higher ideation diversity results in stronger performance. Finally, we strengthen our results by examining additional evaluation metrics beyond the standard medal-based scoring of MLE-bench, showing that our findings still hold across other agent performance metrics. + oai:arXiv.org:2511.15593v2 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Alexis Audran-Reiss, Jordi Armengol-Estap\'e, Karen Hambardzumyan, Amar Budhiraja, Martin Josifoski, Edan Toledo, Rishi Hazra, Despoina Magka, Michael Shvartsman, Parth Pathak, Justine T Kao, Lucia Cipolina-Kun, Bhavul Gauri, Jean-Christophe Gagnon-Audet, Emanuel Tewolde, Jenny Zhang, Taco Cohen, Yossi Adi, Tatiana Shavrina, Yoram Bachrach + + + A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated Code + https://arxiv.org/abs/2511.15817 + arXiv:2511.15817v3 Announce Type: replace +Abstract: Recent advances in large language models (LLMs) have accelerated their adoption in software engineering contexts. However, concerns persist about the structural quality of the code they produce. In particular, LLMs often replicate poor coding practices, introducing code smells (i.e., patterns that hinder readability, maintainability, or design integrity). Although prior research has examined the detection or repair of smells, we still lack a clear understanding of how and when these issues emerge in generated code. + This paper addresses this gap by systematically measuring, explaining and mitigating smell propensity in LLM-generated code. We build on the Propensity Smelly Score (PSC), a probabilistic metric that estimates the likelihood of generating particular smell types, and establish its robustness as a signal of structural quality. Using PSC as an instrument for causal analysis, we identify how generation strategy, model size, model architecture and prompt formulation shape the structural properties of generated code. Our findings show that prompt design and architectural choices play a decisive role in smell propensity and motivate practical mitigation strategies that reduce its occurrence. A user study further demonstrates that PSC helps developers interpret model behavior and assess code quality, providing evidence that smell propensity signals can support human judgement. Taken together, our work lays the groundwork for integrating quality-aware assessments into the evaluation and deployment of LLMs for code. + oai:arXiv.org:2511.15817v3 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + 10.1145/3744916.3773164 + Alejandro Velasco, Daniel Rodriguez-Cardenas, Dipin Khati, David N. Palacio, Luftar Rahman Alif, Denys Poshyvanyk + + + TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning + https://arxiv.org/abs/2511.16147 + arXiv:2511.16147v2 Announce Type: replace +Abstract: Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter update. In this paper, we challenge this convention and unveil a pervasive token-level redundancy in the fine-tuning of large models. We propose TS-PEFT, a theoretically grounded framework utilizing proximal optimization to dynamically identify and skip redundant token updates during training. Our extensive experiments across Natural Language Understanding, Commonsense Reasoning, and Visual Instruction Tuning demonstrate that indiscriminately updating all tokens is not only computationally superfluous but often introduces optimization noise. Strikingly, by discarding 40%-60% of token updates, TS-PEFT consistently matches or surpasses the performance of dense baselines (e.g., LoRA, DoRA). Furthermore, we provide an in-depth analysis revealing that the learned token-level sparsity serves as a superior indicator of module importance compared to traditional weight norms, offering a novel data-driven perspective on the intrinsic adaptation mechanism of large models. + oai:arXiv.org:2511.16147v2 + cs.CL + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Haolin Song, Hongbo Zhu, Tao Yu, Yan Liu, Mingqi Yuan, Wengang Zhou, Hua Chen, Houqiang Li + Dabiao Ma, Ziming Dai, Zhimin Xin, Shu Wang, Ye Wang, Haojun Fei - Unified Video Editing with Temporal Reasoner - https://arxiv.org/abs/2512.07469 - arXiv:2512.07469v1 Announce Type: new -Abstract: Existing video editing methods face a critical trade-off: expert models offer precision but rely on task-specific priors like masks, hindering unification; conversely, unified temporal in-context learning models are mask-free but lack explicit spatial cues, leading to weak instruction-to-region mapping and imprecise localization. To resolve this conflict, we propose VideoCoF, a novel Chain-of-Frames approach inspired by Chain-of-Thought reasoning. VideoCoF enforces a ``see, reason, then edit" procedure by compelling the video diffusion model to first predict reasoning tokens (edit-region latents) before generating the target video tokens. This explicit reasoning step removes the need for user-provided masks while achieving precise instruction-to-region alignment and fine-grained video editing. Furthermore, we introduce a RoPE alignment strategy that leverages these reasoning tokens to ensure motion alignment and enable length extrapolation beyond the training duration. We demonstrate that with a minimal data cost of only 50k video pairs, VideoCoF achieves state-of-the-art performance on VideoCoF-Bench, validating the efficiency and effectiveness of our approach. Our code, weight, data are available at https://github.com/knightyxp/VideoCoF. - oai:arXiv.org:2512.07469v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025 + https://arxiv.org/abs/2511.16205 + arXiv:2511.16205v2 Announce Type: replace +Abstract: Olympiad-level benchmarks in mathematics and physics are crucial testbeds for advanced AI reasoning, but chemistry, with its unique multimodal symbolic language, has remained an open challenge. We introduce ChemO, a new benchmark built from the International Chemistry Olympiad (IChO) 2025. ChemO features two key innovations for automated assessment: Assessment-Equivalent Reformulation (AER), which converts problems requiring visual outputs (e.g., drawing molecules) into computationally tractable formats, and Structured Visual Enhancement (SVE), a diagnostic mechanism to disentangle a model's visual perception capabilities from its core chemical reasoning. To tackle this benchmark, we propose ChemLabs, a hierarchical multi-agent framework that mimics human expert collaboration through specialized agents for problem decomposition, perception, reasoning, and auditing. Experiments on state-of-the-art multimodal models demonstrate that combining SVE with our multi-agent system yields dramatic performance gains. Our top configuration achieves a score of 93.6 out of 100, surpassing an estimated human gold medal threshold and establishing a new state-of-the-art in automated chemical problem-solving. ChemO Dataset: https://huggingface.co/datasets/IDEA-AI4SCI/ChemO + oai:arXiv.org:2511.16205v2 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Xiangpeng Yang, Ji Xie, Yiyuan Yang, Yan Huang, Min Xu, Qiang Wu + Qiang Xu, Shengyuan Bai, Leqing Chen, Zijing Liu, Yu Li - Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation - https://arxiv.org/abs/2512.07472 - arXiv:2512.07472v1 Announce Type: new -Abstract: Vision-Language-Action (VLA) models have shown great performance in robotic manipulation by mapping visual observations and language instructions directly to actions. However, they remain brittle under distribution shifts: when test scenarios change, VLAs often reproduce memorized trajectories instead of adapting to the updated scene, which is a failure mode we refer to as the "Memory Trap". This limitation stems from the end-to-end design, which lacks explicit 3D spatial reasoning and prevents reliable identification of actionable regions in unfamiliar environments. To compensate for this missing spatial understanding, 3D Spatial Affordance Fields (SAFs) can provide a geometric representation that highlights where interactions are physically feasible, offering explicit cues about regions the robot should approach or avoid. We therefore introduce Affordance Field Intervention (AFI), a lightweight hybrid framework that uses SAFs as an on-demand plug-in to guide VLA behavior. Our system detects memory traps through proprioception, repositions the robot to recent high-affordance regions, and proposes affordance-driven waypoints that anchor VLA-generated actions. A SAF-based scorer then selects trajectories with the highest cumulative affordance. Extensive experiments demonstrate that our method achieves an average improvement of 23.5% across different VLA backbones ($\pi_{0}$ and $\pi_{0.5}$) under out-of-distribution scenarios on real-world robotic platforms, and 20.2% on the LIBERO-Pro benchmark, validating its effectiveness in enhancing VLA robustness to distribution shifts. - oai:arXiv.org:2512.07472v1 - cs.RO + Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery + https://arxiv.org/abs/2511.16887 + arXiv:2511.16887v2 Announce Type: replace +Abstract: Glass surfaces are ubiquitous in daily life, typically appearing colorless, transparent, and lacking distinctive features. These characteristics make glass surface detection a challenging computer vision task. Existing glass surface detection methods always rely on boundary cues (e.g., window and door frames) or reflection cues to locate glass surfaces, but they fail to fully exploit the intrinsic properties of the glass itself for accurate localization. We observed that in most real-world scenes, the illumination intensity in front of the glass surface differs from that behind it, which results in variations in the reflections visible on the glass surface. Specifically, when standing on the brighter side of the glass and applying a flash towards the darker side, existing reflections on the glass surface tend to disappear. Conversely, while standing on the darker side and applying a flash towards the brighter side, distinct reflections will appear on the glass surface. Based on this phenomenon, we propose NFGlassNet, a novel method for glass surface detection that leverages the reflection dynamics present in flash/no-flash imagery. Specifically, we propose a Reflection Contrast Mining Module (RCMM) for extracting reflections, and a Reflection Guided Attention Module (RGAM) for fusing features from reflection and glass surface for accurate glass surface detection. For learning our network, we also construct a dataset consisting of 3.3K no-flash and flash image pairs captured from various scenes with corresponding ground truth annotations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code, model, and dataset will be available upon acceptance of the manuscript. + oai:arXiv.org:2511.16887v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Tao Yan, Hao Huang, Yiwei Lu, Zeyu Wang, Ke Xu, Yinghui Wang, Xiaojun Chang, Rynson W. H. Lau + + + Mixed Reality Scenic Live Streaming for Cultural Heritage: Visual Interactions in a Historic Landscape + https://arxiv.org/abs/2511.17246 + arXiv:2511.17246v2 Announce Type: replace +Abstract: Scenic Live Streams (SLS), capturing real-world scenic sites from fixed cameras without streamers, have gained increasing popularity recently. They afford unique real-time lenses into remote sites for viewers' synchronous and collective engagement. Foregrounding its lack of dynamism and interactivity, we aim to maximize the potential of SLS by making it interactive. Namely MRSLS, we overlaid plain SLS with interactive Mixed Reality content that matches the site's geographical structures and local cultural backgrounds. We further highlight the substantial benefit of MRSLS to cultural heritage site interactions, and we demonstrate this design proposal with an MRSLS prototype at a UNESCO-listed heritage site in China. The design process includes an interview (N=6) to pinpoint local scenery and culture, as well as two iterative design studies (N=15, 14). A mixed-methods, between-subjects study (N=43, 37) shows that MRSLS affords immersive scenery appreciation, effective cultural imprints, and vivid shared experience. With its balance between cultural, participatory, and authentic attributes, we appeal for more HCI attention to (MR)SLS as an under-explored design space. + oai:arXiv.org:2511.17246v2 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-sa/4.0/ + Zeyu Huang, Zuyu Xu, Yuanhao Zhang, Chengzhong Liu, Yanwei Zhao, Chuhan Shi, Jason Chen Zhao, Xiaojuan Ma + + + GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning + https://arxiv.org/abs/2511.17582 + arXiv:2511.17582v2 Announce Type: replace +Abstract: Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, DoRA, and HiRA, enable lightweight adaptation of large pre-trained models via low-rank updates. However, existing PEFT approaches apply static, input-agnostic updates to all tokens, disregarding the varying importance and difficulty of different inputs. This uniform treatment can lead to overfitting on trivial content or under-adaptation on more informative regions, especially in autoregressive settings with distinct prefill and decoding dynamics. In this paper, we propose GateRA, a unified framework that introduces token-aware modulation to dynamically adjust the strength of PEFT updates. By incorporating adaptive gating into standard PEFT branches, GateRA enables selective, token-level adaptation, preserving pre-trained knowledge for well-modeled inputs while focusing capacity on challenging cases. Empirical visualizations reveal phase-sensitive behaviors, where GateRA automatically suppresses updates for redundant prefill tokens while emphasizing adaptation during decoding. To promote confident and efficient modulation, we further introduce an entropy-based regularization that encourages near-binary gating decisions. This regularization prevents diffuse update patterns and leads to interpretable, sparse adaptation without hard thresholding. Finally, we present a theoretical analysis showing that GateRA induces a soft gradient-masking effect over the PEFT path, enabling continuous and differentiable control over adaptation. Experiments on multiple commonsense reasoning benchmarks demonstrate that GateRA consistently outperforms or matches prior PEFT methods. + oai:arXiv.org:2511.17582v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Siyu Xu, Zijian Wang, Yunke Wang, Chenghao Xia, Tao Huang, Chang Xu + AAAI 2026 + Jie Ou, Shuaihong Jiang, Yingjun Du, Cees G. M. Snoek - Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels - https://arxiv.org/abs/2512.07474 - arXiv:2512.07474v1 Announce Type: new -Abstract: We present the Living Novel, an end-to-end system that transforms any literary work into an immersive, multi-character conversational experience. This system is designed to solve two fundamental challenges for LLM-driven characters. Firstly, generic LLMs suffer from persona drift, often failing to stay in character. Secondly, agents often exhibit abilities that extend beyond the constraints of the story's world and logic, leading to both narrative incoherence (spoiler leakage) and robustness failures (frame-breaking). To address these challenges, we introduce a novel two-stage training pipeline. Our Deep Persona Alignment (DPA) stage uses data-free reinforcement finetuning to instill deep character fidelity. Our Coherence and Robustness Enhancing (CRE) stage then employs a story-time-aware knowledge graph and a second retrieval-grounded training pass to architecturally enforce these narrative constraints. We validate our system through a multi-phase evaluation using Jules Verne's Twenty Thousand Leagues Under the Sea. A lab study with a detailed ablation of system components is followed by a 5-day in-the-wild diary study. Our DPA pipeline helps our specialized model outperform GPT-4o on persona-specific metrics, and our CRE stage achieves near-perfect performance in coherence and robustness measures. Our study surfaces practical design guidelines for AI-driven narrative systems: we find that character-first self-training is foundational for believability, while explicit story-time constraints are crucial for sustaining coherent, interruption-resilient mobile-web experiences. - oai:arXiv.org:2512.07474v1 - cs.HC + DiscoVerse: Multi-Agent Pharmaceutical Co-Scientist for Traceable Drug Discovery and Reverse Translation + https://arxiv.org/abs/2511.18259 + arXiv:2511.18259v2 Announce Type: replace +Abstract: Pharmaceutical research and development has accumulated vast and heterogeneous archives of data. Much of this knowledge stems from discontinued programs, and reusing these archives is invaluable for reverse translation. However, in practice, such reuse is often infeasible. In this work, we introduce DiscoVerse, a multi-agent co-scientist designed to support pharmaceutical research and development at Roche. Designed as a human-in-the-loop assistant, DiscoVerse enables domain-specific queries by delivering evidence-based answers: it retrieves relevant data, links across documents, summarises key findings and preserves institutional memory. We assess DiscoVerse through expert evaluation of source-linked outputs. Our evaluation spans a selected subset of 180 molecules from Roche's research and development repositories, encompassing over 0.87 billion BPE tokens and more than four decades of research. To our knowledge, this represents the first agentic framework to be systematically assessed on real pharmaceutical data for reverse translation, enabled by authorized access to confidential archives covering the full lifecycle of drug development. Our contributions include: role-specialized agent designs aligned with scientist workflows; human-in-the-loop support for reverse translation; expert evaluation; and a large-scale demonstration showing promising decision-making insights. In brief, across seven benchmark queries, DiscoVerse achieved near-perfect recall ($\geq 0.99$) with moderate precision ($0.71-0.91$). Qualitative assessments and three real-world pharmaceutical use cases further showed faithful, source-linked synthesis across preclinical and clinical evidence. + oai:arXiv.org:2511.18259v2 cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yifei Huang, Tianyu Yan, Sitong Gong, Xiwei Gao, Caixin Kang, Ruicong Liu, Huchuan Lu, Bo Zheng + Xiaochen Zheng, Alvaro Serra, Ilya Schneider Chernov, Maddalena Marchesi, Eunice Musvasva, Tatyana Y. Doktorova - An Analysis of Decision Problems for Relational Pattern Languages under Various Constraints - https://arxiv.org/abs/2512.07476 - arXiv:2512.07476v1 Announce Type: new -Abstract: Patterns are words with terminals and variables. The language of a pattern is the set of words obtained by uniformly substituting all variables with words that contain only terminals. In their original definition, patterns only allow for multiple distinct occurrences of some variables to be related by the equality relation, represented by using the same variable multiple times. In an extended notion, called relational patterns and relational pattern languages, variables may be related by arbitrary other relations. We extend the ongoing investigation of the main decision problems for patterns (namely, the membership problem, the inclusion problem, and the equivalence problem) to relational pattern languages under a wide range of individual relations. It is shown show that - even for many much simpler or less restrictive relations - the complexity and (un)decidability characteristics of these problems do not change compared to the classical case where variables are related only by equality. - oai:arXiv.org:2512.07476v1 - cs.FL - cs.CC - math.CO - Tue, 09 Dec 2025 00:00:00 -0500 - new + Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models + https://arxiv.org/abs/2511.18829 + arXiv:2511.18829v2 Announce Type: replace +Abstract: Heart rate estimation from photoplethysmography (PPG) signals generated by wearable devices such as smartwatches and fitness trackers has significant implications for the health and well-being of individuals. Although prior work has demonstrated deep learning models with strong performance in the heart rate estimation task, in order to deploy these models on wearable devices, these models must also adhere to strict memory and latency constraints. In this work, we explore and characterize how large pre-trained PPG models may be distilled to smaller models appropriate for real-time inference on the edge. We evaluate four distillation strategies through comprehensive sweeps of teacher and student model capacities: (1) hard distillation, (2) soft distillation, (3) decoupled knowledge distillation (DKD), and (4) feature distillation. We present a characterization of the resulting scaling laws describing the relationship between model size and performance. This early investigation lays the groundwork for practical and predictable methods for building edge-deployable models for physiological sensing. + oai:arXiv.org:2511.18829v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Klaus Jansen, Dirk Nowotka, Lis Pirotton, Corinna Wambsganz, Max Wiedenh\"oft + Kanav Arora, Girish Narayanswamy, Shwetak Patel, Richard Li - Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization - https://arxiv.org/abs/2512.07478 - arXiv:2512.07478v1 Announce Type: new -Abstract: Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks. Agentic Reinforcement Learning (Agentic RL) optimizes such models over full tool-interaction trajectories, but two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence; (2) Gradient degradation in Group Relative Policy Optimization (GRPO), where identical rewards within a rollout group yield zero advantage, reducing sample efficiency and destabilizing training. To address these challenges, we propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO). PRS is a curriculum-inspired reward design that introduces dense, stage-wise feedback - encouraging models to first master parseable and properly formatted tool calls, then optimize for factual correctness and answer quality. We instantiate PRS for short-form QA (with a length-aware BLEU to fairly score concise answers) and long-form QA (with LLM-as-a-Judge scoring to prevent reward hacking). VSPO is an enhanced GRPO variant that replaces low-value samples with prompts selected by a task-value metric balancing difficulty and uncertainty, and applies value-smoothing clipping to stabilize gradient updates. Experiments on multiple short-form and long-form QA benchmarks show that PRS consistently outperforms traditional binary rewards, and VSPO achieves superior stability, faster convergence, and higher final performance compared to PPO, GRPO, CISPO, and SFT-only baselines. Together, PRS and VSPO yield LLM-based TIR agents that generalize better across domains. - oai:arXiv.org:2512.07478v1 + Representational Stability of Truth in Large Language Models + https://arxiv.org/abs/2511.19166 + arXiv:2511.19166v2 Announce Type: replace +Abstract: Large language models (LLMs) are widely used for factual tasks such as "What treats asthma?" or "What is the capital of Latvia?". However, it remains unclear how stably LLMs encode distinctions between true, false, and neither-true-nor-false content in their internal probabilistic representations. We introduce representational stability as the robustness of an LLM's veracity representations to perturbations in the operational definition of truth. We assess representational stability by (i) training a linear probe on an LLM's activations to separate true from not-true statements and (ii) measuring how its learned decision boundary shifts under controlled label changes. Using activations from sixteen open-source models and three factual domains, we compare two types of neither statements. The first are fact-like assertions about entities we believe to be absent from any training data. We call these unfamiliar neither statements. The second are nonfactual claims drawn from well-known fictional contexts. We call these familiar neither statements. The unfamiliar statements induce the largest boundary shifts, producing up to $40\%$ flipped truth judgements in fragile domains (such as word definitions), while familiar fictional statements remain more coherently clustered and yield smaller changes ($\leq 8.2\%$). These results suggest that representational stability stems more from epistemic familiarity than from linguistic form. More broadly, our approach provides a diagnostic for auditing and training LLMs to preserve coherent truth assignments under semantic uncertainty, rather than optimizing for output accuracy alone. + oai:arXiv.org:2511.19166v2 cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Zhuoran Zhuang, Ye Chen, Jianghao Su, Chao Luo, Luhui Liu, Xia Zeng - - - Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance - https://arxiv.org/abs/2512.07480 - arXiv:2512.07480v1 Announce Type: new -Abstract: While traditional and neural video codecs (NVCs) have achieved remarkable rate-distortion performance, improving perceptual quality at low bitrates remains challenging. Some NVCs incorporate perceptual or adversarial objectives but still suffer from artifacts due to limited generation capacity, whereas others leverage pretrained diffusion models to improve quality at the cost of heavy sampling complexity. To overcome these challenges, we propose S2VC, a Single-Step diffusion based Video Codec that integrates a conditional coding framework with an efficient single-step diffusion generator, enabling realistic reconstruction at low bitrates with reduced sampling cost. Recognizing the importance of semantic conditioning in single-step diffusion, we introduce Contextual Semantic Guidance to extract frame-adaptive semantics from buffered features. It replaces text captions with efficient, fine-grained conditioning, thereby improving generation realism. In addition, Temporal Consistency Guidance is incorporated into the diffusion U-Net to enforce temporal coherence across frames and ensure stable generation. Extensive experiments show that S2VC delivers state-of-the-art perceptual quality with an average 52.73% bitrate saving over prior perceptual methods, underscoring the promise of single-step diffusion for efficient, high-quality video compression. - oai:arXiv.org:2512.07480v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Zihan Zheng, Yuan Zhang, Yan Lu + Samantha Dies, Courtney Maynard, Germans Savcisens, Tina Eliassi-Rad - From Real-World Traffic Data to Relevant Critical Scenarios - https://arxiv.org/abs/2512.07482 - arXiv:2512.07482v1 Announce Type: new -Abstract: The reliable operation of autonomous vehicles, automated driving functions, and advanced driver assistance systems across a wide range of relevant scenarios is critical for their development and deployment. Identifying a near-complete set of relevant driving scenarios for such functionalities is challenging due to numerous degrees of freedom involved, each affecting the outcomes of the driving scenario differently. Moreover, with increasing technical complexity of new functionalities, the number of potentially relevant, particularly "unknown unsafe" scenarios is increasing. To enhance validation efficiency, it is essential to identify relevant scenarios in advance, starting with simpler domains like highways before moving to more complex environments such as urban traffic. To address this, this paper focuses on analyzing lane change scenarios in highway traffic, which involve multiple degrees of freedom and present numerous safetyrelevant scenarios. We describe the process of data acquisition and processing of real-world data from public highway traffic, followed by the application of criticality measures on trajectory data to evaluate scenarios, as conducted within the AVEAS project (www.aveas.org). By linking the calculated measures to specific lane change driving scenarios and the conditions under which the data was collected, we facilitate the identification of safetyrelevant driving scenarios for various applications. Further, to tackle the extensive range of "unknown unsafe" scenarios, we propose a way to generate relevant scenarios by creating synthetic scenarios based on recorded ones. Consequently, we demonstrate and evaluate a processing chain that enables the identification of safety-relevant scenarios, the development of data-driven methods for extracting these scenarios, and the generation of synthetic critical scenarios via sampling on highways. - oai:arXiv.org:2512.07482v1 - cs.RO - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - 10.1109/IAVVC61942.2025.11219576 - Florian L\"uttner, Nicole Neis, Daniel Stadler, Robin Moss, Mirjam Fehling-Kaschek, Matthias Pfriem, Alexander Stolz, Jens Ziehn + Image2Gcode: Image-to-G-code Generation for Additive Manufacturing Using Diffusion-Transformer Model + https://arxiv.org/abs/2511.20636 + arXiv:2511.20636v2 Announce Type: replace +Abstract: Mechanical design and manufacturing workflows conventionally begin with conceptual design, followed by the creation of a computer-aided design (CAD) model and fabrication through material-extrusion (MEX) printing. This process requires converting CAD geometry into machine-readable G-code through slicing and path planning. While each step is well established, dependence on CAD modeling remains a major bottleneck: constructing object-specific 3D geometry is slow and poorly suited to rapid prototyping. Even minor design variations typically necessitate manual updates in CAD software, making iteration time-consuming and difficult to scale. To address this limitation, we introduce Image2Gcode, an end-to-end data-driven framework that bypasses the CAD stage and generates printer-ready G-code directly from images and part drawings. Instead of relying on an explicit 3D model, a hand-drawn or captured 2D image serves as the sole input. The framework first extracts slice-wise structural cues from the image and then employs a denoising diffusion probabilistic model (DDPM) over G-code sequences. Through iterative denoising, the model transforms Gaussian noise into executable print-move trajectories with corresponding extrusion parameters, establishing a direct mapping from visual input to native toolpaths. By producing structured G-code directly from 2D imagery, Image2Gcode eliminates the need for CAD or STL intermediates, lowering the entry barrier for additive manufacturing and accelerating the design-to-fabrication cycle. This approach supports on-demand prototyping from simple sketches or visual references and integrates with upstream 2D-to-3D reconstruction modules to enable an automated pipeline from concept to physical artifact. The result is a flexible, computationally efficient framework that advances accessibility in design iteration, repair workflows, and distributed manufacturing. + oai:arXiv.org:2511.20636v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Ziyue Wang, Yayati Jadhav, Peter Pak, Amir Barati Farimani - SemanticTours: A Conceptual Framework for Non-Linear, Knowledge Graph-Driven Data Tours - https://arxiv.org/abs/2512.07483 - arXiv:2512.07483v1 Announce Type: new -Abstract: Interactive tours help users explore datasets and provide onboarding. They rely on a linear sequence of views, showing a curated set of relevant data selections and introduce user interfaces. Existing frameworks of tours, however, often do not allow for branching and refining hypotheses outside of a rigid sequence, which is important in knowledge-centric domains such as law. For example, lawyers performing analytical case analysis need to iteratively weigh up different legal norms and construct strings of arguments. To address this gap, we propose SemanticTours, a semantic, graph-based model of tours that shifts from a sequence-based towards a graph-based navigation. Our model constructs a domain-specific knowledge graph that connects data elements based on user-definable semantic relationships. These relationships enable non-linear graph navigation that defines tours. We apply SemanticTours to the domain of law and conceptualize a visual analytics design and interaction concept for analytical reasoning in legal case analysis. Our concept accounts for the inherent complexity of graph-based tours using aggregated graph nodes and supporting navigation with a semantic lens. During an evaluation with six domain experts from law, they suggest that graph-based tours better support their analytical reasoning than sequences. Our work opens research opportunities for such tours to support analytical reasoning in law and other knowledge-centric domains. - oai:arXiv.org:2512.07483v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new + Mortgage Language Model: Domain-Adaptive Pretraining with Residual Instruction, Alignment Tuning, and Task-Specific Routing + https://arxiv.org/abs/2511.21101 + arXiv:2511.21101v2 Announce Type: replace +Abstract: Large Language Models (LLMs) demonstrate exceptional capabilities across general domains, yet their application to specialized sectors such as mortgage finance requires domain-specific knowledge augmentation while preserving instruction-following fidelity. We present MortgageLLM, a novel domain-specific large language model that addresses this dual challenge. It is developed using a dual-track specialization framework from a single base model (LLaMA-3.1-8B). We opted for this dual-expert approach as a single multi-task model suffers from performance trade-offs, where optimizing for structured tasks (via SFT) degrades conversational fidelity (via DPO). Our dual-track method solves this by creating two specialists, allowing each to be optimally trained for its distinct capability. Our approach applies the instruction residual technique to restore instruction-following capabilities post-domain adaptation without supervised fine-tuning. We contribute: (1) application of this residual technique to the highly specialized mortgage finance domain; (2) a dual-expert architecture combining a conversational Q&A model and a structured task model for classification and summarization; and (3) an intelligent task routing mechanism using few-shot classification performed by one of the expert models itself. We validate our approach on domain-specific benchmarks, where our final model (MLM v2) significantly outperforms the base LLaMA-3.1-8B-Instruct, achieving an LLM-as-a-Judge summarization score of 4.58 (vs. 3.99), a Q&A score of 4.09 (vs. 4.0), and a classification score of 2.6 (vs. 1.2). On semantic similarity, our model achieved a BERTScore of 0.77 for summarization (vs. 0.74), 0.68 for Q&A (vs. 0.58), and 0.75 for classification (vs. 0.73), substantially outperforming baseline approaches. + oai:arXiv.org:2511.21101v2 + cs.CL + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Daniel F\"urst, Matthijs Jansen op de Haar, Mennatallah El-Assady, Daniel A Keim, Maximilian T. Fischer + Manish Jain, Satheesh Kumar Ponnambalam, Salman Faroz, Chandrakanth Lns, Vinay Sharma - Materium: An Autoregressive Approach for Material Generation - https://arxiv.org/abs/2512.07486 - arXiv:2512.07486v1 Announce Type: new -Abstract: We present Materium: an autoregressive transformer for generating crystal structures that converts 3D material representations into token sequences. These sequences include elements with oxidation states, fractional coordinates and lattice parameters. Unlike diffusion approaches, which refine atomic positions iteratively through many denoising steps, Materium places atoms at precise fractional coordinates, enabling fast, scalable generation. With this design, the model can be trained in a few hours on a single GPU and generate samples much faster on GPUs and CPUs than diffusion-based approaches. The model was trained and evaluated using multiple properties as conditions, including fundamental properties, such as density and space group, as well as more practical targets, such as band gap and magnetic density. In both single and combined conditions, the model performs consistently well, producing candidates that align with the requested inputs. - oai:arXiv.org:2512.07486v1 + Escaping the Verifier: Learning to Reason via Demonstrations + https://arxiv.org/abs/2511.21667 + arXiv:2511.21667v3 Announce Type: replace +Abstract: Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations that remain under-utilized for reasoning-focused training. We introduce RARO (Relativistic Adversarial Reasoning Optimization) that learns strong reasoning capabilities from only expert demonstrations via Inverse Reinforcement Learning. Our method sets up an adversarial game between a policy and a relativistic critic: the policy learns to mimic expert answers, while the critic aims to identify the experts among (expert, policy) answer pairs. Both the policy and the critic are trained jointly and continuously via RL, and we identify the key stabilization techniques required for robust learning. Empirically, RARO significantly outperforms strong verifier-free baselines on all of our evaluation tasks -- Countdown, DeepMath, and Poetry Writing -- and enjoys the same robust scaling trends as RL with verifiers. These results demonstrate that our method effectively elicits strong reasoning performance from expert demonstrations alone, enabling robust reasoning learning even when task-specific verifiers are unavailable. + oai:arXiv.org:2511.21667v3 cs.LG - cond-mat.mtrl-sci - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Niklas Dobberstein, Jan Hamaekers + Locke Cai, Ivan Provilkov - Artificial Intelligence and Nuclear Weapons Proliferation: The Technological Arms Race for (In)visibility - https://arxiv.org/abs/2512.07487 - arXiv:2512.07487v1 Announce Type: new -Abstract: A robust nonproliferation regime has contained the spread of nuclear weapons to just nine states. Yet, emerging and disruptive technologies are reshaping the landscape of nuclear risks, presenting a critical juncture for decision makers. This article lays out the contours of an overlooked but intensifying technological arms race for nuclear (in)visibility, driven by the interplay between proliferation-enabling technologies (PETs) and detection-enhancing technologies (DETs). We argue that the strategic pattern of proliferation will be increasingly shaped by the innovation pace in these domains. Artificial intelligence (AI) introduces unprecedented complexity to this equation, as its rapid scaling and knowledge substitution capabilities accelerate PET development and challenge traditional monitoring and verification methods. To analyze this dynamic, we develop a formal model centered on a Relative Advantage Index (RAI), quantifying the shifting balance between PETs and DETs. Our model explores how asymmetric technological advancement, particularly logistic AI-driven PET growth versus stepwise DET improvements, expands the band of uncertainty surrounding proliferation detectability. Through replicable scenario-based simulations, we evaluate the impact of varying PET growth rates and DET investment strategies on cumulative nuclear breakout risk. We identify a strategic fork ahead, where detection may no longer suffice without broader PET governance. Governments and international organizations should accordingly invest in policies and tools agile enough to keep pace with tomorrow's technology. - oai:arXiv.org:2512.07487v1 - cs.CY + Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends + https://arxiv.org/abs/2511.22334 + arXiv:2511.22334v2 Announce Type: replace +Abstract: Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy consumption, making them unsuitable for large language models (LLMs). Fortunately, Small Language Models (SLMs) offer lightweight alternatives that bring AI inference to resource-constrained environments by significantly reducing computational cost while remaining suitable for specialization and customization. In this scenario, selecting the hardware platform that best balances performance and efficiency for SLM inference is challenging due to strict resource limitations. To address this issue, this study evaluates the inference performance and energy efficiency of commercial CPUs (Intel and ARM), GPUs (NVIDIA), and NPUs (RaiderChip) for running SLMs. GPUs, the usual platform of choice, are compared against commercial NPUs and recent multi-core CPUs. While NPUs leverage custom hardware designs optimized for computation, modern CPUs increasingly incorporate dedicated features targeting language-model workloads. Using a common execution framework and a suite of state-of-the-art SLMs, we analyze both maximum achievable performance and processing and energy efficiency across commercial solutions available for each platform. The results indicate that specialized backends outperform general-purpose CPUs, with NPUs achieving the highest performance by a wide margin. Bandwidth normalization proves essential for fair cross-architecture comparisons. Although low-power ARM processors deliver competitive results when energy usage is considered, metrics that combine performance and power (such as EDP) again highlight NPUs as the dominant architecture. These findings show that designs optimized for both efficiency and performance offer a clear advantage for edge workloads. + oai:arXiv.org:2511.22334v2 + cs.PF cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - 10.1111/risa.70105 - Risk Analysis 45(11): 3839-3859 (2025) - David M. Allison, Stephen Herzog + Pablo Prieto, Pablo Abad - Efficient Low-Tubal-Rank Tensor Estimation via Alternating Preconditioned Gradient Descent - https://arxiv.org/abs/2512.07490 - arXiv:2512.07490v1 Announce Type: new -Abstract: The problem of low-tubal-rank tensor estimation is a fundamental task with wide applications across high-dimensional signal processing, machine learning, and image science. Traditional approaches tackle such a problem by performing tensor singular value decomposition, which is computationally expensive and becomes infeasible for large-scale tensors. Recent approaches address this issue by factorizing the tensor into two smaller factor tensors and solving the resulting problem using gradient descent. However, this kind of approach requires an accurate estimate of the tensor rank, and when the rank is overestimated, the convergence of gradient descent and its variants slows down significantly or even diverges. To address this problem, we propose an Alternating Preconditioned Gradient Descent (APGD) algorithm, which accelerates convergence in the over-parameterized setting by adding a preconditioning term to the original gradient and updating these two factors alternately. Based on certain geometric assumptions on the objective function, we establish linear convergence guarantees for more general low-tubal-rank tensor estimation problems. Then we further analyze the specific cases of low-tubal-rank tensor factorization and low-tubal-rank tensor recovery. Our theoretical results show that APGD achieves linear convergence even under over-parameterization, and the convergence rate is independent of the tensor condition number. Extensive simulations on synthetic data are carried out to validate our theoretical assertions. - oai:arXiv.org:2512.07490v1 - cs.LG - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models + https://arxiv.org/abs/2511.22425 + arXiv:2511.22425v2 Announce Type: replace +Abstract: We present WUKONG, a novel training-free framework for high-fidelity textured 3D morphing that takes a pair of source and target prompts (image or text) as input. Unlike conventional methods -- which rely on manual correspondence matching and deformation trajectory estimation (limiting generalization and requiring costly preprocessing) -- WUKONG leverages the generative prior of flow-based transformers to produce high-fidelity 3D transitions with rich texture details. To ensure smooth shape transitions, we exploit the inherent continuity of flow-based generative processes and formulate morphing as an optimal transport barycenter problem. We further introduce a sequential initialization strategy to prevent abrupt geometric distortions and preserve identity coherence. For faithful texture preservation, we propose a similarity-guided semantic consistency mechanism that selectively retains high-frequency details and enables precise control over blending dynamics. This avoids common artifacts like oversmoothing while maintaining semantic fidelity. Extensive quantitative and qualitative evaluations demonstrate that WUKONG significantly outperforms state-of-the-art methods, achieving superior results across diverse geometry and texture variations. + oai:arXiv.org:2511.22425v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhiyu Liu, Zhi Han, Yandong Tang, Jun Fan, Yao Wang + Minghao Yin, Yukang Cao, Kai Han - Amulet: Fast TEE-Shielded Inference for On-Device Model Protection - https://arxiv.org/abs/2512.07495 - arXiv:2512.07495v1 Announce Type: new -Abstract: On-device machine learning (ML) introduces new security concerns about model privacy. Storing valuable trained ML models on user devices exposes them to potential extraction by adversaries. The current mainstream solution for on-device model protection is storing the weights and conducting inference within Trusted Execution Environments (TEEs). However, due to limited trusted memory that cannot accommodate the whole model, most existing approaches employ a partitioning strategy, dividing a model into multiple slices that are loaded into the TEE sequentially. This frequent interaction between untrusted and trusted worlds dramatically increases inference latency, sometimes by orders of magnitude. In this paper, we propose Amulet, a fast TEE-shielded on-device inference framework for ML model protection. Amulet incorporates a suite of obfuscation methods specifically designed for common neural network architectures. After obfuscation by the TEE, the entire transformed model can be securely stored in untrusted memory, allowing the inference process to execute directly in untrusted memory with GPU acceleration. For each inference request, only two rounds of minimal-overhead interaction between untrusted and trusted memory are required to process input samples and output results. We also provide theoretical proof from an information-theoretic perspective that the obfuscated model does not leak information about the original weights. We comprehensively evaluated Amulet using diverse model architectures ranging from ResNet-18 to GPT-2. Our approach incurs inference latency only 2.8-4.8x that of unprotected models with negligible accuracy loss, achieving an 8-9x speedup over baseline methods that execute inference entirely within TEEs, and performing approximately 2.2x faster than the state-of-the-art obfuscation-based method. - oai:arXiv.org:2512.07495v1 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - new + Orthogonal Disentanglement with Projected Feature Alignment for Multimodal Emotion Recognition in Conversation + https://arxiv.org/abs/2511.22463 + arXiv:2511.22463v2 Announce Type: replace +Abstract: Multimodal Emotion Recognition in Conversation (MERC) significantly enhances emotion recognition performance by integrating complementary emotional cues from text, audio, and visual modalities. While existing methods commonly utilize techniques such as contrastive learning and cross-attention mechanisms to align cross-modal emotional semantics, they typically overlook modality-specific emotional nuances like micro-expressions, tone variations, and sarcastic language. To overcome these limitations, we propose Orthogonal Disentanglement with Projected Feature Alignment (OD-PFA), a novel framework designed explicitly to capture both shared semantics and modality-specific emotional cues. Our approach first decouples unimodal features into shared and modality-specific components. An orthogonal disentanglement strategy (OD) enforces effective separation between these components, aided by a reconstruction loss to maintain critical emotional information from each modality. Additionally, a projected feature alignment strategy (PFA) maps shared features across modalities into a common latent space and applies a cross-modal consistency alignment loss to enhance semantic coherence. Extensive evaluations on widely-used benchmark datasets, IEMOCAP and MELD, demonstrate effectiveness of our proposed OD-PFA multimodal emotion recognition tasks, as compared with the state-of-the-art approaches. + oai:arXiv.org:2511.22463v2 + cs.MM + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zikai Mao, Lingchen Zhao, Lei Xu, Wentao Dong, Shenyi Zhang, Cong Wang, Qian Wang + Xinyi Che, Wenbo Wang, Jian Guan, Qijun Zhao - How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations - https://arxiv.org/abs/2512.07497 - arXiv:2512.07497v1 Announce Type: new -Abstract: We investigate how large language models (LLMs) fail when operating as autonomous agents with tool-use capabilities. Using the Kamiwaza Agentic Merit Index (KAMI) v0.1 benchmark, we analyze 900 execution traces from three representative models - Granite 4 Small, Llama 4 Maverick, and DeepSeek V3.1 - across filesystem, text extraction, CSV analysis, and SQL scenarios. Rather than focusing on aggregate scores, we perform fine-grained, per-trial behavioral analysis to surface the strategies that enable successful multi-step tool execution and the recurrent failure modes that undermine reliability. Our findings show that model scale alone does not predict agentic robustness: Llama 4 Maverick (400B) performs only marginally better than Granite 4 Small (32B) in some uncertainty-driven tasks, while DeepSeek V3.1's superior reliability derives primarily from post-training reinforcement learning rather than architecture or size. Across models, we identify four recurring failure archetypes: premature action without grounding, over-helpfulness that substitutes missing entities, vulnerability to distractor-induced context pollution, and fragile execution under load. These patterns highlight the need for agentic evaluation methods that emphasize interactive grounding, recovery behavior, and environment-aware adaptation, suggesting that reliable enterprise deployment requires not just stronger models but deliberate training and design choices that reinforce verification, constraint discovery, and adherence to source-of-truth data. - oai:arXiv.org:2512.07497v1 + Visual Orientalism in the AI Era: From West-East Binaries to English-Language Centrism + https://arxiv.org/abs/2511.22931 + arXiv:2511.22931v2 Announce Type: replace +Abstract: Text-to-image AI models systematically encode geopolitical bias through visual representation. Drawing on Said's Orientalism and framing theory, we introduce Visual Orientalism - the dual standard whereby AI depicts Western nations through political-modern symbols while portraying Eastern nations through cultural-traditional symbols. Analyzing 396 AI-generated images across 12 countries and 3 models, we reveal an evolution: Visual Orientalism has shifted from traditional West-versus-East binaries to English-language centrism, where only English-speaking core countries (USA and UK) receive political representation while all other nations - including European powers - face cultural exoticization. This algorithmic reconfiguration operates through automated framing mechanisms shaped by English-language training data dominance. Our findings demonstrate how AI systems function as agents of cultural representation that perpetuate and intensify historical power asymmetries. Addressing Visual Orientalism requires rethinking of algorithmic governance and the geopolitical structures embedded in AI training data. + oai:arXiv.org:2511.22931v2 + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zhilong Zhao, Yindi Liu + + + The Battle of the Water Futures + https://arxiv.org/abs/2511.22986 + arXiv:2511.22986v2 Announce Type: replace +Abstract: The highly anticipated 'Battle of the Water Networks' is back with a new challenge for the water community. This competition will be hosted at the 4th International Joint Conference on Water Distribution Systems Analysis and Computing and Control in the Water Industry (WDSA/CCWI 2026), taking place in Paphos, Cyprus, from May 18-21, 2026. This competition embodies the core mission of Water-Futures and the theme for WDSA/CCWI 2026: "Designing the next generation of urban water (and wastewater) systems." + The objective is to design and operate a water distribution system over a long-term horizon under deep uncertainty, with interventions applied in stages. For the first time, this challenge features a staged-design approach, unobservable and unknown uncertainties, and incorporates elements of policymaking and artificial intelligence. The solutions will be assessed using a transparent and inspectable open-source evaluation framework. + oai:arXiv.org:2511.22986v2 + eess.SY + cs.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-sa/4.0/ + Dennis Zanutto, Christos Michalopoulos, Lydia Tsiami, Andr\'e Artelt, Jasmin Brandt, Demetrios Eliades, Stelios Vrachimis, Stefano Alvisi, Valentina Marsili, Filippo Mazzoni, Panagiotis Smartzis, Barbara Hammer, Phoebe Koundouri, Marios Polycarpou, Dragan Savi\'c + + + Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability? + https://arxiv.org/abs/2512.00218 + arXiv:2512.00218v2 Announce Type: replace +Abstract: AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to which CoT faithfully reflects the underlying reasoning process, and hence the extent to which it can be usefully monitored, may be influenced by certain aspects of training. We investigate how different \emph{training incentives}, applied to a reasoning model, affect its monitorability. We introduce a novel methodology for measuring monitorability according to whether a monitor can predict a key latent variable using the model's reasoning. When controlling for accuracy, we do not find evidence for consistent effects from commonly used incentives (length penalties and KL regularisation), but we find that adversarial optimisation (penalising monitor accuracy) degrades monitor performance, while direct optimisation for monitorability does not reliably lead to improvements. Our code is available at https://github.com/QiyaoWei/reasoning-under-pressure. + oai:arXiv.org:2512.00218v2 cs.AI - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - JV Roig + Matt MacDermott, Qiyao Wei, Rada Djoneva, Francis Rhys Ward - Towards Robust DeepFake Detection under Unstable Face Sequences: Adaptive Sparse Graph Embedding with Order-Free Representation and Explicit Laplacian Spectral Prior - https://arxiv.org/abs/2512.07498 - arXiv:2512.07498v1 Announce Type: new -Abstract: Ensuring the authenticity of video content remains challenging as DeepFake generation becomes increasingly realistic and robust against detection. Most existing detectors implicitly assume temporally consistent and clean facial sequences, an assumption that rarely holds in real-world scenarios where compression artifacts, occlusions, and adversarial attacks destabilize face detection and often lead to invalid or misdetected faces. To address these challenges, we propose a Laplacian-Regularized Graph Convolutional Network (LR-GCN) that robustly detects DeepFakes from noisy or unordered face sequences, while being trained only on clean facial data. Our method constructs an Order-Free Temporal Graph Embedding (OF-TGE) that organizes frame-wise CNN features into an adaptive sparse graph based on semantic affinities. Unlike traditional methods constrained by strict temporal continuity, OF-TGE captures intrinsic feature consistency across frames, making it resilient to shuffled, missing, or heavily corrupted inputs. We further impose a dual-level sparsity mechanism on both graph structure and node features to suppress the influence of invalid faces. Crucially, we introduce an explicit Graph Laplacian Spectral Prior that acts as a high-pass operator in the graph spectral domain, highlighting structural anomalies and forgery artifacts, which are then consolidated by a low-pass GCN aggregation. This sequential design effectively realizes a task-driven spectral band-pass mechanism that suppresses background information and random noise while preserving manipulation cues. Extensive experiments on FF++, Celeb-DFv2, and DFDC demonstrate that LR-GCN achieves state-of-the-art performance and significantly improved robustness under severe global and local disruptions, including missing faces, occlusions, and adversarially perturbed face detections. - oai:arXiv.org:2512.07498v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + TenonOS: A Self-Generating LibOS-on-LibOS Framework for Time-Critical Embedded Operating Systems + https://arxiv.org/abs/2512.00400 + arXiv:2512.00400v2 Announce Type: replace +Abstract: The growing complexity of embedded systems creates tension between rich functionality and strict resource and real-time constraints. Traditional monolithic operating system and hypervisor designs suffer from resource bloat and unpredictable scheduling, making them unsuitable for time-critical workloads where low latency and low jitter are essential. We propose TenonOS, a demand-driven, self-generating, lightweight operating system framework for time-critical embedded systems that rethinks both hypervisor and operating system architectures. TenonOS introduces a LibOS-on-LibOS model that decomposes hypervisor and operating system functionality into fine-grained, reusable micro-libraries. A generative orchestration engine dynamically composes these libraries to synthesize a customized runtime tailored to each application's criticality, timing requirements, and resource profile. TenonOS consists of two core components: Mortise, a minimalist micro-hypervisor, and Tenon, a real-time library operating system. Mortise provides lightweight isolation and removes the usual double-scheduler overhead in virtualized setups, while Tenon provides precise and deterministic task management. By generating only the necessary software stack per workload, TenonOS removes redundant layers, minimizes the trusted computing base, and maximizes responsiveness. Experiments show a 40.28 percent reduction in scheduling latency, an ultra-compact 361 KiB memory footprint, and strong adaptability. + oai:arXiv.org:2512.00400v2 + cs.OS + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Chih-Chung Hsu, Shao-Ning Chen, Chia-Ming Lee, Yi-Fang Wang, Yi-Shiuan Chou + Xinkui Zhao, Yifan Zhang, Haidan Zhao, Hao Zhang, Qingyu Ma, Lufei Zhang, Guanjie Cheng, Shuiguang Deng, Jianwei Yin, Zuoning Chen - MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer - https://arxiv.org/abs/2512.07500 - arXiv:2512.07500v1 Announce Type: new -Abstract: Multi-object video motion transfer poses significant challenges for Diffusion Transformer (DiT) architectures due to inherent motion entanglement and lack of object-level control. We present MultiMotion, a novel unified framework that overcomes these limitations. Our core innovation is Maskaware Attention Motion Flow (AMF), which utilizes SAM2 masks to explicitly disentangle and control motion features for multiple objects within the DiT pipeline. Furthermore, we introduce RectPC, a high-order predictor-corrector solver for efficient and accurate sampling, particularly beneficial for multi-entity generation. To facilitate rigorous evaluation, we construct the first benchmark dataset specifically for DiT-based multi-object motion transfer. MultiMotion demonstrably achieves precise, semantically aligned, and temporally coherent motion transfer for multiple distinct objects, maintaining DiT's high quality and scalability. The code is in the supp. - oai:arXiv.org:2512.07500v1 + IRPO: Boosting Image Restoration via Post-training GRPO + https://arxiv.org/abs/2512.00814 + arXiv:2512.00814v2 Announce Type: replace +Abstract: Recent advances in post-training paradigms have achieved remarkable success in high-level generation tasks, yet their potential for low-level vision remains rarely explored. Existing image restoration (IR) methods rely on pixel-level hard-fitting to ground-truth images, struggling with over-smoothing and poor generalization. To address these limitations, we propose IRPO, a low-level GRPO-based post-training paradigm that systematically explores both data formulation and reward modeling. We first explore a data formulation principle for low-level post-training paradigm, in which selecting underperforming samples from the pre-training stage yields optimal performance and improved efficiency. Furthermore, we model a reward-level criteria system that balances objective accuracy and human perceptual preference through three complementary components: a General Reward for structural fidelity, an Expert Reward leveraging Qwen-VL for perceptual alignment, and a Restoration Reward for task-specific low-level quality. Comprehensive experiments on six in-domain and five out-of-domain (OOD) low-level benchmarks demonstrate that IRPO achieves state-of-the-art results across diverse degradation types, surpassing the AdaIR baseline by 0.83 dB on in-domain tasks and 3.43 dB on OOD settings. Our code can be shown in https://github.com/HaoxuanXU1024/IRPO. + oai:arXiv.org:2512.00814v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Penghui Liu, Jiangshan Wang, Yutong Shen, Shanhui Mo, Chenyang Qi, Yue Ma + Haoxuan Xu, Yi Liu, Boyuan Jiang, Jinlong Peng, Donghao Luo, Xiaobin Hu, Shuicheng Yan, Haoang Li - AutoICE: Automatically Synthesizing Verifiable C Code via LLM-driven Evolution - https://arxiv.org/abs/2512.07501 - arXiv:2512.07501v1 Announce Type: new -Abstract: Automatically synthesizing verifiable code from natural language requirements ensures software correctness and reliability while significantly lowering the barrier to adopting the techniques of formal methods. With the rise of large language models (LLMs), long-standing efforts at autoformalization have gained new momentum. However, existing approaches suffer from severe syntactic and semantic errors due to the scarcity of domain-specific pre-training corpora and often fail to formalize implicit knowledge effectively. In this paper, we propose AutoICE, an LLM-driven evolutionary search for synthesizing verifiable C code. It introduces the diverse individual initialization and the collaborative crossover to enable diverse iterative updates, thereby mitigating error propagation inherent in single-agent iterations. Besides, it employs the self-reflective mutation to facilitate the discovery of implicit knowledge. Evaluation results demonstrate the effectiveness of AutoICE: it successfully verifies $90.36$\% of code, outperforming the state-of-the-art (SOTA) approach. Besides, on a developer-friendly dataset variant, AutoICE achieves a $88.33$\% verification success rate, significantly surpassing the $65$\% success rate of the SOTA approach. - oai:arXiv.org:2512.07501v1 - cs.SE + ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning + https://arxiv.org/abs/2512.00831 + arXiv:2512.00831v2 Announce Type: replace +Abstract: Large Reasoning Models (LRMs) are Large Language Models (LLMs) explicitly trained to generate long-form Chain-of-Thoughts (CoTs), achieving impressive success on challenging tasks like math and programming. However, their underlying reasoning "algorithms" remain poorly understood. To investigate this, we propose ReJump, which represents a reasoning trace as a visitation order over nodes in a tree of intermediate problem-solving steps. Transitions between nodes, which we term jumps, include adjacent moves that capture behaviors such as calculation, and non-adjacent moves that capture behaviors such as backtracking and verification. ReJump enables analyzing LLM reasoning with diverse metrics that quantify exploration, exploitation, overthinking, forgetting, and verification. Using our proposed LLM agent to extract reasoning traces into ReJump format, we evaluate state-of-the-art LRMs on two tasks and find that models with similar accuracy can exhibit distinct reasoning behaviors, while different tasks favor different reasoning styles (e.g., varying balance between exploration and exploitation). To further understand how learning strategies shape reasoning, we use ReJump to compare distilled LRMs with their teachers, CoT-prompted LLMs with LRMs, and to examine how the number of reasoning examples and reinforcement learning affect reasoning behavior. Finally, we show that ReJump can improve reasoning quality at test time through strategies such as ReJump-guided Best-of-N selection and prompt selection. Our code is publicly available at https://github.com/UW-Madison-Lee-Lab/ReJump. + oai:arXiv.org:2512.00831v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Yuchen Zeng, Shuibai Zhang, Wonjun Kang, Shutong Wu, Lynnix Zou, Ying Fan, Heeju Kim, Ziqian Lin, Jungtaek Kim, Hyung Il Koo, Dimitris Papailiopoulos, Kangwook Lee + + + The Necessity of Imperfection:Reversing Model Collapse via Simulating Cognitive Boundedness + https://arxiv.org/abs/2512.01354 + arXiv:2512.01354v3 Announce Type: replace +Abstract: Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human text. Prolonged training on such statistically optimal but cognitively impoverished data accelerates model collapse. + This paper proposes a paradigm shift: instead of imitating the surface properties of data, we simulate the cognitive processes that generate human text. We introduce the Prompt-driven Cognitive Computing Framework (PMCSF), whose core consists of a Cognitive State Decoder (CSD) that reverse-engineers unstructured text into structured cognitive vectors, and a Cognitive Text Encoder (CTE) that re-materializes these states into text enriched with human-typical imperfections via mathematically defined Cognitive Perturbation Operators. + The framework is validated through a two-stage objective evaluation pipeline. First, in cognitive codec verification, CTE text yields a Jensen-Shannon divergence of 0.0614 from human text (vs. 0.4431 for standard LLM output), passes double-blind professional media review, and achieves an intraclass correlation coefficient ICC > 0.9 for cognitive profile alignment across heterogeneous models. Second, in functional gain evaluation, isomorphic stress tests in the A-share market show that strategies incorporating CTE-generated data reduce maximum drawdown by 47.4% during the 2015 crash and deliver 8.6% Defensive Alpha, exceeding transaction costs by a factor of 33. + Our findings demonstrate that modelling human cognitive limitations -- not copying surface data -- enables synthetic data with genuine functional gain, offering a viable technical pathway toward resolving the AI data-collapse crisis. + oai:arXiv.org:2512.01354v3 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.CL + cs.CY + cs.LG + q-fin.TR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Weilin Luo, Xueyi Liang, Haotian Deng, Yanan Liu, Hai Wan + Zhongjie Jiang + + + CLAPS: Posterior-Aware Conformal Intervals via Last-Layer Laplace + https://arxiv.org/abs/2512.01384 + arXiv:2512.01384v2 Announce Type: replace +Abstract: We present CLAPS, a posterior-aware conformal regression method that pairs a Last-Layer Laplace Approximation with split-conformal calibration. From the resulting Gaussian posterior, CLAPS defines a simple two-sided posterior CDF score that aligns the conformity metric with the full predictive shape, not just a point estimate. This alignment yields narrower prediction intervals at the same target coverage, especially on small to medium tabular datasets where data are scarce and uncertainty modeling matters. We also provide a lightweight diagnostic suite that separates aleatoric and epistemic components and visualizes posterior behavior, helping practitioners understand why intervals shrink when they do. Across multiple benchmarks using the same MLP backbone, CLAPS consistently attains nominal coverage with improved efficiency and minimal overhead, offering a clear, practical upgrade to residual-based conformal baselines. + oai:arXiv.org:2512.01384v2 + cs.LG + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh - SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation - https://arxiv.org/abs/2512.07503 - arXiv:2512.07503v1 Announce Type: new -Abstract: Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token prediction during inference. To accelerate autoregressive text-to-image generation, we propose Speculative Jacobi Decoding++ (SJD++), a training-free probabilistic parallel decoding algorithm. Unlike traditional next-token prediction, SJD++ performs multi-token prediction in each forward pass, drastically reducing generation steps. Specifically, it integrates the iterative multi-token prediction mechanism from Jacobi decoding, with the probabilistic drafting-and-verification mechanism from speculative sampling. More importantly, for further acceleration, SJD++ reuses high-confidence draft tokens after each verification phase instead of resampling them all. We conduct extensive experiments on several representative autoregressive text-to-image generation models and demonstrate that SJD++ achieves $2\times$ to $3\times$ inference latency reduction and $2\times$ to $7\times$ step compression, while preserving visual quality with no observable degradation. - oai:arXiv.org:2512.07503v1 + CourtMotion: Learning Event-Driven Motion Representations from Skeletal Data for Basketball + https://arxiv.org/abs/2512.01478 + arXiv:2512.01478v2 Announce Type: replace +Abstract: This paper presents CourtMotion, a spatiotemporal modeling framework for analyzing and predicting game events and plays as they develop in professional basketball. Anticipating basketball events requires understanding both physical motion patterns and their semantic significance in the context of the game. Traditional approaches that use only player positions fail to capture crucial indicators such as body orientation, defensive stance, or shooting preparation motions. Our two-stage approach first processes skeletal tracking data through Graph Neural Networks to capture nuanced motion patterns, then employs a Transformer architecture with specialized attention mechanisms to model player interactions. We introduce event projection heads that explicitly connect player movements to basketball events like passes, shots, and steals, training the model to associate physical motion patterns with their tactical purposes. Experiments on NBA tracking data demonstrate significant improvements over position-only baselines: 35% reduction in trajectory prediction error compared to state-of-the-art position-based models and consistent performance gains across key basketball analytics tasks. The resulting pretrained model serves as a powerful foundation for multiple downstream tasks, with pick detection, shot taker identification, assist prediction, shot location classification, and shot type recognition demonstrating substantial improvements over existing methods. + oai:arXiv.org:2512.01478v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + cs.MA + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Yao Teng, Zhihuan Jiang, Han Shi, Xian Liu, Xuefei Ning, Guohao Dai, Yu Wang, Zhenguo Li, Xihui Liu + Omer Sela (Amazon, Tel Aviv University), Michael Chertok (Amazon), Lior Wolf (Tel Aviv University) - ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points - https://arxiv.org/abs/2512.07504 - arXiv:2512.07504v1 Announce Type: new -Abstract: Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing point inconsistency, where projections of parallel lines fail to converge correctly in 2D space. This leads to structurally implausible geometry that degrades spatial realism, especially in architectural scenes. We propose ControlVP, a user-guided framework for correcting vanishing point inconsistencies in generated images. Our approach extends a pre-trained diffusion model by incorporating structural guidance derived from building contours. We also introduce geometric constraints that explicitly encourage alignment between image edges and perspective cues. Our method enhances global geometric consistency while maintaining visual fidelity comparable to the baselines. This capability is particularly valuable for applications that require accurate spatial structure, such as image-to-3D reconstruction. The dataset and source code are available at https://github.com/RyotaOkumura/ControlVP . - oai:arXiv.org:2512.07504v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + StarDist: A Code Generator for Distributed Graph Algorithms + https://arxiv.org/abs/2512.01646 + arXiv:2512.01646v2 Announce Type: replace +Abstract: Relational data, occurring in the real world, are often structured as graphs, which provide the logical abstraction required to make analytical derivations simpler. As graphs get larger, the irregular access patterns exhibited in most graph algorithms, hamper performance. This, along with NUMA and physical memory limits, results in scaling complexities with sequential/shared memory frameworks. StarPlat's MPI backend abstracts away the programmatic complexity involved in designing optimal distributed graph algorithms. It provides an instrument for coding graph algorithms that scale over distributed memory. In this work, we provide an analysis-transformation framework that leverages general semantics associated with iterations involving nodes and their neighbors, within StarPlat, to aggregate communication. The framework scans for patterns that warrant re-ordering in neighborhood access patterns, aggregate communication, and avoid communication altogether with opportunistic caching in reduction constructs. We also architect an optimized bulk-reduction substrate using Open MPI's passive Remote Memory Access (RMA) constructs. We applied our optimization logic to StarPlat's distributed backend and outperformed d-Galois by 2.05 and DRONE by 1.44 times in Single Source Shortest Paths across several big data graphs. + oai:arXiv.org:2512.01646v2 + cs.DC + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ryota Okumura, Kaede Shiohara, Toshihiko Yamasaki + Barenya Kumar Nandy, Rupesh Nasre - Control of Discrete-Time Linear Systems with Charge-Balanced Inputs - https://arxiv.org/abs/2512.07506 - arXiv:2512.07506v1 Announce Type: new -Abstract: Electrical brain stimulation relies on externally applied currents to modulate neural activity, but safety constraints require each stimulation cycle to be charge-balanced, enforcing a zero net injected charge. However, how such charge-balanced stimulation works remains poorly understood. This paper investigates the ability of charge-balanced inputs to steer state trajectories in discrete-time linear systems. Motivated by both open-loop and adaptive neurostimulation protocols, we study two practically relevant input structures: periodic (repetitive) charge-balanced inputs and non-repetitive charge-balanced inputs. For each case, we derive novel reachability and controllability conditions. The theoretical results are further validated through numerical demonstrations of minimum-energy control input design. - oai:arXiv.org:2512.07506v1 - eess.SY - cs.SY + Inverse Optimality for Fair Digital Twins: A Preference-based approach + https://arxiv.org/abs/2512.01650 + arXiv:2512.01650v2 Announce Type: replace +Abstract: Digital Twins (DTs) are increasingly used as autonomous decision-makers in complex socio-technical systems. However, their mathematically optimal decisions often diverge from human expectations, revealing a persistent mismatch between algorithmic and bounded human rationality. This work addresses this challenge by proposing a framework that introduces fairness as a learnable objective within optimization-based Digital Twins. In this respect, a preference-driven learning workflow that infers latent fairness objectives directly from human pairwise preferences over feasible decisions is introduced. A dedicated Siamese neural network is developed to generate convex quadratic cost functions conditioned on contextual information. The resulting surrogate objectives drive the optimization procedure toward solutions that better reflect human-perceived fairness while maintaining computational efficiency. The effectiveness of the approach is demonstrated on a COVID-19 hospital resource allocation scenario. Overall, this work offers a practical solution to integrate human-centered fairness into the design of autonomous decision-making systems. + oai:arXiv.org:2512.01650v2 + cs.LG + cs.SE math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yuzhen Qin, Zonglin Liu, Marcel van Gerven + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Daniele Masti, Francesco Basciani, Arianna Fedeli, Girgio Gnecco, Francesco Smarra - VP-AutoTest: A Virtual-Physical Fusion Autonomous Driving Testing Platform - https://arxiv.org/abs/2512.07507 - arXiv:2512.07507v1 Announce Type: new -Abstract: The rapid development of autonomous vehicles has led to a surge in testing demand. Traditional testing methods, such as virtual simulation, closed-course, and public road testing, face several challenges, including unrealistic vehicle states, limited testing capabilities, and high costs. These issues have prompted increasing interest in virtual-physical fusion testing. However, despite its potential, virtual-physical fusion testing still faces challenges, such as limited element types, narrow testing scope, and fixed evaluation metrics. To address these challenges, we propose the Virtual-Physical Testing Platform for Autonomous Vehicles (VP-AutoTest), which integrates over ten types of virtual and physical elements, including vehicles, pedestrians, and roadside infrastructure, to replicate the diversity of real-world traffic participants. The platform also supports both single-vehicle interaction and multi-vehicle cooperation testing, employing adversarial testing and parallel deduction to accelerate fault detection and explore algorithmic limits, while OBU and Redis communication enable seamless vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) cooperation across all levels of cooperative automation. Furthermore, VP-AutoTest incorporates a multidimensional evaluation framework and AI-driven expert systems to conduct comprehensive performance assessment and defect diagnosis. Finally, by comparing virtual-physical fusion test results with real-world experiments, the platform performs credibility self-evaluation to ensure both the fidelity and efficiency of autonomous driving testing. Please refer to the website for the full testing functionalities on the autonomous driving public service platform OnSite:https://www.onsite.com.cn. - oai:arXiv.org:2512.07507v1 - cs.RO - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new + HERMES: Heterogeneous Application-Enabled Routing Middleware for Edge-IoT Systems + https://arxiv.org/abs/2512.01824 + arXiv:2512.01824v2 Announce Type: replace +Abstract: The growth of the Internet of Things has enabled a new generation of applications, pushing computation and intelligence toward the network edge. This trend, however, exposes challenges, as the heterogeneity of devices and the complex requirements of applications are often misaligned with the assumptions of traditional routing protocols, which lack the flexibility to accommodate application-layer metrics and policies. This work addresses this gap by proposing a software framework that enhances routing flexibility by dynamically incorporating application-aware decisions. The core of the work establishes a multi-hop Wi-Fi network of heterogeneous devices, specifically ESP8266, ESP32, and Raspberry Pi 3B. The routing layer follows a proactive approach, while the network is fault-tolerant, maintaining operation despite both node loss and message loss. On top of this, a middleware layer introduces three strategies for influencing routing behavior: two adapt the path a message traverses until arriving at the destination, while the third allows applications to shape the network topology. This layer offers a flexible interface for diverse applications. The framework was validated on a physical testbed through edge intelligence use cases, including distributing neural network inference computations across multiple devices and offloading the entire workload to the most capable node. Distributed inference is useful in scenarios requiring low latency, energy efficiency, privacy, and autonomy. Experimental results indicated that device heterogeneity significantly impacts network performance. Throughput and inference duration analysis showed the influence of the strategies on application behaviour, revealed that topology critically affects decentralized performance, and demonstrated the suitability of the framework for complex tasks. + oai:arXiv.org:2512.01824v2 + cs.NI + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yiming Cui, Shiyu Fang, Jiarui Zhang, Yan Huang, Chengkai Xu, Bing Zhu, Hao Zhang, Peng Hang, Jian Sun + J\'essica Consci\^encia, Ant\'onio Grilo - Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces - https://arxiv.org/abs/2512.07509 - arXiv:2512.07509v1 Announce Type: new -Abstract: The overall neural network (NN) performance is closely related to the properties of its embedding distribution in latent space (LS). It has recently been shown that predefined vector systems, specifically An root system vectors, can be used as targets for latent space configurations (LSC) to ensure the desired LS structure. One of the main LSC advantage is the possibility of training classifier NNs without classification layers, which facilitates training NNs on datasets with extremely large numbers of classes. This paper provides a more general overview of possible vector systems for NN training along with their properties and methods for vector system construction. These systems are used to configure LS of encoders and visual transformers to significantly speed up ImageNet-1K and 50k-600k classes LSC training. It is also shown that using the minimum number of LS dimensions for a specific number of classes results in faster convergence. The latter has potential advantages for reducing the size of vector databases used to store NN embeddings. - oai:arXiv.org:2512.07509v1 + The Mean-Field Dynamics of Transformers + https://arxiv.org/abs/2512.01868 + arXiv:2512.01868v2 Announce Type: replace +Abstract: We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein gradient flows, synchronization models (Kuramoto), and mean-shift clustering. Central to our results is a global clustering phenomenon whereby tokens cluster asymptotically after long metastable states where they are arranged into multiple clusters. We further analyze a tractable equiangular reduction to obtain exact clustering rates, show how commonly used normalization schemes alter contraction speeds, and identify a phase transition for long-context attention. The results highlight both the mechanisms that drive representation collapse and the regimes that preserve expressive, multi-cluster structure in deep attention architectures. + oai:arXiv.org:2512.01868v2 cs.LG - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + math-ph + math.DS + math.MP + math.PR + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nikita Gabdullin + Philippe Rigollet - Canonical bidirectional typechecking - https://arxiv.org/abs/2512.07511 - arXiv:2512.07511v1 Announce Type: new -Abstract: We demonstrate that the checkable/synthesisable split in bidirectional typechecking coincides with existing dualities in polarised System L, also known as polarised $\mu\tilde{\mu}$-calculus. Specifically, positive terms and negative coterms are checkable, and negative terms and positive coterms are synthesisable. This combines a standard formulation of bidirectional typechecking with Zeilberger's `cocontextual' variant. We extend this to ordinary `cartesian' System L using Mc Bride's co-de Bruijn formulation of scopes, and show that both can be combined in a linear-nonlinear style, where linear types are positive and cartesian types are negative. This yields a remarkable 3-way coincidence between the shifts of polarised System L, LNL calculi, and bidirectional calculi. - oai:arXiv.org:2512.07511v1 - cs.PL - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new + An Improved Ensemble-Based Machine Learning Model with Feature Optimization for Early Diabetes Prediction + https://arxiv.org/abs/2512.02023 + arXiv:2512.02023v2 Announce Type: replace +Abstract: Diabetes is a serious worldwide health issue, and successful intervention depends on early detection. However, overlapping risk factors and data asymmetry make prediction difficult. To use extensive health survey data to create a machine learning framework for diabetes classification that is both accurate and comprehensible, to produce results that will aid in clinical decision-making. Using the BRFSS dataset, we assessed a number of supervised learning techniques. SMOTE and Tomek Links were used to correct class imbalance. To improve prediction performance, both individual models and ensemble techniques such as stacking were investigated. The 2015 BRFSS dataset, which includes roughly 253,680 records with 22 numerical features, is used in this study. Strong ROC-AUC performance of approximately 0.96 was attained by the individual models Random Forest, XGBoost, CatBoost, and LightGBM.The stacking ensemble with XGBoost and KNN yielded the best overall results with 94.82\% accuracy, ROC-AUC of 0.989, and PR-AUC of 0.991, indicating a favourable balance between recall and precision. In our study, we proposed and developed a React Native-based application with a Python Flask backend to support early diabetes prediction, providing users with an accessible and efficient health monitoring tool. + oai:arXiv.org:2512.02023v2 + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zanzi Mihejevs, Jules Hedges + Md. Najmul Islam, Md. Miner Hossain Rimon, Shah Sadek-E-Akbor Shamim, Zarif Mohaimen Fahad, Md. Jehadul Islam Mony, Md. Jalal Uddin Chowdhury - MeshRipple: Structured Autoregressive Generation of Artist-Meshes - https://arxiv.org/abs/2512.07514 - arXiv:2512.07514v1 Announce Type: new -Abstract: Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface.MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies.This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines. - oai:arXiv.org:2512.07514v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new + Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration + https://arxiv.org/abs/2512.02530 + arXiv:2512.02530v2 Announce Type: replace +Abstract: The exponential growth of digital content presents significant challenges for content safety. Current moderation systems, often based on single models or fixed pipelines, exhibit limitations in identifying implicit risks and providing interpretable judgment processes. To address these issues, we propose Aetheria, a multimodal interpretable content safety framework based on multi-agent debate and collaboration.Employing a collaborative architecture of five core agents, Aetheria conducts in-depth analysis and adjudication of multimodal content through a dynamic, mutually persuasive debate mechanism, which is grounded by RAG-based knowledge retrieval.Comprehensive experiments on our proposed benchmark (AIR-Bench) validate that Aetheria not only generates detailed and traceable audit reports but also demonstrates significant advantages over baselines in overall content safety accuracy, especially in the identification of implicit risks. This framework establishes a transparent and interpretable paradigm, significantly advancing the field of trustworthy AI content moderation. + oai:arXiv.org:2512.02530v2 + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junkai Lin, Hang Long, Huipeng Guo, Jielei Zhang, JiaYi Yang, Tianle Guo, Yang Yang, Jianwen Li, Wenxiao Zhang, Matthias Nie{\ss}ner, Wei Yang + Yuxiang He, Jian Zhao, Yuchen Yuan, Tianle Zhang, Wei Cai, Haojie Cheng, Ziyan Shi, Ming Zhu, Haichuan Tang, Chi Zhang, Xuelong Li + + + Strengthening Han's Fourier Entropy-Influence Inequality via an Information-Theoretic Proof + https://arxiv.org/abs/2512.03117 + arXiv:2512.03117v3 Announce Type: replace +Abstract: We strengthen Han's Fourier entropy-influence inequality $$ H[\widehat{f}] \leq C_{1}I(f) + C_{2}\sum_{i\in [n]}I_{i}(f)\ln\frac{1}{I_{i}(f)} $$ originally proved for $\{-1,1\}$-valued Boolean functions with $C_{1}=3+2\ln 2$ and $C_{2}=1$. We show, by a short information-theoretic proof, that it in fact holds with sharp constants $C_{1}=C_{2}=1$ for all real-valued Boolean functions of unit $L^{2}$-norm, thereby establishing the inequality as an elementary structural property of Shannon entropy and influence. + oai:arXiv.org:2512.03117v3 + cs.IT + math.IT + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Peijie Li, Guangyue Han - SPAD: Seven-Source Token Probability Attribution with Syntactic Aggregation for Detecting Hallucinations in RAG - https://arxiv.org/abs/2512.07515 - arXiv:2512.07515v1 Announce Type: new -Abstract: Detecting hallucinations in Retrieval-Augmented Generation (RAG) remains a challenge. Prior approaches attribute hallucinations to a binary conflict between internal knowledge (stored in FFNs) and retrieved context. However, this perspective is incomplete, failing to account for the impact of other components in the generative process, such as the user query, previously generated tokens, the current token itself, and the final LayerNorm adjustment. To address this, we introduce SPAD. First, we mathematically attribute each token's probability into seven distinct sources: Query, RAG, Past, Current Token, FFN, Final LayerNorm, and Initial Embedding. This attribution quantifies how each source contributes to the generation of the current token. Then, we aggregate these scores by POS tags to quantify how different components drive specific linguistic categories. By identifying anomalies, such as Nouns relying on Final LayerNorm, SPAD effectively detects hallucinations. Extensive experiments demonstrate that SPAD achieves state-of-the-art performance - oai:arXiv.org:2512.07515v1 + Understanding LLM Reasoning for Abstractive Summarization + https://arxiv.org/abs/2512.03503 + arXiv:2512.03503v2 Announce Type: replace +Abstract: While the reasoning capabilities of Large Language Models (LLMs) excel in analytical tasks such as mathematics and code generation, their utility for abstractive summarization remains widely assumed but largely unverified. To bridge this gap, we first tailor general reasoning strategies to the summarization domain. We then conduct a systematic, large scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, assessing both summary quality and faithfulness. Our findings show that reasoning is not a universal solution and its effectiveness is highly dependent on the specific strategy and context. Specifically, we observe a trade-off between summary quality and factual faithfulness: explicit reasoning strategies tend to improve fluency at the expense of factual grounding, while implicit reasoning in LRMs exhibits the inverse pattern. Furthermore, increasing an LRM's internal reasoning budget does not improve, and can even hurt, factual consistency, suggesting that effective summarization demands faithful compression rather than creative over-thinking. + oai:arXiv.org:2512.03503v2 cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pengqian Lu, Jie Lu, Anjin Liu, Guangquan Zhang + Haohan Yuan, Haopeng Zhang - Machine Learning: Progress and Prospects - https://arxiv.org/abs/2512.07519 - arXiv:2512.07519v1 Announce Type: new -Abstract: This Inaugural Lecture was given at Royal Holloway University of London in 1996. It covers an introduction to machine learning and describes various theoretical advances and practical projects in the field. The Lecture here is presented in its original format, but a few remarks have been added in 2025 to reflect recent developments, and the list of references has been updated to enhance the convenience and accuracy for readers. - When did machine learning start? Maybe a good starting point is 1949, when Claude Shannon proposed a learning algorithm for chess-playing programs. Or maybe we should go back to the 1930s when Ronald Fisher developed discriminant analysis - a type of learning where the problem is to construct a decision rule that separates two types of vectors. Or could it be the 18th century when David Hume discussed the idea of induction? Or the 14th century, when William of Ockham formulated the principle of "simplicity" known as "Ockham's razor" (Ockham, by the way, is a small village not far from Royal Holloway). Or it may be that, like almost everything else in Western civilisation and culture, the origin of these ideas lies in the Mediterranean. After all, it was Aristotle who said that "we learn some things only by doing things". - The field of machine learning has been greatly influenced by other disciplines and the subject is in itself not a very homogeneous discipline, but includes separate, overlapping subfields. There are many parallel lines of research in ML: inductive learning, neural networks, clustering, and theories of learning. They are all part of the more general field of machine learning. - oai:arXiv.org:2512.07519v1 + Cross-Space Synergy: A Unified Framework for Multimodal Emotion Recognition in Conversation + https://arxiv.org/abs/2512.03521 + arXiv:2512.03521v2 Announce Type: replace +Abstract: Multimodal Emotion Recognition in Conversation (MERC) aims to predict speakers' emotions by integrating textual, acoustic, and visual cues. Existing approaches either struggle to capture complex cross-modal interactions or experience gradient conflicts and unstable training when using deeper architectures. To address these issues, we propose Cross-Space Synergy (CSS), which couples a representation component with an optimization component. Synergistic Polynomial Fusion (SPF) serves the representation role, leveraging low-rank tensor factorization to efficiently capture high-order cross-modal interactions. Pareto Gradient Modulator (PGM) serves the optimization role, steering updates along Pareto-optimal directions across competing objectives to alleviate gradient conflicts and improve stability. Experiments show that CSS outperforms existing representative methods on IEMOCAP and MELD in both accuracy and training stability, demonstrating its effectiveness in complex multimodal scenarios. + oai:arXiv.org:2512.03521v2 + cs.MM cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alexander Gammerman + Xiaosen Lyu, Jiayu Xiong, Yuren Chen, Wanlong Wang, Xiaoqing Dai, Jing Wang - aLEAKator: HDL Mixed-Domain Simulation for Masked Hardware \& Software Formal Verification - https://arxiv.org/abs/2512.07520 - arXiv:2512.07520v1 Announce Type: new -Abstract: Verifying the security of masked hardware and software implementations, under advanced leakage models, remains a significant challenge, especially then accounting for glitches, transitions and CPU micro-architectural specifics. Existing verification approaches are either restricted to small hardware gadgets, small programs on CPUs such as Sboxes, limited leakage models, or require hardware-specific prior knowledge. In this work, we present aLEAKator, an open-source framework for the automated formal verification of masked cryptographic accelerators and software running on CPUs from their HDL descriptions. Our method introduces mixed-domain simulation, enabling precise modeling and verification under various (including robust and relaxed) 1-probing leakage models, and supports variable signal granularity without being restricted to 1-bit wires. aLEAKator also supports verification in the presence of lookup tables, and does not require prior knowledge of the target CPU architecture. Our approach is validated against existing tools and real-world measurements while providing innovative results such as the verification of a full, first-order masked AES on various CPUs - oai:arXiv.org:2512.07520v1 - cs.AR - cs.CR - cs.SC - Tue, 09 Dec 2025 00:00:00 -0500 - new + On the Temporality for Sketch Representation Learning + https://arxiv.org/abs/2512.04007 + arXiv:2512.04007v2 Announce Type: replace +Abstract: Sketches are simple human hand-drawn abstractions of complex scenes and real-world objects. Although the field of sketch representation learning has advanced significantly, there is still a gap in understanding the true relevance of the temporal aspect to the quality of these representations. This work investigates whether it is indeed justifiable to treat sketches as sequences, as well as which internal orders play a more relevant role. The results indicate that, although the use of traditional positional encodings is valid for modeling sketches as sequences, absolute coordinates consistently outperform relative ones. Furthermore, non-autoregressive decoders outperform their autoregressive counterparts. Finally, the importance of temporality was shown to depend on both the order considered and the task evaluated. + oai:arXiv.org:2512.04007v2 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - No\'e Amiot (ALSOC), Quentin L. Meunier (ALSOC), Karine Heydemann (ALSOC), Emmanuelle Encrenaz (ALSOC) + Marcelo Isaias de Moraes Junior, Moacir Antonelli Ponti - LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings - https://arxiv.org/abs/2512.07522 - arXiv:2512.07522v1 Announce Type: new -Abstract: Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential as a direct training signal remains under-explored. We challenge this status quo and propose LIME (Linguistic Metadata Embeddings), a method that enriches token embeddings with metadata capturing syntax, semantics, and contextual properties. LIME substantially improves pre-training efficiency. Specifically, it adapts up to 56% faster to the training data distribution, while introducing only 0.01% additional parameters at negligible compute overhead. Beyond efficiency, LIME improves tokenization, leading to remarkably stronger language modeling capabilities and generative task performance. These benefits persist across model scales (500M to 2B). In addition, we develop a variant with shifted metadata, LIME+1, that can guide token generation. Given prior metadata for the next token, LIME+1 improves reasoning performance by up to 38% and arithmetic accuracy by up to 35%. - oai:arXiv.org:2512.07522v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Sebastian Sztwiertnia, Felix Friedrich, Kristian Kersting, Patrick Schramowski, Bj\"orn Deiseroth - - - A linear MARS method for three-dimensional interface tracking - https://arxiv.org/abs/2512.07524 - arXiv:2512.07524v1 Announce Type: new -Abstract: For explicit interface tracking in three dimensions, we propose a linear MARS method that (a) represents the interface by a partially ordered set of glued surfaces and approximates each glued surface with a triangular mesh, (b) maintains an $(r,h,\theta)$-regularity on each triangular mesh so that the distance between any pair of adjacent markers is within the range $[rh,h]$ and no angle in any triangle is less than $\theta$, (c) applies to three-dimensional continua with arbitrarily complex topology and geometry, (d) preserves topological structures and geometric features of moving phases under diffeomorphic and isometric flow maps, and (e) achieves second-order and third-order accuracy in terms of the Lagrangian and Eulerian length scales, respectively. Results of classic benchmark tests verify the effectiveness of the novel mesh adjustment algorithms in enforcing the $(r,h,\theta)$-regularity and demonstrate the high accuracy and efficiency of the proposed linear MARS method. - oai:arXiv.org:2512.07524v1 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yunhao Qiu, Qinghai Zhang - - - Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs - https://arxiv.org/abs/2512.07525 - arXiv:2512.07525v1 Announce Type: new -Abstract: Rotary Position Embeddings (RoPE) have become a standard for encoding sequence order in Large Language Models (LLMs) by applying rotations to query and key vectors in the complex plane. Standard implementations, however, utilize only the real component of the complex-valued dot product for attention score calculation. This simplification discards the imaginary component, which contains valuable phase information, leading to a potential loss of relational details crucial for modeling long-context dependencies. In this paper, we propose an extension that re-incorporates this discarded imaginary component. Our method leverages the full complex-valued representation to create a dual-component attention score. We theoretically and empirically demonstrate that this approach enhances the modeling of long-context dependencies by preserving more positional information. Furthermore, evaluations on a suite of long-context language modeling benchmarks show that our method consistently improves performance over the standard RoPE, with the benefits becoming more significant as context length increases. The code is available at https://github.com/OpenMOSS/rope_pp. - oai:arXiv.org:2512.07525v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaoran Liu, Yuerong Song, Zhigeng Liu, Zengfeng Huang, Qipeng Guo, Zhaoxiang Liu, Shiguo Lian, Ziwei He, Xipeng Qiu - - - From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images - https://arxiv.org/abs/2512.07527 - arXiv:2512.07527v1 Announce Type: new -Abstract: City-scale 3D reconstruction from satellite imagery presents the challenge of extreme viewpoint extrapolation, where our goal is to synthesize ground-level novel views from sparse orbital images with minimal parallax. This requires inferring nearly $90^\circ$ viewpoint gaps from image sources with severely foreshortened facades and flawed textures, causing state-of-the-art reconstruction engines such as NeRF and 3DGS to fail. - To address this problem, we propose two design choices tailored for city structures and satellite inputs. First, we model city geometry as a 2.5D height map, implemented as a Z-monotonic signed distance field (SDF) that matches urban building layouts from top-down viewpoints. This stabilizes geometry optimization under sparse, off-nadir satellite views and yields a watertight mesh with crisp roofs and clean, vertically extruded facades. Second, we paint the mesh appearance from satellite images via differentiable rendering techniques. While the satellite inputs may contain long-range, blurry captures, we further train a generative texture restoration network to enhance the appearance, recovering high-frequency, plausible texture details from degraded inputs. - Our method's scalability and robustness are demonstrated through extensive experiments on large-scale urban reconstruction. For example, in our teaser figure, we reconstruct a $4\,\mathrm{km}^2$ real-world region from only a few satellite images, achieving state-of-the-art performance in synthesizing photorealistic ground views. The resulting models are not only visually compelling but also serve as high-fidelity, application-ready assets for downstream tasks like urban planning and simulation. - oai:arXiv.org:2512.07527v1 - cs.CV - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fei Yu, Yu Liu, Luyang Tang, Mingchao Sun, Zengye Ge, Rui Bu, Yuchao Jin, Haisen Zhao, He Sun, Yangyan Li, Mu Xu, Wenzheng Chen, Baoquan Chen - - - Model-Based Reinforcement Learning Under Confounding - https://arxiv.org/abs/2512.07528 - arXiv:2512.07528v1 Announce Type: new -Abstract: We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset. In such settings, conventional model-learning methods are fundamentally inconsistent, as the transition and reward mechanisms generated under a behavioral policy do not correspond to the interventional quantities required for evaluating a state-based policy. To address this issue, we adapt a proximal off-policy evaluation approach that identifies the confounded reward expectation using only observable state-action-reward trajectories under mild invertibility conditions on proxy variables. When combined with a behavior-averaged transition model, this construction yields a surrogate MDP whose Bellman operator is well defined and consistent for state-based policies, and which integrates seamlessly with the maximum causal entropy (MaxCausalEnt) model-learning framework. The proposed formulation enables principled model learning and planning in confounded environments where contextual information is unobserved, unavailable, or impractical to collect. - oai:arXiv.org:2512.07528v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nishanth Venkatesh, Andreas A. Malikopoulos - - - VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection - https://arxiv.org/abs/2512.07533 - arXiv:2512.07533v1 Announce Type: new -Abstract: We propose VulnLLM-R, the~\emph{first specialized reasoning LLM} for vulnerability detection. Our key insight is that LLMs can reason about program states and analyze the potential vulnerabilities, rather than simple pattern matching. This can improve the model's generalizability and prevent learning shortcuts. However, SOTA reasoning LLMs are typically ultra-large, closed-source, or have limited performance in vulnerability detection. To address this, we propose a novel training recipe with specialized data selection, reasoning data generation, reasoning data filtering and correction, and testing-phase optimization. Using our proposed methodology, we train a reasoning model with seven billion parameters. Through extensive experiments on SOTA datasets across Python, C/C++, and Java, we show that VulnLLM-R has superior effectiveness and efficiency than SOTA static analysis tools and both open-source and commercial large reasoning models. We further conduct a detailed ablation study to validate the key designs in our training recipe. Finally, we construct an agent scaffold around our model and show that it outperforms CodeQL and AFL++ in real-world projects. Our agent further discovers a set of zero-day vulnerabilities in actively maintained repositories. This work represents a pioneering effort to enable real-world, project-level vulnerability detection using AI agents powered by specialized reasoning models. The code is available at~\href{https://github.com/ucsb-mlsec/VulnLLM-R}{github}. - oai:arXiv.org:2512.07533v1 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yuzhou Nie, Hongwei Li, Chengquan Guo, Ruizhe Jiang, Zhun Wang, Bo Li, Dawn Song, Wenbo Guo - - - Bandwidth-Aware Network Topology Optimization for Decentralized Learning - https://arxiv.org/abs/2512.07536 - arXiv:2512.07536v1 Announce Type: new -Abstract: Network topology is critical for efficient parameter synchronization in distributed learning over networks. However, most existing studies do not account for bandwidth limitations in network topology design. In this paper, we propose a bandwidth-aware network topology optimization framework to maximize consensus speed under edge cardinality constraints. For heterogeneous bandwidth scenarios, we introduce a maximum bandwidth allocation strategy for the edges to ensure efficient communication among nodes. By reformulating the problem into an equivalent Mixed-Integer SDP problem, we leverage a computationally efficient ADMM-based method to obtain topologies that yield the maximum consensus speed. Within the ADMM substep, we adopt the conjugate gradient method to efficiently solve large-scale linear equations to achieve better scalability. Experimental results demonstrate that the resulting network topologies outperform the benchmark topologies in terms of consensus speed, and reduce the training time required for decentralized learning tasks on real-world datasets to achieve the target test accuracy, exhibiting speedups of more than $1.11\times$ and $1.21\times$ for homogeneous and heterogeneous bandwidth settings, respectively. - oai:arXiv.org:2512.07536v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yipeng Shen, Zehan Zhu, Yan Huang, Changzhi Yan, Cheng Zhuo, Jinming Xu - - - SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents - https://arxiv.org/abs/2512.07538 - arXiv:2512.07538v1 Announce Type: new -Abstract: Recognizing semantic differences across documents, especially in different languages, is crucial for text generation evaluation and multilingual content alignment. However, as a standalone task it has received little attention. We address this by introducing SwissGov-RSD, the first naturalistic, document-level, cross-lingual dataset for semantic difference recognition. It encompasses a total of 224 multi-parallel documents in English-German, English-French, and English-Italian with token-level difference annotations by human annotators. We evaluate a variety of open-source and closed source large language models as well as encoder models across different fine-tuning settings on this new benchmark. Our results show that current automatic approaches perform poorly compared to their performance on monolingual, sentence-level, and synthetic benchmarks, revealing a considerable gap for both LLMs and encoder models. We make our code and datasets publicly available. - oai:arXiv.org:2512.07538v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Michelle Wastl, Jannis Vamvas, Rico Sennrich - - - FRWKV:Frequency-Domain Linear Attention for Long-Term Time Series Forecasting - https://arxiv.org/abs/2512.07539 - arXiv:2512.07539v1 Announce Type: new -Abstract: Traditional Transformers face a major bottleneck in long-sequence time series forecasting due to their quadratic complexity $(\mathcal{O}(T^2))$ and their limited ability to effectively exploit frequency-domain information. Inspired by RWKV's $\mathcal{O}(T)$ linear attention and frequency-domain modeling, we propose FRWKV, a frequency-domain linear-attention framework that overcomes these limitations. Our model integrates linear attention mechanisms with frequency-domain analysis, achieving $\mathcal{O}(T)$ computational complexity in the attention path while exploiting spectral information to enhance temporal feature representations for scalable long-sequence modeling. Across eight real-world datasets, FRWKV achieves a first-place average rank. Our ablation studies confirm the critical roles of both the linear attention and frequency-encoder components. This work demonstrates the powerful synergy between linear attention and frequency analysis, establishing a new paradigm for scalable time series modeling. Code is available at this repository: https://github.com/yangqingyuan-byte/FRWKV. - oai:arXiv.org:2512.07539v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Qingyuan Yang, Shizhuo, Dongyue Chen, Da Teng, Zehua Gan - - - Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation - https://arxiv.org/abs/2512.07540 - arXiv:2512.07540v1 Announce Type: new -Abstract: Error Span Detection (ESD) is a subtask of automatic machine translation evaluation that localizes error spans in translations and labels their severity. State-of-the-art generative ESD methods typically decode using Maximum a Posteriori (MAP), assuming that model-estimated probabilities are perfectly correlated with similarity to human annotation. However, we observed that annotations dissimilar to the human annotation could achieve a higher model likelihood than the human annotation. We address this issue by applying Minimum Bayes Risk (MBR) decoding to generative ESD models. Specifically, we employ sentence- and span-level similarity metrics as utility functions to select candidate hypotheses based on their approximate similarity to the human annotation. Extensive experimental results show that our MBR decoding outperforms the MAP baseline at the system, sentence, and span-levels. Furthermore, to mitigate the computational cost of MBR decoding, we demonstrate that applying MBR distillation enables a standard greedy model to match MBR decoding performance, effectively eliminating the inference-time latency bottleneck. - oai:arXiv.org:2512.07540v1 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Boxuan Lyu, Haiyue Song, Hidetaka Kamigaito, Chenchen Ding, Hideki Tanaka, Masao Utiyama, Kotaro Funakoshi, Manabu Okumura - - - RRAEDy: Adaptive Latent Linearization of Nonlinear Dynamical Systems - https://arxiv.org/abs/2512.07542 - arXiv:2512.07542v1 Announce Type: new -Abstract: Most existing latent-space models for dynamical systems require fixing the latent dimension in advance, they rely on complex loss balancing to approximate linear dynamics, and they don't regularize the latent variables. We introduce RRAEDy, a model that removes these limitations by discovering the appropriate latent dimension, while enforcing both regularized and linearized dynamics in the latent space. Built upon Rank-Reduction Autoencoders (RRAEs), RRAEDy automatically rank and prune latent variables through their singular values while learning a latent Dynamic Mode Decomposition (DMD) operator that governs their temporal progression. This structure-free yet linearly constrained formulation enables the model to learn stable and low-dimensional dynamics without auxiliary losses or manual tuning. We provide theoretical analysis demonstrating the stability of the learned operator and showcase the generality of our model by proposing an extension that handles parametric ODEs. Experiments on canonical benchmarks, including the Van der Pol oscillator, Burgers' equation, 2D Navier-Stokes, and Rotating Gaussians, show that RRAEDy achieves accurate and robust predictions. Our code is open-source and available at https://github.com/JadM133/RRAEDy. We also provide a video summarizing the main results at https://youtu.be/ox70mSSMGrM. - oai:arXiv.org:2512.07542v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Jad Mounayer, Sebastian Rodriguez, Jerome Tomezyk, Chady Ghnatios, Francisco Chinesta - - - Most over-representation of phonological features in basic vocabulary disappears when controlling for spatial and phylogenetic effects - https://arxiv.org/abs/2512.07543 - arXiv:2512.07543v1 Announce Type: new -Abstract: The statistical over-representation of phonological features in the basic vocabulary of languages is often interpreted as reflecting potentially universal sound symbolic patterns. However, most of those results have not been tested explicitly for reproducibility and might be prone to biases in the study samples or models. Many studies on the topic do not adequately control for genealogical and areal dependencies between sampled languages, casting doubts on the robustness of the results. In this study, we test the robustness of a recent study on sound symbolism of basic vocabulary concepts which analyzed245 languages.The new sample includes data on 2864 languages from Lexibank. We modify the original model by adding statistical controls for spatial and phylogenetic dependencies between languages. The new results show that most of the previously observed patterns are not robust, and in fact many patterns disappear completely when adding the genealogical and areal controls. A small number of patterns, however, emerges as highly stable even with the new sample. Through the new analysis, we are able to assess the distribution of sound symbolism on a larger scale than previously. The study further highlights the need for testing all universal claims on language for robustness on various levels. - oai:arXiv.org:2512.07543v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Frederic Blum - - - MoCoRP: Modeling Consistent Relations between Persona and Response for Persona-based Dialogue - https://arxiv.org/abs/2512.07544 - arXiv:2512.07544v1 Announce Type: new -Abstract: As dialogue systems become increasingly important across various domains, a key challenge in persona-based dialogue is generating engaging and context-specific interactions while ensuring the model acts with a coherent personality. However, existing persona-based dialogue datasets lack explicit relations between persona sentences and responses, which makes it difficult for models to effectively capture persona information. To address these issues, we propose MoCoRP (Modeling Consistent Relations between Persona and Response), a framework that incorporates explicit relations into language models. MoCoRP leverages an NLI expert to explicitly extract the NLI relations between persona sentences and responses, enabling the model to effectively incorporate appropriate persona information from the context into its responses. We applied this framework to pre-trained models like BART and further extended it to modern large language models (LLMs) through alignment tuning. Experimental results on the public datasets ConvAI2 and MPChat demonstrate that MoCoRP outperforms existing baselines, achieving superior persona consistency and engaging, context-aware dialogue generation. Furthermore, our model not only excels in quantitative metrics but also shows significant improvements in qualitative aspects. These results highlight the effectiveness of explicitly modeling persona-response relations in persona-based dialogue. The source codes of MoCoRP are available at https://github.com/DMCB-GIST/MoCoRP. - oai:arXiv.org:2512.07544v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Kyungro Lee, Dongha Choi, Hyunju Lee - - - Data-Driven Robust Safety Verification for Markov Decision Processes - https://arxiv.org/abs/2512.07550 - arXiv:2512.07550v1 Announce Type: new -Abstract: In this paper, we propose a data-driven robust safety verification framework for stochastic dynamical systems modeled as Markov decision processes with time-varying and uncertain transition probabilities. Rather than assuming access to the exact nominal transition kernel, we consider the realistic setting where only samples from multiple system executions are available. These samples may correspond to different transition models inside an ambiguity set around the nominal transition kernel. Using these observations, we construct a unified ambiguity set that captures both inherent run-to-run variability in the transition dynamics and finite-sample statistical uncertainty. This ambiguity set is formalized through a Wasserstein-distance ball around a nominal empirical distribution and naturally induces an interval Markov decision process representation of the underlying system. Within this representation, we introduce a robust safety function that characterizes reach-avoid type probabilistic safety under all transition kernels consistent with the interval Markov decision process. We further derive high-confidence safety guarantees for the true, unknown time-varying system. A numerical example illustrates the applicability and effectiveness of the proposed approach. - oai:arXiv.org:2512.07550v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Abhijit Mazumdar, Manuela L. Bujorianu, Rafal Wisniewski - - - Performance of the SafeTerm AI-Based MedDRA Query System Against Standardised MedDRA Queries - https://arxiv.org/abs/2512.07552 - arXiv:2512.07552v1 Announce Type: new -Abstract: In pre-market drug safety review, grouping related adverse event terms into SMQs or OCMQs is critical for signal detection. We assess the performance of SafeTerm Automated Medical Query (AMQ) on MedDRA SMQs. The AMQ is a novel quantitative artificial intelligence system that understands and processes medical terminology and automatically retrieves relevant MedDRA Preferred Terms (PTs) for a given input query, ranking them by a relevance score (0-1) using multi-criteria statistical methods. The system (SafeTerm) embeds medical query terms and MedDRA PTs in a multidimensional vector space, then applies cosine similarity, and extreme-value clustering to generate a ranked list of PTs. Validation was conducted against tier-1 SMQs (110 queries, v28.1). Precision, recall and F1 were computed at multiple similarity-thresholds, defined either manually or using an automated method. High recall (94%)) is achieved at moderate similarity thresholds, indicative of good retrieval sensitivity. Higher thresholds filter out more terms, resulting in improved precision (up to 89%). The optimal threshold (0.70)) yielded an overall recall of (48%) and precision of (45%) across all 110 queries. Restricting to narrow-term PTs achieved slightly better performance at an increased (+0.05) similarity threshold, confirming increased relatedness of narrow versus broad terms. The automatic threshold (0.66) selection prioritizes recall (0.58) to precision (0.29). SafeTerm AMQ achieves comparable, satisfactory performance on SMQs and sanitized OCMQs. It is therefore a viable supplementary method for automated MedDRA query generation, balancing recall and precision. We recommend using suitable MedDRA PT terminology in query formulation and applying the automated threshold method to optimise recall. Increasing similarity scores allows refined, narrow terms selection. - oai:arXiv.org:2512.07552v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla, Elena Hadjicosta - - - ReLaX: Reasoning with Latent Exploration for Large Reasoning Models - https://arxiv.org/abs/2512.07558 - arXiv:2512.07558v1 Announce Type: new -Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated remarkable potential in enhancing the reasoning capability of Large Reasoning Models (LRMs). However, RLVR often leads to entropy collapse, resulting in premature policy convergence and performance saturation. While manipulating token-level entropy has proven effective for promoting policy exploration, we argue that the latent dynamics underlying token generation encode a far richer computational structure for steering policy optimization toward a more effective exploration-exploitation tradeoff. To enable tractable analysis and intervention of the latent dynamics of LRMs, we leverage Koopman operator theory to obtain a linearized representation of their hidden-state dynamics. This enables us to introduce Dynamic Spectral Dispersion (DSD), a new metric to quantify the heterogeneity of the model's latent dynamics, serving as a direct indicator of policy exploration. Building upon these foundations, we propose Reasoning with Latent eXploration (ReLaX), a paradigm that explicitly incorporates latent dynamics to regulate exploration and exploitation during policy optimization. Comprehensive experiments across a wide range of multimodal and text-only reasoning benchmarks show that ReLaX significantly mitigates premature convergence and consistently achieves state-of-the-art performance. - oai:arXiv.org:2512.07558v1 - cs.LG - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Shimin Zhang, Xianwei Chen, Yufan Shen, Ziyuan Ye, Jibin Wu - - - Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models - https://arxiv.org/abs/2512.07564 - arXiv:2512.07564v1 Announce Type: new -Abstract: Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through uncertainty-guided visual re-attention. Our method combines multidimensional uncertainty quantification (token entropy, attention dispersion, semantic consistency, claim confidence) with attention-guided cropping of under-explored regions. Operating entirely with frozen, pretrained VLMs, our framework requires no gradient updates. We validate our approach on the POPE and MMHAL BENCH benchmarks using the Qwen2.5-VL-7B [23] architecture. Experimental results demonstrate that our method reduces hallucination rates by 9.8 percentage points compared to the baseline, while improving object existence accuracy by 4.7 points on adversarial splits. Furthermore, qualitative analysis confirms that uncertainty-guided re-attention successfully grounds corrections in visual evidence where standard decoding fails. We validate our approach on Qwen2.5-VL-7B [23], with plans to extend validation across diverse architectures in future versions. We release our code and methodology to facilitate future research in trustworthy multimodal systems. - oai:arXiv.org:2512.07564v1 - cs.CV - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kassoum Sanogo, Renzo Ardiccioni - - - Dual-Stream Cross-Modal Representation Learning via Residual Semantic Decorrelation - https://arxiv.org/abs/2512.07568 - arXiv:2512.07568v1 Announce Type: new -Abstract: Cross-modal learning has become a fundamental paradigm for integrating heterogeneous information sources such as images, text, and structured attributes. However, multimodal representations often suffer from modality dominance, redundant information coupling, and spurious cross-modal correlations, leading to suboptimal generalization and limited interpretability. In particular, high-variance modalities tend to overshadow weaker but semantically important signals, while na\"ive fusion strategies entangle modality-shared and modality-specific factors in an uncontrolled manner. This makes it difficult to understand which modality actually drives a prediction and to maintain robustness when some modalities are noisy or missing. To address these challenges, we propose a Dual-Stream Residual Semantic Decorrelation Network (DSRSD-Net), a simple yet effective framework that disentangles modality-specific and modality-shared information through residual decomposition and explicit semantic decorrelation constraints. DSRSD-Net introduces: (1) a dual-stream representation learning module that separates intra-modal (private) and inter-modal (shared) latent factors via residual projection; (2) a residual semantic alignment head that maps shared factors from different modalities into a common space using a combination of contrastive and regression-style objectives; and (3) a decorrelation and orthogonality loss that regularizes the covariance structure of the shared space while enforcing orthogonality between shared and private streams, thereby suppressing cross-modal redundancy and preventing feature collapse. Experimental results on two large-scale educational benchmarks demonstrate that DSRSD-Net consistently improves next-step prediction and final outcome prediction over strong single-modality, early-fusion, late-fusion, and co-attention baselines. - oai:arXiv.org:2512.07568v1 - cs.CV - cs.AI - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuecheng Li, Weikuan Jia, Alisher Kurbonaliev, Qurbonaliev Alisher, Khudzhamkulov Rustam, Ismoilov Shuhratjon, Eshmatov Javhariddin, Yuanjie Zheng - - - Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting - https://arxiv.org/abs/2512.07569 - arXiv:2512.07569v1 Announce Type: new -Abstract: Reliable forecasting of multivariate time series under anomalous conditions is crucial in applications such as ATM cash logistics, where sudden demand shifts can disrupt operations. Modern deep forecasters achieve high accuracy on normal data but often fail when distribution shifts occur. We propose Weighted Contrastive Adaptation (WECA), a Weighted contrastive objective that aligns normal and anomaly-augmented representations, preserving anomaly-relevant information while maintaining consistency under benign variations. Evaluations on a nationwide ATM transaction dataset with domain-informed anomaly injection show that WECA improves SMAPE on anomaly-affected data by 6.1 percentage points compared to a normally trained baseline, with negligible degradation on normal data. These results demonstrate that WECA enhances forecasting reliability under anomalies without sacrificing performance during regular operations. - oai:arXiv.org:2512.07569v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Joel Ekstrand, Tor Mattsson, Zahra Taghiyarrenani, Slawomir Nowaczyk, Jens Lundstr\"om, Mikael Lind\'en - - - A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification - https://arxiv.org/abs/2512.07571 - arXiv:2512.07571v1 Announce Type: new -Abstract: This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings from audio with text is the large length of the audio sequence compared to the text one. Our method benefits from an existing speech tokenizer trained for Audio Speech Recognition that output long sequences of tokens from a large vocabulary, making it difficult to integrate it at low cost in a large language model. By applying a simple lasso-based feature selection on multimodal Bag-of-Words representation, we retain only the most important audio tokens for the task, and adapt the language model to them with a self-supervised language modeling objective, before fine-tuning it on the downstream task. We show this helps to improve the performances compared to an unimodal model, to a bigger SpeechLM or to integrating audio via a learned representation. We show the effectiveness of our method on two recent Argumentative Fallacy Detection and Classification tasks where the use of audio was believed counterproductive, reaching state-of-the-art results. We also provide an in-depth analysis of the method, showing that even a random audio token selection helps enhancing the unimodal model. Our code is available [online](https://github.com/salocinc/EACL26SpeechTokFallacy/). - oai:arXiv.org:2512.07571v1 - cs.CL - cs.MM - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Nicolas Calbucura, Valentin Barriere - - - Property Testing of Computational Networks - https://arxiv.org/abs/2512.07577 - arXiv:2512.07577v1 Announce Type: new -Abstract: In this paper we initiate the study of \emph{property testing of weighted computational networks viewed as computational devices}. Our goal is to design property testing algorithms that for a given computational network with oracle access to the weights of the network, accept (with probability at least $\frac23$) any network that computes a certain function (or a function with a certain property) and reject (with probability at least $\frac23$) any network that is \emph{far} from computing the function (or any function with the given property). We parameterize the notion of being far and want to reject networks that are \emph{$(\epsilon,\delta)$-far}, which means that one needs to change an $\epsilon$-fraction of the description of the network to obtain a network that computes a function that differs in at most a $\delta$-fraction of inputs from the desired function (or any function with a given property). - To exemplify our framework, we present a case study involving simple neural Boolean networks with ReLU activation function. As a highlight, we demonstrate that for such networks, any near constant function is testable in query complexity independent of the network's size. We also show that a similar result cannot be achieved in a natural generalization of the distribution-free model to our setting, and also in a related vanilla testing model. - oai:arXiv.org:2512.07577v1 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Artur Czumaj, Christian Sohler - - - All You Need Are Random Visual Tokens? Demystifying Token Pruning in VLLMs - https://arxiv.org/abs/2512.07580 - arXiv:2512.07580v1 Announce Type: new -Abstract: Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however, identifies a key observation: in deeper layers (e.g., beyond the 20th), existing training-free pruning methods perform no better than random pruning. We hypothesize that this degradation is caused by "vanishing token information", where visual tokens progressively lose their salience with increasing network depth. To validate this hypothesis, we quantify a token's information content by measuring the change in the model output probabilities upon its removal. Using this proposed metric, our analysis of the information of visual tokens across layers reveals three key findings: (1) As layers deepen, the information of visual tokens gradually becomes uniform and eventually vanishes at an intermediate layer, which we term as "information horizon", beyond which the visual tokens become redundant; (2) The position of this horizon is not static; it extends deeper for visually intensive tasks, such as Optical Character Recognition (OCR), compared to more general tasks like Visual Question Answering (VQA); (3) This horizon is also strongly correlated with model capacity, as stronger VLLMs (e.g., Qwen2.5-VL) employ deeper visual tokens than weaker models (e.g., LLaVA-1.5). Based on our findings, we show that simple random pruning in deep layers efficiently balances performance and efficiency. Moreover, integrating random pruning consistently enhances existing methods. Using DivPrune with random pruning achieves state-of-the-art results, maintaining 96.9% of Qwen-2.5-VL-7B performance while pruning 50% of visual tokens. The code will be publicly available at https://github.com/YahongWang1/Information-Horizon. - oai:arXiv.org:2512.07580v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yahong Wang, Juncheng Wu, Zhangkai Ni, Longzhen Yang, Yihang Liu, Chengmei Yang, Ying Wen, Xianfeng Tang, Hui Liu, Yuyin Zhou, Lianghua He - - - See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations - https://arxiv.org/abs/2512.07582 - arXiv:2512.07582v1 Announce Type: new -Abstract: Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing approaches still exhibit limited generalization to tasks beyond their training distributions. In contrast, humans possess remarkable proficiency in acquiring novel skills by simply observing others performing them once. Inspired by this capability, we propose ViVLA, a generalist robotic manipulation policy that achieves efficient task learning from a single expert demonstration video at test time. Our approach jointly processes an expert demonstration video alongside the robot's visual observations to predict both the demonstrated action sequences and subsequent robot actions, effectively distilling fine-grained manipulation knowledge from expert behavior and transferring it seamlessly to the agent. To enhance the performance of ViVLA, we develop a scalable expert-agent pair data generation pipeline capable of synthesizing paired trajectories from easily accessible human videos, further augmented by curated pairs from publicly available datasets. This pipeline produces a total of 892,911 expert-agent samples for training ViVLA. Experimental results demonstrate that our ViVLA is able to acquire novel manipulation skills from only a single expert demonstration video at test time. Our approach achieves over 30% improvement on unseen LIBERO tasks and maintains above 35% gains with cross-embodiment videos. Real-world experiments demonstrate effective learning from human videos, yielding more than 38% improvement on unseen tasks. - oai:arXiv.org:2512.07582v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Guangyan Chen, Meiling Wang, Qi Shao, Zichen Zhou, Weixin Mao, Te Cui, Minzhao Zhu, Yinan Deng, Luojie Yang, Zhanqi Zhang, Yi Yang, Hua Chen, Yufeng Yue - - - Complementary Learning Approach for Text Classification using Large Language Models - https://arxiv.org/abs/2512.07583 - arXiv:2512.07583v1 Announce Type: new -Abstract: In this study, we propose a structured methodology that utilizes large language models (LLMs) in a cost-efficient and parsimonious manner, integrating the strengths of scholars and machines while offsetting their respective weaknesses. Our methodology, facilitated through a chain of thought and few-shot learning prompting from computer science, extends best practices for co-author teams in qualitative research to human-machine teams in quantitative research. This allows humans to utilize abductive reasoning and natural language to interrogate not just what the machine has done but also what the human has done. Our method highlights how scholars can manage inherent weaknesses OF LLMs using careful, low-cost techniques. We demonstrate how to use the methodology to interrogate human-machine rating discrepancies for a sample of 1,934 press releases announcing pharmaceutical alliances (1990-2017). - oai:arXiv.org:2512.07583v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - 10.2139/ssrn.5577090 - Navid Asgari, Benjamin M. Cole - - - LongCat-Image Technical Report - https://arxiv.org/abs/2512.07584 - arXiv:2512.07584v1 Announce Type: new -Abstract: We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models. 1) We achieve this through rigorous data curation strategies across the pre-training, mid-training, and SFT stages, complemented by the coordinated use of curated reward models during the RL phase. This strategy establishes the model as a new state-of-the-art (SOTA), delivering superior text-rendering capabilities and remarkable photorealism, and significantly enhancing aesthetic quality. 2) Notably, it sets a new industry standard for Chinese character rendering. By supporting even complex and rare characters, it outperforms both major open-source and commercial solutions in coverage, while also achieving superior accuracy. 3) The model achieves remarkable efficiency through its compact design. With a core diffusion model of only 6B parameters, it is significantly smaller than the nearly 20B or larger Mixture-of-Experts (MoE) architectures common in the field. This ensures minimal VRAM usage and rapid inference, significantly reducing deployment costs. Beyond generation, LongCat-Image also excels in image editing, achieving SOTA results on standard benchmarks with superior editing consistency compared to other open-source works. 4) To fully empower the community, we have established the most comprehensive open-source ecosystem to date. We are releasing not only multiple model versions for text-to-image and image editing, including checkpoints after mid-training and post-training stages, but also the entire toolchain of training procedure. We believe that the openness of LongCat-Image will provide robust support for developers and researchers, pushing the frontiers of visual content creation. - oai:arXiv.org:2512.07584v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Meituan LongCat Team, Hanghang Ma, Haoxian Tan, Jiale Huang, Junqiang Wu, Jun-Yan He, Lishuai Gao, Songlin Xiao, Xiaoming Wei, Xiaoqi Ma, Xunliang Cai, Yayong Guan, Jie Hu - - - Optimal Pulse Patterns through a Hybrid Optimal Control Perspective - https://arxiv.org/abs/2512.07585 - arXiv:2512.07585v1 Announce Type: new -Abstract: Optimal pulse patterns (OPPs) are a modulation method in which the switching angles and levels of a switching signal are computed via an offline optimization procedure to minimize a performance metric, typically the harmonic distortions of the load current. Additional constraints can be incorporated into the optimization problem to achieve secondary objectives, such as the limitation of specific harmonics or the reduction of power converter losses. The resulting optimization problem, however, is highly nonconvex, featuring a trigonometric objective function and constraints as well as both real- and integer-valued optimization variables. This work casts the task of OPP synthesis for a multilevel converter as an optimal control problem of a hybrid system. This problem is in turn lifted into a convex but infinite-dimensional conic program of occupation measures using established methods in convex relaxations of optimal control. Lower bounds on the minimum achievable harmonic distortion are acquired by solving a sequence of semidefinite programs via the moment-sum-of-squares hierarchy, where each semidefinite program scales in a jointly linear manner with the numbers of permitted switching transitions and converter voltage levels. - oai:arXiv.org:2512.07585v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jared Miller, Petros Karamanakos - - - Understanding Individual Decision-Making in Multi-Agent Reinforcement Learning: A Dynamical Systems Approach - https://arxiv.org/abs/2512.07588 - arXiv:2512.07588v1 Announce Type: new -Abstract: Analysing learning behaviour in Multi-Agent Reinforcement Learning (MARL) environments is challenging, in particular with respect to \textit{individual} decision-making. Practitioners frequently tend to study or compare MARL algorithms from a qualitative perspective largely due to the inherent stochasticity in practical algorithms arising from random dithering exploration strategies, environment transition noise, and stochastic gradient updates to name a few. Traditional analytical approaches, such as replicator dynamics, often rely on mean-field approximations to remove stochastic effects, but this simplification, whilst able to provide general overall trends, might lead to dissonance between analytical predictions and actual realisations of individual trajectories. In this paper, we propose a novel perspective on MARL systems by modelling them as \textit{coupled stochastic dynamical systems}, capturing both agent interactions and environmental characteristics. Leveraging tools from dynamical systems theory, we analyse the stability and sensitivity of agent behaviour at individual level, which are key dimensions for their practical deployments, for example, in presence of strict safety requirements. This framework allows us, for the first time, to rigorously study MARL dynamics taking into consideration their inherent stochasticity, providing a deeper understanding of system behaviour and practical insights for the design and control of multi-agent learning processes. - oai:arXiv.org:2512.07588v1 - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - James Rudd-Jones, Mar\'ia P\'erez-Ortiz, Mirco Musolesi - - - Robust Variational Model Based Tailored UNet: Leveraging Edge Detector and Mean Curvature for Improved Image Segmentation - https://arxiv.org/abs/2512.07590 - arXiv:2512.07590v1 Announce Type: new -Abstract: To address the challenge of segmenting noisy images with blurred or fragmented boundaries, this paper presents a robust version of Variational Model Based Tailored UNet (VM_TUNet), a hybrid framework that integrates variational methods with deep learning. The proposed approach incorporates physical priors, an edge detector and a mean curvature term, into a modified Cahn-Hilliard equation, aiming to combine the interpretability and boundary-smoothing advantages of variational partial differential equations (PDEs) with the strong representational ability of deep neural networks. The architecture consists of two collaborative modules: an F module, which conducts efficient frequency domain preprocessing to alleviate poor local minima, and a T module, which ensures accurate and stable local computations, backed by a stability estimate. Extensive experiments on three benchmark datasets indicate that the proposed method achieves a balanced trade-off between performance and computational efficiency, which yields competitive quantitative results and improved visual quality compared to pure convolutional neural network (CNN) based models, while achieving performance close to that of transformer-based method with reasonable computational expense. - oai:arXiv.org:2512.07590v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Kaili Qi, Zhongyi Huang, Wenli Yang - - - Extended formulations for the maximum weighted co-2-plex problem - https://arxiv.org/abs/2512.07592 - arXiv:2512.07592v1 Announce Type: new -Abstract: Given an input graph and weights on its vertices, the maximum co-2-plex problem is to find a subset of vertices maximizing the sum of their weights and inducing a graph of degree at most 1. In this article, we analyze polyhedral aspects of the maximum co-2-plex problem. The co-2-plexes of a graph are known to be in bijection with the stable sets of an auxiliary graph called the utter graph~\cite{dupontbouillard2024contractions}. We use this bijection to characterize contraction perfect graphs' co-2-plex polytopes in an extended space. It turns out that the total dual integrality of the associated linear system also characterizes contraction perfectness of the input graph. - By projecting this extended space formulation, we obtain the natural variable space description of the co-2-plex polytopes of trees. This projection yields a new family of valid inequalities for the co-2-plex polytope and we characterize when they define facets. Moreover, we show that these inequalities can be separated in polynomial time. We characterize the graphs for which this formulation describes an integer polytope. - These linear systems are extended to valid integer linear programs (ILPs) for the maximum co-2-plex problem whose linear relaxation values are tighter than the state of the art for this problem~\cite{bala}. Finally, we provide an experimental comparison of several implementations of our new ILP formulations with the state-of-the-art ILP for this problem and analyze their respective performances relatively to the density of the input graphs. - oai:arXiv.org:2512.07592v1 - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Alexandre Dupont-Bouillard, Pierre Fouilhoux, Roland Grappe, Mathieu Lacroix - - - Specializing anti-unification for interaction models composition via gate connections - https://arxiv.org/abs/2512.07595 - arXiv:2512.07595v1 Announce Type: new -Abstract: Interaction models describe distributed systems as algebraic terms, with gates marking interaction points between local views. Composing local models into a coherent global one requires aligning these gates while respecting the algebraic laws of interaction operators. We specialize anti-unification (or generalization) via a special constant-preserving variant, which preserves designated constants while generalizing the remaining structure. We develop a dedicated rule-based procedure for computing these generalizations, prove its termination, soundness, and completeness, extend it modulo equational theories, and integrate it into a standard anti-unification framework. A prototype tool demonstrates the approach's ability to recompose global interactions from partial views. - oai:arXiv.org:2512.07595v1 - cs.FL - cs.SC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Joel Nguetoum (Paris-Saclay University, CEA, List, Palaiseau, France, Paris-Saclay University, CentraleSupelec, MICS, Gif-sur-Yvette, France), Boutheina Bannour (Paris-Saclay University, CEA, List, Palaiseau, France), Pascale Le Gall (Paris-Saclay University, CentraleSupelec, MICS, Gif-sur-Yvette, France), Erwan Mahe (Paris-Saclay University, CEA, List, Palaiseau, France) - - - More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery - https://arxiv.org/abs/2512.07596 - arXiv:2512.07596v1 Announce Type: new -Abstract: The recent Segment Anything Model (SAM) 3 has introduced significant advancements over its predecessor, SAM 2, particularly with the integration of language-based segmentation and enhanced 3D perception capabilities. SAM 3 supports zero-shot segmentation across a wide range of prompts, including point, bounding box, and language-based prompts, allowing for more flexible and intuitive interactions with the model. In this empirical evaluation, we assess the performance of SAM 3 in robot-assisted surgery, benchmarking its zero-shot segmentation with point and bounding box prompts and exploring its effectiveness in dynamic video tracking, alongside its newly introduced language prompt segmentation. While language prompts show potential, their performance in the surgical domain is currently suboptimal, highlighting the need for further domain-specific training. Additionally, we investigate SAM 3's 3D reconstruction abilities, demonstrating its capacity to process surgical scene data and reconstruct 3D anatomical structures from 2D images. Through comprehensive testing on the MICCAI EndoVis 2017 and EndoVis 2018 benchmarks, SAM 3 shows clear improvements over SAM and SAM 2 in both image and video segmentation under spatial prompts, while zero-shot evaluations on SCARED, StereoMIS, and EndoNeRF indicate strong monocular depth estimation and realistic 3D instrument reconstruction, yet also reveal remaining limitations in complex, highly dynamic surgical scenes. - oai:arXiv.org:2512.07596v1 - cs.CV - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wenzhen Dong, Jieming Yu, Yiming Huang, Hongqiu Wang, Lei Zhu, Albert C. S. Chung, Hongliang Ren, Long Bai - - - Online Segment Any 3D Thing as Instance Tracking - https://arxiv.org/abs/2512.07599 - arXiv:2512.07599v1 Announce Type: new -Abstract: Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to aggregate semantic information from Vision Foundation Models (VFMs) outputs that are lifted into 3D point clouds, facilitating spatial information propagation through inter-query interactions. Nevertheless, perception is an inherently dynamic process, rendering temporal understanding a critical yet overlooked dimension within these prevailing query-based pipelines. Therefore, to further unlock the temporal environmental perception capabilities of embodied agents, our work reconceptualizes online 3D segmentation as an instance tracking problem (AutoSeg3D). Our core strategy involves utilizing object queries for temporal information propagation, where long-term instance association promotes the coherence of features and object identities, while short-term instance update enriches instant observations. Given that viewpoint variations in embodied robotics often lead to partial object visibility across frames, this mechanism aids the model in developing a holistic object understanding beyond incomplete instantaneous views. Furthermore, we introduce spatial consistency learning to mitigate the fragmentation problem inherent in VFMs, yielding more comprehensive instance information for enhancing the efficacy of both long-term and short-term temporal learning. The temporal information exchange and consistency learning facilitated by these sparse object queries not only enhance spatial comprehension but also circumvent the computational burden associated with dense temporal point cloud interactions. Our method establishes a new state-of-the-art, surpassing ESAM by 2.8 AP on ScanNet200 and delivering consistent gains on ScanNet, SceneNN, and 3RScan datasets. - oai:arXiv.org:2512.07599v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Hanshi Wang, Zijian Cai, Jin Gao, Yiwei Zhang, Weiming Hu, Ke Wang, Zhipeng Zhang - - - Algorithm-hardware co-design of neuromorphic networks with dual memory pathways - https://arxiv.org/abs/2512.07602 - arXiv:2512.07602v1 Announce Type: new -Abstract: Spiking neural networks excel at event-driven sensing yet maintaining task-relevant context over long timescales. However building these networks in hardware respecting both tight energy and memory budgets, remains a core challenge in the field. We address this challenge through novel algorithm-hardware co-design effort. At the algorithm level, inspired by the cortical fast-slow organization in the brain, we introduce a neural network with an explicit slow memory pathway that, combined with fast spiking activity, enables a dual memory pathway (DMP) architecture in which each layer maintains a compact low-dimensional state that summarizes recent activity and modulates spiking dynamics. This explicit memory stabilizes learning while preserving event-driven sparsity, achieving competitive accuracy on long-sequence benchmarks with 40-60% fewer parameters than equivalent state-of-the-art spiking neural networks. At the hardware level, we introduce a near-memory-compute architecture that fully leverages the advantages of the DMP architecture by retaining its compact shared state while optimizing dataflow, across heterogeneous sparse-spike and dense-memory pathways. We show experimental results that demonstrate more than a 4x increase in throughput and over a 5x improvement in energy efficiency compared with state-of-the-art implementations. Together, these contributions demonstrate that biological principles can guide functional abstractions that are both algorithmically effective and hardware-efficient, establishing a scalable co-design paradigm for real-time neuromorphic computation and learning. - oai:arXiv.org:2512.07602v1 - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pengfei Sun, Zhe Su, Jascha Achterberg, Giacomo Indiveri, Dan F. M. Goodman, Danyal Akarca - - - Decomposition Sampling for Efficient Region Annotations in Active Learning - https://arxiv.org/abs/2512.07606 - arXiv:2512.07606v1 Announce Type: new -Abstract: Active learning improves annotation efficiency by selecting the most informative samples for annotation and model training. While most prior work has focused on selecting informative images for classification tasks, we investigate the more challenging setting of dense prediction, where annotations are more costly and time-intensive, especially in medical imaging. Region-level annotation has been shown to be more efficient than image-level annotation for these tasks. However, existing methods for representative annotation region selection suffer from high computational and memory costs, irrelevant region choices, and heavy reliance on uncertainty sampling. We propose decomposition sampling (DECOMP), a new active learning sampling strategy that addresses these limitations. It enhances annotation diversity by decomposing images into class-specific components using pseudo-labels and sampling regions from each class. Class-wise predictive confidence further guides the sampling process, ensuring that difficult classes receive additional annotations. Across ROI classification, 2-D segmentation, and 3-D segmentation, DECOMP consistently surpasses baseline methods by better sampling minority-class regions and boosting performance on these challenging classes. Code is in https://github.com/JingnaQiu/DECOMP.git. - oai:arXiv.org:2512.07606v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jingna Qiu, Frauke Wilm, Mathias \"Ottl, Jonas Utz, Maja Schlereth, Moritz Schillinger, Marc Aubreville, Katharina Breininger - - - Metric-Fair Prompting: Treating Similar Samples Similarly - https://arxiv.org/abs/2512.07608 - arXiv:2512.07608v1 Announce Type: new -Abstract: We introduce \emph{Metric-Fair Prompting}, a fairness-aware prompting framework that guides large language models (LLMs) to make decisions under metric-fairness constraints. In the application of multiple-choice medical question answering, each {(question, option)} pair is treated as a binary instance with label $+1$ (correct) or $-1$ (incorrect). To promote {individual fairness}~--~treating similar instances similarly~--~we compute question similarity using NLP embeddings and solve items in \emph{joint pairs of similar questions} rather than in isolation. The prompt enforces a global decision protocol: extract decisive clinical features, map each \((\text{question}, \text{option})\) to a score $f(x)$ that acts as confidence, and impose a Lipschitz-style constraint so that similar inputs receive similar scores and, hence, consistent outputs. Evaluated on the {MedQA (US)} benchmark, Metric-Fair Prompting is shown to improve performance over standard single-item prompting, demonstrating that fairness-guided, confidence-oriented reasoning can enhance LLM accuracy on high-stakes clinical multiple-choice questions. - oai:arXiv.org:2512.07608v1 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - NeurIPS 2025 Workshop on Socially Responsible and Trustworthy Foundation Models - Jing Wang, Jie Shen, Xing Niu, Tong Zhang, Jeremy Weiss - - - Obstacle Avoidance of UAV in Dynamic Environments Using Direction and Velocity-Adaptive Artificial Potential Field - https://arxiv.org/abs/2512.07609 - arXiv:2512.07609v1 Announce Type: new -Abstract: The conventional Artificial Potential Field (APF) is fundamentally limited by the local minima issue and its inability to account for the kinematics of moving obstacles. This paper addresses the critical challenge of autonomous collision avoidance for Unmanned Aerial Vehicles (UAVs) operating in dynamic and cluttered airspace by proposing a novel Direction and Relative Velocity Weighted Artificial Potential Field (APF). In this approach, a bounded weighting function, $\omega(\theta,v_{e})$, is introduced to dynamically scale the repulsive potential based on the direction and velocity of the obstacle relative to the UAV. This robust APF formulation is integrated within a Model Predictive Control (MPC) framework to generate collision-free trajectories while adhering to kinematic constraints. Simulation results demonstrate that the proposed method effectively resolves local minima and significantly enhances safety by enabling smooth, predictive avoidance maneuvers. The system ensures superior path integrity and reliable performance, confirming its viability for autonomous navigation in complex environments. - oai:arXiv.org:2512.07609v1 - eess.SY - cs.RO - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Nikita Vaibhav Pavle, Shrreya Rajneesh, Rakesh Kumar Sahoo, Manoranjan Sinha - - - Comparative Analysis and Parametric Tuning of PPO, GRPO, and DAPO for LLM Reasoning Enhancement - https://arxiv.org/abs/2512.07611 - arXiv:2512.07611v1 Announce Type: new -Abstract: This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning evaluation: models are first fine-tuned on the specialized Countdown Game and then assessed on a suite of general-purpose reasoning benchmarks. Across all tasks, RL-trained models outperform their corresponding base models, although the degree of improvement differs by benchmark. - Our parametric analysis offers practical guidance for RL-based LLM training. Increasing the group size in GRPO and DAPO leads to more stable training dynamics and higher accuracy, while the impact of the KL-penalty coefficient is non-monotonic. Additionally, we find that the Dynamic Sampling (DS) component in DAPO does not improve performance; in fact, the best overall results are achieved with DAPO when DS is disabled. - oai:arXiv.org:2512.07611v1 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yongsheng Lian - - - PCMind-2.1-Kaiyuan-2B Technical Report - https://arxiv.org/abs/2512.07612 - arXiv:2512.07612v1 Announce Type: new -Abstract: The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relies on closed-source, high-quality data and training recipes. To address this, we introduce PCMind-2.1-Kaiyuan-2B, a fully open-source 2-billion-parameter model focused on improving training efficiency and effectiveness under resource constraints. Our methodology includes three key innovations: a Quantile Data Benchmarking method for systematically comparing heterogeneous open-source datasets and providing insights on data mixing strategies; a Strategic Selective Repetition scheme within a multi-phase paradigm to effectively leverage sparse, high-quality data; and a Multi-Domain Curriculum Training policy that orders samples by quality. Supported by a highly optimized data preprocessing pipeline and architectural modifications for FP16 stability, Kaiyuan-2B achieves performance competitive with state-of-the-art fully open-source models, demonstrating practical and scalable solutions for resource-limited pretraining. We release all assets (including model weights, data, and code) under Apache 2.0 license at https://huggingface.co/thu-pacman/PCMind-2.1-Kaiyuan-2B. - oai:arXiv.org:2512.07612v1 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Kairong Luo, Zhenbo Sun, Xinyu Shi, Shengqi Chen, Bowen Yu, Yunyi Chen, Chenyi Dang, Hengtao Tao, Hui Wang, Fangming Liu, Kaifeng Lyu, Wenguang Chen - - - A Retrospective on Ultrasound Mid-Air Haptics in HCI - https://arxiv.org/abs/2512.07613 - arXiv:2512.07613v1 Announce Type: new -Abstract: In 2013, the UltraHaptics system demonstrated that focused ultrasound could generate perceivable mid-air tactile sensations, building on earlier explorations of airborne ultrasound as a haptic medium. These contributions established ultrasound mid-air haptics (UMH) as a viable interaction modality and laid the technical and perceptual foundations for subsequent advances in Human-Computer Interaction (HCI). In this extended abstract, we revisit this formative work, trace the research and design trajectories it enabled, and reflect on how UMH has supported multisensory interaction, immersion, and inclusion. We also highlight how this line of research exemplifies the value of interdisciplinary collaboration to advance novel interactive technologies. - oai:arXiv.org:2512.07613v1 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Arthur Fleig - - - Approximation Algorithms for the $b$-Matching and List-Restricted Variants of MaxQAP - https://arxiv.org/abs/2512.07618 - arXiv:2512.07618v1 Announce Type: new -Abstract: We study approximation algorithms for two natural generalizations of the Maximum Quadratic Assignment Problem (MaxQAP). In the Maximum List-Restricted Quadratic Assignment Problem, each node in one partite set may only be matched to nodes from a prescribed list. For instances on $n$ nodes where every list has size at least $n - O(\sqrt{n})$, we design a randomized $O(\sqrt{n})$-approximation algorithm based on the linear-programming relaxation and randomized rounding framework of Makarychev, Manokaran, and Sviridenko. In the Maximum Quadratic $b$-Matching Assignment Problem, we seek a $b$-matching that maximizes the MaxQAP objective. We refine the standard MaxQAP relaxation and combine randomized rounding over $b$ independent iterations with a polynomial-time algorithm for maximum-weight $b$-matching problem to obtain an $O(\sqrt{bn})$-approximation. When $b$ is constant and all lists have size $n - O(\sqrt{n})$, our guarantees asymptotically match the best known approximation factor for MaxQAP, yielding the first approximation algorithms for these two variants. - oai:arXiv.org:2512.07618v1 - cs.DS - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jiratchaphat Nanta, Vorapong Suppakitpaisarn, Piyashat Sripratak - - - An\'alisis de rendimiento y eficiencia energ\'etica en el cluster Raspberry Pi Cronos - https://arxiv.org/abs/2512.07622 - arXiv:2512.07622v1 Announce Type: new -Abstract: This article presents an evaluation of the computational performance and energy efficiency of the Cronos cluster, composed of Raspberry Pi4 and 3b microcomputers designed for educational purposes. Experimental tests were performed using the High Performance Linpack (HPL) benchmark, under a resource management environment configured with Slurm and parallel communication via Open MPI. The study focuses on analyzing scalability, stability, and power consumption during the execution of computationally intensive workloads, considering different node configurations. The results show that the cluster achieves a performance of up to 6.91 GFLOPS in homogeneous configurations of 6 Raspberry Pi 4 nodes, and that the use of heterogeneous nodes (including Raspberry Pi 3b) can negatively impact stability and efficiency. Additionally, the total electrical consumption of the system was measured during the runs, allowing for the estimation of the performance-to-consumption ratio (GFLOPS/W) as a comparative metric. This study constitutes a concrete contribution to the design, evaluation, and utilization of low-cost ARM clusters in educational and research contexts. - oai:arXiv.org:2512.07622v1 - cs.AR - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Martha Semken, Mariano Vargas, Ignacio Tula, Giuliana Zorzoli, Andr\'es Rojas Paredes - - - Context-Adaptive Color Optimization for Web Accessibility: Balancing Perceptual Fidelity and Functional Requirements - https://arxiv.org/abs/2512.07623 - arXiv:2512.07623v1 Announce Type: new -Abstract: We extend our OKLCH-based accessibility optimization with context-adaptive constraint strategies that achieve near-universal success rates across diverse use cases. Our original strict algorithm reached 66-77% success by prioritizing minimal perceptual change ($\Delta E \leq 5.0$), optimizing for enterprise contexts where brand fidelity is paramount. However, this one-size-fits-all approach fails to serve the broader ecosystem of web developers who need accessible solutions even when strict perceptual constraints cannot be satisfied. We introduce recursive optimization (Mode~1) that compounds small adjustments across iterations, achieving 93.68% success on all color pairs and 100% success on reasonable pairs (contrast ratio $\rho > 2.0$), representing a +27.23 percentage point improvement. A relaxed fallback mode (Mode~2) handles pathological edge cases, reaching 98.73% overall success. Evaluation on 10,000 realistic web color pairs demonstrates that context-aware constraint relaxation, combined with absolute hue preservation, enables practical accessibility compliance while maintaining brand color identity. The median perceptual change remains zero across all modes (most pairs already comply), while the 90th percentile reaches $\Delta E_{2000} = 15.55$ in Mode~1 -- perceptually acceptable when hue invariance preserves the essential character of the original color. The approach is deployed in CM-Colors v0.5.0 (800+ monthly downloads), providing developers with explicit control over the accessibility-fidelity trade-off appropriate to their context. - oai:arXiv.org:2512.07623v1 - cs.HC - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lalitha A R - - - Time Series Foundation Models for Process Model Forecasting - https://arxiv.org/abs/2512.07624 - arXiv:2512.07624v1 Announce Type: new -Abstract: Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of directly-follows (DF) relations, complementing predictive process monitoring that focuses on single-case prefixes. Prior benchmarks show that machine learning and deep learning models provide only modest gains over statistical baselines, mainly due to the sparsity and heterogeneity of the DF time series. We investigate Time Series Foundation Models (TSFMs), large pre-trained models for generic time series, as an alternative for PMF. Using DF time series derived from real-life event logs, we compare zero-shot use of TSFMs, without additional training, with fine-tuned variants adapted on PMF-specific data. TSFMs generally achieve lower forecasting errors (MAE and RMSE) than traditional and specialized models trained from scratch on the same logs, indicating effective transfer of temporal structure from non-process domains. While fine-tuning can further improve accuracy, the gains are often small and may disappear on smaller or more complex datasets, so zero-shot use remains a strong default. Our study highlights the generalization capability and data efficiency of TSFMs for process-related time series and, to the best of our knowledge, provides the first systematic evaluation of temporal foundation models for PMF. - oai:arXiv.org:2512.07624v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yongbo Yu, Jari Peeperkorn, Johannes De Smedt, Jochen De Weerdt - - - Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization - https://arxiv.org/abs/2512.07627 - arXiv:2512.07627v1 Announce Type: new -Abstract: Transformer architectures offer significant advantages regarding the generation of symbolic music; their capabilities for incorporating user preferences toward what they generate is being studied under many aspects. This paper studies the inclusion of predefined chord constraints in melodic harmonization, i.e., where a desired chord at a specific location is provided along with the melody as inputs and the autoregressive transformer model needs to incorporate the chord in the harmonization that it generates. The peculiarities of involving such constraints is discussed and an algorithm is proposed for tackling this task. This algorithm is called B* and it combines aspects of beam search and A* along with backtracking to force pretrained transformers to satisfy the chord constraints, at the correct onset position within the correct bar. The algorithm is brute-force and has exponential complexity in the worst case; however, this paper is a first attempt to highlight the difficulties of the problem and proposes an algorithm that offers many possibilities for improvements since it accommodates the involvement of heuristics. - oai:arXiv.org:2512.07627v1 - cs.SD - cs.AI - cs.SC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - 10.5281/zenodo.16948248 - Maximos Kaliakatsos-Papakostas, Konstantinos Soiledis, Theodoros Tsamis, Dimos Makris, Vassilis Katsouros, Emilios Cambouropoulos - - - MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation - https://arxiv.org/abs/2512.07628 - arXiv:2512.07628v1 Announce Type: new -Abstract: Compositionality is critical for 3D object and scene generation, but existing part-aware 3D generation methods suffer from poor scalability due to quadratic global attention costs when increasing the number of components. In this work, we present MoCA, a compositional 3D generative model with two key designs: (1) importance-based component routing that selects top-k relevant components for sparse global attention, and (2) unimportant components compression that preserve contextual priors of unselected components while reducing computational complexity of global attention. With these designs, MoCA enables efficient, fine-grained compositional 3D asset creation with scalable number of components. Extensive experiments show MoCA outperforms baselines on both compositional object and scene generation tasks. Project page: https://lizhiqi49.github.io/MoCA - oai:arXiv.org:2512.07628v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Zhiqi Li, Wenhuan Li, Tengfei Wang, Zhenwei Wang, Junta Wu, Haoyuan Wang, Yunhan Yang, Zehuan Huang, Yang Li, Peidong Liu, Chunchao Guo - - - The Agent Capability Problem: Predicting Solvability Through Information-Theoretic Bounds - https://arxiv.org/abs/2512.07631 - arXiv:2512.07631v1 Announce Type: new -Abstract: When should an autonomous agent commit resources to a task? We introduce the Agent Capability Problem (ACP), a framework for predicting whether an agent can solve a problem under resource constraints. Rather than relying on empirical heuristics, ACP frames problem-solving as information acquisition: an agent requires $\Itotal$ bits to identify a solution and gains $\Istep$ bits per action at cost $\Cstep$, yielding an effective cost $\Ceff = (\Itotal/\Istep), \Cstep$ that predicts resource requirements before search. We prove that $\Ceff$ lower-bounds expected cost and provide tight probabilistic upper bounds. Experimental validation shows that ACP predictions closely track actual agent performance, consistently bounding search effort while improving efficiency over greedy and random strategies. The framework generalizes across LLM-based and agentic workflows, linking principles from active learning, Bayesian optimization, and reinforcement learning through a unified information-theoretic lens. \ - oai:arXiv.org:2512.07631v1 - cs.AI - cs.CC - cs.IT - cs.LG - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Shahar Lutati - - - Service Registration, Indexing, Discovery & Selection; An Architectural Survey Toward a GenAI-Driven Future - https://arxiv.org/abs/2512.07638 - arXiv:2512.07638v1 Announce Type: new -Abstract: The emergence of sixth-generation (6G) networks marks a paradigm shift: by unifying an edge-to-cloud computing continuum with ultra-high-performance networking, 6G will enable capabilities far beyond today's boundaries. As use-case diversity grows exponentially and user adoption drives traffic to unprecedented and highly dynamic levels, novel service orchestration mechanisms are indispensable. In this paper, we adopt an architectural viewpoint, examining Service Registration, Indexing, Discovery, and Selection (SRIDS) as fundamental elements of 6G service provision. We first establish the theoretical foundations of SRIDS in 6G by defining its core concepts, detailing its end-to-end workflow, reviewing current standardization efforts, and projecting its future design objectives, including reliability, scalability, automaticity and adaptability, determinism, efficiency, sustainability, semantic-awareness, security, privacy, and trust. We then perform a comprehensive literature review and gap analysis encompassing both existing surveys and recent research efforts, identifying conceptual and methodological gaps that hinder unified SRIDS in 6G. Next, we introduce a taxonomy that classifies SRIDS mechanisms into centralized, distributed, decentralized, and hybrid architectures, and systematically examine the relevant studies within each category. Each work is evaluated against the extracted design objectives. Building on these findings, we propose a hybrid architectural framework, combining centralized data management to ensure consistency and agility with distributed coordination to enhance scalability in emerging 6G use cases. The framework incorporates innovative technologies, such as Generative Artificial Intelligence (GenAI). We conclude by highlighting open challenges and suggesting directions for future research. - oai:arXiv.org:2512.07638v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Mohammad Farhoudi, Masoud Shokrnezhad, Tarik Taleb - - - A Mathematical Theory of Top-$k$ Sparse Attention via Total Variation Distance - https://arxiv.org/abs/2512.07647 - arXiv:2512.07647v1 Announce Type: new -Abstract: We develop a unified mathematical framework for certified Top-$k$ attention truncation that quantifies approximation error at both the distribution and output levels. For a single attention distribution $P$ and its Top-$k$ truncation $\hat P$, we show that the total-variation distance coincides with the discarded softmax tail mass and satisfies $\mathrm{TV}(P,\hat P)=1-e^{-\mathrm{KL}(\hat P\Vert P)}$, yielding sharp Top-$k$-specific bounds in place of generic inequalities. From this we derive non-asymptotic deterministic bounds -- from a single boundary gap through multi-gap and blockwise variants -- that control $\mathrm{TV}(P,\hat P)$ using only the ordered logits. Using an exact head-tail decomposition, we prove that the output error factorizes as $\|\mathrm{Attn}(q,K,V)-\mathrm{Attn}_k(q,K,V)\|_2=\tau\|\mu_{\mathrm{tail}}-\mu_{\mathrm{head}}\|_2$ with $\tau=\mathrm{TV}(P,\hat P)$, yielding a new head-tail diameter bound $\|\mathrm{Attn}(q,K,V)-\mathrm{Attn}_k(q,K,V)\|_2\le\tau\,\mathrm{diam}_{H,T}$ and refinements linking the error to $\mathrm{Var}_P(V)$. Under an i.i.d. Gaussian score model $s_i\sim\mathcal N(\mu,\sigma^2)$ we derive closed-form tail masses and an asymptotic rule for the minimal $k_\varepsilon$ ensuring $\mathrm{TV}(P,\hat P)\le\varepsilon$, namely $k_\varepsilon/n\approx\Phi_c(\sigma+\Phi^{-1}(\varepsilon))$. Experiments on bert-base-uncased and synthetic logits confirm the predicted scaling of $k_\varepsilon/n$ and show that certified Top-$k$ can reduce scored keys by 2-4$\times$ on average while meeting the prescribed total-variation budget. - oai:arXiv.org:2512.07647v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Georgios Tzachristas, Lei Deng, Ioannis Tzachristas, Gong Zhang, Renhai Chen - - - Exploring Test-time Scaling via Prediction Merging on Large-Scale Recommendation - https://arxiv.org/abs/2512.07650 - arXiv:2512.07650v1 Announce Type: new -Abstract: Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However, how to efficiently utilize and scale up computational resources during test time remains underexplored, which can prove to be a scaling-efficient approach and bring orthogonal improvements in LM domains. The key point in applying test-time scaling to DLRS lies in effectively generating diverse yet meaningful outputs for the same instance. We propose two ways: One is to explore the heterogeneity of different model architectures. The other is to utilize the randomness of model initialization under a homogeneous architecture. The evaluation is conducted across eight models, including both classic and SOTA models, on three benchmarks. Sufficient evidence proves the effectiveness of both solutions. We further prove that under the same inference budget, test-time scaling can outperform parameter scaling. Our test-time scaling can also be seamlessly accelerated with the increase in parallel servers when deployed online, without affecting the inference time on the user side. Code is available. - oai:arXiv.org:2512.07650v1 - cs.IR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fuyuan Lyu, Zhentai Chen, Jingyan Jiang, Lingjie Li, Xing Tang, Xiuqiang He, Xue Liu - - - Liver Fibrosis Quantification and Analysis: The LiQA Dataset and Baseline Method - https://arxiv.org/abs/2512.07651 - arXiv:2512.07651v1 Announce Type: new -Abstract: Liver fibrosis represents a significant global health burden, necessitating accurate staging for effective clinical management. This report introduces the LiQA (Liver Fibrosis Quantification and Analysis) dataset, established as part of the CARE 2024 challenge. Comprising $440$ patients with multi-phase, multi-center MRI scans, the dataset is curated to benchmark algorithms for Liver Segmentation (LiSeg) and Liver Fibrosis Staging (LiFS) under complex real-world conditions, including domain shifts, missing modalities, and spatial misalignment. We further describe the challenge's top-performing methodology, which integrates a semi-supervised learning framework with external data for robust segmentation, and utilizes a multi-view consensus approach with Class Activation Map (CAM)-based regularization for staging. Evaluation of this baseline demonstrates that leveraging multi-source data and anatomical constraints significantly enhances model robustness in clinical settings. - oai:arXiv.org:2512.07651v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yuanye Liu, Hanxiao Zhang, Nannan Shi, Yuxin Shi, Arif Mahmood, Murtaza Taj, Xiahai Zhuang - - - An AI-Powered Autonomous Underwater System for Sea Exploration and Scientific Research - https://arxiv.org/abs/2512.07652 - arXiv:2512.07652v1 Announce Type: new -Abstract: Traditional sea exploration faces significant challenges due to extreme conditions, limited visibility, and high costs, resulting in vast unexplored ocean regions. This paper presents an innovative AI-powered Autonomous Underwater Vehicle (AUV) system designed to overcome these limitations by automating underwater object detection, analysis, and reporting. The system integrates YOLOv12 Nano for real-time object detection, a Convolutional Neural Network (CNN) (ResNet50) for feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and K-Means++ clustering for grouping marine objects based on visual characteristics. Furthermore, a Large Language Model (LLM) (GPT-4o Mini) is employed to generate structured reports and summaries of underwater findings, enhancing data interpretation. The system was trained and evaluated on a combined dataset of over 55,000 images from the DeepFish and OzFish datasets, capturing diverse Australian marine environments. Experimental results demonstrate the system's capability to detect marine objects with a mAP@0.5 of 0.512, a precision of 0.535, and a recall of 0.438. The integration of PCA effectively reduced feature dimensionality while preserving 98% variance, facilitating K-Means clustering which successfully grouped detected objects based on visual similarities. The LLM integration proved effective in generating insightful summaries of detections and clusters, supported by location data. This integrated approach significantly reduces the risks associated with human diving, increases mission efficiency, and enhances the speed and depth of underwater data analysis, paving the way for more effective scientific research and discovery in challenging marine environments. - oai:arXiv.org:2512.07652v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hamad Almazrouei, Mariam Al Nasseri, Maha Alzaabi - - - Optimization-Guided Diffusion for Interactive Scene Generation - https://arxiv.org/abs/2512.07661 - arXiv:2512.07661v1 Announce Type: new -Abstract: Realistic and diverse multi-agent driving scenes are crucial for evaluating autonomous vehicles, but safety-critical events which are essential for this task are rare and underrepresented in driving datasets. Data-driven scene generation offers a low-cost alternative by synthesizing complex traffic behaviors from existing driving logs. However, existing models often lack controllability or yield samples that violate physical or social constraints, limiting their usability. We present OMEGA, an optimization-guided, training-free framework that enforces structural consistency and interaction awareness during diffusion-based sampling from a scene generation model. OMEGA re-anchors each reverse diffusion step via constrained optimization, steering the generation towards physically plausible and behaviorally coherent trajectories. Building on this framework, we formulate ego-attacker interactions as a game-theoretic optimization in the distribution space, approximating Nash equilibria to generate realistic, safety-critical adversarial scenarios. Experiments on nuPlan and Waymo show that OMEGA improves generation realism, consistency, and controllability, increasing the ratio of physically and behaviorally valid scenes from 32.35% to 72.27% for free exploration capabilities, and from 11% to 80% for controllability-focused generation. Our approach can also generate $5\times$ more near-collision frames with a time-to-collision under three seconds while maintaining the overall scene realism. - oai:arXiv.org:2512.07661v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Shiaho Li, Naisheng Ye, Tianyu Li, Kashyap Chitta, Tuo An, Peng Su, Boyang Wang, Haiou Liu, Chen Lv, Hongyang Li - - - Neural Compress-and-Forward for the Primitive Diamond Relay Channel - https://arxiv.org/abs/2512.07662 - arXiv:2512.07662v1 Announce Type: new -Abstract: The diamond relay channel, where a source communicates with a destination via two parallel relays, is one of the canonical models for cooperative communications. We focus on the primitive variant, where each relay observes a noisy version of the source signal and forwards a compressed description over an orthogonal, noiseless, finite-rate link to the destination. Compress-and-forward (CF) is particularly effective in this setting, especially under oblivious relaying where relays lack access to the source codebook. While neural CF methods have been studied in single-relay channels, extending them to the two-relay case is non-trivial, as it requires fully distributed compression without any inter-relay coordination. We demonstrate that learning-based quantizers at the relays can harness input correlations by operating remote, yet in a collaborative fashion, enabling effective distributed compression in line with Berger-Tung-style coding. Each relay separately compresses its observation using a one-shot learned quantizer, and the destination jointly decodes the source message. Simulation results show that the proposed scheme, trained end-to-end with finite-order modulation, operates close to the known theoretical bounds. These results demonstrate that neural CF can scale to multi-relay systems while maintaining both performance and interpretability. - oai:arXiv.org:2512.07662v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ozan Ayg\"un, Ezgi Ozyilkan, Elza Erkip - - - A Framework for Data Valuation and Monetisation - https://arxiv.org/abs/2512.07664 - arXiv:2512.07664v1 Announce Type: new -Abstract: As organisations increasingly recognise data as a strategic resource, they face the challenge of translating informational assets into measurable business value. Existing valuation approaches remain fragmented, often separating economic, governance, and strategic perspectives and lacking operational mechanisms suitable for real settings. This paper introduces a unified valuation framework that integrates these perspectives into a coherent decision-support model. Building on two artefacts from the Horizon Europe DATAMITE project, a taxonomy of data-quality and performance metrics, and an Analytic Network Process (ANP) tool for deriving relative importance, we develop a hybrid valuation model. The model combines qualitative scoring, cost- and utility-based estimation, relevance/quality indexing, and multi-criteria weighting to define data value transparently and systematically. Anchored in the Balanced Scorecard (BSC), the framework aligns indicators and valuation outcomes with organisational strategy, enabling firms to assess monetisation potential across Data-as-a-Service, Information-as-a-Service, and Answers-as-a-Service pathways. Methodologically, the study follows a Design Science approach complemented by embedded case studies with industrial partners, which informed continual refinement of the model. Because the evaluation is connected to a high-level taxonomy, the approach also reveals how valuation considerations map to BSC perspectives. Across the analysed use cases, the framework demonstrated flexibility, transparency, and reduced arbitrariness in valuation, offering organisations a structured basis for linking data assets to strategic and economic outcomes. - oai:arXiv.org:2512.07664v1 - cs.CY - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Eduardo Vyhmeister, Bastien Pietropaoli, UdoBub, Rob Schneider, Andrea Visentin - - - Reliable agent engineering should integrate machine-compatible organizational principles - https://arxiv.org/abs/2512.07665 - arXiv:2512.07665v1 Announce Type: new -Abstract: As AI agents built on large language models (LLMs) become increasingly embedded in society, issues of coordination, control, delegation, and accountability are entangled with concerns over their reliability. To design and implement LLM agents around reliable operations, we should consider the task complexity in the application settings and reduce their limitations while striving to minimize agent failures and optimize resource efficiency. High-functioning human organizations have faced similar balancing issues, which led to evidence-based theories that seek to understand their functioning strategies. We examine the parallels between LLM agents and the compatible frameworks in organization science, focusing on what the design, scaling, and management of organizations can inform agentic systems towards improving reliability. We offer three preliminary accounts of organizational principles for AI agent engineering to attain reliability and effectiveness, through balancing agency and capabilities in agent design, resource constraints and performance benefits in agent scaling, and internal and external mechanisms in agent management. Our work extends the growing exchanges between the operational and governance principles of AI systems and social systems to facilitate system integration. - oai:arXiv.org:2512.07665v1 - cs.CY - cs.MA - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - R. Patrick Xian, Garry A. Gabison, Ahmed Alaa, Christoph Riedl, Grigorios G. Chrysos - - - Bridging Code Graphs and Large Language Models for Better Code Understanding - https://arxiv.org/abs/2512.07666 - arXiv:2512.07666v1 Announce Type: new -Abstract: Large Language Models (LLMs) have demonstrated remarkable performance in code intelligence tasks such as code generation, summarization, and translation. However, their reliance on linearized token sequences limits their ability to understand the structural semantics of programs. While prior studies have explored graphaugmented prompting and structure-aware pretraining, they either suffer from prompt length constraints or require task-specific architectural changes that are incompatible with large-scale instructionfollowing LLMs. To address these limitations, this paper proposes CGBridge, a novel plug-and-play method that enhances LLMs with Code Graph information through an external, trainable Bridge module. CGBridge first pre-trains a code graph encoder via selfsupervised learning on a large-scale dataset of 270K code graphs to learn structural code semantics. It then trains an external module to bridge the modality gap among code, graph, and text by aligning their semantics through cross-modal attention mechanisms. Finally, the bridge module generates structure-informed prompts, which are injected into a frozen LLM, and is fine-tuned for downstream code intelligence tasks. Experiments show that CGBridge achieves notable improvements over both the original model and the graphaugmented prompting method. Specifically, it yields a 16.19% and 9.12% relative gain in LLM-as-a-Judge on code summarization, and a 9.84% and 38.87% relative gain in Execution Accuracy on code translation. Moreover, CGBridge achieves over 4x faster inference than LoRA-tuned models, demonstrating both effectiveness and efficiency in structure-aware code understanding. - oai:arXiv.org:2512.07666v1 - cs.CL - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zeqi Chen, Zhaoyang Chu, Yi Gui, Feng Guo, Yao Wan, Chuan Shi - - - Depth-Wise Activation Steering for Honest Language Models - https://arxiv.org/abs/2512.07667 - arXiv:2512.07667v1 Announce Type: new -Abstract: Large language models sometimes assert falsehoods despite internally representing the correct answer, failures of honesty rather than accuracy, which undermines auditability and safety. Existing approaches largely optimize factual correctness or depend on retraining and brittle single-layer edits, offering limited leverage over truthful reporting. We present a training-free activation steering method that weights steering strength across network depth using a Gaussian schedule. On the MASK benchmark, which separates honesty from knowledge, we evaluate seven models spanning the LLaMA, Qwen, and Mistral families and find that Gaussian scheduling improves honesty over no-steering and single-layer baselines in six of seven models. Equal-budget ablations on LLaMA-3.1-8B-Instruct and Qwen-2.5-7B-Instruct show the Gaussian schedule outperforms random, uniform, and box-filter depth allocations, indicating that how intervention is distributed across depth materially affects outcomes beyond total strength. The method is simple, model-agnostic, requires no finetuning, and provides a low-cost control knob for eliciting truthful reporting from models' existing capabilities. - oai:arXiv.org:2512.07667v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Gracjan G\'oral, Marysia Winkels, Steven Basart - - - EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset - https://arxiv.org/abs/2512.07668 - arXiv:2512.07668v1 Announce Type: new -Abstract: We address the challenge of predicting human visual attention during real-world navigation by measuring and modeling egocentric pedestrian eye gaze in an outdoor campus setting. We introduce the EgoCampus dataset, which spans 25 unique outdoor paths over 6 km across a university campus with recordings from more than 80 distinct human pedestrians, resulting in a diverse set of gaze-annotated videos. The system used for collection, Meta's Project Aria glasses, integrates eye tracking, front-facing RGB cameras, inertial sensors, and GPS to provide rich data from the human perspective. Unlike many prior egocentric datasets that focus on indoor tasks or exclude eye gaze information, our work emphasizes visual attention while subjects walk in outdoor campus paths. Using this data, we develop EgoCampusNet, a novel method to predict eye gaze of navigating pedestrians as they move through outdoor environments. Our contributions provide both a new resource for studying real-world attention and a resource for future work in gaze prediction models for navigation. Dataset and code are available upon request, and will be made publicly available at a later date at https://github.com/ComputerVisionRutgers/EgoCampus . - oai:arXiv.org:2512.07668v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Ronan John, Aditya Kesari, Vincenzo DiMatteo, Kristin Dana - - - Multi-Domain Motion Embedding: Expressive Real-Time Mimicry for Legged Robots - https://arxiv.org/abs/2512.07673 - arXiv:2512.07673v1 Announce Type: new -Abstract: Effective motion representation is crucial for enabling robots to imitate expressive behaviors in real time, yet existing motion controllers often ignore inherent patterns in motion. Previous efforts in representation learning do not attempt to jointly capture structured periodic patterns and irregular variations in human and animal movement. To address this, we present Multi-Domain Motion Embedding (MDME), a motion representation that unifies the embedding of structured and unstructured features using a wavelet-based encoder and a probabilistic embedding in parallel. This produces a rich representation of reference motions from a minimal input set, enabling improved generalization across diverse motion styles and morphologies. We evaluate MDME on retargeting-free real-time motion imitation by conditioning robot control policies on the learned embeddings, demonstrating accurate reproduction of complex trajectories on both humanoid and quadruped platforms. Our comparative studies confirm that MDME outperforms prior approaches in reconstruction fidelity and generalizability to unseen motions. Furthermore, we demonstrate that MDME can reproduce novel motion styles in real-time through zero-shot deployment, eliminating the need for task-specific tuning or online retargeting. These results position MDME as a generalizable and structure-aware foundation for scalable real-time robot imitation. - oai:arXiv.org:2512.07673v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Matthias Heyrman, Chenhao Li, Victor Klemm, Dongho Kang, Stelian Coros, Marco Hutter - - - DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations - https://arxiv.org/abs/2512.07674 - arXiv:2512.07674v1 Announce Type: new -Abstract: Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This is particularly true in Magnetic Resonance Imaging, where scanner hardware differences, diverse acquisition protocols, and varying sequence parameters introduce substantial domain shifts that obscure underlying biological signals. Data harmonization methods aim to reduce these instrumental and acquisition variability, but existing approaches remain insufficient. When applied to imaging data, image-based harmonization approaches are often restricted by the need for target images, while existing text-guided methods rely on simplistic labels that fail to capture complex acquisition details or are typically restricted to datasets with limited variability, failing to capture the heterogeneity of real-world clinical environments. To address these limitations, we propose DIST-CLIP (Disentangled Style Transfer with CLIP Guidance), a unified framework for MRI harmonization that flexibly uses either target images or DICOM metadata for guidance. Our framework explicitly disentangles anatomical content from image contrast, with the contrast representations being extracted using pre-trained CLIP encoders. These contrast embeddings are then integrated into the anatomical content via a novel Adaptive Style Transfer module. We trained and evaluated DIST-CLIP on diverse real-world clinical datasets, and showed significant improvements in performance when compared against state-of-the-art methods in both style translation fidelity and anatomical preservation, offering a flexible solution for style transfer and standardizing MRI data. Our code and weights will be made publicly available upon publication. - oai:arXiv.org:2512.07674v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez, Paul Wright, Mehmet Yigitsoy, Sebastien Ourselin, Jorge Cardoso - - - A Bootstrap Perspective on Stochastic Gradient Descent - https://arxiv.org/abs/2512.07676 - arXiv:2512.07676v1 Announce Type: new -Abstract: Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the statistical bootstrap: SGD uses gradient variability under batch sampling as a proxy for solution variability under the randomness of the data collection process. We use empirical results and theoretical analysis to substantiate this claim. In idealized experiments on empirical risk minimization, we show that SGD is drawn to parameter choices that are robust under resampling and thus avoids spurious solutions even if they lie in wider and deeper minima of the training loss. We prove rigorously that by implicitly regularizing the trace of the gradient covariance matrix, SGD controls the algorithmic variability. This regularization leads to solutions that are less sensitive to sampling noise, thereby improving generalization. Numerical experiments on neural network training show that explicitly incorporating the estimate of the algorithmic variability as a regularizer improves test performance. This fact supports our claim that bootstrap estimation underpins SGD's generalization advantages. - oai:arXiv.org:2512.07676v1 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hongjian Lan, Yucong Liu, Florian Sch\"afer - - - AMBER: Aerial deployable gripping crawler with compliant microspine for canopy manipulation - https://arxiv.org/abs/2512.07680 - arXiv:2512.07680v1 Announce Type: new -Abstract: This paper presents an aerially deployable crawler designed for adaptive locomotion and manipulation within tree canopies. The system combines compliant microspine-based tracks, a dual-track rotary gripper, and an elastic tail, enabling secure attachment and stable traversal across branches of varying curvature and inclination. - Experiments demonstrate reliable gripping up to 90 degrees of body roll and inclination, while effective climbing on branches inclined up to 67.5 degrees, achieving a maximum speed of 0.55 body lengths per second on horizontal branches. The compliant tracks allow yaw steering of up to 10 degrees, enhancing maneuverability on irregular surfaces. - Power measurements show efficient operation with a dimensionless cost of transport over an order of magnitude lower than typical hovering power consumption in aerial robots. Integrated within a drone-tether deployment system, the crawler provides a robust, low-power platform for environmental sampling and in-canopy sensing, bridging the gap between aerial and surface-based ecological robotics. - oai:arXiv.org:2512.07680v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - P. A. Wigner, L. Romanello, A. Hammad, P. H. Nguyen, T. Lan, S. F. Armanini, B. B. Kocer, M. Kovac - - - When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks - https://arxiv.org/abs/2512.07684 - arXiv:2512.07684v1 Announce Type: new -Abstract: Online incivility has emerged as a widespread and persistent problem in digital communities, imposing substantial social and psychological burdens on users. Although many platforms attempt to curb incivility through moderation and automated detection, the performance of existing approaches often remains limited in both accuracy and efficiency. To address this challenge, we propose a Graph Neural Network (GNN) framework for detecting three types of uncivil behavior (i.e., toxicity, aggression, and personal attacks) within the English Wikipedia community. Our model represents each user comment as a node, with textual similarity between comments defining the edges, allowing the network to jointly learn from both linguistic content and relational structures among comments. We also introduce a dynamically adjusted attention mechanism that adaptively balances nodal and topological features during information aggregation. Empirical evaluations demonstrate that our proposed architecture outperforms 12 state-of-the-art Large Language Models (LLMs) across multiple metrics while requiring significantly lower inference cost. These findings highlight the crucial role of structural context in detecting online incivility and address the limitations of text-only LLM paradigms in behavioral prediction. All datasets and comparative outputs will be publicly available in our repository to support further research and reproducibility. - oai:arXiv.org:2512.07684v1 - cs.CL - cs.AI - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zihan Chen, Lanyu Yu - - - HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs - https://arxiv.org/abs/2512.07687 - arXiv:2512.07687v1 Announce Type: new -Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding tasks. While these models often produce linguistically coherent output, they often suffer from hallucinations, generating descriptions that are factually inconsistent with the visual content, potentially leading to adverse consequences. Therefore, the assessment of hallucinations in MLLM has become increasingly crucial in the model development process. Contemporary methodologies predominantly depend on external LLM evaluators, which are themselves susceptible to hallucinations and may present challenges in terms of domain adaptation. In this study, we propose the hypothesis that hallucination manifests as measurable irregularities within the internal layer dynamics of MLLMs, not merely due to distributional shifts but also in the context of layer-wise analysis of specific assumptions. By incorporating such modifications, \textsc{\textsc{HalluShift++}} broadens the efficacy of hallucination detection from text-based large language models (LLMs) to encompass multimodal scenarios. Our codebase is available at https://github.com/C0mRD/HalluShift_Plus. - oai:arXiv.org:2512.07687v1 - cs.CL - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Sujoy Nath, Arkaprabha Basu, Sharanya Dasgupta, Swagatam Das - - - Automated Generation of Custom MedDRA Queries Using SafeTerm Medical Map - https://arxiv.org/abs/2512.07694 - arXiv:2512.07694v1 Announce Type: new -Abstract: In pre-market drug safety review, grouping related adverse event terms into standardised MedDRA queries or the FDA Office of New Drugs Custom Medical Queries (OCMQs) is critical for signal detection. We present a novel quantitative artificial intelligence system that understands and processes medical terminology and automatically retrieves relevant MedDRA Preferred Terms (PTs) for a given input query, ranking them by a relevance score using multi-criteria statistical methods. The system (SafeTerm) embeds medical query terms and MedDRA PTs in a multidimensional vector space, then applies cosine similarity and extreme-value clustering to generate a ranked list of PTs. Validation was conducted against the FDA OCMQ v3.0 (104 queries), restricted to valid MedDRA PTs. Precision, recall and F1 were computed across similarity-thresholds. High recall (>95%) is achieved at moderate thresholds. Higher thresholds improve precision (up to 86%). The optimal threshold (~0.70 - 0.75) yielded recall ~50% and precision ~33%. Narrow-term PT subsets performed similarly but required slightly higher similarity thresholds. The SafeTerm AI-driven system provides a viable supplementary method for automated MedDRA query generation. A similarity threshold of ~0.60 is recommended initially, with increased thresholds for refined term selection. - oai:arXiv.org:2512.07694v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla, Elena Hadjicosta - - - Delay-Aware Diffusion Policy: Bridging the Observation-Execution Gap in Dynamic Tasks - https://arxiv.org/abs/2512.07697 - arXiv:2512.07697v1 Announce Type: new -Abstract: As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization from zero delay to measured delay during training and inference. We introduce Delay-Aware Diffusion Policy (DA-DP), a framework for explicitly incorporating inference delays into policy learning. DA-DP corrects zero-delay trajectories to their delay-compensated counterparts, and augments the policy with delay conditioning. We empirically validate DA-DP on a variety of tasks, robots, and delays and find its success rate more robust to delay than delay-unaware methods. DA-DP is architecture agnostic and transfers beyond diffusion policies, offering a general pattern for delay-aware imitation learning. More broadly, DA-DP encourages evaluation protocols that report performance as a function of measured latency, not just task difficulty. - oai:arXiv.org:2512.07697v1 - cs.RO - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Aileen Liao, Dong-Ki Kim, Max Olan Smith, Ali-akbar Agha-mohammadi, Shayegan Omidshafiei - - - sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only - https://arxiv.org/abs/2512.07698 - arXiv:2512.07698v1 Announce Type: new -Abstract: Understanding articulated objects is a fundamental challenge in robotics and digital twin creation. To effectively model such objects, it is essential to recover both part segmentation and the underlying joint parameters. Despite the importance of this task, previous work has largely focused on setups like multi-view systems, object scanning, or static cameras. In this paper, we present the first data-driven approach that jointly predicts part segmentation and joint parameters from monocular video captured with a freely moving camera. Trained solely on synthetic data, our method demonstrates strong generalization to real-world objects, offering a scalable and practical solution for articulated object understanding. Our approach operates directly on casually recorded video, making it suitable for real-time applications in dynamic environments. Project webpage: https://aartykov.github.io/sim2art/ - oai:arXiv.org:2512.07698v1 - cs.CV - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Arslan Artykov, Corentin Sautier, Vincent Lepetit - - - Linear Quadratic Control with Non-Markovian and Non-Semimartingale Noise Models - https://arxiv.org/abs/2512.07699 - arXiv:2512.07699v1 Announce Type: new -Abstract: The standard linear quadratic Gaussian (LQG) framework assumes a Brownian noise process and relies on classical stochastic calculus tools, such as those based on It\^o calculus. In this paper, we solve a generalized linear quadratic optimal control problem where the process and measurement noises can be non-Markovian and non-semimartingale stochastic processes with sample paths that have low H\"older regularity. Since these noise models do not, in general, permit the use of the standard It\^o calculus, we employ rough path theory to formulate and solve the problem. By leveraging signature representations and controlled rough paths, we derive the optimal state estimation and control strategies. - oai:arXiv.org:2512.07699v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Mostafa M. Shibl, Sharan Srinivasan, Harsha Honnappa, Vijay Gupta - - - Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment - https://arxiv.org/abs/2512.07702 - arXiv:2512.07702v1 Announce Type: new -Abstract: Despite substantial progress in text-to-image generation, achieving precise text-image alignment remains challenging, particularly for prompts with rich compositional structure or imaginative elements. To address this, we introduce Negative Prompting for Image Correction (NPC), an automated pipeline that improves alignment by identifying and applying negative prompts that suppress unintended content. We begin by analyzing cross-attention patterns to explain why both targeted negatives-those directly tied to the prompt's alignment error-and untargeted negatives-tokens unrelated to the prompt but present in the generated image-can enhance alignment. To discover useful negatives, NPC generates candidate prompts using a verifier-captioner-proposer framework and ranks them with a salient text-space score, enabling effective selection without requiring additional image synthesis. On GenEval++ and Imagine-Bench, NPC outperforms strong baselines, achieving 0.571 vs. 0.371 on GenEval++ and the best overall performance on Imagine-Bench. By guiding what not to generate, NPC provides a principled, fully automated route to stronger text-image alignment in diffusion models. Code is released at https://github.com/wiarae/NPC. - oai:arXiv.org:2512.07702v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Sangha Park, Eunji Kim, Yeongtak Oh, Jooyoung Choi, Sungroh Yoon - - - PVeRA: Probabilistic Vector-Based Random Matrix Adaptation - https://arxiv.org/abs/2512.07703 - arXiv:2512.07703v1 Announce Type: new -Abstract: Large foundation models have emerged in the last years and are pushing performance boundaries for a variety of tasks. Training or even finetuning such models demands vast datasets and computational resources, which are often scarce and costly. Adaptation methods provide a computationally efficient solution to address these limitations by allowing such models to be finetuned on small amounts of data and computing power. This is achieved by appending new trainable modules to frozen backbones with only a fraction of the trainable parameters and fitting only these modules on novel tasks. Recently, the VeRA adapter was shown to excel in parameter-efficient adaptations by utilizing a pair of frozen random low-rank matrices shared across all layers. In this paper, we propose PVeRA, a probabilistic version of the VeRA adapter, which modifies the low-rank matrices of VeRA in a probabilistic manner. This modification naturally allows handling inherent ambiguities in the input and allows for different sampling configurations during training and testing. A comprehensive evaluation was performed on the VTAB-1k benchmark and seven adapters, with PVeRA outperforming VeRA and other adapters. Our code for training models with PVeRA and benchmarking all adapters is available https://github.com/leofillioux/pvera. - oai:arXiv.org:2512.07703v1 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Leo Fillioux, Enzo Ferrante, Paul-Henry Courn\`ede, Maria Vakalopoulou, Stergios Christodoulidis - - - Enhancing Channel Estimation for OTFS systems using Sparse Bayesian Learning with Adaptive Threshold - https://arxiv.org/abs/2512.07704 - arXiv:2512.07704v1 Announce Type: new -Abstract: Orthogonal time frequency space (OTFS) modulation is a two-dimensional modulation scheme designed in the delay-Doppler (DD) domain, exhibiting superior performance over orthogonal frequency division multiplexing (OFDM) modulation in environments with high Doppler frequency shifts. We investigated the channel estimation in the DD domain of OTFS systems, modeling it as a sparse signal recovery problem. Subsequently, within the existing sparse Bayesian learning framework, we proposed an adaptive Bayesian threshold-based active denoising mechanism. Combined with inverse-free sparse Bayesian learning, this effectively addresses the pseudo-peak issue in low signal-to-noise ratio (SNR) scenarios while maintaining low complexity. The simulation results demonstrate that this algorithm outperforms existing channel estimation algorithms in terms of anti-noise performance and complexity. - oai:arXiv.org:2512.07704v1 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tengfei Qi, Yifei Yang, Xiong Deng, Zhinan Sun, Ziqiang Gao, Xihua Zou, Wei Pan, Lianshan Yan - - - In-Context and Few-Shots Learning for Forecasting Time Series Data based on Large Language Models - https://arxiv.org/abs/2512.07705 - arXiv:2512.07705v1 Announce Type: new -Abstract: Existing data-driven approaches in modeling and predicting time series data include ARIMA (Autoregressive Integrated Moving Average), Transformer-based models, LSTM (Long Short-Term Memory) and TCN (Temporal Convolutional Network). These approaches, and in particular deep learning-based models such as LSTM and TCN, have shown great results in predicting time series data. With the advancement of leveraging pre-trained foundation models such as Large Language Models (LLMs) and more notably Google's recent foundation model for time series data, {\it TimesFM} (Time Series Foundation Model), it is of interest to investigate whether these foundation models have the capability of outperforming existing modeling approaches in analyzing and predicting time series data. - This paper investigates the performance of using LLM models for time series data prediction. We investigate the in-context learning methodology in the training of LLM models that are specific to the underlying application domain. More specifically, the paper explores training LLMs through in-context, zero-shot and few-shot learning and forecasting time series data with OpenAI {\tt o4-mini} and Gemini 2.5 Flash Lite, as well as the recent Google's Transformer-based TimesFM, a time series-specific foundation model, along with two deep learning models, namely TCN and LSTM networks. The findings indicate that TimesFM has the best overall performance with the lowest RMSE value (0.3023) and the competitive inference time (266 seconds). Furthermore, OpenAI's o4-mini also exhibits a good performance based on Zero Shot learning. - These findings highlight pre-trained time series foundation models as a promising direction for real-time forecasting, enabling accurate and scalable deployment with minimal model adaptation. - oai:arXiv.org:2512.07705v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Saroj Gopali, Bipin Chhetri, Deepika Giri, Sima Siami-Namini, Akbar Siami Namin - - - Each Prompt Matters: Scaling Reinforcement Learning Without Wasting Rollouts on Hundred-Billion-Scale MoE - https://arxiv.org/abs/2512.07710 - arXiv:2512.07710v1 Announce Type: new -Abstract: We present CompassMax-V3-Thinking, a hundred-billion-scale MoE reasoning model trained with a new RL framework built on one principle: each prompt must matter. Scaling RL to this size exposes critical inefficiencies-zero-variance prompts that waste rollouts, unstable importance sampling over long horizons, advantage inversion from standard reward models, and systemic bottlenecks in rollout processing. To overcome these challenges, we introduce several unified innovations: (1) Multi-Stage Zero-Variance Elimination, which filters out non-informative prompts and stabilizes group-based policy optimization (e.g. GRPO) by removing wasted rollouts; (2) ESPO, an entropy-adaptive optimization method that balances token-level and sequence-level importance sampling to maintain stable learning dynamics; (3) a Router Replay strategy that aligns training-time MoE router decisions with inference-time behavior to mitigate train-infer discrepancies, coupled with a reward model adjustment to prevent advantage inversion; (4) a high-throughput RL system with FP8-precision rollouts, overlapped reward computation, and length-aware scheduling to eliminate performance bottlenecks. Together, these contributions form a cohesive pipeline that makes RL on hundred-billion-scale MoE models stable and efficient. The resulting model delivers strong performance across both internal and public evaluations. - oai:arXiv.org:2512.07710v1 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Anxiang Zeng, Haibo Zhang, Hailing Zhang, Kaixiang Mo, Liang Yao, Ling Hu, Long Zhang, Shuman Liu, Shuyi Xie, Yanshi Li, Yizhang Chen, Yuepeng Sheng, Yuwei Huang, Zhaochen Xu, Zhiqiang Zhou, Ziqin Liew - - - UnCageNet: Tracking and Pose Estimation of Caged Animal - https://arxiv.org/abs/2512.07712 - arXiv:2512.07712v1 Announce Type: new -Abstract: Animal tracking and pose estimation systems, such as STEP (Simultaneous Tracking and Pose Estimation) and ViTPose, experience substantial performance drops when processing images and videos with cage structures and systematic occlusions. We present a three-stage preprocessing pipeline that addresses this limitation through: (1) cage segmentation using a Gabor-enhanced ResNet-UNet architecture with tunable orientation filters, (2) cage inpainting using CRFill for content-aware reconstruction of occluded regions, and (3) evaluation of pose estimation and tracking on the uncaged frames. Our Gabor-enhanced segmentation model leverages orientation-aware features with 72 directional kernels to accurately identify and segment cage structures that severely impair the performance of existing methods. Experimental validation demonstrates that removing cage occlusions through our pipeline enables pose estimation and tracking performance comparable to that in environments without occlusions. We also observe significant improvements in keypoint detection accuracy and trajectory consistency. - oai:arXiv.org:2512.07712v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - 10.1145/3774521.3774619 - Sayak Dutta, Harish Katti, Shashikant Verma, Shanmuganathan Raman - - - Research on a Monitoring System for High-Voltage Cables in a Coal Mine Based on Intelligent Sensing Technology - https://arxiv.org/abs/2512.07714 - arXiv:2512.07714v1 Announce Type: new -Abstract: Given the importance of monitoring the operational status of high-voltage cables in coal mines, this study investigates the application of intelligent sensing technology to the online monitoring of such cables. Taking an actual coal mine as a case study, a three-layer architecture high-voltage cable monitoring system was designed. The system employs high-frequency current sensors and distributed optical fiber temperature sensors to achieve real-time acquisition of partial discharge signals and temperature distribution data. Data analysis and fault diagnosis are performed through a combined approach of edge computing and cloud computing. The research results demonstrate that the system can accurately identify cable insulation defects and potential overheating hazards, with a diagnostic accuracy exceeding 95%, thereby significantly enhancing the reliability of power supply in mines. - oai:arXiv.org:2512.07714v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Z Gao, J Li, L Tao, B Meng - - - ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation - https://arxiv.org/abs/2512.07720 - arXiv:2512.07720v1 Announce Type: new -Abstract: Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction models, are fast and capable of producing stable body structures, but they often suffer from artifacts such as blurry textures and stiff, unnatural motion. In contrast, generative video models show promising performance by synthesizing photorealistic and dynamic results, but they frequently struggle with unstable behavior, including body structural errors and identity drift. To address these limitations, we propose a novel approach that combines the strengths of both paradigms. Our framework employs a 3D reconstruction model to provide robust structural and appearance priors, which in turn guides a real-time autoregressive video diffusion model for rendering. This process enables the model to synthesize high-frequency, photorealistic details and fluid dynamics in real time, effectively reducing texture blur and motion stiffness while preventing the structural inconsistencies common in video generation methods. By uniting the geometric stability of 3D reconstruction with the generative capabilities of video models, our method produces high-fidelity digital avatars with realistic appearance and dynamic, temporally coherent motion. Experiments demonstrate that our approach significantly reduces artifacts and achieves substantial improvements in visual quality over leading methods, providing a robust and efficient solution for real-time applications such as gaming and virtual reality. Project page: https://lhyfst.github.io/visa - oai:arXiv.org:2512.07720v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Fan Yang, Heyuan Li, Peihao Li, Weihao Yuan, Lingteng Qiu, Chaoyue Song, Cheng Chen, Yisheng He, Shifeng Zhang, Xiaoguang Han, Steven Hoi, Guosheng Lin - - - Enabling Delayed-Full Charging Through Transformer-Based Real-Time-to-Departure Modeling for EV Battery Longevity - https://arxiv.org/abs/2512.07723 - arXiv:2512.07723v1 Announce Type: new -Abstract: Electric vehicles (EVs) are key to sustainable mobility, yet their lithium-ion batteries (LIBs) degrade more rapidly under prolonged high states of charge (SOC). This can be mitigated by delaying full charging \ours until just before departure, which requires accurate prediction of user departure times. In this work, we propose Transformer-based real-time-to-event (TTE) model for accurate EV departure prediction. Our approach represents each day as a TTE sequence by discretizing time into grid-based tokens. Unlike previous methods primarily dependent on temporal dependency from historical patterns, our method leverages streaming contextual information to predict departures. Evaluation on a real-world study involving 93 users and passive smartphone data demonstrates that our method effectively captures irregular departure patterns within individual routines, outperforming baseline models. These results highlight the potential for practical deployment of the \ours algorithm and its contribution to sustainable transportation systems. - oai:arXiv.org:2512.07723v1 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yonggeon Lee, Jibin Hwang, Alfred Malengo Kondoro, Juhyun Song, Youngtae Noh - - - The Native Spiking Microarchitecture: From Iontronic Primitives to Bit-Exact FP8 Arithmetic - https://arxiv.org/abs/2512.07724 - arXiv:2512.07724v1 Announce Type: new -Abstract: The 2025 Nobel Prize in Chemistry for Metal-Organic Frameworks (MOFs) and recent breakthroughs by Huanting Wang's team at Monash University establish angstrom-scale channels as promising post-silicon substrates with native integrate-and-fire (IF) dynamics. However, utilizing these stochastic, analog materials for deterministic, bit-exact AI workloads (e.g., FP8) remains a paradox. Existing neuromorphic methods often settle for approximation, failing Transformer precision standards. To traverse the gap "from stochastic ions to deterministic floats," we propose a Native Spiking Microarchitecture. Treating noisy neurons as logic primitives, we introduce a Spatial Combinational Pipeline and a Sticky-Extra Correction mechanism. Validation across all 16,129 FP8 pairs confirms 100% bit-exact alignment with PyTorch. Crucially, our architecture reduces Linear layer latency to O(log N), yielding a 17x speedup. Physical simulations further demonstrate robustness against extreme membrane leakage (beta approx 0.01), effectively immunizing the system against the stochastic nature of the hardware. - oai:arXiv.org:2512.07724v1 - cs.ET - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhengzheng Tang - - - Privacy Practices of Browser Agents - https://arxiv.org/abs/2512.07725 - arXiv:2512.07725v1 Announce Type: new -Abstract: This paper presents a systematic evaluation of the privacy behaviors and attributes of eight recent, popular browser agents. Browser agents are software that automate Web browsing using large language models and ancillary tooling. However, the automated capabilities that make browser agents powerful also make them high-risk points of failure. Both the kinds of tasks browser agents are designed to execute, along with the kinds of information browser agents are entrusted with to fulfill those tasks, mean that vulnerabilities in these tools can result in enormous privacy harm. - This work presents a framework of five broad factors (totaling 15 distinct measurements) to measure the privacy risks in browser agents. Our framework assesses i. vulnerabilities in the browser agent's components, ii. how the browser agent protects against website behaviors, iii. whether the browser agent prevents cross-site tracking, iv. how the agent responds to privacy-affecting prompts, and v. whether the tool leaks personal information to sites. We apply our framework to eight browser agents and identify 30 vulnerabilities, ranging from disabled browser privacy features to "autocompleting" sensitive personal information in form fields. We have responsibly disclosed our findings, and plan to release our dataset and other artifacts. - oai:arXiv.org:2512.07725v1 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Alisha Ukani, Hamed Haddadi, Ali Shahin Shamsabadi, Peter Snyder - - - Multi-Generator Continual Learning for Robust Delay Prediction in 6G - https://arxiv.org/abs/2512.07726 - arXiv:2512.07726v1 Announce Type: new -Abstract: In future 6G networks, dependable networks will enable telecommunication services such as remote control of robots or vehicles with strict requirements on end-to-end network performance in terms of delay, delay variation, tail distributions, and throughput. With respect to such networks, it is paramount to be able to determine what performance level the network segment can guarantee at a given point in time. One promising approach is to use predictive models trained using machine learning (ML). Predicting performance metrics such as one-way delay (OWD), in a timely manner, provides valuable insights for the network, user equipments (UEs), and applications to address performance trends, deviations, and violations. Over the course of time, a dynamic network environment results in distributional shifts, which causes catastrophic forgetting and drop of ML model performance. In continual learning (CL), the model aims to achieve a balance between stability and plasticity, enabling new information to be learned while preserving previously learned knowledge. In this paper, we target on the challenges of catastrophic forgetting of OWD prediction model. We propose a novel approach which introducing the concept of multi-generator for the state-of-the-art CL generative replay framework, along with tabular variational autoencoders (TVAE) as generators. The domain knowledge of UE capabilities is incorporated into the learning process for determining generator setup and relevance. The proposed approach is evaluated across a diverse set of scenarios with data that is collected in a realistic 5G testbed, demonstrating its outstanding performance in comparison to baselines. - oai:arXiv.org:2512.07726v1 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaoyu Lan, Jalil Taghia, Hannes Larsson, Andreas Johnsson - - - On computing the (exact) Fr\'echet distance with a frog - https://arxiv.org/abs/2512.07728 - arXiv:2512.07728v1 Announce Type: new -Abstract: The continuous Frechet distance between two polygonal curves is classically computed by exploring their free space diagram. Recently, Har-Peled, Raichel, and Robson [SoCG'25] proposed a radically different approach: instead of directly traversing the continuous free space, they approximate the distance by computing paths in a discrete graph derived from the discrete free space, recursively bisecting edges until the discrete value converges to the continuous Frechet distance. They implement this so-called frog-based technique and report substantial practical speedups over the state of the art. - We revisit the frog-based approach and address three of its limitations. First, the method does not compute the Frechet distance exactly. Second, the recursive bisection procedure only introduces the monotonicity events required to realise the Frechet distance asymptotically, that is, only in the limit. Third, the applied simplification technique is heuristic. Motivated by theoretical considerations, we develop new techniques that guarantee exactness, polynomial-time convergence, and near-optimal lossless simplifications. We provide an open-source C++ implementation of our variant. - Our primary contribution is an extensive empirical evaluation. As expected, exact computation introduces overhead and increases the median running time. Yet, method is often faster in the worst case, the slowest ten percent of instances, or even on average due to its convergence guarantees. More surprisingly, in our experiments, the implementation of Bringmann, Kuennemann, and Nusser [SoCG'19] consistently outperforms all frog-based approaches in practice. This appears to contrast published claims of the efficiency of the frog-based techniques. These results thereby provide nuanced perspective on frogs: highlighting both the theoretical appeal, but also the practical limitations. - oai:arXiv.org:2512.07728v1 - cs.CG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Jacobus Conradi, Ivor van der Hoog, Eva Rotenberg - - - Improving action classification with brain-inspired deep networks - https://arxiv.org/abs/2512.07729 - arXiv:2512.07729v1 Announce Type: new -Abstract: Action recognition is also key for applications ranging from robotics to healthcare monitoring. Action information can be extracted from the body pose and movements, as well as from the background scene. However, the extent to which deep neural networks (DNNs) make use of information about the body and information about the background remains unclear. Since these two sources of information may be correlated within a training dataset, DNNs might learn to rely predominantly on one of them, without taking full advantage of the other. Unlike DNNs, humans have domain-specific brain regions selective for perceiving bodies, and regions selective for perceiving scenes. The present work tests whether humans are thus more effective at extracting information from both body and background, and whether building brain-inspired deep network architectures with separate domain-specific streams for body and scene perception endows them with more human-like performance. We first demonstrate that DNNs trained using the HAA500 dataset perform almost as accurately on versions of the stimuli that show both body and background and on versions of the stimuli from which the body was removed, but are at chance-level for versions of the stimuli from which the background was removed. Conversely, human participants (N=28) can recognize the same set of actions accurately with all three versions of the stimuli, and perform significantly better on stimuli that show only the body than on stimuli that show only the background. Finally, we implement and test a novel architecture patterned after domain specificity in the brain with separate streams to process body and background information. We show that 1) this architecture improves action recognition performance, and 2) its accuracy across different versions of the stimuli follows a pattern that matches more closely the pattern of accuracy observed in human participants. - oai:arXiv.org:2512.07729v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Aidas Aglinskas, Stefano Anzellotti - - - SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination - https://arxiv.org/abs/2512.07730 - arXiv:2512.07730v1 Announce Type: new -Abstract: Although Multimodal Large Language Models (MLLMs) have advanced substantially, they remain vulnerable to object hallucination caused by language priors and visual information loss. To address this, we propose SAVE (Sparse Autoencoder-Driven Visual Information Enhancement), a framework that mitigates hallucination by steering the model along Sparse Autoencoder (SAE) latent features. A binary object-presence question-answering probe identifies the SAE features most indicative of the model's visual information processing, referred to as visual understanding features. Steering the model along these identified features reinforces grounded visual understanding and effectively reduces hallucination. With its simple design, SAVE outperforms state-of-the-art training-free methods on standard benchmarks, achieving a 10\%p improvement in CHAIR\_S and consistent gains on POPE and MMHal-Bench. Extensive evaluations across multiple models and layers confirm the robustness and generalizability of our approach. Further analysis reveals that steering along visual understanding features suppresses the generation of uncertain object tokens and increases attention to image tokens, mitigating hallucination. Code is released at https://github.com/wiarae/SAVE. - oai:arXiv.org:2512.07730v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Sangha Park, Seungryong Yoo, Jisoo Mok, Sungroh Yoon - - - SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery - https://arxiv.org/abs/2512.07733 - arXiv:2512.07733v1 Announce Type: new -Abstract: Despite advancements in Multi-modal Large Language Models (MLLMs) for scene understanding, their performance on complex spatial reasoning tasks requiring mental simulation remains significantly limited. Current methods often rely on passive observation of spatial data, failing to internalize an active mental imagery process. To bridge this gap, we propose SpatialDreamer, a reinforcement learning framework that enables spatial reasoning through a closedloop process of active exploration, visual imagination via a world model, and evidence-grounded reasoning. To address the lack of fine-grained reward supervision in longhorizontal reasoning tasks, we propose Geometric Policy Optimization (GeoPO), which introduces tree-structured sampling and step-level reward estimation with geometric consistency constraints. Extensive experiments demonstrate that SpatialDreamer delivers highly competitive results across multiple challenging benchmarks, signifying a critical advancement in human-like active spatial mental simulation for MLLMs. - oai:arXiv.org:2512.07733v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Meng Cao, Xingyu Li, Xue Liu, Ian Reid, Xiaodan Liang - - - Time-asymptotic behavior of the Boltzmann equation with random inputs in whole space and its stochastic Galerkin approximation - https://arxiv.org/abs/2512.07735 - arXiv:2512.07735v1 Announce Type: new -Abstract: We consider the Boltzmann equation with random uncertainties arising from the initial data and collision kernel in the {\it whole space}, along with their stochastic Galerkin (SG) approximations. By employing Green's function method, we show that, the higher-order derivatives of the solution with respect to the random variable exhibit polynomial decay over time. These results are then applied to analyze the SG method for the SG system and to demonstrate the polynomial decay of the numerical error over time. - oai:arXiv.org:2512.07735v1 - math.NA - cs.NA - math.AP - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Shi Jin, Qi Shao, Haitao Wang - - - HLTCOE Evaluation Team at TREC 2025: VQA Track - https://arxiv.org/abs/2512.07738 - arXiv:2512.07738v1 Announce Type: new -Abstract: The HLTCOE Evaluation team participated in TREC VQA's Answer Generation (AG) task, for which we developed a listwise learning framework that aims to improve semantic precision and ranking consistency in answer generation. Given a video-question pair, a base multimodal model first generates multiple candidate answers, which are then reranked using a model trained with a novel Masked Pointer Cross-Entropy Loss with Rank Weights. This objective integrates pointer-based candidate selection, rank-dependent weighting, and masked cross-entropy under vocabulary restriction, enabling stable and interpretable listwise optimization. By bridging generative modeling with discriminative ranking, our method produces coherent, fine-grained answer lists. Experiments reveal consistent gains in accuracy and ranking stability, especially for questions requiring temporal reasoning and semantic disambiguation. - oai:arXiv.org:2512.07738v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Dengjia Zhang, Charles Weng, Katherine Guerrerio, Yi Lu, Kenton Murray, Alexander Martin, Reno Kriz, Benjamin Van Durme - - - A multimodal Bayesian Network for symptom-level depression and anxiety prediction from voice and speech data - https://arxiv.org/abs/2512.07741 - arXiv:2512.07741v1 Announce Type: new -Abstract: During psychiatric assessment, clinicians observe not only what patients report, but important nonverbal signs such as tone, speech rate, fluency, responsiveness, and body language. Weighing and integrating these different information sources is a challenging task and a good candidate for support by intelligence-driven tools - however this is yet to be realized in the clinic. Here, we argue that several important barriers to adoption can be addressed using Bayesian network modelling. To demonstrate this, we evaluate a model for depression and anxiety symptom prediction from voice and speech features in large-scale datasets (30,135 unique speakers). Alongside performance for conditions and symptoms (for depression, anxiety ROC-AUC=0.842,0.831 ECE=0.018,0.015; core individual symptom ROC-AUC>0.74), we assess demographic fairness and investigate integration across and redundancy between different input modality types. Clinical usefulness metrics and acceptability to mental health service users are explored. When provided with sufficiently rich and large-scale multimodal data streams and specified to represent common mental conditions at the symptom rather than disorder level, such models are a principled approach for building robust assessment support tools: providing clinically-relevant outputs in a transparent and explainable format that is directly amenable to expert clinical supervision. - oai:arXiv.org:2512.07741v1 - cs.LG - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Agnes Norbury, George Fairs, Alexandra L. Georgescu, Matthew M. Nour, Emilia Molimpakis, Stefano Goria - - - DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving - https://arxiv.org/abs/2512.07745 - arXiv:2512.07745v1 Announce Type: new -Abstract: Generative diffusion models for end-to-end autonomous driving often suffer from mode collapse, tending to generate conservative and homogeneous behaviors. While DiffusionDrive employs predefined anchors representing different driving intentions to partition the action space and generate diverse trajectories, its reliance on imitation learning lacks sufficient constraints, resulting in a dilemma between diversity and consistent high quality. In this work, we propose DiffusionDriveV2, which leverages reinforcement learning to both constrain low-quality modes and explore for superior trajectories. This significantly enhances the overall output quality while preserving the inherent multimodality of its core Gaussian Mixture Model. First, we use scale-adaptive multiplicative noise, ideal for trajectory planning, to promote broad exploration. Second, we employ intra-anchor GRPO to manage advantage estimation among samples generated from a single anchor, and inter-anchor truncated GRPO to incorporate a global perspective across different anchors, preventing improper advantage comparisons between distinct intentions (e.g., turning vs. going straight), which can lead to further mode collapse. DiffusionDriveV2 achieves 91.2 PDMS on the NAVSIM v1 dataset and 85.5 EPDMS on the NAVSIM v2 dataset in closed-loop evaluation with an aligned ResNet-34 backbone, setting a new record. Further experiments validate that our approach resolves the dilemma between diversity and consistent high quality for truncated diffusion models, achieving the best trade-off. Code and model will be available at https://github.com/hustvl/DiffusionDriveV2 - oai:arXiv.org:2512.07745v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jialv Zou, Shaoyu Chen, Bencheng Liao, Zhiyu Zheng, Yuehao Song, Lefei Zhang, Qian Zhang, Wenyu Liu, Xinggang Wang - - - Unison: A Fully Automatic, Task-Universal, and Low-Cost Framework for Unified Understanding and Generation - https://arxiv.org/abs/2512.07747 - arXiv:2512.07747v1 Announce Type: new -Abstract: Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive paradigm, and the other adopts a two-stage scheme connecting pre-trained understanding and generative models for alignment fine-tuning. The former demands massive data and computing resources unaffordable for ordinary researchers. Though the latter requires a lower training cost, existing works often suffer from limited task coverage or poor generation quality. Both approaches lack the ability to parse input meta-information (such as task type, image resolution, video duration, etc.) and require manual parameter configuration that is tedious and non-intelligent. In this paper, we propose Unison which adopts the two-stage scheme while preserving the capabilities of the pre-trained models well. With an extremely low training cost, we cover a variety of multimodal understanding tasks, including text, image, and video understanding, as well as diverse generation tasks, such as text-to-visual content generation, editing, controllable generation, and IP-based reference generation. We also equip our model with the ability to automatically parse user intentions, determine the target task type, and accurately extract the meta-information required for the corresponding task. This enables full automation of various multimodal tasks without human intervention. Experiments demonstrate that, under a low-cost setting of only 500k training samples and 50 GPU hours, our model can accurately and automatically identify tasks and extract relevant parameters, and achieve superior performance across a variety of understanding and generation tasks. - oai:arXiv.org:2512.07747v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shihao Zhao, Yitong Chen, Zeyinzi Jiang, Bojia Zi, Shaozhe Hao, Yu Liu, Chaojie Mao, Kwan-Yee K. Wong - - - The explicit game-theoretic linear quadratic regulator for constrained multi-agent systems - https://arxiv.org/abs/2512.07749 - arXiv:2512.07749v1 Announce Type: new -Abstract: We present an efficient algorithm to compute the explicit open-loop solution to both finite and infinite-horizon dynamic games subject to state and input constraints. Our approach relies on a multiparametric affine variational inequality characterization of the open-loop Nash equilibria and extends the classical explicit constrained LQR and MPC frameworks to multi-agent non-cooperative settings. A key practical implication is that linear-quadratic game-theoretic MPC becomes viable even at very high sampling rates for multi-agent systems of moderate size. Extensive numerical experiments demonstrate order-of-magnitude improvements in online computation time and solution accuracy compared with state-of-the-art game-theoretic solvers. - oai:arXiv.org:2512.07749v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Emilio Benenati, Giuseppe Belgioioso - - - A Performance Analyzer for a Public Cloud's ML-Augmented VM Allocator - https://arxiv.org/abs/2512.07750 - arXiv:2512.07750v1 Announce Type: new -Abstract: Many operational cloud systems use one or more machine learning models that help them achieve better efficiency and performance. But operators do not have tools to help them understand how each model and the interaction between them affect the end-to-end system performance. SANJESH is such a tool. SANJESH supports a diverse set of performance-related queries which we answer through a bi-level optimization. We invent novel mechanisms to solve this optimization more quickly. These techniques allow us to solve an optimization which prior work failed to solve even after $24$ hours. - As a proof of concept, we apply SANJESH to an example production system that uses multiple ML models to optimize virtual machine (VM) placement. These models impact how many servers the operators uses to host VMs and the frequency with which it has to live-migrate them because the servers run out of resources. SANJESH finds scenarios where these models cause $~4\times$ worse performance than what simulation-based approaches detect. - oai:arXiv.org:2512.07750v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Roozbeh Bostandoost, Pooria Namyar, Siva Kesava Reddy Kakarla, Ryan Beckett, Santiago Segarra, Eli Cortez, Ankur Mallick, Kevin Hsieh, Rodrigo Fonseca, Mohammad Hajiesmaili, Behnaz Arzani - - - UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction - https://arxiv.org/abs/2512.07756 - arXiv:2512.07756v1 Announce Type: new -Abstract: Clinical ultrasound acquisition is highly operator-dependent, where rapid probe motion and brightness fluctuations often lead to reconstruction errors that reduce trust and clinical utility. We present UltrasODM, a dual-stream framework that assists sonographers during acquisition through calibrated per-frame uncertainty, saliency-based diagnostics, and actionable prompts. UltrasODM integrates (i) a contrastive ranking module that groups frames by motion similarity, (ii) an optical-flow stream fused with Dual-Mamba temporal modules for robust 6-DoF pose estimation, and (iii) a Human-in-the-Loop (HITL) layer combining Bayesian uncertainty, clinician-calibrated thresholds, and saliency maps highlighting regions of low confidence. When uncertainty exceeds the threshold, the system issues unobtrusive alerts suggesting corrective actions such as re-scanning highlighted regions or slowing the sweep. Evaluated on a clinical freehand ultrasound dataset, UltrasODM reduces drift by 15.2%, distance error by 12.1%, and Hausdorff distance by 10.1% relative to UltrasOM, while producing per-frame uncertainty and saliency outputs. By emphasizing transparency and clinician feedback, UltrasODM improves reconstruction reliability and supports safer, more trustworthy clinical workflows. Our code is publicly available at https://github.com/AnandMayank/UltrasODM. - oai:arXiv.org:2512.07756v1 - cs.CV - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Mayank Anand, Ujair Alam, Surya Prakash, Priya Shukla, Gora Chand Nandi, Domenec Puig - - - Augmented Neural Ordinary Differential Equations for Power System Identification - https://arxiv.org/abs/2512.07757 - arXiv:2512.07757v1 Announce Type: new -Abstract: Due the complexity of modern power systems, modeling based on first-order principles becomes increasingly difficult. As an alternative, dynamical models for simulation and control design can be obtained by black-box identification techniques. One such technique for the identification of continuous-time systems are neural ordinary differential equations. For training and inference, they require initial values of system states, such as phase angles and frequencies. While frequencies can typically be measured, phase angle measurements are usually not available. To tackle this problem, we propose a novel structure based on augmented neural ordinary differential equations, learning latent phase angle representations on historic observations with temporal convolutional networks. Our approach combines state-of-the art deep learning techniques, avoiding the necessity of phase angle information for the power system identification. Results show, that our approach clearly outperforms simpler augmentation techniques. - oai:arXiv.org:2512.07757v1 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hannes M. H. Wolf, Christian A. Hans - - - Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification - https://arxiv.org/abs/2512.07760 - arXiv:2512.07760v1 Announce Type: new -Abstract: Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation. Given the significant gap across visible and infrared modality, estimating reliable cross-modality association becomes a major challenge in USVI-ReID. Existing methods usually adopt optimal transport to associate the intra-modality clusters, which is prone to propagating the local cluster errors, and also overlooks global instance-level relations. By mining and attending to the visible-infrared modality bias, this paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning. Motivated by the camera-aware distance rectification in single-modality re-ID, we propose modality-aware Jaccard distance to mitigate the distance bias caused by modality discrepancy, so that more reliable cross-modality associations can be estimated through global clustering. To further improve cross-modality representation learning, a `split-and-contrast' strategy is designed to obtain modality-specific global prototypes. By explicitly aligning these prototypes under global association guidance, modality-invariant yet ID-discriminative representation learning can be achieved. While conceptually simple, our method obtains state-of-the-art performance on benchmark VI-ReID datasets and outperforms existing methods by a significant margin, validating its effectiveness. - oai:arXiv.org:2512.07760v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Menglin Wang, Xiaojin Gong, Jiachen Li, Genlin Ji - - - RL-MTJail: Reinforcement Learning for Automated Black-Box Multi-Turn Jailbreaking of Large Language Models - https://arxiv.org/abs/2512.07761 - arXiv:2512.07761v1 Announce Type: new -Abstract: Large language models are vulnerable to jailbreak attacks, threatening their safe deployment in real-world applications. This paper studies black-box multi-turn jailbreaks, aiming to train attacker LLMs to elicit harmful content from black-box models through a sequence of prompt-output interactions. Existing approaches typically rely on single turn optimization, which is insufficient for learning long-term attack strategies. To bridge this gap, we formulate the problem as a multi-turn reinforcement learning task, directly optimizing the harmfulness of the final-turn output as the outcome reward. To mitigate sparse supervision and promote long-term attack strategies, we propose two heuristic process rewards: (1) controlling the harmfulness of intermediate outputs to prevent triggering the black-box model's rejection mechanisms, and (2) maintaining the semantic relevance of intermediate outputs to avoid drifting into irrelevant content. Experimental results on multiple benchmarks show consistently improved attack success rates across multiple models, highlighting the effectiveness of our approach. The code is available at https://github.com/xxiqiao/RL-MTJail. Warning: This paper contains examples of harmful content. - oai:arXiv.org:2512.07761v1 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fuli Feng, Xiangnan He - - - Toward Seamless Physical Human-Humanoid Interaction: Insights from Control, Intent, and Modeling with a Vision for What Comes Next - https://arxiv.org/abs/2512.07765 - arXiv:2512.07765v1 Announce Type: new -Abstract: Physical Human-Humanoid Interaction (pHHI) is a rapidly advancing field with significant implications for deploying robots in unstructured, human-centric environments. In this review, we examine the current state of the art in pHHI through three core pillars: (i) humanoid modeling and control, (ii) human intent estimation, and (iii) computational human models. For each pillar, we survey representative approaches, identify open challenges, and analyze current limitations that hinder robust, scalable, and adaptive interaction. These include the need for whole-body control strategies capable of handling uncertain human dynamics, real-time intent inference under limited sensing, and modeling techniques that account for variability in human physical states. Although significant progress has been made within each domain, integration across pillars remains limited. We propose pathways for unifying methods across these areas to enable cohesive interaction frameworks. This structure enables us not only to map the current landscape but also to propose concrete directions for future research that aim to bridge these domains. Additionally, we introduce a unified taxonomy of interaction types based on modality, distinguishing between direct interactions (e.g., physical contact) and indirect interactions (e.g., object-mediated), and on the level of robot engagement, ranging from assistance to cooperation and collaboration. For each category in this taxonomy, we provide the three core pillars that highlight opportunities for cross-pillar unification. Our goal is to suggest avenues to advance robust, safe, and intuitive physical interaction, providing a roadmap for future research that will allow humanoid systems to effectively understand, anticipate, and collaborate with human partners in diverse real-world settings. - oai:arXiv.org:2512.07765v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Gustavo A. Cardona, Shubham S. Kumbhar, Panagiotis Artemiadis - - - Formalized Hopfield Networks and Boltzmann Machines - https://arxiv.org/abs/2512.07766 - arXiv:2512.07766v1 Announce Type: new -Abstract: Neural networks are widely used, yet their analysis and verification remain challenging. In this work, we present a Lean 4 formalization of neural networks, covering both deterministic and stochastic models. We first formalize Hopfield networks, recurrent networks that store patterns as stable states. We prove convergence and the correctness of Hebbian learning, a training rule that updates network parameters to encode patterns, here limited to the case of pairwise-orthogonal patterns. We then consider stochastic networks, where updates are probabilistic and convergence is to a stationary distribution. As a canonical example, we formalize the dynamics of Boltzmann machines and prove their ergodicity, showing convergence to a unique stationary distribution using a new formalization of the Perron-Frobenius theorem. - oai:arXiv.org:2512.07766v1 - cs.LG - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Matteo Cipollina, Michail Karatarakis, Freek Wiedijk - - - OptMap: Geometric Map Distillation via Submodular Maximization - https://arxiv.org/abs/2512.07775 - arXiv:2512.07775v1 Announce Type: new -Abstract: Autonomous robots rely on geometric maps to inform a diverse set of perception and decision-making algorithms. As autonomy requires reasoning and planning on multiple scales of the environment, each algorithm may require a different map for optimal performance. Light Detection And Ranging (LiDAR) sensors generate an abundance of geometric data to satisfy these diverse requirements, but selecting informative, size-constrained maps is computationally challenging as it requires solving an NP-hard combinatorial optimization. In this work we present OptMap: a geometric map distillation algorithm which achieves real-time, application-specific map generation via multiple theoretical and algorithmic innovations. A central feature is the maximization of set functions that exhibit diminishing returns, i.e., submodularity, using polynomial-time algorithms with provably near-optimal solutions. We formulate a novel submodular reward function which quantifies informativeness, reduces input set sizes, and minimizes bias in sequentially collected datasets. Further, we propose a dynamically reordered streaming submodular algorithm which improves empirical solution quality and addresses input order bias via an online approximation of the value of all scans. Testing was conducted on open-source and custom datasets with an emphasis on long-duration mapping sessions, highlighting OptMap's minimal computation requirements. Open-source ROS1 and ROS2 packages are available and can be used alongside any LiDAR SLAM algorithm. - oai:arXiv.org:2512.07775v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - David Thorne, Nathan Chan, Christa S. Robison, Philip R. Osteen, Brett T. Lopez - - - GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring - https://arxiv.org/abs/2512.07776 - arXiv:2512.07776v1 Announce Type: new -Abstract: Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals from vast archives of camera trap footage. The primary obstacle to automating this process has been the lack of large-scale, "in-the-wild" video datasets suitable for training robust deep learning models. To address this gap, we introduce a comprehensive benchmark with three novel datasets: Gorilla-SPAC-Wild, the largest video dataset for wild primate re-identification to date; Gorilla-Berlin-Zoo, for assessing cross-domain re-identification generalization; and Gorilla-SPAC-MoT, for evaluating multi-object tracking in camera trap footage. Building on these datasets, we present GorillaWatch, an end-to-end pipeline integrating detection, tracking, and re-identification. To exploit temporal information, we introduce a multi-frame self-supervised pretraining strategy that leverages consistency in tracklets to learn domain-specific features without manual labels. To ensure scientific validity, a differentiable adaptation of AttnLRP verifies that our model relies on discriminative biometric traits rather than background correlations. Extensive benchmarking subsequently demonstrates that aggregating features from large-scale image backbones outperforms specialized video architectures. Finally, we address unsupervised population counting by integrating spatiotemporal constraints into standard clustering to mitigate over-segmentation. We publicly release all code and datasets to facilitate scalable, non-invasive monitoring of endangered species - oai:arXiv.org:2512.07776v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Maximilian Schall, Felix Leonard Kn\"ofel, Noah Elias K\"onig, Jan Jonas Kubeler, Maximilian von Klinski, Joan Wilhelm Linnemann, Xiaoshi Liu, Iven Jelle Schlegelmilch, Ole Woyciniuk, Alexandra Schild, Dante Wasmuht, Magdalena Bermejo Espinet, German Illera Basas, Gerard de Melo - - - Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives? - https://arxiv.org/abs/2512.07777 - arXiv:2512.07777v1 Announce Type: new -Abstract: Leveraging a dataset of paired narratives, we investigate the extent to which large language models (LLMs) can reliably separate incoherent and coherent stories. A probing study finds that LLMs' internal representations can reliably identify incoherent narratives. However, LLMs generate responses to rating questions that fail to satisfactorily separate the coherent and incoherent narratives across several prompt variations, hinting at a gap in LLM's understanding of storytelling. The reasoning LLMs tested do not eliminate these deficits, indicating that thought strings may not be able to fully address the discrepancy between model internal state and behavior. Additionally, we find that LLMs appear to be more sensitive to incoherence resulting from an event that violates the setting (e.g., a rainy day in the desert) than to incoherence arising from a character violating an established trait (e.g., Mary, a vegetarian, later orders a cheeseburger), suggesting that LLMs may rely more on prototypical world knowledge than building meaning-based narrative coherence. The consistent asymmetry found in our results suggests that LLMs do not have a complete grasp on narrative coherence. - oai:arXiv.org:2512.07777v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Karin de Langis, P\"uren \"Oncel, Ryan Peters, Andrew Elfenbein, Laura Kristen Allen, Andreas Schramm, Dongyeop Kang - - - Distribution Matching Variational AutoEncoder - https://arxiv.org/abs/2512.07778 - arXiv:2512.07778v1 Announce Type: new -Abstract: Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space without explicitly shaping its distribution, making it unclear which types of distributions are optimal for modeling. We introduce \textbf{Distribution-Matching VAE} (\textbf{DMVAE}), which explicitly aligns the encoder's latent distribution with an arbitrary reference distribution via a distribution matching constraint. This generalizes beyond the Gaussian prior of conventional VAEs, enabling alignment with distributions derived from self-supervised features, diffusion noise, or other prior distributions. With DMVAE, we can systematically investigate which latent distributions are more conducive to modeling, and we find that SSL-derived distributions provide an excellent balance between reconstruction fidelity and modeling efficiency, reaching gFID equals 3.2 on ImageNet with only 64 training epochs. Our results suggest that choosing a suitable latent distribution structure (achieved via distribution-level alignment), rather than relying on fixed priors, is key to bridging the gap between easy-to-model latents and high-fidelity image synthesis. Code is avaliable at https://github.com/sen-ye/dmvae. - oai:arXiv.org:2512.07778v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Sen Ye, Jianning Pei, Mengde Xu, Shuyang Gu, Chunyu Wang, Liwei Wang, Han Hu - - - GatedFWA: Linear Flash Windowed Attention with Gated Associative Memory - https://arxiv.org/abs/2512.07782 - arXiv:2512.07782v1 Announce Type: new -Abstract: Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention pattern, but under an \textit{Associative Memory} interpretation, its difference-style update renders the training objective effectively \emph{unbounded}. In contrast, Softmax attention normalizes updates, leading to \emph{memory shrinkage and gradient vanishing}. We propose GatedFWA: a Memory-\underline{Gated} (\underline{F}lash) \underline{W}indowed \underline{A}ttention mechanism that preserves SWAs efficiency while stabilizing memory updates and making gradient flow controllable. In essence, GatedFWA accumulate a per-token/head gate into a decay bias added to the attention logits, acting as a learnable contraction in the memory recurrence. We implement a fused one-pass gate preprocessing and a FlashAttention-compatible kernel that injects the gate under a sliding mask, ensuring I/O efficiency and numerical stability. On language modelling benchmarks, GatedFWA delivers competitive throughput with negligible overhead and better use of global context, and it integrates cleanly with token compression/selection methods such as NSA and generalizes to various autoregressive domains. - oai:arXiv.org:2512.07782v1 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiaxu Liu, Yuhe Bai, Christos-Savvas Bouganis - - - On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models - https://arxiv.org/abs/2512.07783 - arXiv:2512.07783v1 Announce Type: new -Abstract: Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during pre-training. A central challenge is the lack of control in modern training pipelines: large-scale pre-training corpora are opaque, mid-training is often underexamined, and RL objectives interact with unknown prior knowledge in complex ways. To resolve this ambiguity, we develop a fully controlled experimental framework that isolates the causal contributions of pre-training, mid-training, and RL-based post-training. Our approach employs synthetic reasoning tasks with explicit atomic operations, parseable step-by-step reasoning traces, and systematic manipulation of training distributions. We evaluate models along two axes: extrapolative generalization to more complex compositions and contextual generalization across surface contexts. Using this framework, we reconcile competing views on RL's effectiveness. We show that: 1) RL produces true capability gains (pass@128) only when pre-training leaves sufficient headroom and when RL data target the model's edge of competence, tasks at the boundary that are difficult but not yet out of reach. 2) Contextual generalization requires minimal yet sufficient pre-training exposure, after which RL can reliably transfer. 3) Mid-training significantly enhances performance under fixed compute compared with RL only, demonstrating its central but underexplored role in training pipelines. 4) Process-level rewards reduce reward hacking and improve reasoning fidelity. Together, these results clarify the interplay between pre-training, mid-training, and RL, offering a foundation for understanding and improving reasoning LM training strategies. - oai:arXiv.org:2512.07783v1 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Charlie Zhang, Graham Neubig, Xiang Yue - - - Designing Co-operation in Systems of Hierarchical, Multi-objective Schedulers for Stream Processing - https://arxiv.org/abs/2512.07792 - arXiv:2512.07792v1 Announce Type: new -Abstract: Stream processing is a computing paradigm that supports real-time data processing for a wide variety of applications. At Meta, it's used across the company for various tasks such as deriving product insights, providing and improving user services, and enabling AI at scale for our ever-growing user base. Meta's current stream processing framework supports processing TerraBytes(TBs) of data in mere seconds. This is enabled by our efficient schedulers and multi-layered infrastructure, which allocate workloads across various compute resources, working together in hierarchies across various parts of the infrastructure. But with the ever growing complexity of applications, and user needs, areas of the infrastructure that previously required minimal load balancing, now must be made more robust and proactive to application load. In our work we explore how to build and design such a system that focuses on load balancing over key compute resources and properties of these applications. We also showcase how to integrate new schedulers into the hierarchy of the existing ones, allowing multiple schedulers to work together and perform load balancing, at their infrastructure level, effectively. - oai:arXiv.org:2512.07792v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Animesh Dangwal, Yufeng Jiang, Charlie Arnold, Jun Fan, Mohamed Bassem, Aish Rajagopal - - - ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning - https://arxiv.org/abs/2512.07795 - arXiv:2512.07795v1 Announce Type: new -Abstract: Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, current evaluation practices overwhelmingly report single-run accuracy while ignoring the intrinsic uncertainty that naturally arises from stochastic decoding. This omission creates a blind spot because practitioners cannot reliably assess whether a method's reported performance is stable, reproducible, or cost-consistent. We introduce ReasonBENCH, the first benchmark designed to quantify the underlying instability in LLM reasoning. ReasonBENCH provides (i) a modular evaluation library that standardizes reasoning frameworks, models, and tasks, (ii) a multi-run protocol that reports statistically reliable metrics for both quality and cost, and (iii) a public leaderboard to encourage variance-aware reporting. Across tasks from different domains, we find that the vast majority of reasoning strategies and models exhibit high instability. Notably, even strategies with similar average performance can display confidence intervals up to four times wider, and the top-performing methods often incur higher and less stable costs. Such instability compromises reproducibility across runs and, consequently, the reliability of reported performance. To better understand these dynamics, we further analyze the impact of prompts, model families, and scale on the trade-off between solve rate and stability. Our results highlight reproducibility as a critical dimension for reliable LLM reasoning and provide a foundation for future reasoning methods and uncertainty quantification techniques. ReasonBENCH is publicly available at https://github.com/au-clan/ReasonBench . - oai:arXiv.org:2512.07795v1 - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Nearchos Potamitis, Lars Klein, Akhil Arora - - - Large Causal Models from Large Language Models - https://arxiv.org/abs/2512.07796 - arXiv:2512.07796v1 Announce Type: new -Abstract: We introduce a new paradigm for building large causal models (LCMs) that exploits the enormous potential latent in today's large language models (LLMs). We describe our ongoing experiments with an implemented system called DEMOCRITUS (Decentralized Extraction of Manifold Ontologies of Causal Relations Integrating Topos Universal Slices) aimed at building, organizing, and visualizing LCMs that span disparate domains extracted from carefully targeted textual queries to LLMs. DEMOCRITUS is methodologically distinct from traditional narrow domain and hypothesis centered causal inference that builds causal models from experiments that produce numerical data. A high-quality LLM is used to propose topics, generate causal questions, and extract plausible causal statements from a diverse range of domains. The technical challenge is then to take these isolated, fragmented, potentially ambiguous and possibly conflicting causal claims, and weave them into a coherent whole, converting them into relational causal triples and embedding them into a LCM. Addressing this technical challenge required inventing new categorical machine learning methods, which we can only briefly summarize in this paper, as it is focused more on the systems side of building DEMOCRITUS. We describe the implementation pipeline for DEMOCRITUS comprising of six modules, examine its computational cost profile to determine where the current bottlenecks in scaling the system to larger models. We describe the results of using DEMOCRITUS over a wide range of domains, spanning archaeology, biology, climate change, economics, medicine and technology. We discuss the limitations of the current DEMOCRITUS system, and outline directions for extending its capabilities. - oai:arXiv.org:2512.07796v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Sridhar Mahadevan - - - LLM Use for Mental Health: Crowdsourcing Users' Sentiment-based Perspectives and Values from Social Discussions - https://arxiv.org/abs/2512.07797 - arXiv:2512.07797v1 Announce Type: new -Abstract: Large language models (LLMs) chatbots like ChatGPT are increasingly used for mental health support. They offer accessible, therapeutic support but also raise concerns about misinformation, over-reliance, and risks in high-stakes contexts of mental health. We crowdsource large-scale users' posts from six major social media platforms to examine how people discuss their interactions with LLM chatbots across different mental health conditions. Through an LLM-assisted pipeline grounded in Value-Sensitive Design (VSD), we mapped the relationships across user-reported sentiments, mental health conditions, perspectives, and values. Our results reveal that the use of LLM chatbots is condition-specific. Users with neurodivergent conditions (e.g., ADHD, ASD) report strong positive sentiments and instrumental or appraisal support, whereas higher-risk disorders (e.g., schizophrenia, bipolar disorder) show more negative sentiments. We further uncover how user perspectives co-occur with underlying values, such as identity, autonomy, and privacy. Finally, we discuss shifting from "one-size-fits-all" chatbot design toward condition-specific, value-sensitive LLM design. - oai:arXiv.org:2512.07797v1 - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Lingyao Li, Xiaoshan Huang, Renkai Ma, Ben Zefeng Zhang, Haolun Wu, Fan Yang, Chen Chen - - - Quantifying the Carbon Reduction of DAG Workloads: A Job Shop Scheduling Perspective - https://arxiv.org/abs/2512.07799 - arXiv:2512.07799v1 Announce Type: new -Abstract: Carbon-aware schedulers aim to reduce the operational carbon footprint of data centers by running flexible workloads during periods of low carbon intensity. Most schedulers treat workloads as single monolithic tasks, ignoring that many jobs, like video encoding or offline inference, consist of smaller tasks with specific dependencies and resource needs; however, knowledge of this structure enables opportunities for greater carbon efficiency. - We quantify the maximum benefit of a dependency-aware approach for batch workloads. We model the problem as a flexible job-shop scheduling variant and use an offline solver to compute upper bounds on carbon and energy savings. Results show up to $25\%$ lower carbon emissions on average without increasing the optimal makespan (total job completion time) compared to a makespan-only baseline. Although in heterogeneous server setup, these schedules may use more energy than energy-optimal ones. Our results also show that allowing twice the optimal makespan nearly doubles the carbon savings, underscoring the tension between carbon, energy, and makespan. We also highlight key factors such as job structure and server count influence the achievable carbon reductions. - oai:arXiv.org:2512.07799v1 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Roozbeh Bostandoost, Adam Lechowicz, Walid A. Hanafy, Prashant Shenoy, Mohammad Hajiesmaili - - - Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support - https://arxiv.org/abs/2512.07801 - arXiv:2512.07801v1 Announce Type: new -Abstract: LLM-based agents are rapidly being plugged into expert decision-support, yet in messy, high-stakes settings they rarely make the team smarter: human-AI teams often underperform the best individual, experts oscillate between verification loops and over-reliance, and the promised complementarity does not materialise. We argue this is not just a matter of accuracy, but a fundamental gap in how we conceive AI assistance: expert decisions are made through collaborative cognitive processes where mental models, goals, and constraints are continually co-constructed, tested, and revised between human and AI. We propose Collaborative Causal Sensemaking (CCS) as a research agenda and organizing framework for decision-support agents: systems designed as partners in cognitive work, maintaining evolving models of how particular experts reason, helping articulate and revise goals, co-constructing and stress-testing causal hypotheses, and learning from the outcomes of joint decisions so that both human and agent improve over time. We sketch challenges around training ecologies that make collaborative thinking instrumentally valuable, representations and interaction protocols for co-authored models, and evaluation centred on trust and complementarity. These directions can reframe MAS research around agents that participate in collaborative sensemaking and act as AI teammates that think with their human partners. - oai:arXiv.org:2512.07801v1 - cs.CL - cs.AI - cs.HC - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Raunak Jain, Mudita Khurana - - - OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory - https://arxiv.org/abs/2512.07802 - arXiv:2512.07802v1 Announce Type: new -Abstract: Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrative. However, existing multi-shot video generation (MSV) methods struggle to effectively model long-range cross-shot context, as they rely on limited temporal windows or single keyframe conditioning, leading to degraded performance under complex narratives. In this work, we propose OneStory, enabling global yet compact cross-shot context modeling for consistent and scalable narrative generation. OneStory reformulates MSV as a next-shot generation task, enabling autoregressive shot synthesis while leveraging pretrained image-to-video (I2V) models for strong visual conditioning. We introduce two key modules: a Frame Selection module that constructs a semantically-relevant global memory based on informative frames from prior shots, and an Adaptive Conditioner that performs importance-guided patchification to generate compact context for direct conditioning. We further curate a high-quality multi-shot dataset with referential captions to mirror real-world storytelling patterns, and design effective training strategies under the next-shot paradigm. Finetuned from a pretrained I2V model on our curated 60K dataset, OneStory achieves state-of-the-art narrative coherence across diverse and complex scenes in both text- and image-conditioned settings, enabling controllable and immersive long-form video storytelling. - oai:arXiv.org:2512.07802v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Zhaochong An, Menglin Jia, Haonan Qiu, Zijian Zhou, Xiaoke Huang, Zhiheng Liu, Weiming Ren, Kumara Kahatapitiya, Ding Liu, Sen He, Chenyang Zhang, Tao Xiang, Fanny Yang, Serge Belongie, Tian Xie - - - Group Representational Position Encoding - https://arxiv.org/abs/2512.07805 - arXiv:2512.07805v1 Announce Type: new -Abstract: We present GRAPE (Group RepresentAtional Position Encoding), a unified framework for positional encoding based on group actions. GRAPE brings together two families of mechanisms: (i) multiplicative rotations (Multiplicative GRAPE) in $\mathrm{SO}(d)$ and (ii) additive logit biases (Additive GRAPE) arising from unipotent actions in the general linear group $\mathrm{GL}$. In Multiplicative GRAPE, a position $n \in \mathbb{Z}$ (or $t \in \mathbb{R}$) acts as $\mathbf{G}(n)=\exp(n\,\omega\,\mathbf{L})$ with a rank-2 skew generator $\mathbf{L} \in \mathbb{R}^{d \times d}$, yielding a relative, compositional, norm-preserving map with a closed-form matrix exponential. RoPE is recovered exactly when the $d/2$ planes are the canonical coordinate pairs with log-uniform spectrum. Learned commuting subspaces and compact non-commuting mixtures strictly extend this geometry to capture cross-subspace feature coupling at $O(d)$ and $O(r d)$ cost per head, respectively. In Additive GRAPE, additive logits arise as rank-1 (or low-rank) unipotent actions, recovering ALiBi and the Forgetting Transformer (FoX) as exact special cases while preserving an exact relative law and streaming cacheability. Altogether, GRAPE supplies a principled design space for positional geometry in long-context models, subsuming RoPE and ALiBi as special cases. Project Page: https://github.com/model-architectures/GRAPE. - oai:arXiv.org:2512.07805v1 - cs.LG - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yifan Zhang, Zixiang Chen, Yifeng Liu, Zhen Qin, Huizhuo Yuan, Kangping Xu, Yang Yuan, Quanquan Gu, Andrew Chi-Chih Yao - - - Multi-view Pyramid Transformer: Look Coarser to See Broader - https://arxiv.org/abs/2512.07806 - arXiv:2512.07806v1 Announce Type: new -Abstract: We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a single forward pass. Drawing on the idea of ``looking broader to see the whole, looking finer to see the details," MVP is built on two core design principles: 1) a local-to-global inter-view hierarchy that gradually broadens the model's perspective from local views to groups and ultimately the full scene, and 2) a fine-to-coarse intra-view hierarchy that starts from detailed spatial representations and progressively aggregates them into compact, information-dense tokens. This dual hierarchy achieves both computational efficiency and representational richness, enabling fast reconstruction of large and complex scenes. We validate MVP on diverse datasets and show that, when coupled with 3D Gaussian Splatting as the underlying 3D representation, it achieves state-of-the-art generalizable reconstruction quality while maintaining high efficiency and scalability across a wide range of view configurations. - oai:arXiv.org:2512.07806v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-sa/4.0/ - Gyeongjin Kang, Seungkwon Yang, Seungtae Nam, Younggeun Lee, Jungwoo Kim, Eunbyung Park - - - Lang3D-XL: Language Embedded 3D Gaussians for Large-scale Scenes - https://arxiv.org/abs/2512.07807 - arXiv:2512.07807v1 Announce Type: new -Abstract: Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. This allows for a more intuitive human-computer interaction, enabling querying or editing scenes using natural language, and could potentially improve tasks like scene retrieval, navigation, and multimodal reasoning. While such capabilities could be transformative, in particular for large-scale scenes, we find that recent feature distillation approaches cannot effectively learn over massive Internet data due to challenges in semantic feature misalignment and inefficiency in memory and runtime. To this end, we propose a novel approach to address these challenges. First, we introduce extremely low-dimensional semantic bottleneck features as part of the underlying 3D Gaussian representation. These are processed by rendering and passing them through a multi-resolution, feature-based, hash encoder. This significantly improves efficiency both in runtime and GPU memory. Second, we introduce an Attenuated Downsampler module and propose several regularizations addressing the semantic misalignment of ground truth 2D features. We evaluate our method on the in-the-wild HolyScenes dataset and demonstrate that it surpasses existing approaches in both performance and efficiency. - oai:arXiv.org:2512.07807v1 - cs.CV - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shai Krakovsky, Gal Fiebelman, Sagie Benaim, Hadar Averbuch-Elor - - - Auditing Games for Sandbagging - https://arxiv.org/abs/2512.07810 - arXiv:2512.07810v1 Announce Type: new -Abstract: Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagging detection techniques using an auditing game. First, a red team fine-tuned five models, some of which conditionally underperformed, as a proxy for sandbagging. Second, a blue team used black-box, model-internals, or training-based approaches to identify sandbagging models. We found that the blue team could not reliably discriminate sandbaggers from benign models. Black-box approaches were defeated by effective imitation of a weaker model. Linear probes, a model-internals approach, showed more promise but their naive application was vulnerable to behaviours instilled by the red team. We also explored capability elicitation as a strategy for detecting sandbagging. Although Prompt-based elicitation was not reliable, training-based elicitation consistently elicited full performance from the sandbagging models, using only a single correct demonstration of the evaluation task. However the performance of benign models was sometimes also raised, so relying on elicitation as a detection strategy was prone to false-positives. In the short-term, we recommend developers remove potential sandbagging using on-distribution training for elicitation. In the longer-term, further research is needed to ensure the efficacy of training-based elicitation, and develop robust methods for sandbagging detection. We open source our model organisms at https://github.com/AI-Safety-Institute/sandbagging_auditing_games and select transcripts and results at https://huggingface.co/datasets/sandbagging-games/evaluation_logs . A demo illustrating the game can be played at https://sandbagging-demo.far.ai/ . - oai:arXiv.org:2512.07810v1 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Jordan Taylor, Sid Black, Dillon Bowen, Thomas Read, Satvik Golechha, Alex Zelenka-Martin, Oliver Makins, Connor Kissane, Kola Ayonrinde, Jacob Merizian, Samuel Marks, Chris Cundy, Joseph Bloom - - - Inchworm-Inspired Soft Robot with Groove-Guided Locomotion - https://arxiv.org/abs/2512.07813 - arXiv:2512.07813v1 Announce Type: new -Abstract: Soft robots require directional control to navigate complex terrains. However, achieving such control often requires multiple actuators, which increases mechanical complexity, complicates control systems, and raises energy consumption. Here, we introduce an inchworm-inspired soft robot whose locomotion direction is controlled passively by patterned substrates. The robot employs a single rolled dielectric elastomer actuator, while groove patterns on a 3D-printed substrate guide its alignment and trajectory. Through systematic experiments, we demonstrate that varying groove angles enables precise control of locomotion direction without the need for complex actuation strategies. This groove-guided approach reduces energy consumption, simplifies robot design, and expands the applicability of bio-inspired soft robots in fields such as search and rescue, pipe inspection, and planetary exploration. - oai:arXiv.org:2512.07813v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Hari Prakash Thanabalan, Lars Bengtsson, Ugo Lafont, Giovanni Volpe - - - Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach - https://arxiv.org/abs/2512.07814 - arXiv:2512.07814v1 Announce Type: new -Abstract: Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns due to their reliance on open-source repositories containing abundant personally identifiable information (PII). Prior work shows that commercial models can reproduce sensitive PII, yet existing studies largely treat PII as a single category and overlook the heterogeneous risks among different types. We investigate whether distinct PII types vary in their likelihood of being learned and leaked by LLM4Code, and whether this relationship is causal. Our methodology includes building a dataset with diverse PII types, fine-tuning representative models of different scales, computing training dynamics on real PII data, and formulating a structural causal model to estimate the causal effect of learnability on leakage. Results show that leakage risks differ substantially across PII types and correlate with their training dynamics: easy-to-learn instances such as IP addresses exhibit higher leakage, while harder types such as keys and passwords leak less frequently. Ambiguous types show mixed behaviors. This work provides the first causal evidence that leakage risks are type-dependent and offers guidance for developing type-aware and learnability-aware defenses for LLM4Code. - oai:arXiv.org:2512.07814v1 - cs.SE - cs.AI - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Hua Yang (North Carolina State University), Alejandro Velasco (William & Mary), Sen Fang (North Carolina State University), Bowen Xu (North Carolina State University), Denys Poshyvanyk (William & Mary) - - - Provable Long-Range Benefits of Next-Token Prediction - https://arxiv.org/abs/2512.07818 - arXiv:2512.07818v1 Announce Type: new -Abstract: Why do modern language models, trained to do well on next-word prediction, appear to generate coherent documents and capture long-range structure? Here we show that next-token prediction is provably powerful for learning longer-range structure, even with common neural network architectures. Specifically, we prove that optimizing next-token prediction over a Recurrent Neural Network (RNN) yields a model that closely approximates the training distribution: for held-out documents sampled from the training distribution, no algorithm of bounded description length limited to examining the next $k$ tokens, for any $k$, can distinguish between $k$ consecutive tokens of such documents and $k$ tokens generated by the learned language model following the same prefix. We provide polynomial bounds (in $k$, independent of the document length) on the model size needed to achieve such $k$-token indistinguishability, offering a complexity-theoretic explanation for the long-range coherence observed in practice. - oai:arXiv.org:2512.07818v1 - cs.LG - cs.AI - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Xinyuan Cao, Santosh S. Vempala - - - Efficient and Compliant Control Framework for Versatile Human-Humanoid Collaborative Transportation - https://arxiv.org/abs/2512.07819 - arXiv:2512.07819v1 Announce Type: new -Abstract: We present a control framework that enables humanoid robots to perform collaborative transportation tasks with a human partner. The framework supports both translational and rotational motions, which are fundamental to co-transport scenarios. It comprises three components: a high-level planner, a low-level controller, and a stiffness modulation mechanism. At the planning level, we introduce the Interaction Linear Inverted Pendulum (I-LIP), which, combined with an admittance model and an MPC formulation, generates dynamically feasible footstep plans. These are executed by a QP-based whole-body controller that accounts for the coupled humanoid-object dynamics. Stiffness modulation regulates robot-object interaction, ensuring convergence to the desired relative configuration defined by the distance between the object and the robot's center of mass. We validate the effectiveness of the framework through real-world experiments conducted on the Digit humanoid platform. To quantify collaboration quality, we propose an efficiency metric that captures both task performance and inter-agent coordination. We show that this metric highlights the role of compliance in collaborative tasks and offers insights into desirable trajectory characteristics across both high- and low-level control layers. Finally, we showcase experimental results on collaborative behaviors, including translation, turning, and combined motions such as semi circular trajectories, representative of naturally occurring co-transportation tasks. - oai:arXiv.org:2512.07819v1 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shubham S. Kumbhar, Abhijeet M. Kulkarni, Panagiotis Artemiadis - - - Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces - https://arxiv.org/abs/2512.07820 - arXiv:2512.07820v1 Announce Type: new -Abstract: We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA) that leverages multi-domain information to learn EEG representations for brain-computer interfaces. Our model leverages graph convolutional networks to fuse embeddings from frequency-based topographical maps and time-frequency spectrograms, capturing inter-domain relationships. GEEGA addresses the challenge of achieving high inter-class separability, which arises from the temporally dynamic and subject-sensitive nature of EEG signals by incorporating the center loss and pairwise difference loss. Additionally, GEEGA incorporates a gradient alignment strategy to resolve conflicts between gradients from different domains and the fused embeddings, ensuring that discrepancies, where gradients point in conflicting directions, are aligned toward a unified optimization direction. We validate the efficacy of our method through extensive experiments on three publicly available EEG datasets: BCI-2a, CL-Drive and CLARE. Comprehensive ablation studies further highlight the impact of various components of our model. - oai:arXiv.org:2512.07820v1 - cs.HC - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Prithila Angkan, Amin Jalali, Paul Hungler, Ali Etemad - - - WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling - https://arxiv.org/abs/2512.07821 - arXiv:2512.07821v1 Announce Type: new -Abstract: Recent video generators achieve striking photorealism, yet remain fundamentally inconsistent in 3D. We present WorldReel, a 4D video generator that is natively spatio-temporally consistent. WorldReel jointly produces RGB frames together with 4D scene representations, including pointmaps, camera trajectory, and dense flow mapping, enabling coherent geometry and appearance modeling over time. Our explicit 4D representation enforces a single underlying scene that persists across viewpoints and dynamic content, yielding videos that remain consistent even under large non-rigid motion and significant camera movement. We train WorldReel by carefully combining synthetic and real data: synthetic data providing precise 4D supervision (geometry, motion, and camera), while real videos contribute visual diversity and realism. This blend allows WorldReel to generalize to in-the-wild footage while preserving strong geometric fidelity. Extensive experiments demonstrate that WorldReel sets a new state-of-the-art for consistent video generation with dynamic scenes and moving cameras, improving metrics of geometric consistency, motion coherence, and reducing view-time artifacts over competing methods. We believe that WorldReel brings video generation closer to 4D-consistent world modeling, where agents can render, interact, and reason about scenes through a single and stable spatiotemporal representation. - oai:arXiv.org:2512.07821v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Shaoheng Fang, Hanwen Jiang, Yunpeng Bai, Niloy J. Mitra, Qixing Huang - - - Studying the Role of Reusing Crowdsourcing Knowledge in Software Development - https://arxiv.org/abs/2512.07824 - arXiv:2512.07824v1 Announce Type: new -Abstract: Crowdsourcing platforms, such as Stack Overflow, have changed and impacted the software development practice. In these platforms, developers share and reuse their software development and programming experience. Therefore, a plethora of research work focused on crowdsourcing in software engineering and showed that, among other things, crowdsourced development tends to increase developers' productivity and reduce time-to-market. However, in crowdsourcing, the empirical studies of software quality are lacking, and simple questions, such as what developers use the crowdsourcing knowledge for, are unanswered. - Therefore, our research focused on studying the impact of reusing crowdsourcing knowledge on software projects. To do so, we conduct several large-scale empirical studies on some of the well-known crowdsourcing platforms, including Stack Overflow and npm. Our results showed that reusing knowledge from these crowdsourcing platforms has the potential to assist software development practice, specifically in the form of reusing crowdsourced code. However, using such knowledge affects the quality of the software in several aspects, such as making the software projects suffer from dependency overhead and increasing the maintenance effort. Based on these findings, we use the gained knowledge to make sound data-driven decisions where we examine software quality assurance methods to mitigate the risk of relying on crowd sourcing knowledge in software development. We examine the use of continuous integration (CI). Our analysis showed how CI can be improved to increase developers' productivity and save their resources. - oai:arXiv.org:2512.07824v1 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Rabe Abdalkareem - - - OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing - https://arxiv.org/abs/2512.07826 - arXiv:2512.07826v1 Announce Type: new -Abstract: The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulously designed data pipeline with rigorous quality filtering. OpenVE-3M surpasses existing open-source datasets in terms of scale, diversity of edit types, instruction length, and overall quality. Furthermore, to address the lack of a unified benchmark in the field, we construct OpenVE-Bench, containing 431 video-edit pairs that cover a diverse range of editing tasks with three key metrics highly aligned with human judgment. We present OpenVE-Edit, a 5B model trained on our dataset that demonstrates remarkable efficiency and effectiveness by setting a new state-of-the-art on OpenVE-Bench, outperforming all prior open-source models including a 14B baseline. Project page is at https://github.com/lewandofskee/OpenVE. - oai:arXiv.org:2512.07826v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Haoyang He, Jie Wang, Jiangning Zhang, Zhucun Xue, Xingyuan Bu, Qiangpeng Yang, Shilei Wen, Lei Xie - - - An Adaptive Multi-Layered Honeynet Architecture for Threat Behavior Analysis via Deep Learning - https://arxiv.org/abs/2512.07827 - arXiv:2512.07827v1 Announce Type: new -Abstract: The escalating sophistication and variety of cyber threats have rendered static honeypots inadequate, necessitating adaptive, intelligence-driven deception. In this work, ADLAH is introduced: an Adaptive Deep Learning Anomaly Detection Honeynet designed to maximize high-fidelity threat intelligence while minimizing cost through autonomous orchestration of infrastructure. The principal contribution is offered as an end-to-end architectural blueprint and vision for an AI-driven deception platform. Feasibility is evidenced by a functional prototype of the central decision mechanism, in which a reinforcement learning (RL) agent determines, in real time, when sessions should be escalated from low-interaction sensor nodes to dynamically provisioned, high-interaction honeypots. Because sufficient live data were unavailable, field-scale validation is not claimed; instead, design trade-offs and limitations are detailed, and a rigorous roadmap toward empirical evaluation at scale is provided. Beyond selective escalation and anomaly detection, the architecture pursues automated extraction, clustering, and versioning of bot attack chains, a core capability motivated by the empirical observation that exposed services are dominated by automated traffic. Together, these elements delineate a practical path toward cost-efficient capture of high-value adversary behavior, systematic bot versioning, and the production of actionable threat intelligence. - oai:arXiv.org:2512.07827v1 - cs.CR - cs.DC - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lukas Johannes M\"oller - - - The Adoption and Usage of AI Agents: Early Evidence from Perplexity - https://arxiv.org/abs/2512.07828 - arXiv:2512.07828v1 Announce Type: new -Abstract: This paper presents the first large-scale field study of the adoption, usage intensity, and use cases of general-purpose AI agents operating in open-world web environments. Our analysis centers on Comet, an AI-powered browser developed by Perplexity, and its integrated agent, Comet Assistant. Drawing on hundreds of millions of anonymized user interactions, we address three fundamental questions: Who is using AI agents? How intensively are they using them? And what are they using them for? Our findings reveal substantial heterogeneity in adoption and usage across user segments. Earlier adopters, users in countries with higher GDP per capita and educational attainment, and individuals working in digital or knowledge-intensive sectors -- such as digital technology, academia, finance, marketing, and entrepreneurship -- are more likely to adopt or actively use the agent. To systematically characterize the substance of agent usage, we introduce a hierarchical agentic taxonomy that organizes use cases across three levels: topic, subtopic, and task. The two largest topics, Productivity & Workflow and Learning & Research, account for 57% of all agentic queries, while the two largest subtopics, Courses and Shopping for Goods, make up 22%. The top 10 out of 90 tasks represent 55% of queries. Personal use constitutes 55% of queries, while professional and educational contexts comprise 30% and 16%, respectively. In the short term, use cases exhibit strong stickiness, but over time users tend to shift toward more cognitively oriented topics. The diffusion of increasingly capable AI agents carries important implications for researchers, businesses, policymakers, and educators, inviting new lines of inquiry into this rapidly emerging class of AI capabilities. - oai:arXiv.org:2512.07828v1 - cs.LG - econ.GN - q-fin.EC - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jeremy Yang, Noah Yonack, Kate Zyskowski, Denis Yarats, Johnny Ho, Jerry Ma - - - One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation - https://arxiv.org/abs/2512.07829 - arXiv:2512.07829v1 Announce Type: new -Abstract: Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual representations, either by aligning them inside VAEs or directly within the generative model. However, adapting such representations remains challenging due to fundamental mismatches between understanding-oriented features and generation-friendly latent spaces. Representation encoders benefit from high-dimensional latents that capture diverse hypotheses for masked regions, whereas generative models favor low-dimensional latents that must faithfully preserve injected noise. This discrepancy has led prior work to rely on complex objectives and architectures. In this work, we propose FAE (Feature Auto-Encoder), a simple yet effective framework that adapts pre-trained visual representations into low-dimensional latents suitable for generation using as little as a single attention layer, while retaining sufficient information for both reconstruction and understanding. The key is to couple two separate deep decoders: one trained to reconstruct the original feature space, and a second that takes the reconstructed features as input for image generation. FAE is generic; it can be instantiated with a variety of self-supervised encoders (e.g., DINO, SigLIP) and plugged into two distinct generative families: diffusion models and normalizing flows. Across class-conditional and text-to-image benchmarks, FAE achieves strong performance. For example, on ImageNet 256x256, our diffusion model with CFG attains a near state-of-the-art FID of 1.29 (800 epochs) and 1.70 (80 epochs). Without CFG, FAE reaches the state-of-the-art FID of 1.48 (800 epochs) and 2.08 (80 epochs), demonstrating both high quality and fast learning. - oai:arXiv.org:2512.07829v1 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuan Gao, Chen Chen, Tianrong Chen, Jiatao Gu - - - UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation - https://arxiv.org/abs/2512.07831 - arXiv:2512.07831v1 Announce Type: new -Abstract: Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and limited modal diversity for comprehensive world knowledge representation. To address these limitations, we introduce UnityVideo, a unified framework for world-aware video generation that jointly learns across multiple modalities (segmentation masks, human skeletons, DensePose, optical flow, and depth maps) and training paradigms. Our approach features two core components: (1) dynamic noising to unify heterogeneous training paradigms, and (2) a modality switcher with an in-context learner that enables unified processing via modular parameters and contextual learning. We contribute a large-scale unified dataset with 1.3M samples. Through joint optimization, UnityVideo accelerates convergence and significantly enhances zero-shot generalization to unseen data. We demonstrate that UnityVideo achieves superior video quality, consistency, and improved alignment with physical world constraints. Code and data can be found at: https://github.com/dvlab-research/UnityVideo - oai:arXiv.org:2512.07831v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Jiehui Huang, Yuechen Zhang, Xu He, Yuan Gao, Zhi Cen, Bin Xia, Yan Zhou, Xin Tao, Pengfei Wan, Jiaya Jia - - - Do Generalisation Results Generalise? - https://arxiv.org/abs/2512.07832 - arXiv:2512.07832v1 Announce Type: new -Abstract: A large language model's (LLM's) out-of-distribution (OOD) generalisation ability is crucial to its deployment. Previous work assessing LLMs' generalisation performance, however, typically focuses on a single out-of-distribution dataset. This approach may fail to precisely evaluate the capabilities of the model, as the data shifts encountered once a model is deployed are much more diverse. In this work, we investigate whether OOD generalisation results generalise. More specifically, we evaluate a model's performance across multiple OOD testsets throughout a finetuning run; we then evaluate the partial correlation of performances across these testsets, regressing out in-domain performance. This allows us to assess how correlated are generalisation performances once in-domain performance is controlled for. Analysing OLMo2 and OPT, we observe no overarching trend in generalisation results: the existence of a positive or negative correlation between any two OOD testsets depends strongly on the specific choice of model analysed. - oai:arXiv.org:2512.07832v1 - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Matteo Boglioni, Andrea Sgobbi, Gabriel Tavernini, Francesco Rita, Marius Mosbach, Tiago Pimentel - - - Relational Visual Similarity - https://arxiv.org/abs/2512.07833 - arXiv:2512.07833v1 Announce Type: new -Abstract: Humans do not just see attribute similarity -- we also see relational similarity. An apple is like a peach because both are reddish fruit, but the Earth is also like a peach: its crust, mantle, and core correspond to the peach's skin, flesh, and pit. This ability to perceive and recognize relational similarity, is arguable by cognitive scientist to be what distinguishes humans from other species. Yet, all widely used visual similarity metrics today (e.g., LPIPS, CLIP, DINO) focus solely on perceptual attribute similarity and fail to capture the rich, often surprising relational similarities that humans perceive. How can we go beyond the visible content of an image to capture its relational properties? How can we bring images with the same relational logic closer together in representation space? To answer these questions, we first formulate relational image similarity as a measurable problem: two images are relationally similar when their internal relations or functions among visual elements correspond, even if their visual attributes differ. We then curate 114k image-caption dataset in which the captions are anonymized -- describing the underlying relational logic of the scene rather than its surface content. Using this dataset, we finetune a Vision-Language model to measure the relational similarity between images. This model serves as the first step toward connecting images by their underlying relational structure rather than their visible appearance. Our study shows that while relational similarity has a lot of real-world applications, existing image similarity models fail to capture it -- revealing a critical gap in visual computing. - oai:arXiv.org:2512.07833v1 - cs.CV - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Thao Nguyen, Sicheng Mo, Krishna Kumar Singh, Yilin Wang, Jing Shi, Nicholas Kolkin, Eli Shechtman, Yong Jae Lee, Yuheng Li - - - Voxify3D: Pixel Art Meets Volumetric Rendering - https://arxiv.org/abs/2512.07834 - arXiv:2512.07834v1 Announce Type: new -Abstract: Voxel art is a distinctive stylization widely used in games and digital media, yet automated generation from 3D meshes remains challenging due to conflicting requirements of geometric abstraction, semantic preservation, and discrete color coherence. Existing methods either over-simplify geometry or fail to achieve the pixel-precise, palette-constrained aesthetics of voxel art. We introduce Voxify3D, a differentiable two-stage framework bridging 3D mesh optimization with 2D pixel art supervision. Our core innovation lies in the synergistic integration of three components: (1) orthographic pixel art supervision that eliminates perspective distortion for precise voxel-pixel alignment; (2) patch-based CLIP alignment that preserves semantics across discretization levels; (3) palette-constrained Gumbel-Softmax quantization enabling differentiable optimization over discrete color spaces with controllable palette strategies. This integration addresses fundamental challenges: semantic preservation under extreme discretization, pixel-art aesthetics through volumetric rendering, and end-to-end discrete optimization. Experiments show superior performance (37.12 CLIP-IQA, 77.90\% user preference) across diverse characters and controllable abstraction (2-8 colors, 20x-50x resolutions). Project page: https://yichuanh.github.io/Voxify-3D/ - oai:arXiv.org:2512.07834v1 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - new - http://creativecommons.org/licenses/by/4.0/ - Yi-Chuan Huang, Jiewen Chan, Hao-Jen Chien, Yu-Lun Liu - - - A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation - https://arxiv.org/abs/2512.02195 - arXiv:2512.02195v1 Announce Type: cross -Abstract: This paper presents an initial study performed by the MODOMA system. The MODOMA is a computational multi-agent laboratory environment for unsupervised language acquisition experiments such that acquisition is based on the interaction between two language models, an adult and a child agent. Although this framework employs statistical as well as rule-based procedures, the result of language acquisition is a knowledge-based language model, which can be used to generate and parse new utterances of the target language. This system is fully parametrized and researchers can control all aspects of the experiments while the results of language acquisition, that is, the acquired grammatical knowledge, are explicitly represented and can be consulted. Thus, this system introduces novel possibilities for conducting computational language acquisition experiments. The experiments presented by this paper demonstrate that functional and content categories can be acquired and represented by the daughter agent based on training and test data containing different amounts of exemplars generated by the adult agent. Interestingly, similar patterns, which are well-established for human-generated data, are also found for these machine-generated data. As the procedures resulted in the successful acquisition of discrete grammatical categories by the child agent, these experiments substantiate the validity of the MODOMA approach to modelling language acquisition. - oai:arXiv.org:2512.02195v1 - cs.CL - cs.AI - cs.LG - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Computational Linguistics in the Netherlands Journal, 14, 167-189 (2025) - David Ph. Shakouri, Crit Cremers, Niels O. Schiller - - - Intrusion Detection on Resource-Constrained IoT Devices with Hardware-Aware ML and DL - https://arxiv.org/abs/2512.02272 - arXiv:2512.02272v1 Announce Type: cross -Abstract: This paper proposes a hardware-aware intrusion detection system (IDS) for Internet of Things (IoT) and Industrial IoT (IIoT) networks; it targets scenarios where classification is essential for fast, privacy-preserving, and resource-efficient threat detection. The goal is to optimize both tree-based machine learning (ML) models and compact deep neural networks (DNNs) within strict edge-device constraints. This allows for a fair comparison and reveals trade-offs between model families. We apply constrained grid search for tree-based classifiers and hardware-aware neural architecture search (HW-NAS) for 1D convolutional neural networks (1D-CNNs). Evaluation on the Edge-IIoTset benchmark shows that selected models meet tight flash, RAM, and compute limits: LightGBM achieves 95.3% accuracy using 75 KB flash and 1.2 K operations, while the HW-NAS-optimized CNN reaches 97.2% with 190 KB flash and 840 K floating-point operations (FLOPs). We deploy the full pipeline on a Raspberry Pi 3 B Plus, confirming that tree-based models operate within 30 ms and that CNNs remain suitable when accuracy outweighs latency. These results highlight the practicality of hardware-constrained model design for real-time IDS at the edge. - oai:arXiv.org:2512.02272v1 - cs.NI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Ali Diab, Adel Chehade, Edoardo Ragusa, Paolo Gastaldo, Rodolfo Zunino, Amer Baghdadi, Mostafa Rizk - - - Physics Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation - https://arxiv.org/abs/2512.05976 - arXiv:2512.05976v1 Announce Type: cross -Abstract: Designing materials with controlled heat flow at the nano-scale is central to advances in microelectronics, thermoelectrics, and energy-conversion technologies. At these scales, phonon transport follows the Boltzmann Transport Equation (BTE), which captures non-diffusive (ballistic) effects but is too costly to solve repeatedly in inverse-design loops. Existing surrogate approaches trade speed for accuracy: fast macroscopic solvers can overestimate conductivities by hundreds of percent, while recent data-driven operator learners often require thousands of high-fidelity simulations. This creates a need for a fast, data-efficient surrogate that remains reliable across ballistic and diffusive regimes. We introduce a Physics-Enhanced Deep Surrogate (PEDS) that combines a differentiable Fourier solver with a neural generator and couples it with uncertainty-driven active learning. The Fourier solver acts as a physical inductive bias, while the network learns geometry-dependent corrections and a mixing coefficient that interpolates between macroscopic and nano-scale behavior. PEDS reduces training-data requirements by up to 70% compared with purely data-driven baselines, achieves roughly 5% fractional error with only 300 high-fidelity BTE simulations, and enables efficient design of porous geometries spanning 12-85 W m$^{-1}$ K$^{-1}$ with average design errors of 4%. The learned mixing parameter recovers the ballistic-diffusive transition and improves out of distribution robustness. These results show that embedding simple, differentiable low-fidelity physics can dramatically increase surrogate data-efficiency and interpretability, making repeated PDE-constrained optimization practical for nano-scale thermal-materials design. - oai:arXiv.org:2512.05976v1 - physics.comp-ph - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Antonio Varagnolo, Giuseppe Romano, Rapha\"el Pestourie - - - Accelerating Materials Discovery: Learning a Universal Representation of Chemical Processes for Cross-Domain Property Prediction - https://arxiv.org/abs/2512.05979 - arXiv:2512.05979v1 Announce Type: cross -Abstract: Experimental validation of chemical processes is slow and costly, limiting exploration in materials discovery. Machine learning can prioritize promising candidates, but existing data in patents and literature is heterogeneous and difficult to use. We introduce a universal directed-tree process-graph representation that unifies unstructured text, molecular structures, and numeric measurements into a single machine-readable format. To learn from this structured data, we developed a multi-modal graph neural network with a property-conditioned attention mechanism. Trained on approximately 700,000 process graphs from nearly 9,000 diverse documents, our model learns semantically rich embeddings that generalize across domains. When fine-tuned on compact, domain-specific datasets, the pretrained model achieves strong performance, demonstrating that universal process representations learned at scale transfer effectively to specialized prediction tasks with minimal additional data. - oai:arXiv.org:2512.05979v1 - physics.chem-ph - cs.AI - cs.DM - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mikhail Tsitsvero, Atsuyuki Nakao, Hisaki Ikebata - - - FlockVote: LLM-Empowered Agent-Based Modeling for Simulating U.S. Presidential Elections - https://arxiv.org/abs/2512.05982 - arXiv:2512.05982v1 Announce Type: cross -Abstract: Modeling complex human behavior, such as voter decisions in national elections, is a long-standing challenge for computational social science. Traditional agent-based models (ABMs) are limited by oversimplified rules, while large-scale statistical models often lack interpretability. We introduce FlockVote, a novel framework that uses Large Language Models (LLMs) to build a "computational laboratory" of LLM agents for political simulation. Each agent is instantiated with a high-fidelity demographic profile and dynamic contextual information (e.g. candidate policies), enabling it to perform nuanced, generative reasoning to simulate a voting decision. We deploy this framework as a testbed on the 2024 U.S. Presidential Election, focusing on seven key swing states. Our simulation's macro-level results successfully replicate the real-world outcome, demonstrating the high fidelity of our "virtual society". The primary contribution is not only the prediction, but also the framework's utility as an interpretable research tool. FlockVote moves beyond black-box outputs, allowing researchers to probe agent-level rationale and analyze the stability and sensitivity of LLM-driven social simulations. - oai:arXiv.org:2512.05982v1 - physics.soc-ph - cs.AI - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lingfeng Zhou, Yi Xu, Zhenyu Wang, Dequan Wang - - - Stronger is not better: Better Augmentations in Contrastive Learning for Medical Image Segmentation - https://arxiv.org/abs/2512.05992 - arXiv:2512.05992v1 Announce Type: cross -Abstract: Self-supervised contrastive learning is among the recent representation learning methods that have shown performance gains in several downstream tasks including semantic segmentation. This paper evaluates strong data augmentation, one of the most important components for self-supervised contrastive learning's improved performance. Strong data augmentation involves applying the composition of multiple augmentation techniques on images. Surprisingly, we find that the existing data augmentations do not always improve performance for semantic segmentation for medical images. We experiment with other augmentations that provide improved performance. - oai:arXiv.org:2512.05992v1 - eess.IV - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Azeez Idris, Abdurahman Ali Mohammed, Samuel Fanijo - - - KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening - https://arxiv.org/abs/2512.05994 - arXiv:2512.05994v1 Announce Type: cross -Abstract: With the rapid advancement of conversational and diffusion-based AI, there is a growing adoption of AI in educational services, ranging from grading and assessment tools to personalized learning systems that provide targeted support for students. However, this adaptability has yet to fully extend to the domain of children's speech, where existing models often fail due to their reliance on datasets designed for clear, articulate adult speech. Children, particularly those in early developmental stages or with speech and language pathologies, present unique challenges that current AI models and datasets are ill-equipped to handle. To address this, we introduce KidSpeak, a multi-task speech-enhanced Foundation Model capable of both generative and discriminative tasks specifically tailored to children's speech patterns. Our framework employs a two-stage training process that incorporates phonetic knowledge into the speech encoder, achieving an average accuracy of 87% across four separate tasks. Furthermore, recognizing the limitations of scalable human annotation and existing speech alignment tools, we propose the Flexible and Automatic Speech Aligner (FASA) and leverage the method to construct high quality datasets for training and evaluation. This novel alignment tool significantly improves the quality of aligned children's speech from noisy data, enhancing data quality by 13.6x compared to human annotations, as demonstrated on the CHILDES dataset. To the best of our knowledge, KidSpeak and FASA represent the first comprehensive solution designed for speech and language therapy in children, offering both a multi-purpose speech LLM and a robust alignment tool. - oai:arXiv.org:2512.05994v1 - eess.AS - cs.AI - cs.CL - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Rohan Sharma, Dancheng Liu, Jingchen Sun, Shijie Zhou, Jiayu Qin, Jinjun Xiong, Changyou Chen - - - Small Language Models Reshape Higher Education: Courses, Textbooks, and Teaching - https://arxiv.org/abs/2512.06001 - arXiv:2512.06001v1 Announce Type: cross -Abstract: While large language models (LLMs) have introduced novel paradigms in science and education, their adoption in higher education is constrained by inherent limitations. These include a tendency to produce inaccuracies and high computational requirements, which compromise the strict demands for accurate and reliable knowledge essential in higher education. Small language models (MiniLMs), by contrast, offer distinct advantages in professional education due to their lightweight nature and precise retrieval capabilities. This research takes "Atmospheric Physics" as an example. We established a specialized corpus and image repository by gathering over 550,000 full-text PDFs from over 130 international well-respected journals in Earth and environmental science. From this collection, we extracted over 100 million high-quality sentence-level corpus and more than 3 million high-resolution academic images. Using MiniLMs, these resources were organized into a high-dimensional vector library for precise retrieval and efficient utilization of extensive educational content. Consequently, we systematically redesigned the courses, textbooks, and teaching strategies for "Atmospheric Physics" based on MiniLMs. The course is designed as a "interdisciplinary-frontier" system, breaking down traditional boundaries between atmospheric science, space science, hydrology, and remote sensing. Teaching materials are transformed from static, lagging text formats into a dynamic digital resource library powered by MiniLM. For teaching methods, we have designed a question-based learning pathway. This paradigm promotes a shift from passive knowledge transfer to active cognitive development. Consequently, this MiniLM-driven "Atmospheric Physics" course demonstrates a specific avenue for "AI for education". - oai:arXiv.org:2512.06001v1 - physics.ed-ph - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Jian Zhang, Jia Shao - - - Semantic Temporal Single-photon LiDAR - https://arxiv.org/abs/2512.06008 - arXiv:2512.06008v1 Announce Type: cross -Abstract: Temporal single-photon (TSP-) LiDAR presents a promising solution for imaging-free target recognition over long distances with reduced size, cost, and power consumption. However, existing TSP-LiDAR approaches are ineffective in handling open-set scenarios where unknown targets emerge, and they suffer significant performance degradation under low signal-to-noise ratio (SNR) and short acquisition times (fewer photons). Here, inspired by semantic communication, we propose a semantic TSP-LiDAR based on a self-updating semantic knowledge base (SKB), in which the target recognition processing of TSP-LiDAR is formulated as a semantic communication. The results, both simulation and experiment, demonstrate that our approach surpasses conventional methods, particularly under challenging conditions of low SNR and limited acquisition time. More importantly, our self-updating SKB mechanism can dynamically update the semantic features of newly encountered targets in the SKB, enabling continuous adaptation without the need for extensive retraining of the neural network. In fact, a recognition accuracy of 89% is achieved on nine types of unknown targets in real-world experiments, compared to 66% without the updating mechanism. These findings highlight the potential of our framework for adaptive and robust target recognition in complex and dynamic environments. - oai:arXiv.org:2512.06008v1 - eess.IV - cs.CV - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fang Li, Tonglin Mu, Shuling Li, Junran Guo, Keyuan Li, Jianing Li, Ziyang Luo, Xiaodong Fan, Ye Chen, Yunfeng Liu, Hong Cai, Lip Ket Chin, Jinbei Zhang, Shihai Sun - - - Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows - https://arxiv.org/abs/2512.06031 - arXiv:2512.06031v1 Announce Type: cross -Abstract: We present MRPARCv2, Multi-resolution Physics-Aware Recurrent Convolutional Neural Network, designed to model complex flows by embedding the structure of advection-diffusion-reaction equations and leveraging a multi-resolution architecture. MRPARCv2 introduces hierarchical discretization and cross-resolution feature communication to improve the accuracy and efficiency of flow simulations. We evaluate the model on a challenging 2D turbulent radiative layer dataset from The Well multi-physics benchmark repository and demonstrate significant improvements when compared to the single resolution baseline model, in both Variance Scaled Root Mean Squared Error and physics-driven metrics, including turbulent kinetic energy spectra and mass-temperature distributions. Despite having 30% fewer trainable parameters, MRPARCv2 outperforms its predecessor by up to 50% in roll-out prediction error and 86% in spectral error. A preliminary study on uncertainty quantification was performed, and we also analyzed the model's performance under different levels of abstractions of the flow, specifically on sampling subsets of field variables. We find that the absence of physical constraints on the equation of state (EOS) in the network architecture leads to degraded accuracy. A variable substitution experiment confirms that this issue persists regardless of which physical quantity is predicted directly. Our findings highlight the advantages of multi-resolution inductive bias for capturing multi-scale flow dynamics and suggest the need for future PIML models to embed EOS knowledge to enhance physical fidelity. - oai:arXiv.org:2512.06031v1 - physics.flu-dyn - cs.LG - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1063/5.0295883 - APL Mach. Learn. 3, 046110 (2025) - Xinlun Cheng, Joseph Choi, H. S. Udaykumar, Stephen Baek - - - Quantum, Diplomacy, and Geopolitics - https://arxiv.org/abs/2512.06052 - arXiv:2512.06052v1 Announce Type: cross -Abstract: Quantum technologies -- spanning communication, sensing, computing, and cryptography -- are rapidly emerging as critical paths of geopolitical competition and strategic defence innovation. Unlike traditional technological advances, quantum introduces novel capabilities that fundamentally disrupt established norms of security, intelligence, and diplomatic engagement. This strategic analysis explores the evolving quantum landscape through the dual lenses of diplomacy and geopolitics, with specific implications for defence leaders, policymakers, and industry stakeholders. The benefits and challenges of quantum technologies are examined from a diplomatic and geopolitical perspective to help leaders make informed strategic decisions. Leading powers now recognise quantum as a domain where technological leadership directly translates to geopolitical influence, compelling an intense race for dominance alongside new forms of multilateral diplomacy aimed at managing both risks and opportunities. Quantum technologies do not all have the same operational maturity, but technological progress is accelerating. Post-quantum cryptography demands immediate action -- every encrypted communication created today may be harvested and decrypted within the decade by adversaries equipped with quantum capabilities. - oai:arXiv.org:2512.06052v1 - physics.soc-ph - cs.CY - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Axel Ferrazzini - - - Unifying Entropy Regularization in Optimal Control: From and Back to Classical Objectives via Iterated Soft Policies and Path Integral Solutions - https://arxiv.org/abs/2512.06109 - arXiv:2512.06109v1 Announce Type: cross -Abstract: This paper develops a unified perspective on several stochastic optimal control formulations through the lens of Kullback-Leibler regularization. We propose a central problem that separates the KL penalties on policies and transitions, assigning them independent weights, thereby generalizing the standard trajectory-level KL-regularization commonly used in probabilistic and KL-regularized control. This generalized formulation acts as a generative structure allowing to recover various control problems. These include the classical Stochastic Optimal Control (SOC), Risk-Sensitive Optimal Control (RSOC), and their policy-based KL-regularized counterparts. The latter we refer to as soft-policy SOC and RSOC, facilitating alternative problems with tractable solutions. Beyond serving as regularized variants, we show that these soft-policy formulations majorize the original SOC and RSOC problem. This means that the regularized solution can be iterated to retrieve the original solution. Furthermore, we identify a structurally synchronized case of the risk-seeking soft-policy RSOC formulation, wherein the policy and transition KL-regularization weights coincide. Remarkably, this specific setting gives rise to several powerful properties such as a linear Bellman equation, path integral solution, and, compositionality, thereby extending these computationally favourable properties to a broad class of control problems. - oai:arXiv.org:2512.06109v1 - math.OC - cs.LG - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Ajinkya Bhole, Mohammad Mahmoudi Filabadi, Guillaume Crevecoeur, Tom Lefebvre - - - Deadline-Aware Scheduling of Distributed Quantum Circuits in Near-Term Quantum Cloud - https://arxiv.org/abs/2512.06157 - arXiv:2512.06157v1 Announce Type: cross -Abstract: Distributed quantum computing (DQC) enables scalable quantum computations by distributing large quantum circuits on multiple quantum processing units (QPUs) in the quantum cloud. In DQC, after partitioning quantum circuits, they must be scheduled and executed on heterogenous QPUs while balancing latency, overhead, QPU communication resource limits. However, since fully functioning quantum communication networks have not been realized yet, near-term quantum clouds will only rely on local operations and classical communication settings between QPUs, without entangled quantum links. Additionally, existing DQC scheduling frameworks do not account for user-defined execution deadlines and adopt inefficient wire cutting techniques. Accordingly, in this work, a deadline aware DQC scheduling framework with efficient wire cutting for near-term quantum cloud is proposed. The proposed framework schedules partitioned quantum subcircuits while accounting for circuit deadlines and QPU capacity limits. It also captures dependencies between partitioned subcircuits and distributes the execution of the sampling shots on different QPUs to have efficient wire cutting and faster execution. In this regard, a deadline-aware circuit scheduling optimization problem is formulated, and solved using simulated annealing. Simulation results show a marked improvement over existing shot-agnostic frameworks under urgent deadlines, reaching a 12.8% increase in requests served before their deadlines. Additionally, the proposed framework serves 8.16% more requests, on average, compared to state-of-the-art dependency-agnostic baseline frameworks, and by 9.60% versus the dependency-and-shot-agnostic baseline, all while achieving a smaller makespan of the DQC execution. Moreover, the proposed framework serves 23.7%, 24.5%, and 25.38% more requests compared to greedy, list scheduling, and random schedulers, respectively. - oai:arXiv.org:2512.06157v1 - quant-ph - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nour Dehaini, Christia Chahoud, Mahdi Chehimi - - - Beyond Lux thresholds: a systematic pipeline for classifying biologically relevant light contexts from wearable data - https://arxiv.org/abs/2512.06181 - arXiv:2512.06181v1 Announce Type: cross -Abstract: Background: Wearable spectrometers enable field quantification of biologically relevant light, yet reproducible pipelines for contextual classification remain under-specified. - Objective: To establish and validate a subject-wise evaluated, reproducible pipeline and actionable design rules for classifying natural vs. artificial light from wearable spectral data. - Methods: We analysed ActLumus recordings from 26 participants, each monitored for at least 7 days at 10-second sampling, paired with daily exposure diaries. The pipeline fixes the sequence: domain selection, log-base-10 transform, L2 normalisation excluding total intensity (to avoid brightness shortcuts), hour-level medoid aggregation, sine/cosine hour encoding, and MLP classifier, evaluated under participant-wise cross-validation. - Results: The proposed sequence consistently achieved high performance on the primary task, with representative configurations reaching AUC = 0.938 (accuracy 88%) for natural vs. artificial classification on the held-out subject split. In contrast, indoor vs. outdoor classification remained at feasibility level due to spectral overlap and class imbalance (best AUC approximately 0.75; majority-class collapse without contextual sensors). Threshold baselines were insufficient on our data, supporting the need for spectral-temporal modelling beyond illuminance cut-offs. - Conclusions: We provide a reproducible, auditable baseline pipeline and design rules for contextual light classification under subject-wise generalisation. All code, configuration files, and derived artefacts will be openly archived (GitHub + Zenodo DOI) to support reuse and benchmarking. - oai:arXiv.org:2512.06181v1 - q-bio.QM - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yanuo Zhou - - - Forests of Uncertaint(r)ees: Using tree-based ensembles to estimate probability distributions of future conflict - https://arxiv.org/abs/2512.06210 - arXiv:2512.06210v1 Announce Type: cross -Abstract: Predictions of fatalities from violent conflict on the PRIO-GRID-month (pgm) level are characterized by high levels of uncertainty, limiting their usefulness in practical applications. We discuss the two main sources of uncertainty for this prediction task, the nature of violent conflict and data limitations, embedding this in the wider literature on uncertainty quantification in machine learning. We develop a strategy to quantify uncertainty in conflict forecasting, shifting from traditional point predictions to full predictive distributions. Our approach compares and combines multiple tree-based classifiers and distributional regressors in a custom auto-ML setup, estimating distributions for each pgm individually. We also test the integration of regional models in spatial ensembles as a potential avenue to reduce uncertainty. The models are able to consistently outperform a suite of benchmarks derived from conflict history in predictions up to one year in advance, with performance driven by regions where conflict was observed. With our evaluation, we emphasize the need to understand how a metric behaves for a given prediction problem, in our case characterized by extremely high zero-inflatedness. While not resulting in better predictions, the integration of smaller models does not decrease performance for this prediction task, opening avenues to integrate data sources with less spatial coverage in the future. - oai:arXiv.org:2512.06210v1 - stat.AP - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Daniel Mittermaier, Tobias Bohne, Martin Hofer, Daniel Racek - - - Beamspace Dimensionality Reduction for Massive MU-MIMO: Geometric Insights and Information-Theoretic Limits - https://arxiv.org/abs/2512.06234 - arXiv:2512.06234v1 Announce Type: cross -Abstract: Beamspace dimensionality reduction, a classical tool in array processing, has been shown in recent work to significantly reduce computational complexity and training overhead for adaptive reception in massive multiuser (MU) MIMO. For sparse multipath propagation and uniformly spaced antenna arrays, beamspace transformation, or application of a spatial FFT, concentrates the energy of each user into a small number of spatial frequency bins. Empirical evaluations demonstrate the efficacy of linear Minimum Mean Squared Error (LMMSE) detection performed in parallel using a beamspace window of small, fixed size for each user, even as the number of antennas and users scale up, while being robust to moderate variations in the relative powers of the users. In this paper, we develop a fundamental geometric understanding of this ``unreasonable effectiveness'' in a regime in which zero-forcing solutions do not exist. For simplified channel models, we show that, when we enforce a suitable separation in spatial frequency between users, the interference power falling into a desired user's beamspace window of size $W$ concentrates into a number of dominant eigenmodes smaller than $W$, with the desired user having relatively small projection onto these modes. Thus, linear suppression of dominant interference modes can be accomplished with small noise enhancement. We show that similar observations apply for MIMO-OFDM over wideband multipath channels synthesized from measured 28 GHz data. We propose, and evaluate via information-theoretic benchmarks, per-subcarrier reduced dimension beamspace LMMSE in this setting. - oai:arXiv.org:2512.06234v1 - eess.SP - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Canan Cebeci, Oveys Delafrooz Noroozi, Upamanyu Madhow - - - Contextual Strongly Convex Simulation Optimization: Optimize then Predict with Inexact Solutions - https://arxiv.org/abs/2512.06270 - arXiv:2512.06270v1 Announce Type: cross -Abstract: In this work, we study contextual strongly convex simulation optimization and adopt an "optimize then predict" (OTP) approach for real-time decision making. In the offline stage, simulation optimization is conducted across a set of covariates to approximate the optimal-solution function; in the online stage, decisions are obtained by evaluating this approximation at the observed covariate. The central theoretical challenge is to understand how the inexactness of solutions generated by simulation-optimization algorithms affects the optimality gap, which is overlooked in existing studies. To address this, we develop a unified analysis framework that explicitly accounts for both solution bias and variance. Using Polyak-Ruppert averaging SGD as an illustrative simulation-optimization algorithm, we analyze the optimality gap of OTP under four representative smoothing techniques: $k$ nearest neighbor, kernel smoothing, linear regression, and kernel ridge regression. We establish convergence rates, derive the optimal allocation of the computational budget $\Gamma$ between the number of design covariates and the per-covariate simulation effort, and demonstrate the convergence rate can approximately achieve $\Gamma^{-1}$ under appropriate smoothing technique and sample-allocation rule. Finally, through a numerical study, we validate the theoretical findings and demonstrate the effectiveness and practical value of the proposed approach. - oai:arXiv.org:2512.06270v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Nifei Lin, Heng Luo, L. Jeff Hong - - - Interpretable Neural Approximation of Stochastic Reaction Dynamics with Guaranteed Reliability - https://arxiv.org/abs/2512.06294 - arXiv:2512.06294v1 Announce Type: cross -Abstract: Stochastic Reaction Networks (SRNs) are a fundamental modeling framework for systems ranging from chemical kinetics and epidemiology to ecological and synthetic biological processes. A central computational challenge is the estimation of expected outputs across initial conditions and times, a task that is rarely solvable analytically and becomes computationally prohibitive with current methods such as Finite State Projection or the Stochastic Simulation Algorithm. Existing deep learning approaches offer empirical scalability, but provide neither interpretability nor reliability guarantees, limiting their use in scientific analysis and in applications where model outputs inform real-world decisions. Here we introduce DeepSKA, a neural framework that jointly achieves interpretability, guaranteed reliability, and substantial computational gains. DeepSKA yields mathematically transparent representations that generalise across states, times, and output functions, and it integrates this structure with a small number of stochastic simulations to produce unbiased, provably convergent, and dramatically lower-variance estimates than classical Monte Carlo. We demonstrate these capabilities across nine SRNs, including nonlinear and non-mass-action models with up to ten species, where DeepSKA delivers accurate predictions and orders-of-magnitude efficiency improvements. This interpretable and reliable neural framework offers a principled foundation for developing analogous methods for other Markovian systems, including stochastic differential equations. - oai:arXiv.org:2512.06294v1 - q-bio.MN - cs.LG - math.PR - q-bio.QM - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Quentin Badolle, Arthur Theuer, Zhou Fang, Ankit Gupta, Mustafa Khammash - - - Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation - https://arxiv.org/abs/2512.06304 - arXiv:2512.06304v1 Announce Type: cross -Abstract: Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modalities of auxiliary information such as prompts and emotion tags. It changes para-linguistic features from one to another, while maintaining linguistic contents. Recently, VC models have made rapid advancements in both generation quality and personalization capabilities. These developments have attracted considerable attention for diverse applications, including privacy preservation, voice-print reproduction for the deceased, and dysarthric speech recovery. However, these models only learn non-robust features due to the clean training data. Subsequently, it results in unsatisfactory performances when dealing with degraded input speech in real-world scenarios, including additional noise, reverberation, adversarial attacks, or even minor perturbation. Hence, it demands robust deployments, especially in real-world settings. Although latest researches attempt to find potential attacks and countermeasures for VC systems, there remains a significant gap in the comprehensive understanding of how robust the VC model is under input manipulation. here also raises many questions: For instance, to what extent do different forms of input degradation attacks alter the expected output of VC models? Is there potential for optimizing these attack and defense strategies? To answer these questions, we classify existing attack and defense methods from the perspective of input manipulation and evaluate the impact of degraded input speech across four dimensions, including intelligibility, naturalness, timbre similarity, and subjective perception. Finally, we outline open issues and future directions. - oai:arXiv.org:2512.06304v1 - eess.AS - cs.AI - cs.CR - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xining Song, Zhihua Wei, Rui Wang, Haixiao Hu, Yanxiang Chen, Meng Han - - - Modeling Spatio-temporal Extremes via Conditional Variational Autoencoders - https://arxiv.org/abs/2512.06348 - arXiv:2512.06348v1 Announce Type: cross -Abstract: Extreme weather events are widely studied in fields such as agriculture, ecology, and meteorology. The spatio-temporal co-occurrence of extreme events can strengthen or weaken under changing climate conditions. In this paper, we propose a novel approach to model spatio-temporal extremes by integrating climate indices via a conditional variational autoencoder (cXVAE). A convolutional neural network (CNN) is embedded in the decoder to convolve climatological indices with the spatial dependence within the latent space, thereby allowing the decoder to be dependent on the climate variables. There are three main contributions here. First, we demonstrate through extensive simulations that the proposed conditional XVAE accurately emulates spatial fields and recovers spatially and temporally varying extremal dependence with very low computational cost post training. Second, we provide a simple, scalable approach to detecting condition-driven shifts and whether the dependence structure is invariant to the conditioning variable. Third, when dependence is found to be condition-sensitive, the conditional XVAE supports counterfactual experiments allowing intervention on the climate covariate and propagating the associated change through the learned decoder to quantify differences in joint tail risk, co-occurrence ranges, and return metrics. To demonstrate the practical utility and performance of the model in real-world scenarios, we apply our method to analyze the monthly maximum Fire Weather Index (FWI) over eastern Australia from 2014 to 2024 conditioned on the El Ni\~{n}o/Southern Oscillation (ENSO) index. - oai:arXiv.org:2512.06348v1 - stat.ML - cs.LG - stat.ME - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-sa/4.0/ - Xiaoyu Ma, Likun Zhang, Christopher K. Wikle - - - Stabilizing Rate of Stochastic Control Systems with Multiplicative Noise - https://arxiv.org/abs/2512.06349 - arXiv:2512.06349v1 Announce Type: cross -Abstract: This paper develops a quantitative framework for analyzing the mean-square exponential stabilization of stochastic linear systems with multiplicative noise, focusing specifically on the optimal stabilizing rate, which characterizes the fastest exponential stabilization achievable under admissible control policies. -Our contributions are twofold. First, we extend norm-based techniques from deterministic switched systems to the stochastic setting, deriving a verifiable necessary and sufficient condition for the exact attainability of the optimal stabilizing rate, together with computable upper and lower bounds. Second, by restricting attention to state-feedback policies, we reformulate the optimal stabilizing rate problem as an optimal control problem with a nonlinear cost function and derive a Bellman-type equation. Since this Bellman-type equation is not directly tractable, we recast it as a nonlinear matrix eigenvalue problem whose valid solutions require strictly positive-definite matrices. To ensure the existence of such solutions, we introduce a regularization scheme and develop a Regularized Normalized Value Iteration (RNVI) algorithm, which in turn generates strictly positive-definite fixed points for a perturbed version of original nonlinear matrix eigenvalue problem while producing feedback controllers. Evaluating these regularized solutions further yields certified lower and upper bounds for the optimal stabilizing rate, resulting in a constructive and verifiable framework for determining the fastest achievable mean-square stabilization under multiplicative noise. - oai:arXiv.org:2512.06349v1 - math.OC - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hui Jia, Yuan-Hua Ni, Guangchen Wang - - - Demographic Dependence of Vaccine Adoption under Opinion Persuasion - https://arxiv.org/abs/2512.06385 - arXiv:2512.06385v1 Announce Type: cross -Abstract: Inspired by contagion models of social belief formation, we develop an epistemically-informed modeling framework, SIS-Vo, in which vaccine-related information propagates on a signed opinion network. Our model allows for heterogeneous treatment effects of policy messages across subpopulations through demographic-specific responses. We derive fixed-point characterizations of the healthy (disease-free) and endemic equilibria of this model, and obtain conditions for local stability of the healthy state in terms of the contact network and opinion-dependent vaccination capacities. Using numerical simulations, we illustrate how suitably targeted policy interventions, acting through opinion dynamics, can stabilize the epidemic process by moving the system towards the healthy regime. The SIS-Vo framework thus provides a natural basis for control-theoretic analysis of vaccination policies that remain robust even when misinformation targets specific subgroups. - oai:arXiv.org:2512.06385v1 - physics.soc-ph - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Alessandro Casu, Camilla Quaresmini, Robin Delabays, Lewis Mitchell, Philip E. Par\'e - - - Canonical Tail Dependence for Soft Extremal Clustering of Multichannel Brain Signals - https://arxiv.org/abs/2512.06435 - arXiv:2512.06435v1 Announce Type: cross -Abstract: We develop a novel characterization of extremal dependence between two cortical regions of the brain when its signals display extremely large amplitudes. We show that connectivity in the tails of the distribution reveals unique features of extreme events (e.g., seizures) that can help to identify their occurrence. Numerous studies have established that connectivity-based features are effective for discriminating brain states. Here, we demonstrate the advantage of the proposed approach: that tail connectivity provides additional discriminatory power, enabling more accurate identification of extreme-related events and improved seizure risk management. Common approaches in tail dependence modeling use pairwise summary measures or parametric models. However, these approaches do not identify channels that drive the maximal tail dependence between two groups of signals -- an information that is useful when analyzing electroencephalography of epileptic patients where specific channels are responsible for seizure occurrences. A familiar approach in traditional signal processing is canonical correlation, which we extend to the tails to develop a visualization of extremal channel-contributions. Through the tail pairwise dependence matrix (TPDM), we develop a computationally-efficient estimator for our canonical tail dependence measure. Our method is then used for accurate frequency-based soft clustering of neonates, distinguishing those with seizures from those without. - oai:arXiv.org:2512.06435v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Mara Sherlin Talento, Jordan Richards, Raphael Huser, Hernando Ombao - - - Characteristic Bending in Incompressible Flows - https://arxiv.org/abs/2512.06455 - arXiv:2512.06455v1 Announce Type: cross -Abstract: We present the Characteristic Bending (CB) method, a general framework for advecting quantities under incompressible velocity fields. The method builds on standard semi-Lagrangian advection by interpreting the backward-in-time characteristic reconstruction as the construction of a reference map, a diffeomorphism between the current and initial geometries of the advected space. From this viewpoint, the CB method applies a volume-preserving projection to the map, systematically removing spurious compressible errors arising from time integration, interpolation, or from velocity fields that are only approximately divergence-free. This projection bends the characteristics toward the divergence-free space, preserving mass and geometric features of the advected fields, even in the presence of significant error. We demonstrate the method in both two and three dimensions using benchmark problems and for multiphase flows governed by the incompressible Navier-Stokes equations. The results show that the CB method serves as a drop-in replacement for traditional semi-Lagrangian schemes and as an augmentation of reference map formulations, offering improved robustness and accuracy in incompressible flow simulations. - oai:arXiv.org:2512.06455v1 - physics.flu-dyn - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Matthew Blomquist, St\'ephane Gaudreault, Maxime Theillard - - - Detrended cross-correlations and their random matrix limit: an example from the cryptocurrency market - https://arxiv.org/abs/2512.06473 - arXiv:2512.06473v1 Announce Type: cross -Abstract: Correlations in complex systems are often obscured by nonstationarity, long-range memory, and heavy-tailed fluctuations, which limit the usefulness of traditional covariance-based analyses. To address these challenges, we construct scale and fluctuation-dependent correlation matrices using the multifractal detrended cross-correlation coefficient $\rho_r$ that selectively emphasizes fluctuations of different amplitudes. We examine the spectral properties of these detrended correlation matrices and compare them to the spectral properties of the matrices calculated in the same way from synthetic Gaussian and $q$Gaussian signals. Our results show that detrending, heavy tails, and the fluctuation-order parameter $r$ jointly produce spectra, which substantially depart from the random case even under absence of cross-correlations in time series. Applying this framework to one-minute returns of 140 major cryptocurrencies from 2021-2024 reveals robust collective modes, including a dominant market factor and several sectoral components whose strength depends on the analyzed scale and fluctuation order. After filtering out the market mode, the empirical eigenvalue bulk aligns closely with the limit of random detrended cross-correlations, enabling clear identification of structurally significant outliers. Overall, the study provides a refined spectral baseline for detrended cross-correlations and offers a promising tool for distinguishing genuine interdependencies from noise in complex, nonstationary, heavy-tailed systems. - oai:arXiv.org:2512.06473v1 - q-fin.ST - cs.CE - physics.data-an - stat.AP - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - 10.3390/e27121236 - Entropy 2025, 27(12), 1236 - Stanis{\l}aw Dro\.zd\.z, Pawe{\l} Jarosz, Jaros{\l}aw Kwapie\'n, Maria Skupie\'n, Marcin W\k{a}torek - - - Non-Equiprobable Signaling for Wireless Channels Subject to Mobility and Delay Spread - https://arxiv.org/abs/2512.06494 - arXiv:2512.06494v1 Announce Type: cross -Abstract: This letter describes how to improve performance of OFDM systems by combining non-equiprobable signaling with low density parity check (LDPC) coding. We partition a standard QAM constellation into annular subconstellations of equal size, and we implement non-equiprobable signaling through a shaping code which selects subconstellations with large average energy less frequently than subconstellations with small average energy. In equiprobable signaling, the LDPC code selects a signal point from the inner subconstellation. In non-equiprobable signaling this inner signal point has a representative in each subconstellation and the shaping code selects the representative for transmission. It is possible to use standard QAM constellations to achieve any desired fractional bit rate with this method of shaping the energy distribution of the transmitted signal. We describe how to combine coding and shaping by integrating shaping into the calculation of log-likelihood ratios (LLRs) necessary for decoding LDPC codes. We present simulation results for non-equiprobable transmission at $1.5$ bits/symbol on a representative Veh-A channel showing gains of $4$ dB at a bit error rate (BER) of $10^{-3}$. As the transmission rate increases, the gains from non-equiprobable signaling diminish, but we show through simulation that they are still significant for $16$-QAM. - oai:arXiv.org:2512.06494v1 - eess.SP - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sandesh Rao Mattu, Nishant Mehrotra, Robert Calderbank - - - PRIMRose: Insights into the Per-Residue Energy Metrics of Proteins with Double InDel Mutations using Deep Learning - https://arxiv.org/abs/2512.06496 - arXiv:2512.06496v1 Announce Type: cross -Abstract: Understanding how protein mutations affect protein structure is essential for advancements in computational biology and bioinformatics. We introduce PRIMRose, a novel approach that predicts energy values for each residue given a mutated protein sequence. Unlike previous models that assess global energy shifts, our method analyzes the localized energetic impact of double amino acid insertions or deletions (InDels) at the individual residue level, enabling residue-specific insights into structural and functional disruption. We implement a Convolutional Neural Network architecture to predict the energy changes of each residue in a protein mutation. We train our model on datasets constructed from nine proteins, grouped into three categories: one set with exhaustive double InDel mutations, another with approximately 145k randomly sampled double InDel mutations, and a third with approximately 80k randomly sampled double InDel mutations. Our model achieves high predictive accuracy across a range of energy metrics as calculated by the Rosetta molecular modeling suite and reveals localized patterns that influence model performance, such as solvent accessibility and secondary structure context. This per-residue analysis offers new insights into the mutational tolerance of specific regions within proteins and provides higher interpretable and biologically meaningful predictions of InDels' effects. - oai:arXiv.org:2512.06496v1 - q-bio.BM - cs.AI - cs.LG - cs.NE - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3768322.3769032 - BCB Companion 2025: Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics - Stella Brown, Nicolas Preisig, Autumn Davis, Brian Hutchinson, Filip Jagodzinski - - - AI as "Co-founder": GenAI for Entrepreneurship - https://arxiv.org/abs/2512.06506 - arXiv:2512.06506v1 Announce Type: cross -Abstract: This paper studies whether, how, and for whom generative artificial intelligence (GenAI) facilitates firm creation. Our identification strategy exploits the November 2022 release of ChatGPT as a global shock that lowered start-up costs and leverages variations across geo-coded grids with differential pre-existing AI-specific human capital. Using high-resolution and universal data on Chinese firm registrations by the end of 2024, we find that grids with stronger AI-specific human capital experienced a sharp surge in new firm formation$\unicode{x2013}$driven entirely by small firms, contributing to 6.0% of overall national firm entry. Large-firm entry declines, consistent with a shift toward leaner ventures. New firms are smaller in capital, shareholder number, and founding team size, especially among small firms. The effects are strongest among firms with potential AI applications, weaker financing needs, and among first-time entrepreneurs. Overall, our results highlight that GenAI serves as a pro-competitive force by disproportionately boosting small-firm entry. - oai:arXiv.org:2512.06506v1 - econ.GN - cs.AI - q-fin.EC - stat.AP - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Junhui Jeff Cai, Xian Gu, Liugang Sheng, Mengjia Xia, Linda Zhao, Wu Zhu - - - A Latent Variable Framework for Scaling Laws in Large Language Models - https://arxiv.org/abs/2512.06553 - arXiv:2512.06553v1 Announce Type: cross -Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated by the rapid emergence of numerous new LLM families with distinct architectures and training strategies, evaluated on an increasing number of benchmarks. This heterogeneity makes a single global scaling curve inadequate for capturing how performance varies across families and benchmarks. To address this, we propose a latent variable modeling framework in which each LLM family is associated with a latent variable that captures the common underlying features in that family. An LLM's performance on different benchmarks is then driven by its latent skills, which are jointly determined by the latent variable and the model's own observable features. We develop an estimation procedure for this latent variable model and establish its statistical properties. We also design efficient numerical algorithms that support estimation and various downstream tasks. Empirically, we evaluate the approach on 12 widely used benchmarks from the Open LLM Leaderboard (v1/v2). - oai:arXiv.org:2512.06553v1 - stat.AP - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Peiyao Cai, Chengyu Cui, Felipe Maia Polo, Seamus Somerstep, Leshem Choshen, Mikhail Yurochkin, Moulinath Banerjee, Yuekai Sun, Kean Ming Tan, Gongjun Xu - - - Switched Linear Ensemble Systems and Structural Controllability - https://arxiv.org/abs/2512.06561 - arXiv:2512.06561v1 Announce Type: cross -Abstract: This paper introduces and solves a structural controllability problem for ensembles of switched linear systems. All individual subsystems in the ensemble are sparse, governed by the same sparsity pattern, and undergo switching at the same sequence of time instants. The controllability of an ensemble system describes the ability to use a common control input to simultaneously steer every individual system. A sparsity pattern is called structurally controllable for pair \((k,q)\) if it admits a controllable ensemble of \(q\) individual systems with at most \(k\) switches. We derive a necessary and sufficient condition for a sparsity pattern to be structurally controllable for a given \((k,q)\), and characterize when a sparsity pattern admits a finite \(k\) that guarantees structural controllability for \((k,q)\) for arbitrary $q$. Compared with the linear time-invariant ensemble case, this second condition is strictly weaker. We further show that these conditions have natural connections with maximum flow, and hence can be checked by polynomial algorithms. Specifically, the time complexity of deciding structural controllability is \(O(n^3)\) and the complexity of computing the smallest number of switches needed is \(O(n^3 \log n)\), with \(n\) the dimension of each individual subsystem. - oai:arXiv.org:2512.06561v1 - math.OC - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Haoyu Yin, Yi Li, Ouyang Du, Bruno Sinopoli, Xudong Chen - - - Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions - https://arxiv.org/abs/2512.06615 - arXiv:2512.06615v1 Announce Type: cross -Abstract: We present latent nonlinear denoising score matching (LNDSM), a novel training objective for score-based generative models that integrates nonlinear forward dynamics with the VAE-based latent SGM framework. This combination is achieved by reformulating the cross-entropy term using the approximate Gaussian transition induced by the Euler-Maruyama scheme. To ensure numerical stability, we identify and remove two zero-mean but variance exploding terms arising from small time steps. Experiments on variants of the MNIST dataset demonstrate that the proposed method achieves faster synthesis and enhanced learning of inherently structured distributions. Compared to benchmark structure-agnostic latent SGMs, LNDSM consistently attains superior sample quality and variability. - oai:arXiv.org:2512.06615v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Kaichen Shen, Wei Zhu - - - Optimal Preconditioning is a Geodesically Convex Optimization Problem - https://arxiv.org/abs/2512.06618 - arXiv:2512.06618v1 Announce Type: cross -Abstract: We introduce a unified framework for computing approximately-optimal preconditioners for solving linear and non-linear systems of equations. We demonstrate that the condition number minimization problem, under structured transformations such as diagonal and block-diagonal preconditioners, is geodesically convex with respect to unitarily invariant norms, including the Frobenius and Bombieri--Weyl norms. This allows us to introduce efficient first-order algorithms with precise convergence guarantees. -For linear systems, we analyze the action of symmetric Lie subgroups $G \subseteq \GL_m(\CC) \times \GL_n(\CC)$ on the input matrix and prove that the logarithm of the condition number is a smooth geodesically convex function on the associated Riemannian quotient manifold. We obtain explicit gradient formulas, show Lipschitz continuity, and prove convergence rates for computing the optimal Frobenius condition number: $\widetilde{O}(1/\eps^2)$ iterations for general two-sided preconditioners and $\widetilde{O}(\kappa_F^2 \log(1/\eps))$ for strongly convex cases such as left preconditioning. We extend our framework to consider preconditioning of polynomial systems $\f(x) = 0$, where $\f$ is a system of multivariate polynomials. We analyze the local condition number $\mu(\f, \xi)$, at a root $\xi$ and prove that it also admits a geodesically convex formulation under appropriate group actions. We deduce explicit formulas for the Riemannian gradients and present convergence bounds for the corresponding optimization algorithms. To the best of our knowledge, this is the first preconditioning algorithm with theoretical guarantees for polynomial systems. - oai:arXiv.org:2512.06618v1 - math.OC - cs.CC - cs.NA - math.AG - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - M. Levent Do\u{g}an, Alperen Erg\"ur, Elias Tsigaridas - - - Half-explicit Runge-Kutta integrators for variational multiscale turbulence modeling: Toward higher-order accuracy in space and time - https://arxiv.org/abs/2512.06626 - arXiv:2512.06626v1 Announce Type: cross -Abstract: The residual-based variational multiscale (VMS) formulation has achieved remarkable success in large-eddy simulation of turbulent flows. However, its temporal discretization has largely remained limited to second-order implicit schemes. The present work aims at advancing this direction through the introduction of Runge-Kutta (RK) schemes within the VMS framework in a mathematically consistent manner. Guided by the Rothe method, the half-explicit RK scheme is employed as its accuracy is theoretically guaranteed for index-2 differential-algebraic equations. Owing to the explicit treatment of the nonlinear term, the resulting spatial problem exhibits a structure analogous to that of the Darcy equation. Following the philosophy of the VMS analysis, a subgrid-scale model is derived without invoking linearization based on perturbation series and related assumptions. The analysis further reveals that the parameter in the subgrid model is independent of the spatial mesh size. Fourier analysis demonstrates that the Rothe method, compared with the conventional vertical method of lines, provides improved dissipation and dispersion properties and exhibits a larger stability region for convection-dominated regimes. In the Taylor-Green vortex benchmark, the proposed schemes demonstrate superior performance as a large-eddy simulation model, achieving higher fidelity in predicting the kinetic energy evolution, energy spectra, and vortex structures than the conventional VMS formulation. Simulations of the open cavity flow further show that the proposed schemes can accurately capture the periodic limit cycle caused by the supercritical Hopf bifurcation, confirming its effectiveness and fidelity for highly sensitive flow instability problems. - oai:arXiv.org:2512.06626v1 - physics.flu-dyn - cs.NA - math.NA - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yujie Sun, Chi Ding, Ju Liu - - - Learning to Hedge Swaptions - https://arxiv.org/abs/2512.06639 - arXiv:2512.06639v1 Announce Type: cross -Abstract: This paper investigates the deep hedging framework, based on reinforcement learning (RL), for the dynamic hedging of swaptions, contrasting its performance with traditional sensitivity-based rho-hedging. We design agents under three distinct objective functions (mean squared error, downside risk, and Conditional Value-at-Risk) to capture alternative risk preferences and evaluate how these objectives shape hedging styles. Relying on a three-factor arbitrage-free dynamic Nelson-Siegel model for our simulation experiments, our findings show that near-optimal hedging effectiveness is achieved when using two swaps as hedging instruments. Deep hedging strategies dynamically adapt the hedging portfolio's exposure to risk factors across states of the market. In our experiments, their out-performance over rho-hedging strategies persists even in the presence some of model misspecification. These results highlight RL's potential to deliver more efficient and resilient swaption hedging strategies. - oai:arXiv.org:2512.06639v1 - q-fin.RM - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Zaniar Ahmadi, Fr\'ed\'eric Godin - - - Phase-multiplexed optical computing: Reconfiguring a multi-task diffractive optical processor using illumination phase diversity - https://arxiv.org/abs/2512.06658 - arXiv:2512.06658v1 Announce Type: cross -Abstract: We report a monochrome multi-task diffractive network architecture that leverages illumination phase multiplexing to dynamically reconfigure its output function and accurately implement a large group of complex-valued linear transformations between an input and output aperture. Each member of the desired group of T unique transformations is encoded and addressed with a distinct 2D illumination phase profile, termed "phase key", which illuminates the input aperture, activating the corresponding transformation at the output field-of-view. A common diffractive optical network, optimized with T phase keys, demultiplexes these encoded inputs and accurately executes any of the T distinct linear transformations at its output. We demonstrate that a diffractive network composed of N = 2 x T x Ni x No optimized diffractive features can realize T distinct complex-valued linear transformations, accurately executed for any complex field at the input aperture, where Ni and No refer to the input/output pixels, respectively. In our proof-of-concept numerical analysis, T = 512 complex-valued transformations are implemented by the same monochrome diffractive network with negligible error using illumination phase diversity. Compared with wavelength-multiplexed diffractive systems, phase-multiplexing architecture significantly lowers the transformation errors, potentially enabling larger-scale optical transformations to be implemented through a monochrome processor. Phase-multiplexed multi-task diffractive networks would enhance the capabilities of optical computing and machine-vision systems. - oai:arXiv.org:2512.06658v1 - physics.optics - cs.NE - physics.app-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiao Wang, Aydogan Ozcan - - - Optimal experimental design with k-space data: application to inverse hemodynamics - https://arxiv.org/abs/2512.06712 - arXiv:2512.06712v1 Announce Type: cross -Abstract: Subject-specific cardiovascular models rely on parameter estimation using measurements such as 4D Flow MRI data. However, acquiring high-resolution, high-fidelity functional flow data is costly and taxing for the patient. As a result, there is growing interest in using highly undersampled MRI data to reduce acquisition time and thus the cost, while maximizing the information gain from the data. Examples of such recent work include inverse problems to estimate boundary conditions of aortic blood flow from highly undersampled k-space data. The undersampled data is selected based on a predefined sampling mask which can significantly influences the performance and the quality of the solution of the inverse problem. While there are many established sampling patterns to collect undersampled data, it remains unclear how to select the best sampling pattern for a given set of inference parameters. In this paper we propose an Optimal Experimental Design (OED) framework for MRI measurements in k-space, aiming to find optimal masks for estimating specific parameters directly from k-space. As OED is typically applied to sensor placement problems in spatial locations, this is, to our knowledge, the first time the technique is used in this context. We demonstrate that the masks optimized by employing OED consistently outperform conventional sampling patterns in terms of parameter estimation accuracy and variance, facilitating a speed-up of 10x of the acquisition time while maintaining accuracy. - oai:arXiv.org:2512.06712v1 - physics.med-ph - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Miriam L\"ocke, Ahmed Attia, Dariusz Uc\'inski, Crist\'obal Bertoglio - - - GPU-Accelerated Optimization Solver for Unit Commitment in Large-Scale Power Grids - https://arxiv.org/abs/2512.06715 - arXiv:2512.06715v1 Announce Type: cross -Abstract: This work presents a GPU-accelerated solver for the unit commitment (UC) problem in large-scale power grids. The solver uses the Primal-Dual Hybrid Gradient (PDHG) algorithm to efficiently solve the relaxed linear subproblem, achieving faster bound estimation and improved crossover and branch-and-bound convergence compared to conventional CPU-based methods. These improvements significantly reduce the total computation time for the mixed-integer linear UC problem. The proposed approach is validated on large-scale systems, including 4224-, 6049-, and 6717-bus networks with long control horizons and computationally intensive problems, demonstrating substantial speed-ups while maintaining solution quality. - oai:arXiv.org:2512.06715v1 - math.OC - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hussein Sharadga, Javad Mohammadi - - - Virtual Qudits for Simon's Problem: Dimension-Lifted Algorithms on Qubit Hardware - https://arxiv.org/abs/2512.06756 - arXiv:2512.06756v1 Announce Type: cross -Abstract: Simon's problem admits an exponential quantum speedup, but current quantum devices support only qubits. This work introduces a general construction for simulating qudit versions of Simon's algorithm on qubit hardware by defining virtual qudits implemented through controlled permutations and qudit phase operations. We build a dimension lifted oracle that encodes the hidden shift in dimension d and show how to realize its action using only qubit gates. We mathematically verify that the lifted circuit reproduces the correct measurement statistics, analyze the depth overhead tradeoffs as a function of d, and provide numerical simulations in QuTiP for example values. Our approach demonstrates how higher-dimensional structures can be embedded into qubit devices and provides a general method for extending qudit algorithms to current hardware. - oai:arXiv.org:2512.06756v1 - quant-ph - cs.CC - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Abed Semre (Computer Science Department, Technion - Israel Institute of Technology, Haifa, Israel), Steven Frankel (Faculty of Mechanical Engineering, Technion - Israel Institute of Technology, Haifa, Israel) - - - ADAM Optimization with Adaptive Batch Selection - https://arxiv.org/abs/2512.06795 - arXiv:2512.06795v1 Announce Type: cross -Abstract: Adam is a widely used optimizer in neural network training due to its adaptive learning rate. However, because different data samples influence model updates to varying degrees, treating them equally can lead to inefficient convergence. To address this, a prior work proposed adapting the sampling distribution using a bandit framework to select samples adaptively. While promising, the bandit-based variant of Adam suffers from limited theoretical guarantees. In this paper, we introduce Adam with Combinatorial Bandit Sampling (AdamCB), which integrates combinatorial bandit techniques into Adam to resolve these issues. AdamCB is able to fully utilize feedback from multiple samples at once, enhancing both theoretical guarantees and practical performance. Our regret analysis shows that AdamCB achieves faster convergence than Adam-based methods including the previous bandit-based variant. Numerical experiments demonstrate that AdamCB consistently outperforms existing methods. - oai:arXiv.org:2512.06795v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Proc. The Thirteenth International Conference on Learning Representations (ICLR), 2025 - Gyu Yeol Kim, Min-hwan Oh - - - Optimal and Diffusion Transports in Machine Learning - https://arxiv.org/abs/2512.06797 - arXiv:2512.06797v1 Announce Type: cross -Abstract: Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This includes sampling via diffusion methods, optimizing the weights of neural networks, and analyzing the evolution of token distributions across layers of large language models. While the targeted applications differ (samples, weights, tokens), their mathematical descriptions share a common structure. A key idea is to switch from the Eulerian representation of densities to their Lagrangian counterpart through vector fields that advect particles. This dual view introduces challenges, notably the non-uniqueness of Lagrangian vector fields, but also opportunities to craft density evolutions and flows with favorable properties in terms of regularity, stability, and computational tractability. This survey presents an overview of these methods, with emphasis on two complementary approaches: diffusion methods, which rely on stochastic interpolation processes and underpin modern generative AI, and optimal transport, which defines interpolation by minimizing displacement cost. We illustrate how both approaches appear in applications ranging from sampling, neural network optimization, to modeling the dynamics of transformers for large language models. - oai:arXiv.org:2512.06797v1 - math.OC - cs.AI - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Gabriel Peyr\'e - - - Circular Chromatic Numbers, Balanceability, Relation Algebras, and Network Satisfaction Problems - https://arxiv.org/abs/2512.06878 - arXiv:2512.06878v1 Announce Type: cross -Abstract: In this paper, we characterize graphs with circular chromatic number less than 3 in terms of certain balancing labellings studied in the context of signed graphs. In fact, we construct a signed graph which is universal for all such labellings of graphs with circular chromatic number less than $3$, and is closely related to the generic circular triangle-free graph studied by Bodirsky and Guzm\'an-Pro. Moreover, our universal structure gives rise to a representation of the relation algebra $56_{65}$. We then use this representation to show that the network satisfaction problem described by this relation algebra belongs to NP. This concludes the full classification of the existence of a universal square representation, as well as the complexity of the corresponding network satisfaction problem, for relation algebras with at most four atoms. - oai:arXiv.org:2512.06878v1 - math.CO - cs.DM - math.RA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Manuel Bodirsky, Santiago Guzm\'an-Pro, Moritz Jahn, Mat\v{e}j Kone\v{c}n\'y, Paul Winkler - - - Symmetric Aggregation of Conformity Scores for Efficient Uncertainty Sets - https://arxiv.org/abs/2512.06945 - arXiv:2512.06945v1 Announce Type: cross -Abstract: Access to multiple predictive models trained for the same task, whether in regression or classification, is increasingly common in many applications. Aggregating their predictive uncertainties to produce reliable and efficient uncertainty quantification is therefore a critical but still underexplored challenge, especially within the framework of conformal prediction (CP). While CP methods can generate individual prediction sets from each model, combining them into a single, more informative set remains a challenging problem. To address this, we propose SACP (Symmetric Aggregated Conformal Prediction), a novel method that aggregates nonconformity scores from multiple predictors. SACP transforms these scores into e-values and combines them using any symmetric aggregation function. This flexible design enables a robust, data-driven framework for selecting aggregation strategies that yield sharper prediction sets. We also provide theoretical insights that help justify the validity and performance of the SACP approach. Extensive experiments on diverse datasets show that SACP consistently improves efficiency and often outperforms state-of-the-art model aggregation baselines. - oai:arXiv.org:2512.06945v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Nabil Alami, Jad Zakharia, Souhaib Ben Taieb - - - PARIS: Pruning Algorithm via the Representer theorem for Imbalanced Scenarios - https://arxiv.org/abs/2512.06950 - arXiv:2512.06950v1 Announce Type: cross -Abstract: The challenge of \textbf{imbalanced regression} arises when standard Empirical Risk Minimization (ERM) biases models toward high-frequency regions of the data distribution, causing severe degradation on rare but high-impact ``tail'' events. Existing strategies uch as loss re-weighting or synthetic over-sampling often introduce noise, distort the underlying distribution, or add substantial algorithmic complexity. - We introduce \textbf{PARIS} (Pruning Algorithm via the Representer theorem for Imbalanced Scenarios), a principled framework that mitigates imbalance by \emph{optimizing the training set itself}. PARIS leverages the representer theorem for neural networks to compute a \textbf{closed-form representer deletion residual}, which quantifies the exact change in validation loss caused by removing a single training point \emph{without retraining}. Combined with an efficient Cholesky rank-one downdating scheme, PARIS performs fast, iterative pruning that eliminates uninformative or performance-degrading samples. - We use a real-world space weather example, where PARIS reduces the training set by up to 75\% while preserving or improving overall RMSE, outperforming re-weighting, synthetic oversampling, and boosting baselines. Our results demonstrate that representer-guided dataset pruning is a powerful, interpretable, and computationally efficient approach to rare-event regression. - oai:arXiv.org:2512.06950v1 - stat.ML - cs.LG - physics.space-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Enrico Camporeale - - - Statistical analysis of Inverse Entropy-regularized Reinforcement Learning - https://arxiv.org/abs/2512.06956 - arXiv:2512.06956v1 Announce Type: cross -Abstract: Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of the recovered reward: many reward functions can induce the same optimal policy, rendering the inverse problem ill-posed. In this paper, we develop a statistical framework for Inverse Entropy-regularized Reinforcement Learning that resolves this ambiguity by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual. This combination yields a unique and well-defined so-called least-squares reward consistent with the expert policy. We model the expert demonstrations as a Markov chain with the invariant distribution defined by an unknown expert policy $\pi^\star$ and estimate the policy by a penalized maximum-likelihood procedure over a class of conditional distributions on the action space. We establish high-probability bounds for the excess Kullback--Leibler divergence between the estimated policy and the expert policy, accounting for statistical complexity through covering numbers of the policy class. These results lead to non-asymptotic minimax optimal convergence rates for the least-squares reward function, revealing the interplay between smoothing (entropy regularization), model complexity, and sample size. Our analysis bridges the gap between behavior cloning, inverse reinforcement learning, and modern statistical learning theory. - oai:arXiv.org:2512.06956v1 - stat.ML - cs.LG - math.ST - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Denis Belomestny, Alexey Naumov, Sergey Samsonov - - - Learning Conditional Independence Differential Graphs From Time-Dependent Data - https://arxiv.org/abs/2512.06960 - arXiv:2512.06960v1 Announce Type: cross -Abstract: Estimation of differences in conditional independence graphs (CIGs) of two time series Gaussian graphical models (TSGGMs) is investigated where the two TSGGMs are known to have similar structure. The TSGGM structure is encoded in the inverse power spectral density (IPSD) of the time series. In several existing works, one is interested in estimating the difference in two precision matrices to characterize underlying changes in conditional dependencies of two sets of data consisting of independent and identically distributed (i.i.d.) observations. In this paper we consider estimation of the difference in two IPSDs to characterize the underlying changes in conditional dependencies of two sets of time-dependent data. Our approach accounts for data time dependencies unlike past work. We analyze a penalized D-trace loss function approach in the frequency domain for differential graph learning, using Wirtinger calculus. We consider both convex (group lasso) and non-convex (log-sum and SCAD group penalties) penalty/regularization functions. An alternating direction method of multipliers (ADMM) algorithm is presented to optimize the objective function. We establish sufficient conditions in a high-dimensional setting for consistency (convergence of the inverse power spectral density to true value in the Frobenius norm) and graph recovery. Both synthetic and real data examples are presented in support of the proposed approaches. In synthetic data examples, our log-sum-penalized differential time-series graph estimator significantly outperformed our lasso based differential time-series graph estimator which, in turn, significantly outperformed an existing lasso-penalized i.i.d. modeling approach, with $F_1$ score as the performance metric. - oai:arXiv.org:2512.06960v1 - stat.ML - cs.LG - eess.SP - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - 10.1109/ACCESS.2025.3639399 - Jitendra K Tugnait - - - Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging - https://arxiv.org/abs/2512.06977 - arXiv:2512.06977v1 Announce Type: cross -Abstract: Accurate multi-slice reconstruction from limited measurement data is crucial to speed up the acquisition process in medical and scientific imaging. However, it remains challenging due to the ill-posed nature of the problem and the high computational and memory demands. We propose a framework that addresses these challenges by integrating partitioned diffusion priors with physics-based constraints. By doing so, we substantially reduce memory usage per GPU while preserving high reconstruction quality, outperforming both physics-only and full multi-slice reconstruction baselines for different modalities, namely Magnetic Resonance Imaging (MRI) and four-dimensional Scanning Transmission Electron Microscopy (4D-STEM). Additionally, we show that the proposed method improves in-distribution accuracy as well as strong generalization to out-of-distribution datasets. - oai:arXiv.org:2512.06977v1 - eess.IV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Laurentius Valdy, Richard D. Paul, Alessio Quercia, Zhuo Cao, Xuan Zhao, Hanno Scharr, Arya Bangun - - - Bell Numbers and Stirling Numbers of the Mycielskian of Trees - https://arxiv.org/abs/2512.06980 - arXiv:2512.06980v1 Announce Type: cross -Abstract: We establish explicit formulas for Bell numbers and graphical Stirling numbers of complete multipartite graphs, complete bipartite graphs with removed perfect matchings, and Mycielskian trees. For complete multipartite graphs $K(n_1,\ldots,n_\ell)$, we provide a simplified proof that $B(G) = \prod_{i=1}^\ell \bell{n_i}$. We derive $B(K_{n,n} - M) = \sum_{k=0}^{n} \binom{n}{k} \bell{k}^2$ for removed perfect matching $M$, and for Mycielskian star graphs, $B(M(St_n); 3) = 2^n + 1$ and $B(M(St_n); 2n) = 2n^2 - 3n + 3$. Results extend to Mycielskians of arbitrary trees. Our computational verifications establish links between graphical Bell numbers and fundamental sequences in combinatorics and pattern avoidance, including identification of several OEIS entries: A000051, A096376, A116735, A384980, A384981, A384988, A385432, and A385437. - oai:arXiv.org:2512.06980v1 - math.CO - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - J. Allagan, G. Morgan, D. Sinclair - - - Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length - https://arxiv.org/abs/2512.07019 - arXiv:2512.07019v1 Announce Type: cross -Abstract: The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to provide guidance for both downstream applications and actionable future improvements. The Item Response Theory (IRT) model with Computerized Adaptive Testing has recently emerged as a promising framework for evaluating LLMs via their response accuracy. Beyond simple response accuracy, LLMs' chain of thought (CoT) lengths serve as a vital indicator of their reasoning ability. To leverage the CoT length information to assist the evaluation of LLMs, we propose the Latency-Response Theory (LaRT) model, which jointly models both the response accuracy and CoT length by introducing a key correlation parameter between the latent ability and the latent speed. We derive an efficient stochastic approximation Expectation-Maximization algorithm for parameter estimation. We establish rigorous identifiability results for the latent ability and latent speed parameters to ensure the statistical validity of their estimation. Through both theoretical asymptotic analyses and simulation studies, we demonstrate LaRT's advantages over IRT in terms of superior estimation accuracy and shorter confidence intervals for latent trait estimation. To evaluate LaRT in real data, we collect responses from diverse LLMs on popular benchmark datasets. We find that LaRT yields different LLM rankings than IRT and outperforms IRT across multiple key evaluation metrics including predictive power, item efficiency, ranking validity, and LLM evaluation efficiency. Code and data are available at https://github.com/Toby-X/Latency-Response-Theory-Model. - oai:arXiv.org:2512.07019v1 - stat.ME - cs.AI - stat.AP - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhiyu Xu, Jia Liu, Yixin Wang, Yuqi Gu - - - Random Access for LEO Satellite Communication Systems via Deep Learning - https://arxiv.org/abs/2512.07053 - arXiv:2512.07053v1 Announce Type: cross -Abstract: Integrating contention-based random access procedures into low Earth orbit (LEO) satellite communication (SatCom) systems poses new challenges, including long propagation delays, large Doppler shifts, and a large number of simultaneous access attempts. These factors degrade the efficiency and responsiveness of conventional random access schemes, particularly in scenarios such as satellite-based internet of things and direct-to-device services. In this paper, we propose a deep learning-based random access framework designed for LEO SatCom systems. The framework incorporates an early preamble collision classifier that uses multi-antenna correlation features and a lightweight 1D convolutional neural network to estimate the number of collided users at the earliest stage. Based on this estimate, we introduce an opportunistic transmission scheme that balances access probability and resource efficiency to improve success rates and reduce delay. Simulation results under 3GPP-compliant LEO settings confirm that the proposed framework achieves higher access success probability, lower delay, better physical uplink shared channel utilization, and reduced computational complexity compared to existing schemes. - oai:arXiv.org:2512.07053v1 - eess.SP - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hyunwoo Lee, Ian P. Roberts, Jinkyo Jeong, Daesik Hong - - - Beam search decoder for quantum LDPC codes - https://arxiv.org/abs/2512.07057 - arXiv:2512.07057v1 Announce Type: cross -Abstract: We propose a decoder for quantum low density parity check (LDPC) codes based on a beam search heuristic guided by belief propagation (BP). Our beam search decoder applies to all quantum LDPC codes and achieves different speed-accuracy tradeoffs by tuning its parameters such as the beam width. We perform numerical simulations under circuit level noise for the $[[144, 12, 12]]$ bivariate bicycle (BB) code at noise rate $p=10^{-3}$ to estimate the logical error rate and the 99.9 percentile runtime and we compare with the BP-OSD decoder which has been the default quantum LDPC decoder for the past six years. A variant of our beam search decoder with a beam width of 64 achieves a $17\times$ reduction in logical error rate. With a beam width of 8, we reach the same logical error rate as BP-OSD with a $26.2\times$ reduction in the 99.9 percentile runtime. We identify the beam search decoder with beam width of 32 as a promising candidate for trapped ion architectures because it achieves a $5.6\times$ reduction in logical error rate with a 99.9 percentile runtime per syndrome extraction round below 1ms at $p=5 \times10^{-4}$. Remarkably, this is achieved in software on a single core, without any parallelization or specialized hardware (FPGA, ASIC), suggesting one might only need three 32-core CPUs to decode a trapped ion quantum computer with 1000 logical qubits. - oai:arXiv.org:2512.07057v1 - quant-ph - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Min Ye, Dave Wecker, Nicolas Delfosse - - - The Equational Theories Project: Advancing Collaborative Mathematical Research at Scale - https://arxiv.org/abs/2512.07087 - arXiv:2512.07087v1 Announce Type: cross -Abstract: We report on the Equational Theories Project (ETP), an online collaborative pilot project to explore new ways to collaborate in mathematics with machine assistance. The project successfully determined all 22 028 942 edges of the implication graph between the 4694 simplest equational laws on magmas, by a combination of human-generated and automated proofs, all validated by the formal proof assistant language Lean. As a result of this project, several new constructions of magmas satisfying specific laws were discovered, and several auxiliary questions were also addressed, such as the effect of restricting attention to finite magmas. - oai:arXiv.org:2512.07087v1 - math.RA - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Matthew Bolan, Joachim Breitner, Jose Brox, Nicholas Carlini, Mario Carneiro, Floris van Doorn, Martin Dvorak, Andr\'es Goens, Aaron Hill, Harald Husum, Hern\'an Ibarra Mejia, Zoltan Kocsis, Bruno Le Floch, Amir Livne Bar-on, Lorenzo Luccioli, Douglas McNeil, Alex Meiburg, Pietro Monticone, Pace P. Nielsen, Emmanuel Osalotioman Osazuwa, Giovanni Paolini, Marco Petracci, Bernhard Reinke, David Renshaw, Marcus Rossel, Cody Roux, J\'er\'emy Scanvic, Shreyas Srinivas, Anand Rao Tadipatri, Terence Tao, Vlad Tsyrklevich, Fernando Vaquerizo-Villar, Daniel Weber, Fan Zhen - - - TagLabel: RFID Based Orientation and Material Sensing for Automated Package Inspection - https://arxiv.org/abs/2512.07097 - arXiv:2512.07097v1 Announce Type: cross -Abstract: Modern logistics systems face increasing difficulty in identifying counterfeit products, fraudulent returns, and hazardous items concealed within packages, yet current package screening methods remain too slow, expensive, and impractical for widespread use. This paper presents TagLabel, an RFID based system that determines both the orientation and contents of packages using low cost passive UHF tags. By analyzing how materials change RSSI and phase, the system identifies the contents of a package without opening it. Using orientation inferred from phase differences, tag occlusion, and antenna gain patterns, the system selects the tag with the greatest occlusion for accurate material sensing. We evaluate two and three tag configurations, and show that both can deliver high orientation and material sensing performance through the use of machine learning classifiers, even in realistic RF environments. When combined into a unified pipeline, TagLabel achieves more than 80 percent accuracy across all package orientations. Because it requires only standard RFID hardware and offers fast scanning times, this approach provides a practical way to enhance package inspection and improve automation in logistics operations. - oai:arXiv.org:2512.07097v1 - eess.SP - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - David Wang, Jiale Zhang, Pei Zhang - - - Scheduling in Quantum Satellite Networks: Fairness and Performance Optimization - https://arxiv.org/abs/2512.07108 - arXiv:2512.07108v1 Announce Type: cross -Abstract: Quantum satellite networks offer a promising solution for achieving long-distance quantum communication by enabling entanglement distribution across global scales. This work formulates and solves the quantum satellite network scheduling problem by optimizing satellite-to-ground station pair assignments under realistic system and environmental constraints. Our framework accounts for limited satellite and ground station resources, fairness, entanglement fidelity thresholds, and real world non-idealities including atmospheric losses, weather and background noise. In addition, we incorporate the complexities of multi-satellite relays enabled via inter-satellite links. We propose an integer linear programming (ILP) based optimization framework that supports multiple scheduling objectives, allowing us to analyze tradeoffs between maximizing total entanglement distribution rate and ensuring fairness across ground station pairs. Our framework can also be used as a benchmark tool to measure the performance of other potential transmission scheduling policies. - oai:arXiv.org:2512.07108v1 - quant-ph - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Ashutosh Jayant Dikshit, Naga Lakshmi Anipeddi, Prajit Dhara, Saikat Guha, Deirdre Kilbane, Leandros Tassiulas, Don Towsley, Nitish K. Panigrahy - - - DeepSVM: Learning Stochastic Volatility Models with Physics-Informed Deep Operator Networks - https://arxiv.org/abs/2512.07162 - arXiv:2512.07162v1 Announce Type: cross -Abstract: Real-time calibration of stochastic volatility models (SVMs) is computationally bottlenecked by the need to repeatedly solve coupled partial differential equations (PDEs). In this work, we propose DeepSVM, a physics-informed Deep Operator Network (PI-DeepONet) designed to learn the solution operator of the Heston model across its entire parameter space. Unlike standard data-driven deep learning (DL) approaches, DeepSVM requires no labelled training data. Rather, we employ a hard-constrained ansatz that enforces terminal payoffs and static no-arbitrage conditions by design. Furthermore, we use Residual-based Adaptive Refinement (RAR) to stabilize training in difficult regions subject to high gradients. Overall, DeepSVM achieves a final training loss of $10^{-5}$ and predicts highly accurate option prices across a range of typical market dynamics. While pricing accuracy is high, we find that the model's derivatives (Greeks) exhibit noise in the at-the-money (ATM) regime, highlighting the specific need for higher-order regularization in physics-informed operator learning. - oai:arXiv.org:2512.07162v1 - q-fin.CP - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kieran A. Malandain, Selim Kalici, Hakob Chakhoyan - - - Clinical Interpretability of Deep Learning Segmentation Through Shapley-Derived Agreement and Uncertainty Metrics - https://arxiv.org/abs/2512.07224 - arXiv:2512.07224v1 Announce Type: cross -Abstract: Segmentation is the identification of anatomical regions of interest, such as organs, tissue, and lesions, serving as a fundamental task in computer-aided diagnosis in medical imaging. Although deep learning models have achieved remarkable performance in medical image segmentation, the need for explainability remains critical for ensuring their acceptance and integration in clinical practice, despite the growing research attention in this area. Our approach explored the use of contrast-level Shapley values, a systematic perturbation of model inputs to assess feature importance. While other studies have investigated gradient-based techniques through identifying influential regions in imaging inputs, Shapley values offer a broader, clinically aligned approach, explaining how model performance is fairly attributed to certain imaging contrasts over others. Using the BraTS 2024 dataset, we generated rankings for Shapley values for four MRI contrasts across four model architectures. Two metrics were proposed from the Shapley ranking: agreement between model and ``clinician" imaging ranking, and uncertainty quantified through Shapley ranking variance across cross-validation folds. Higher-performing cases (Dice \textgreater0.6) showed significantly greater agreement with clinical rankings. Increased Shapley ranking variance correlated with decreased performance (U-Net: $r=-0.581$). These metrics provide clinically interpretable proxies for model reliability, helping clinicians better understand state-of-the-art segmentation models. - oai:arXiv.org:2512.07224v1 - eess.IV - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Tianyi Ren, Daniel Low, Pittra Jaengprajak, Juampablo Heras Rivera, Jacob Ruzevick, Mehmet Kurt - - - Unsupervised Single-Channel Audio Separation with Diffusion Source Priors - https://arxiv.org/abs/2512.07226 - arXiv:2512.07226v1 Announce Type: cross -Abstract: Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in real-world scenarios is often difficult. This data scarcity can degrade model performance under unseen conditions and limit generalization ability. To this end, in this work, we approach this problem from an unsupervised perspective, framing it as a probabilistic inverse problem. Our method requires only diffusion priors trained on individual sources. Separation is then achieved by iteratively guiding an initial state toward the solution through reconstruction guidance. Importantly, we introduce an advanced inverse problem solver specifically designed for separation, which mitigates gradient conflicts caused by interference between the diffusion prior and reconstruction guidance during inverse denoising. This design ensures high-quality and balanced separation performance across individual sources. Additionally, we find that initializing the denoising process with an augmented mixture instead of pure Gaussian noise provides an informative starting point that significantly improves the final performance. To further enhance audio prior modeling, we design a novel time-frequency attention-based network architecture that demonstrates strong audio modeling capability. Collectively, these improvements lead to significant performance gains, as validated across speech-sound event, sound event, and speech separation tasks. - oai:arXiv.org:2512.07226v1 - eess.AS - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Runwu Shi, Chang Li, Jiang Wang, Rui Zhang, Nabeela Khan, Benjamin Yen, Takeshi Ashizawa, Kazuhiro Nakadai - - - Non-Hermitian Bose-Hubbard-like quantum models - https://arxiv.org/abs/2512.07250 - arXiv:2512.07250v1 Announce Type: cross -Abstract: Among all of the non-Hermitian large-tridiagonal-matrix quantum Hamiltonians we choose a subclass with the structure resembling the ``benchmark'' realistic Bose-Hubbard model. We demonstrate that this choice can be declared user-friendly in the sense that the underlying singular values can be specified via a ``Hermitized'' Schr\"{o}dinger-like equation. In particular, the related ``Hermitized'' Green's functions is shown given the two alternative compact and numerically efficient matrix continued fraction forms. - oai:arXiv.org:2512.07250v1 - quant-ph - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - 10.1088/1742-6596/3152/1/012023 - J. Phys.: Conf. Ser. 3152 (2025) 012023 - Miloslav Znojil - - - Affine Subspace Models and Clustering for Patch-Based Image Denoising - https://arxiv.org/abs/2512.07259 - arXiv:2512.07259v1 Announce Type: cross -Abstract: Image tile-based approaches are popular in many image processing applications such as denoising (e.g., non-local means). A key step in their use is grouping the images into clusters, which usually proceeds iteratively splitting the images into clusters and fitting a model for the images in each cluster. Linear subspaces have emerged as a suitable model for tile clusters; however, they are not well matched to images patches given that images are non-negative and thus not distributed around the origin in the tile vector space. We study the use of affine subspace models for the clusters to better match the geometric structure of the image tile vector space. We also present a simple denoising algorithm that relies on the affine subspace clustering model using least squares projection. We review several algorithmic approaches to solve the affine subspace clustering problem and show experimental results that highlight the performance improvements in clustering and denoising. - oai:arXiv.org:2512.07259v1 - eess.IV - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Tharindu Wickremasinghe, Marco F. Duarte - - - Non-negative DAG Learning from Time-Series Data - https://arxiv.org/abs/2512.07267 - arXiv:2512.07267v1 Announce Type: cross -Abstract: This work aims to learn the directed acyclic graph (DAG) that captures the instantaneous dependencies underlying a multivariate time series. The observed data follow a linear structural vector autoregressive model (SVARM) with both instantaneous and time-lagged dependencies, where the instantaneous structure is modeled by a DAG to reflect potential causal relationships. While recent continuous relaxation approaches impose acyclicity through smooth constraint functions involving powers of the adjacency matrix, they lead to non-convex optimization problems that are challenging to solve. In contrast, we assume that the underlying DAG has only non-negative edge weights, and leverage this additional structure to impose acyclicity via a convex constraint. This enables us to cast the problem of non-negative DAG recovery from multivariate time-series data as a convex optimization problem in abstract form, which we solve using the method of multipliers. Crucially, the convex formulation guarantees global optimality of the solution. Finally, we assess the performance of the proposed method on synthetic time-series data, where it outperforms existing alternatives. - oai:arXiv.org:2512.07267v1 - eess.SP - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Samuel Rey, Gonzalo Mateos - - - Verifiable Deep Quantitative Group Testing - https://arxiv.org/abs/2512.07279 - arXiv:2512.07279v1 Announce Type: cross -Abstract: We present a neural network-based framework for solving the quantitative group testing (QGT) problem that achieves both high decoding accuracy and structural verifiability. In QGT, the objective is to identify a small subset of defective items among $N$ candidates using only $M \ll N$ pooled tests, each reporting the number of defectives in the tested subset. We train a multi-layer perceptron to map noisy measurement vectors to binary defect indicators, achieving accurate and robust recovery even under sparse, bounded perturbations. Beyond accuracy, we show that the trained network implicitly learns the underlying pooling structure that links items to tests, allowing this structure to be recovered directly from the network's Jacobian. This indicates that the model does not merely memorize training patterns but internalizes the true combinatorial relationships governing QGT. Our findings reveal that standard feedforward architectures can learn verifiable inverse mappings in structured combinatorial recovery problems. - oai:arXiv.org:2512.07279v1 - eess.SP - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Shreyas Jayant Grampurohit, Satish Mulleti, Ajit Rajwade - - - Equivariant Diffusion for Crystal Structure Prediction - https://arxiv.org/abs/2512.07289 - arXiv:2512.07289v1 Announce Type: cross -Abstract: In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process. - oai:arXiv.org:2512.07289v1 - cond-mat.mtrl-sci - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Peijia Lin, Pin Chen, Rui Jiao, Qing Mo, Jianhuan Cen, Wenbing Huang, Yang Liu, Dan Huang, Yutong Lu - - - Exact Synthetic Populations for Scalable Societal and Market Modeling - https://arxiv.org/abs/2512.07306 - arXiv:2512.07306v1 Announce Type: cross -Abstract: We introduce a constraint-programming framework for generating synthetic populations that reproduce target statistics with high precision while enforcing full individual consistency. Unlike data-driven approaches that infer distributions from samples, our method directly encodes aggregated statistics and structural relations, enabling exact control of demographic profiles without requiring any microdata. We validate the approach on official demographic sources and study the impact of distributional deviations on downstream analyses. This work is conducted within the Pollitics project developed by Emotia, where synthetic populations can be queried through large language models to model societal behaviors, explore market and policy scenarios, and provide reproducible decision-grade insights without personal data. - oai:arXiv.org:2512.07306v1 - stat.ML - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Thierry Petit, Arnault Pachot - - - Two-dimensional RMSD projections for reaction path visualization and validation - https://arxiv.org/abs/2512.07329 - arXiv:2512.07329v1 Announce Type: cross -Abstract: Transition state or minimum energy path finding methods constitute a routine component of the computational chemistry toolkit. Standard analysis involves trajectories conventionally plotted in terms of the relative energy to the initial state against a cumulative displacement variable, or the image number. These dimensional reductions obscure structural rearrangements in high dimensions and may often be trajectory dependent. This precludes the ability to compare optimization trajectories of different methods beyond the number of calculations, time taken, and final saddle geometry. We present a method mapping trajectories onto a two-dimension surface defined by a permutation corrected root mean square deviation from the reactant and product configurations. Energy is represented as an interpolated color-mapped surface constructed from all optimization steps using radial basis functions. This representation highlights optimization trajectories, identifies endpoint basins, and diagnoses convergence concerns invisible in one-dimensional profiles. We validate the framework on a cycloaddition reaction, showing that a machine-learned potential saddle and density functional theory reference lie on comparable energy contours despite geometric displacements. - oai:arXiv.org:2512.07329v1 - physics.chem-ph - cond-mat.mtrl-sci - cs.LG - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Rohit Goswami (Institute IMX and Lab-COSMO, \'Ecole polytechnique f\'ed\'erale de Lausanne) - - - Machine learning in an expectation-maximisation framework for nowcasting - https://arxiv.org/abs/2512.07335 - arXiv:2512.07335v1 Announce Type: cross -Abstract: Decision making often occurs in the presence of incomplete information, leading to the under- or overestimation of risk. Leveraging the observable information to learn the complete information is called nowcasting. In practice, incomplete information is often a consequence of reporting or observation delays. In this paper, we propose an expectation-maximisation (EM) framework for nowcasting that uses machine learning techniques to model both the occurrence as well as the reporting process of events. We allow for the inclusion of covariate information specific to the occurrence and reporting periods as well as characteristics related to the entity for which events occurred. We demonstrate how the maximisation step and the information flow between EM iterations can be tailored to leverage the predictive power of neural networks and (extreme) gradient boosting machines (XGBoost). With simulation experiments, we show that we can effectively model both the occurrence and reporting of events when dealing with high-dimensional covariate information. In the presence of non-linear effects, we show that our methodology outperforms existing EM-based nowcasting frameworks that use generalised linear models in the maximisation step. Finally, we apply the framework to the reporting of Argentinian Covid-19 cases, where the XGBoost-based approach again is most performant. - oai:arXiv.org:2512.07335v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-sa/4.0/ - Paul Wilsens, Katrien Antonio, Gerda Claeskens - - - An Asynchronous Mixed-Signal Resonate-and-Fire Neuron - https://arxiv.org/abs/2512.07361 - arXiv:2512.07361v1 Announce Type: cross -Abstract: Analog computing at the edge is an emerging strategy to limit data storage and transmission requirements, as well as energy consumption, and its practical implementation is in its initial stages of development. Translating properties of biological neurons into hardware offers a pathway towards low-power, real-time edge processing. Specifically, resonator neurons offer selectivity to specific frequencies as a potential solution for temporal signal processing. Here, we show a fabricated Complementary Metal-Oxide-Semiconductor (CMOS) mixed-signal Resonate-and-Fire (R&F) neuron circuit implementation that emulates the behavior of these neural cells responsible for controlling oscillations within the central nervous system. We integrate the design with asynchronous handshake capabilities, perform comprehensive variability analyses, and characterize its frequency detection functionality. Our results demonstrate the feasibility of large-scale integration within neuromorphic systems, thereby advancing the exploitation of bio-inspired circuits for efficient edge temporal signal processing. - oai:arXiv.org:2512.07361v1 - eess.SP - cs.NE - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-sa/4.0/ - Giuseppe Leo, Paolo Gibertini, Irem Ilter, Erika Covi, Ole Richter, Elisabetta Chicca - - - From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent - https://arxiv.org/abs/2512.07397 - arXiv:2512.07397v1 Announce Type: cross -Abstract: We consider the problem of recovering an unknown low-dimensional vector from noisy, underdetermined observations. We focus on the Generalized Projected Gradient Descent (GPGD) framework, which unifies traditional sparse recovery methods and modern approaches using learned deep projective priors. We extend previous convergence results to robustness to model and projection errors. We use these theoretical results to explore ways to better control stability and robustness constants. To reduce recovery errors due to measurement noise, we consider generalized back-projection strategies to adapt GPGD to structured noise, such as sparse outliers. To improve the stability of GPGD, we propose a normalized idempotent regularization for the learning of deep projective priors. We provide numerical experiments in the context of sparse recovery and image inverse problems, highlighting the trade-offs between identifiability and stability that can be achieved with such methods. - oai:arXiv.org:2512.07397v1 - eess.IV - cs.NE - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ali Joundi (IMB), Yann Traonmilin (IMB), Jean-Fran\c{c}ois Aujol (UB, IMB) - - - Microseismic event classification with a lightweight Fourier Neural Operator model - https://arxiv.org/abs/2512.07425 - arXiv:2512.07425v1 Announce Type: cross -Abstract: Real-time monitoring of induced seismicity is crucial for mitigating operational hazards, relying on the rapid and accurate classification of microseismic events from continuous data streams. However, while many deep learning models excel at this task, their high computational requirements often limit their practical application in real-time monitoring systems. To address this limitation, a lightweight model based on the Fourier Neural Operator (FNO) is proposed for microseismic event classification, leveraging its inherent resolution-invariance and computational efficiency for waveform processing. In the STanford EArthquake Dataset (STEAD), a global and large-scale database of seismic waveforms, the FNO-based model demonstrates high effectiveness for trigger classification, with an F1 score of 95% even in the scenario of data sparsity in training. The new FNO model greatly decreases the computer power needed relative to current deep learning models without sacrificing the classification success rate measured by the F1 score. A test on a real microseismic dataset shows a classification success rate with an F1 score of 98%, outperforming many traditional deep-learning techniques. A combination of high success rate and low computational power indicates that the FNO model can serve as a methodology of choice for real-time monitoring of microseismicity for induced seismicity. The method saves computational resources and facilitates both post-processing and real-time seismic processing suitable for the implementation of traffic light systems to prevent undesired induced seismicity. - oai:arXiv.org:2512.07425v1 - physics.geo-ph - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Ayrat Abdullin, Umair bin Waheed, Leo Eisner, Abdullatif Al-Shuhail - - - Social welfare optimisation in well-mixed and structured populations - https://arxiv.org/abs/2512.07453 - arXiv:2512.07453v1 Announce Type: cross -Abstract: Research on promoting cooperation among autonomous, self-regarding agents has often focused on the bi-objective optimisation problem: minimising the total incentive cost while maximising the frequency of cooperation. However, the optimal value of social welfare under such constraints remains largely unexplored. In this work, we hypothesise that achieving maximal social welfare is not guaranteed at the minimal incentive cost required to drive agents to a desired cooperative state. To address this gap, we adopt to a single-objective approach focused on maximising social welfare, building upon foundational evolutionary game theory models that examined cost efficiency in finite populations, in both well-mixed and structured population settings. Our analytical model and agent-based simulations show how different interference strategies, including rewarding local versus global behavioural patterns, affect social welfare and dynamics of cooperation. Our results reveal a significant gap in the per-individual incentive cost between optimising for pure cost efficiency or cooperation frequency and optimising for maximal social welfare. Overall, our findings indicate that incentive design, policy, and benchmarking in multi-agent systems and human societies should prioritise welfare-centric objectives over proxy targets of cost or cooperation frequency. - oai:arXiv.org:2512.07453v1 - physics.soc-ph - cs.AI - cs.MA - math.OC - nlin.AO - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Van An Nguyen, Vuong Khang Huynh, Ho Nam Duong, Huu Loi Bui, Hai Anh Ha, Quang Dung Le, Le Quoc Dung Ngo, Tan Dat Nguyen, Ngoc Ngu Nguyen, Hoai Thuong Nguyen, Zhao Song, Le Hong Trang, The Anh Han - - - Optimized Machine Learning Methods for Studying the Thermodynamic Behavior of Complex Spin Systems - https://arxiv.org/abs/2512.07458 - arXiv:2512.07458v1 Announce Type: cross -Abstract: This paper presents a systematic study of the application of convolutional neural networks (CNNs) as an efficient and versatile tool for the analysis of critical and low-temperature phase states in spin system models. The problem of calculating the dependence of the average energy on the spatial distribution of exchange integrals for the Edwards-Anderson model on a square lattice with frustrated interactions is considered. We further construct a single convolutional classifier of phase states of the ferromagnetic Ising model on square, triangular, honeycomb, and kagome lattices, trained on configurations generated by the Swendsen-Wang cluster algorithm. Computed temperature profiles of the averaged posterior probability of the high-temperature phase form clear S-shaped curves that intersect in the vicinity of the theoretical critical temperatures and allow one to determine the critical temperature for the kagome lattice without additional retraining. It is shown that convolutional models substantially reduce the root-mean-square error (RMSE) compared with fully connected architectures and efficiently capture complex correlations between thermodynamic characteristics and the structure of magnetic correlated systems. - oai:arXiv.org:2512.07458v1 - physics.comp-ph - cond-mat.dis-nn - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dmitrii Kapitan, Pavel Ovchinnikov, Konstantin Soldatov, Petr Andriushchenko, Vitalii Kapitan - - - Permanent and transitory crime risk in variable-density hot spot analysis - https://arxiv.org/abs/2512.07467 - arXiv:2512.07467v1 Announce Type: cross -Abstract: Crime prevention measures, aiming for the effective and efficient spending of public resources, rely on the empirical analysis of spatial and temporal data for public safety outcomes. We perform a variable-density cluster analysis on crime incident reports in the City of Chicago for the years 2001--2022 to investigate changes in crime share composition for hot spots of different densities. Contributing to and going beyond the existing wealth of research on criminological applications in the operational research literature, we study the evolution of crime type shares in clusters over the course of two decades and demonstrate particularly notable impacts of the COVID-19 pandemic and its associated social contact avoidance measures, as well as a dependence of these effects on the primary function of city areas. Our results also indicate differences in the relative difficulty to address specific crime types, and an analysis of spatial autocorrelations further shows variations in incident uniformity between clusters and outlier areas at different distance radii. We discuss our findings in the context of the interplay between operational research and criminal justice, the practice of hot spot policing and public safety optimization, and the factors contributing to, and challenges and risks due to, data biases as an often neglected factor in criminological applications. - oai:arXiv.org:2512.07467v1 - stat.AP - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Ben Moews - - - Recovery of the optimal control value function in reproducing kernel Hilbert spaces from verification conditions - https://arxiv.org/abs/2512.07477 - arXiv:2512.07477v1 Announce Type: cross -Abstract: Approximating the optimal value function $v^*$ for infinite-horizon, nonlinear, autonomous optimal control problems is both challenging and essential for synthesizing real-time optimal feedback. We develop an abstract optimal recovery framework in reproducing kernel Hilbert spaces (RKHS) for reconstructing unknown target functions from mixed equality and inequality functional constraints. Within this framework, the approximation of $v^*$ is cast as a collocation-type problem derived from verification conditions for optimality -- most prominently, the Hamilton-Jacobi-Bellman (HJB) equation -- that uniquely characterizes $v^*$. As the set of collocation points becomes dense in the ambient domain $\Omega$, we establish convergence of the RKHS approximants to $v^*$: globally on $\Omega$ in the RKHS norm when $v^*$ is analytic, and locally (in a neighborhood of the origin) in the RKHS norm when $v^*$ is bounded from above and below by quadratic functions. Furthermore, we show that a practical numerical realization of the abstract scheme reduces to the classical policy iteration algorithm. Numerical experiments support the effectiveness of the proposed approach. - oai:arXiv.org:2512.07477v1 - math.OC - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tobias Ehring, Behzad Azmi, Bernard Haasdonk - - - High-Dimensional Change Point Detection using Graph Spanning Ratio - https://arxiv.org/abs/2512.07541 - arXiv:2512.07541v1 Announce Type: cross -Abstract: Inspired by graph-based methodologies, we introduce a novel graph-spanning algorithm designed to identify changes in both offline and online data across low to high dimensions. This versatile approach is applicable to Euclidean and graph-structured data with unknown distributions, while maintaining control over error probabilities. Theoretically, we demonstrate that the algorithm achieves high detection power when the magnitude of the change surpasses the lower bound of the minimax separation rate, which scales on the order of $\sqrt{nd}$. Our method outperforms other techniques in terms of accuracy for both Gaussian and non-Gaussian data. Notably, it maintains strong detection power even with small observation windows, making it particularly effective for online environments where timely and precise change detection is critical. - oai:arXiv.org:2512.07541v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Youngwen Sun, Katerina Papagiannouli, Vladimir Spokoiny - - - On Conditional Independence Graph Learning From Multi-Attribute Gaussian Dependent Time Series - https://arxiv.org/abs/2512.07557 - arXiv:2512.07557v1 Announce Type: cross -Abstract: Estimation of the conditional independence graph (CIG) of high-dimensional multivariate Gaussian time series from multi-attribute data is considered. Existing methods for graph estimation for such data are based on single-attribute models where one associates a scalar time series with each node. In multi-attribute graphical models, each node represents a random vector or vector time series. In this paper we provide a unified theoretical analysis of multi-attribute graph learning for dependent time series using a penalized log-likelihood objective function formulated in the frequency domain using the discrete Fourier transform of the time-domain data. We consider both convex (sparse-group lasso) and non-convex (log-sum and SCAD group penalties) penalty/regularization functions. We establish sufficient conditions in a high-dimensional setting for consistency (convergence of the inverse power spectral density to true value in the Frobenius norm), local convexity when using non-convex penalties, and graph recovery. We do not impose any incoherence or irrepresentability condition for our convergence results. We also empirically investigate selection of the tuning parameters based on the Bayesian information criterion, and illustrate our approach using numerical examples utilizing both synthetic and real data. - oai:arXiv.org:2512.07557v1 - stat.ML - cs.LG - eess.SP - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - 10.1109/OJSP.2025.3578807 - IEEE Open Journal of Signal Processing, vol. 6, pp. 705-721, 2025 - Jitendra K. Tugnait - - - Precise Liver Tumor Segmentation in CT Using a Hybrid Deep Learning-Radiomics Framework - https://arxiv.org/abs/2512.07574 - arXiv:2512.07574v1 Announce Type: cross -Abstract: Accurate three-dimensional delineation of liver tumors on contrast-enhanced CT is a prerequisite for treatment planning, navigation and response assessment, yet manual contouring is slow, observer-dependent and difficult to standardise across centres. Automatic segmentation is complicated by low lesion-parenchyma contrast, blurred or incomplete boundaries, heterogeneous enhancement patterns, and confounding structures such as vessels and adjacent organs. We propose a hybrid framework that couples an attention-enhanced cascaded U-Net with handcrafted radiomics and voxel-wise 3D CNN refinement for joint liver and liver-tumor segmentation. First, a 2.5D two-stage network with a densely connected encoder, sub-pixel convolution decoders and multi-scale attention gates produces initial liver and tumor probability maps from short stacks of axial slices. Inter-slice temporal consistency is then enforced by a simple three-slice refinement rule along the cranio-caudal direction, which restores thin and tiny lesions while suppressing isolated noise. Next, 728 radiomic descriptors spanning intensity, texture, shape, boundary and wavelet feature groups are extracted from candidate lesions and reduced to 20 stable, highly informative features via multi-strategy feature selection; a random forest classifier uses these features to reject false-positive regions. Finally, a compact 3D patch-based CNN derived from AlexNet operates in a narrow band around the tumor boundary to perform voxel-level relabelling and contour smoothing. - oai:arXiv.org:2512.07574v1 - eess.IV - cs.CR - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuecheng Li, Weikuan Jia, Komildzhon Sharipov, Alimov Ruslan, Lutfuloev Mazbutdzhon, Ismoilov Shuhratjon, Yuanjie Zheng - - - R2MF-Net: A Recurrent Residual Multi-Path Fusion Network for Robust Multi-directional Spine X-ray Segmentation - https://arxiv.org/abs/2512.07576 - arXiv:2512.07576v1 Announce Type: cross -Abstract: Accurate segmentation of spinal structures in X-ray images is a prerequisite for quantitative scoliosis assessment, including Cobb angle measurement, vertebral translation estimation and curvature classification. In routine practice, clinicians acquire coronal, left-bending and right-bending radiographs to jointly evaluate deformity severity and spinal flexibility. However, the segmentation step remains heavily manual, time-consuming and non-reproducible, particularly in low-contrast images and in the presence of rib shadows or overlapping tissues. To address these limitations, this paper proposes R2MF-Net, a recurrent residual multi-path encoder--decoder network tailored for automatic segmentation of multi-directional spine X-ray images. The overall design consists of a coarse segmentation network and a fine segmentation network connected in cascade. Both stages adopt an improved Inception-style multi-branch feature extractor, while a recurrent residual jump connection (R2-Jump) module is inserted into skip paths to gradually align encoder and decoder semantics. A multi-scale cross-stage skip (MC-Skip) mechanism allows the fine network to reuse hierarchical representations from multiple decoder levels of the coarse network, thereby strengthening the stability of segmentation across imaging directions and contrast conditions. Furthermore, a lightweight spatial-channel squeeze-and-excitation block (SCSE-Lite) is employed at the bottleneck to emphasize spine-related activations and suppress irrelevant structures and background noise. We evaluate R2MF-Net on a clinical multi-view radiograph dataset comprising 228 sets of coronal, left-bending and right-bending spine X-ray images with expert annotations. - oai:arXiv.org:2512.07576v1 - eess.IV - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuecheng Li, Weikuan Jia, Komildzhon Sharipov, Sharipov Hotam Beknazarovich, Farzona S. Ataeva, Qurbonaliev Alisher, Yuanjie Zheng - - - $\phi$-test: Global Feature Selection and Inference for Shapley Additive Explanations - https://arxiv.org/abs/2512.07578 - arXiv:2512.07578v1 Announce Type: cross -Abstract: We propose $\phi$-test, a global feature-selection and significance procedure for black-box predictors that combines Shapley attributions with selective inference. Given a trained model and an evaluation dataset, $\phi$-test performs SHAP-guided screening and fits a linear surrogate on the screened features via a selection rule with a tractable selective-inference form. For each retained feature, it outputs a Shapley-based global score, a surrogate coefficient, and post-selection $p$-values and confidence intervals in a global feature-importance table. Experiments on real tabular regression tasks with tree-based and neural backbones suggest that $\phi$-test can retain much of the predictive ability of the original model while using only a few features and producing feature sets that remain fairly stable across resamples and backbone classes. In these settings, $\phi$-test acts as a practical global explanation layer linking Shapley-based importance summaries with classical statistical inference. - oai:arXiv.org:2512.07578v1 - stat.ML - cs.LG - stat.ME - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh - - - A Closed-form Solution to the Wahba Problem for Pairwise Similar Quaternions - https://arxiv.org/abs/2512.07597 - arXiv:2512.07597v1 Announce Type: cross -Abstract: We present a closed-form solution to Wahba's problem in the quaternion domain for the special case of two vector observations. Existing approaches, including Davenport's $q$-method, QUEST, Horn's method, and ESOQ algorithms, recover the optimal quaternion through the eigendecomposition of a $4\times4$ matrix or iterative numerical methods. Consequently, these methods do not reveal the analytic structure of the optimal quaternion. - In this work, we derive an explicit analytical characterization of all quaternions that yield zero Wahba cost for the case $\ell=2$. Our approach builds on a connection between quaternion similarity, the singular Sylvester equation $aq=qb$, and quaternion square roots established in our previous work [1]. We provide (i) necessary and sufficient conditions under which the Wahba's cost function is zero and (ii) a closed-form parameterization of all such quaternions. This eliminates the need for eigenvalue computations and enables a direct algebraic understanding of the underlying geometry of Wahba's problem. - oai:arXiv.org:2512.07597v1 - math.RA - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hristina Radak, Christian Scheunert, Frank H. P. Fitzek - - - Bimorph Lithium Niobate Piezoelectric Micromachined Ultrasonic Transducers - https://arxiv.org/abs/2512.07718 - arXiv:2512.07718v1 Announce Type: cross -Abstract: Piezoelectric micromachined ultrasonic transducers (PMUTs) are widely used in applications that demand mechanical resilience, thermal stability, and compact form factors. Lead zirconate titanate (PZT) and aluminum nitride (AlN) active layers are used in PMUTs to enable acoustic actuation, sensing, or bidirectional operation. These platforms rely on bimorph films to maximize electromechanical coupling ($k^2$) through thin-film deposition, which uses intermediate electrode layers to establish opposing electric fields. Consequently, incumbent PMUT platforms are limited in achievable film thickness and feature material interfaces that compromise mechanical integrity and thermal performance. Combined with the intrinsic limitations of PZT and AlN, these factors motivate exploration of alternative PMUT material platforms. Recent efforts have sought to demonstrate that single-crystal lithium niobate (LN) is a promising candidate, offering substantially higher $k^2$ and bidirectional performance. Advances in LN film transfer technology have enabled the formation of periodically poled piezoelectric (P3F) LN, facilitating a bimorph stack without intermediate electrodes. In this work, we showcase bimorph PMUTs incorporating a mechanically robust, 20 micron thick P3F LN active layer. We establish the motivation for LN PMUTs through a material comparison, followed by extensive membrane geometry optimization and subsequent enhancement of the PMUT's $k^2$. We demonstrate a 775 kHz flexural mode device with a quality factor (Q) of 200 and an extracted $k^2$ of 6.4%, yielding a high transmit efficiency of 65 nm/V with a mechanically robust active layer. We leverage the high performance to demonstrate extreme-temperature resilience, showcasing stable device operation up to 600 degrees C and survival up to 900 degrees C, highlighting LN's potential as a resilient PMUT platform. - oai:arXiv.org:2512.07718v1 - cond-mat.mtrl-sci - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Vakhtang Chulukhadze, Zihuan Liu, Ziqian Yao, Lezli Matto, Tzu-Hsuan Hsu, Nishanth Ravi, Xiaoyu Niu, Michael E. Liao, Mark S. Goorsky, Neal Hall, Ruochen Lu - - - A scalable and real-time neural decoder for topological quantum codes - https://arxiv.org/abs/2512.07737 - arXiv:2512.07737v1 Announce Type: cross -Abstract: Fault-tolerant quantum computing will require error rates far below those achievable with physical qubits. Quantum error correction (QEC) bridges this gap, but depends on decoders being simultaneously fast, accurate, and scalable. This combination of requirements has not yet been met by a machine-learning decoder, nor by any decoder for promising resource-efficient codes such as the colour code. Here we introduce AlphaQubit 2, a neural-network decoder that achieves near-optimal logical error rates for both surface and colour codes at large scales under realistic noise. For the colour code, it is orders of magnitude faster than other high-accuracy decoders. For the surface code, we demonstrate real-time decoding faster than 1 microsecond per cycle up to distance 11 on current commercial accelerators with better accuracy than leading real-time decoders. These results support the practical application of a wider class of promising QEC codes, and establish a credible path towards high-accuracy, real-time neural decoding at the scales required for fault-tolerant quantum computation. - oai:arXiv.org:2512.07737v1 - quant-ph - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - Andrew W. Senior, Thomas Edlich, Francisco J. H. Heras, Lei M. Zhang, Oscar Higgott, James S. Spencer, Taylor Applebaum, Sam Blackwell, Justin Ledford, Akvil\.e \v{Z}emgulyt\.e, Augustin \v{Z}\'idek, Noah Shutty, Andrew Cowie, Yin Li, George Holland, Peter Brooks, Charlie Beattie, Michael Newman, Alex Davies, Cody Jones, Sergio Boixo, Hartmut Neven, Pushmeet Kohli, Johannes Bausch - - - Physics-Informed Neural Networks for Source Inversion and Parameters Estimation in Atmospheric Dispersion - https://arxiv.org/abs/2512.07755 - arXiv:2512.07755v1 Announce Type: cross -Abstract: Recent studies have shown the success of deep learning in solving forward and inverse problems in engineering and scientific computing domains, such as physics-informed neural networks (PINNs). In the fields of atmospheric science and environmental monitoring, estimating emission source locations is a central task that further relies on multiple model parameters that dictate velocity profiles and diffusion parameters. Estimating these parameters at the same time as emission sources from scarce data is a difficult task. In this work, we achieve this by leveraging the flexibility and generality of PINNs. We use a weighted adaptive method based on the neural tangent kernels to solve a source inversion problem with parameter estimation on the 2D and 3D advection-diffusion equations with unknown velocity and diffusion coefficients that may vary in space and time. Our proposed weighted adaptive method is presented as an extension of PINNs for forward PDE problems to a highly ill-posed source inversion and parameter estimation problem. The key idea behind our methodology is to attempt the joint recovery of the solution, the sources along with the unknown parameters, thereby using the underlying partial differential equation as a constraint that couples multiple unknown functional parameters, leading to more efficient use of the limited information in the measurements. We present various numerical experiments, using different types of measurements that model practical engineering systems, to show that our proposed method is indeed successful and robust to additional noise in the measurements. - oai:arXiv.org:2512.07755v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Brenda Anague, Bamdad Hosseini, Issa Karambal, Jean Medard Ngnotchouye - - - Distribution-informed Online Conformal Prediction - https://arxiv.org/abs/2512.07770 - arXiv:2512.07770v1 Announce Type: cross -Abstract: Conformal prediction provides a pivotal and flexible technique for uncertainty quantification by constructing prediction sets with a predefined coverage rate. Many online conformal prediction methods have been developed to address data distribution shifts in fully adversarial environments, resulting in overly conservative prediction sets. We propose Conformal Optimistic Prediction (COP), an online conformal prediction algorithm incorporating underlying data pattern into the update rule. Through estimated cumulative distribution function of non-conformity scores, COP produces tighter prediction sets when predictable pattern exists, while retaining valid coverage guarantees even when estimates are inaccurate. We establish a joint bound on coverage and regret, which further confirms the validity of our approach. We also prove that COP achieves distribution-free, finite-sample coverage under arbitrary learning rates and can converge when scores are $i.i.d.$. The experimental results also show that COP can achieve valid coverage and construct shorter prediction intervals than other baselines. - oai:arXiv.org:2512.07770v1 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Dongjian Hu, Junxi Wu, Shu-Tao Xia, Changliang Zou - - - Optimal Auction Design under Costly Learning - https://arxiv.org/abs/2512.07798 - arXiv:2512.07798v1 Announce Type: cross -Abstract: We study optimal auction design in an independent private values environment where bidders can endogenously -- but at a cost -- improve information about their own valuations. The optimal mechanism is two-stage: at stage-1 bidders register an information acquisition plan and pay a transfer; at stage-2 they bid, and allocation and payments are determined. We show that the revenue-optimal stage-2 rule is the Vickrey--Clarke--Groves (VCG) mechanism, while stage-1 transfers implement the optimal screening of types and absorb information rents consistent with incentive compatibility and participation. By committing to VCG ex post, the pre-auction information game becomes a potential game, so equilibrium information choices maximize expected welfare; the stage-1 fee schedule then transfers an optimal amount of payoff without conditioning on unverifiable cost scales. The design is robust to asymmetric primitives and accommodates a wide range of information technologies, providing a simple implementation that unifies efficiency and optimal revenue in environments with endogenous information acquisition. - oai:arXiv.org:2512.07798v1 - econ.TH - cs.GT - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kemal Ozbek - - - LUNA: LUT-Based Neural Architecture for Fast and Low-Cost Qubit Readout - https://arxiv.org/abs/2512.07808 - arXiv:2512.07808v1 Announce Type: cross -Abstract: Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. Deep neural networks (DNNs) have recently emerged as a promising solution to improve readout accuracy . Prior hardware implementations of DNN-based readout are resource-intensive and suffer from high inference latency, limiting their practical use in low-latency decoding and quantum error correction (QEC) loops. This paper proposes LUNA, a fast and efficient superconducting qubit readout accelerator that combines low-cost integrator-based preprocessing with Look-Up Table (LUT) based neural networks for classification. The architecture uses simple integrators for dimensionality reduction with minimal hardware overhead, and employs LogicNets (DNNs synthesized into LUT logic) to drastically reduce resource usage while enabling ultra-low-latency inference. We integrate this with a differential evolution based exploration and optimization framework to identify high-quality design points. Our results show up to a 10.95x reduction in area and 30% lower latency with little to no loss in fidelity compared to the state-of-the-art. LUNA enables scalable, low-footprint, and high-speed qubit readout, supporting the development of larger and more reliable quantum computing systems. - oai:arXiv.org:2512.07808v1 - quant-ph - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - cross - http://creativecommons.org/licenses/by/4.0/ - M. A. Farooq, G. Di Guglielmo, A. Rajagopala, N. Tran, V. A. Chhabria, A. Arora - - - Real-time Air Pollution prediction model based on Spatiotemporal Big data - https://arxiv.org/abs/1805.00432 - arXiv:1805.00432v4 Announce Type: replace -Abstract: Air pollution is one of the most concerns for urban areas. Many countries have constructed monitoring stations to hourly collect pollution values. Recently, there is a research in Daegu city, Korea for real-time air quality monitoring via sensors installed on taxis running across the whole city. The collected data is huge (1-second interval) and in both Spatial and Temporal format. In this paper, based on this spatiotemporal Big data, we propose a real-time air pollution prediction model based on Convolutional Neural Network (CNN) algorithm for image-like Spatial distribution of air pollution. Regarding to Temporal information in the data, we introduce a combination of a Long Short-Term Memory (LSTM) unit for time series data and a Neural Network model for other air pollution impact factors such as weather conditions to build a hybrid prediction model. This model is simple in architecture but still brings good prediction ability. - oai:arXiv.org:1805.00432v4 - cs.CY - cs.IR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - The International Conference on Big data, IoT, and Cloud Computing (BIC 2018) - Van-Duc Le, Tien-Cuong Bui, Sang Kyun Cha - - - The Optimal Approximation Factor in Density Estimation - https://arxiv.org/abs/1902.05876 - arXiv:1902.05876v4 Announce Type: replace -Abstract: Consider the following problem: given two arbitrary densities $q_1,q_2$ and a sample-access to an unknown target density $p$, find which of the $q_i$'s is closer to $p$ in total variation. - A remarkable result due to Yatracos shows that this problem is tractable in the following sense: there exists an algorithm that uses $O(\epsilon^{-2})$ samples from $p$ and outputs~$q_i$ such that with high probability, $TV(q_i,p) \leq 3\cdot\mathsf{opt} + \epsilon$, where $\mathsf{opt}= \min\{TV(q_1,p),TV(q_2,p)\}$. Moreover, this result extends to any finite class of densities $\mathcal{Q}$: there exists an algorithm that outputs the best density in $\mathcal{Q}$ up to a multiplicative approximation factor of 3. - We complement and extend this result by showing that: (i) the factor 3 can not be improved if one restricts the algorithm to output a density from $\mathcal{Q}$, and (ii) if one allows the algorithm to output arbitrary densities (e.g.\ a mixture of densities from $\mathcal{Q}$), then the approximation factor can be reduced to 2, which is optimal. In particular this demonstrates an advantage of improper learning over proper in this setup. - We develop two approaches to achieve the optimal approximation factor of 2: an adaptive one and a static one. Both approaches are based on a geometric point of view of the problem and rely on estimating surrogate metrics to the total variation. Our sample complexity bounds exploit techniques from {\it Adaptive Data Analysis}. - oai:arXiv.org:1902.05876v4 - cs.LG - cs.CC - cs.IT - math.IT - math.PR - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Olivier Bousquet, Daniel Kane, Shay Moran - - - Bounded Languages Described by GF(2)-grammars - https://arxiv.org/abs/1912.13401 - arXiv:1912.13401v5 Announce Type: replace -Abstract: GF(2)-grammars are a recently introduced grammar family with some unusual algebraic properties. They are closely connected to unambiguous grammars. By using the method of formal power series, we establish strong conditions that are necessary for subsets of a^* b^* and a^* b^* c^* to be described by some GF(2)-grammar. By further applying the established results, we settle the long-standing open question of proving inherent ambiguity of the language {a^n b^m c^k | n != m or m != k}$, as well as give a new purely algebraic proof of the inherent ambiguity of the language {a^n b^m c^k}{n = m or m = k}. - oai:arXiv.org:1912.13401v5 - cs.FL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Vladislav Makarov - - - Cumulative Games: Who is the current player? - https://arxiv.org/abs/2005.06326 - arXiv:2005.06326v2 Announce Type: replace -Abstract: Combinatorial Game Theory(CGT)is a branch of Game Theory that has developed largely independently of Economic Game Theory (EGT), and is concerned with deep mathematical properties of two-player zero-sum games recursively defined over various combinatorial structures. The aim of this work is to lay the foundations for bridging the conceptual and technical gaps between CGT and EGT, here interpreted as multiplayer Extensive Form Games, so that they can be treated within a unified framework. More specifically, we introduce a class of $n$-player, general-sum games, called {\sc Cumulative Games}, which can be analyzed using tools from both CGT and EGT. We show how two of the most fundamental definitions of CGT, the outcome function and the disjunctive sum operator, naturally extend to the class of {\sc Cumulative Games}. The outcome function allows for efficient equilibrium computation under certain restrictions, while the disjunctive sum operator lets us define a partial order over games according to the advantage that a given player has. Finally, we show that any Extensive Form Game can be written as a {\sc Cumulative Game}. - oai:arXiv.org:2005.06326v2 - cs.GT - math.CO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Urban Larsson, Reshef Meir, Yair Zick - - - Exact recovery of planted cliques in semi-random graphs - https://arxiv.org/abs/2011.08447 - arXiv:2011.08447v5 Announce Type: replace -Abstract: In this paper, we study the Planted Clique problem in a semi-random model. Our model is inspired from the Feige-Kilian model [16] which has been studied in many other works [8,11,17,26,35,38] for a variety of graph problems. Our algorithm and analysis is on similar lines to the one studied for the Densest $k$-subgraph problem in the work of Khanna and Louis [25]. - As a by-product of our main result, we give an alternate SDP-based rounding algorithm (with similar guarantees) for solving the Planted Clique problem in a random graph. - oai:arXiv.org:2011.08447v5 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yash Khanna - - - Scale-invariant Monte Carlo and multilevel Monte Carlo estimation of mean and variance: An application to simulation of linear elastic bone tissue - https://arxiv.org/abs/2106.13723 - arXiv:2106.13723v4 Announce Type: replace -Abstract: We propose novel scale-invariant error estimators for the Monte Carlo and multilevel Monte Carlo estimation of mean and variance. For any linear transformation of the distribution of the quantity of interest, the computation cost across fidelity levels is optimized using a normalized error estimate, which is not only fully dimensionless but also remains robust to variation in characteristics of the distribution. We demonstrate the effectiveness of the algorithms through application to a mechanical simulation of linear elastic bone tissue, where material uncertainty incorporating both heterogeneity and random anisotropy is considered in the constitutive law. - oai:arXiv.org:2106.13723v4 - math.NA - cs.CE - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sharana Kumar Shivanand, Bojana Rosi\'c - - - Contest Design with Threshold Objectives - https://arxiv.org/abs/2109.03179 - arXiv:2109.03179v3 Announce Type: replace -Abstract: We study contests where the designer's objective is an extension of the widely studied objective of maximizing the total output: The designer gets zero marginal utility from a player's output if the output of the player is very low or very high. We consider two variants of this setting, which correspond to two objective functions: binary threshold, where the designer's utility is a non-decreasing function of the number of players with output above a certain threshold; and linear threshold, where a player's contribution to the designer's utility is linear in her output if the output is between a lower and an upper threshold, and becomes constant below the lower and above the upper threshold. For both of these objectives, we study rank-order allocation contests and general contests. We characterize the contests that maximize the designer's objective and indicate techniques to efficiently compute them. - oai:arXiv.org:2109.03179v3 - cs.GT - econ.TH - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Edith Elkind, Abheek Ghosh, Paul W. Goldberg - - - ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data - https://arxiv.org/abs/2112.03084 - arXiv:2112.03084v2 Announce Type: replace -Abstract: Recommender system is an applicable technique in most E-commerce commercial product technical designs. However, nearly all recommender system faces a challenge called the cold-start problem. The problem is so notorious that almost every industrial practitioner needs to resolve this issue when building recommender systems. Most cold-start problem solvers need some kind of data input as the starter of the system. On the other hand, many real-world applications place popular items or random items as recommendation results. In this paper, we propose a new technique called ZeroMat that requries no input data at all and predicts the user item rating data that is competitive in Mean Absolute Error and fairness metric compared with the classic matrix factorization with affluent data, and much better performance than random placement. - oai:arXiv.org:2112.03084v2 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/ICISCAE52414.2021.9590668 - Hao Wang - - - Deep transfer learning for image classification: a survey - https://arxiv.org/abs/2205.09904 - arXiv:2205.09904v2 Announce Type: replace -Abstract: Deep neural networks such as convolutional neural networks (CNNs) and transformers have achieved many successes in image classification in recent years. It has been consistently demonstrated that best practice for image classification is when large deep models can be trained on abundant labelled data. However there are many real world scenarios where the requirement for large amounts of training data to get the best performance cannot be met. In these scenarios transfer learning can help improve performance. To date there have been no surveys that comprehensively review deep transfer learning as it relates to image classification overall. However, several recent general surveys of deep transfer learning and ones that relate to particular specialised target image classification tasks have been published. We believe it is important for the future progress in the field that all current knowledge is collated and the overarching patterns analysed and discussed. In this survey we formally define deep transfer learning and the problem it attempts to solve in relation to image classification. We survey the current state of the field and identify where recent progress has been made. We show where the gaps in current knowledge are and make suggestions for how to progress the field to fill in these knowledge gaps. We present a new taxonomy of the applications of transfer learning for image classification. This taxonomy makes it easier to see overarching patterns of where transfer learning has been effective and, where it has failed to fulfill its potential. This also allows us to suggest where the problems lie and how it could be used more effectively. We show that under this new taxonomy, many of the applications where transfer learning has been shown to be ineffective or even hinder performance are to be expected when taking into account the source and target datasets and the techniques used. - oai:arXiv.org:2205.09904v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jo Plested, Musa Phiri, Tom Gedeon - - - Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic Grasping - https://arxiv.org/abs/2303.11228 - arXiv:2303.11228v3 Announce Type: replace -Abstract: Object segmentation for robotic grasping under dynamic conditions often faces challenges such as occlusion, low light conditions, motion blur and object size variance. To address these challenges, we propose a Deep Learning network that fuses two types of visual signals, event-based data and RGB frame data. The proposed Bimodal SegNet network has two distinct encoders, one for each signal input and a spatial pyramidal pooling with atrous convolutions. Encoders capture rich contextual information by pooling the concatenated features at different resolutions while the decoder obtains sharp object boundaries. The evaluation of the proposed method undertakes five unique image degradation challenges including occlusion, blur, brightness, trajectory and scale variance on the Event-based Segmentation (ESD) Dataset. The evaluation results show a 6-10\% segmentation accuracy improvement over state-of-the-art methods in terms of mean intersection over the union and pixel accuracy. The model code is available at https://github.com/sanket0707/Bimodal-SegNet.git - oai:arXiv.org:2303.11228v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sanket Kachole, Xiaoqian Huang, Fariborz Baghaei Naeini, Rajkumar Muthusamy, Dimitrios Makris, Yahya Zweiri - - - Polymorphic Coverage Types - https://arxiv.org/abs/2304.03393 - arXiv:2304.03393v3 Announce Type: replace -Abstract: Test input generators are an important part of property-based testing (PBT) frameworks, and a key expectation is that they be capable of producing all acceptable elements that satisfy both the function's input type and the generator-provided constraints. However, it is not readily apparent how to validate whether a particular generator's output satisfies this coverage requirement. In practice, developers typically rely on manual inspection and post-mortem analysis of test runs to determine whether a generator provides sufficient coverage; these approaches are error-prone and difficult to scale as generators grow more complex. To address this problem, we present a new refinement-type-based verification procedure for validating the coverage provided by input test generators, based on a novel interpretation of types that embeds "must-style" underapproximate reasoning principles as a fundamental part of the type system. In our formulation, the types associated with expressions capture the set of values guaranteed to be produced by the expression, rather than the usual interpretation in which types represent the set of values an expression may produce. We formalize the notion of coverage types in a rich core language supporting higher-order functions and inductive datatypes. To better support real-world test generators, we extend this type system with type and qualifier polymorphism, enabling static verification of coverage guarantees for test input generators constructed using the monadic combinators found in most PBT frameworks. Finally, we have implemented a coverage type checker for OCaml programs based on this core calculus and present a detailed evaluation of its utility using a corpus of benchmarks drawn from both the PBT literature and open-source projects. - oai:arXiv.org:2304.03393v3 - cs.PL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhe Zhou, Ashish Mishra, Benjamin Delaware, Suresh Jagannathan - - - Static Pricing Guarantees for Queueing Systems - https://arxiv.org/abs/2305.09168 - arXiv:2305.09168v5 Announce Type: replace -Abstract: We consider a general queueing system with price-sensitive customers in which the service provider seeks to balance two objectives, maximizing the average revenue rate and minimizing the average queue length. Customers arrive according to a Poisson process, observe an offered price, and decide to join the queue if their valuation exceeds the price. The queue is operated first-in first-out, can have multiple servers, and the service times are exponential. Our model represents applications in areas like make-to-order manufacturing, cloud computing, and food delivery. - The optimal solution for our model is dynamic; the price changes as the state of the system changes. However, such dynamic pricing policies may be undesirable for a variety of reasons. In this work, we provide non-asymptotic performance guarantees for a simple and natural class of static pricing policies which charge a fixed price up to a certain occupancy threshold and then allow no more customers into the system. Despite the mixed-sign objective, we are able to show our policy can guarantee a constant fraction of the optimal dynamic pricing policy in the worst-case. We also show that our policy yields a family of bi-criteria approximations that simultaneously guarantee a constant fraction of the optimal revenue with at most a constant factor increase in expected queue length. For instance, our policy for the M/M/1 setting can be set so that its worst-case guarantees is at least 50, 66, 75, or 80% of the optimal revenue and at most a 0, 16, 54, or 100% increase in the optimal queue length, respectively. We also provide guarantees for settings with multiple servers as well as the expected sojourn time objective. In a large simulation, we show that our class of policies is at most 4% sub-optimal on average. - oai:arXiv.org:2305.09168v5 - cs.DS - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jacob Bergquist, Adam N. Elmachtoub - - - Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning - https://arxiv.org/abs/2305.12066 - arXiv:2305.12066v4 Announce Type: replace -Abstract: Visual content understanding frequently relies on multi-task models to extract robust representations of a single visual input for multiple downstream tasks. However, in comparison to extensively studied single-task models, the adversarial robustness of multi-task models has received significantly less attention and many questions remain unclear: 1) How robust are multi-task models to single task adversarial attacks, 2) Can adversarial attacks be designed to simultaneously attack all tasks in a multi-task model, and 3) How does parameter sharing across tasks affect multi-task model robustness to adversarial attacks? This paper aims to answer these questions through careful analysis and rigorous experimentation. First, we analyze the inherent drawbacks of two commonly-used adaptations of single-task white-box attacks in attacking multi-task models. We then propose a novel attack framework, Dynamic Gradient Balancing Attack (DGBA). Our framework poses the problem of attacking all tasks in a multi-task model as an optimization problem that can be efficiently solved through integer linear programming. Extensive evaluation on two popular MTL benchmarks, NYUv2 and Tiny-Taxonomy, demonstrates the effectiveness of DGBA compared to baselines in attacking both clean and adversarially trained multi-task models. Our results also reveal a fundamental trade-off between improving task accuracy via parameter sharing across tasks and undermining model robustness due to increased attack transferability from parameter sharing. - oai:arXiv.org:2305.12066v4 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1016/j.neucom.2025.131503 - Lijun Zhang, Xiao Liu, Kaleel Mahmood, Caiwen Ding, Hui Guan - - - Wholesale Market Participation via Competitive DER Aggregation - https://arxiv.org/abs/2307.02004 - arXiv:2307.02004v5 Announce Type: replace -Abstract: We consider the aggregation of distributed energy resources (DERs), such as solar PV, energy storage, and flexible loads, by a profit-seeking aggregator participating directly in the wholesale market under distribution network access constraints. We propose a competitive DER aggregator (DERA) model that directly controls local DERs to maximize its profits, while ensuring each aggregated customer gains a surplus higher than their surplus under the regulated retail tariff. The DERA participates in the wholesale electricity market as virtual storage with optimized generation offers and consumption bids derived from the propoed competitive aggregation model. Also derived are DERA's bid curves for the distribution network access and DERA's profitability when competing with the regulated retail tariff. We show that, with the same distribution network access, the proposed DERA's wholesale market participation achieves the same welfare-maximizing outcome as when its customers participate directly in the wholesale market. Extensive numerical studies compare the proposed DERA with existing methods in terms of customer surplus and DERA profit. We empirically evaluate how many DERAs can survive in the competition at long-run equilibrium, and assess the impacts of DER adoption levels and distribution network access on short-run operations. - oai:arXiv.org:2307.02004v5 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Cong Chen, Ahmed S. Alahmed, Timothy D. Mount, Lang Tong - - - Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey - https://arxiv.org/abs/2308.09388 - arXiv:2308.09388v3 Announce Type: replace -Abstract: Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation. Recently, the diffusion model has achieved significant advancements in the visual generation of AIGC, thereby raising an intuitive question, "whether diffusion model can boost image restoration". To answer this, some pioneering studies attempt to integrate diffusion models into the image restoration task, resulting in superior performances than previous GAN-based methods. Despite that, a comprehensive and enlightening survey on diffusion model-based image restoration remains scarce. In this paper, we are the first to present a comprehensive review of recent diffusion model-based methods on image restoration, encompassing the learning paradigm, conditional strategy, framework design, modeling strategy, and evaluation. Concretely, we first introduce the background of the diffusion model briefly and then present two prevalent workflows that exploit diffusion models in image restoration. Subsequently, we classify and emphasize the innovative designs using diffusion models for both IR and blind/real-world IR, intending to inspire future development. To evaluate existing methods thoroughly, we summarize the commonly-used dataset, implementation details, and evaluation metrics. Additionally, we present the objective comparison for open-sourced methods across three tasks, including image super-resolution, deblurring, and inpainting. Ultimately, informed by the limitations in existing works, we propose five potential and challenging directions for the future research of diffusion model-based IR, including sampling efficiency, model compression, distortion simulation and estimation, distortion invariant learning, and framework design. - oai:arXiv.org:2308.09388v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xin Li, Yulin Ren, Xin Jin, Cuiling Lan, Xingrui Wang, Wenjun Zeng, Xinchao Wang, Zhibo Chen - - - A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization - https://arxiv.org/abs/2310.04752 - arXiv:2310.04752v2 Announce Type: replace -Abstract: Due to the inherent imbalance in real-world datasets, na\"ive Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalization to minority classes. To rebalance the learning process, one straightforward yet effective approach is to modify the loss function via class-dependent terms, such as re-weighting and logit-adjustment. However, existing analysis of these loss-oriented methods remains coarse-grained and fragmented, failing to explain some empirical results. After reviewing prior work, we find that the properties used through their analysis are typically global, i.e., defined over the whole dataset. Hence, these properties fail to effectively capture how class-dependent terms influence the learning process. To bridge this gap, we turn to explore the localized versions of such properties i.e., defined within each class. Specifically, we employ localized calibration to provide consistency validation across a broader range of losses and localized Lipschitz continuity to provide a fine-grained generalization bound. In this way, we reach a unified perspective for improving and adjusting loss-oriented methods. Finally, a principled learning algorithm is developed based on these insights. Empirical results on both traditional ResNets and foundation models validate our theoretical analyses and demonstrate the effectiveness of the proposed method. - oai:arXiv.org:2310.04752v2 - cs.LG - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/TPAMI.2025.3609440 - Zitai Wang, Qianqian Xu, Zhiyong Yang, Zhikang Xu, Linchao Zhang, Xiaochun Cao, Qingming Huang - - - Game of arrivals at a two queue network with heterogeneous customer routes - https://arxiv.org/abs/2310.18149 - arXiv:2310.18149v2 Announce Type: replace -Abstract: We consider a queuing network that opens at a specified time, where customers are non-atomic and belong to different classes. Each class has its own route, and as is typical in the literature, the costs are a linear function of waiting and service completion time. We restrict ourselves to a two class, two queue network: this simplification is well motivated as the diversity in solution structure as a function of problem parameters is substantial even in this simple setting (e.g., a specific routing structure involves eight different regimes), suggesting a combinatorial blow up as the number of queues, routes and customer classes increase. We identify the unique Nash equilibrium customer arrival profile when the customer linear cost preferences are different. This profile is a function of problem parameters including the size of each class, service rates at each queue, and customer cost preferences. When customer cost preferences match, under certain parametric settings, the equilibrium arrival profiles may not be unique and may lie in a convex set. We further make a surprising observation that in some parametric settings, customers in one class may arrive in disjoint intervals. Further, the two classes may arrive in contiguous intervals or in overlapping intervals, and at varying rates within an interval, depending upon the problem parameters. - oai:arXiv.org:2310.18149v2 - cs.PF - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Agniv Bandyopadhyay, Sandeep Juneja - - - Asynchronous Bioplausible Neuron for SNN for Event Vision - https://arxiv.org/abs/2311.11853 - arXiv:2311.11853v3 Announce Type: replace -Abstract: Spiking Neural Networks (SNNs) offer a biologically inspired approach to computer vision that can lead to more efficient processing of visual data with reduced energy consumption. However, maintaining homeostasis within these networks is challenging, as it requires continuous adjustment of neural responses to preserve equilibrium and optimal processing efficiency amidst diverse and often unpredictable input signals. In response to these challenges, we propose the Asynchronous Bioplausible Neuron (ABN), a dynamic spike firing mechanism to auto-adjust the variations in the input signal. Comprehensive evaluation across various datasets demonstrates ABN's enhanced performance in image classification and segmentation, maintenance of neural equilibrium, and energy efficiency. - oai:arXiv.org:2311.11853v3 - cs.NE - cs.CV - q-bio.NC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sanket Kachole, Hussain Sajwani, Fariborz Baghaei Naeini, Dimitrios Makris, Yahya Zweiri - - - RIS-Assisted Generalized Receive Quadrature Spatial Modulation with Extension to Multicast Communications - https://arxiv.org/abs/2311.18542 - arXiv:2311.18542v2 Announce Type: replace -Abstract: This paper proposes a novel reconfigurable intelligent surface (RIS)-assisted generalized receive quadrature spatial modulation (RIS-GRQSM) scheme to enhance the spectral efficiency (SE) of RIS-aided \textit{quadrature} spatial modulation (QSM) systems. By leveraging the principle of \textit{generalized} spatial modulation (GSM), multiple receive antennas are independently activated for \textit{both} the in-phase and quadrature components of spatial symbols. To fully exploit the potential of RIS, we formulate a max-min optimization problem to adjust the phase shifts of all RIS elements, thereby maximizing the effective signal-to-noise ratios (SNRs) at the activated antennas. Using Lagrange duality, the original high-dimensional non-convex problem is reduced to a tractable problem with a smaller number of real variables, and a closed-form suboptimal solution is also proposed, which achieves near-optimal performance with a sufficiently large RIS. At the receiver, a low-complexity non-coherent energy-based greedy detector (GD) is introduced for efficient symbol detection. We further extend the RIS-GRQSM framework to a multicast communication system, where all users receive identical information with equal SNR levels, and provide a detailed performance analysis of both systems. In particular, we derive the average bit error probability (ABEP) for the proposed RIS-GRQSM and multicast systems under optimal and suboptimal optimization strategies. Numerical results show that RIS-GRQSM significantly improves the SE and error rate performance compared with benchmark schemes, while the multicast extension achieves performance close to benchmark methods at substantially lower complexity. - oai:arXiv.org:2311.18542v2 - cs.IT - eess.SP - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mohamad H. Dinan, Khatereh Nadali, Mark F. Flanagan - - - Who Are Tweeting About Academic Publications? A Systematic Review and Meta-Analysis of Altmetric Studies - https://arxiv.org/abs/2312.06399 - arXiv:2312.06399v3 Announce Type: replace -Abstract: Understanding who shares academic publications on Twitter is critical to interpreting altmetrics as signals of scholarly or societal impact. Prior studies have used diverse and often incompatible user classification schemes, making synthesis difficult. This study presents a systematic review and meta-analysis of 23 empirical studies (covering 79,014 Twitter users, over 20 million tweets, and more than 5 million tweeted publications) to estimate category-specific engagement across three metrics: user counts, tweets, and tweeted publications. We developed a harmonized categorization scheme encompassing 11 user types and applied both Random Effects Models (REM) and Beta-Binomial Hierarchical Models (BBHM) to estimate proportions, account for study-level variation, and model uncertainty. Across all indicators, individual users were the most active, comprising 66% of users, 55% of tweets, and 50% of tweeted publications. BBHM further enabled in-category vs. out-of-category comparisons and revealed engagement differences not detected by REM. T-tests on study-level means confirmed significant differences between academic individuals and other user types. Despite methodological heterogeneity, results consistently show that academic and non-academic individuals statistically equally dominate Twitter engagement with scholarly content. Our findings support the need for standardized user classification schemes and demonstrate the value of Bayesian modeling for synthesizing altmetric data in study variation and sparsity. - oai:arXiv.org:2312.06399v3 - cs.DL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ashraf Maleki, Kim Holmberg - - - A New Framework for Bounding Reachability Probabilities of Continuous-time Stochastic Systems - https://arxiv.org/abs/2312.15843 - arXiv:2312.15843v3 Announce Type: replace -Abstract: This manuscript presents an innovative framework for constructing barrier functions to bound reachability probabilities for continuous-time stochastic systems described by stochastic differential equations (SDEs). The reachability probabilities considered in this paper encompass two aspects: the probability of reaching a set of specified states within a predefined finite time horizon, and the probability of reaching a set of specified states at a particular time instant. The barrier functions presented in this manuscript are developed either by relaxing a parabolic partial differential equation that characterizes the exact reachability probability or by applying the Gr\"onwall's inequality. In comparison to the prevailing construction method, which relies on Doob's non-negative supermartingale inequality (or Ville's inequality), the proposed barrier functions provide stronger alternatives, complement existing methods, or fill gaps. - oai:arXiv.org:2312.15843v3 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bai Xue - - - Hidden Minima in Two-Layer ReLU Networks - https://arxiv.org/abs/2312.16819 - arXiv:2312.16819v3 Announce Type: replace -Abstract: We consider the optimization problem arising from fitting two-layer ReLU networks with $d$ inputs under the square loss, where labels are generated by a target network. Two infinite families of spurious minima have recently been identified: one whose loss vanishes as $d \to \infty$, and another whose loss remains bounded away from zero. The latter are nevertheless avoided by vanilla SGD, and thus hidden, motivating the search for analytic properties distinguishing the two types. Perhaps surprisingly, the Hessian spectra of hidden and non-hidden minima agree up to terms of order $O(d^{-1/2})$, providing limited explanatory power. Consequently, our analysis of hidden minima proceeds instead via curves along which the loss is minimized or maximized. The main result is that arcs emanating from hidden minima differ, characteristically, by their structure and symmetry, precisely on account of the $O(d^{-1/2})$-eigenvalue terms absent from previous analyses. - oai:arXiv.org:2312.16819v3 - cs.LG - math.OC - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yossi Arjevani - - - Recognition of Unit Segment and Polyline Graphs is $\exists\mathbb{R}$-Complete - https://arxiv.org/abs/2401.02172 - arXiv:2401.02172v3 Announce Type: replace -Abstract: Given a set of objects $O$ in the plane, the corresponding intersection graph is defined as follows. Each object defines a vertex and an edge joins two vertices whenever the corresponding objects intersect. We study here the case of unit segments and polylines with exactly $k$ bends. In the recognition problem, we are given a graph and want to decide whether the graph can be represented as an intersection graph of certain geometric objects. In previous work it was shown that various recognition problems are $\exists\mathbb{R}$-complete, leaving unit segments and polylines among the few remaining natural cases where the recognition complexity remained open. We show that recognition for both families of objects is $\exists\mathbb{R}$-complete. - oai:arXiv.org:2401.02172v3 - cs.CG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Michael Hoffmann, Tillmann Miltzow, Simon Weber, Lasse Wulf - - - Deep Learning Meets Mechanism Design: Key Results and Some Novel Applications - https://arxiv.org/abs/2401.05683 - arXiv:2401.05683v2 Announce Type: replace -Abstract: Mechanism design is essentially reverse engineering of games and involves inducing a game among strategic agents in a way that the induced game satisfies a set of desired properties in an equilibrium of the game. Desirable properties for a mechanism include incentive compatibility, individual rationality, welfare maximisation, revenue maximisation (or cost minimisation), fairness of allocation, etc. It is known from mechanism design theory that only certain strict subsets of these properties can be simultaneously satisfied exactly by any given mechanism. Often, the mechanisms required by real-world applications may need a subset of these properties that are theoretically impossible to be simultaneously satisfied. In such cases, a prominent recent approach is to use a deep learning based approach to learn a mechanism that approximately satisfies the required properties by minimizing a suitably defined loss function. In this paper, we present, from relevant literature, technical details of using a deep learning approach for mechanism design and provide an overview of key results in this topic. We demonstrate the power of this approach for three illustrative case studies: (a) efficient energy management in a vehicular network (b) resource allocation in a mobile network (c) designing a volume discount procurement auction for agricultural inputs. Section 6 concludes the paper. - oai:arXiv.org:2401.05683v2 - cs.GT - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - V. Udaya Sankar, Vishisht Srihari Rao, Y. Narahari - - - Distributed Traffic Signal Control of Interconnected Intersections: A Two-Lane Traffic Network Model - https://arxiv.org/abs/2401.11483 - arXiv:2401.11483v2 Announce Type: replace -Abstract: In this paper, we investigate traffic signal control in a network of interconnected intersections, aiming to balance lane-level vehicle densities through optimal green-time allocation. We develop a two-lane traffic flow model that explicitly captures lane-specific propagation dynamics, addressing key limitations of conventional road-level formulations. The proposed model offers a more granular and flexible representation of urban traffic, enabling controllers to react more accurately to lane-specific congestion patterns. Building on this model, we design a distributed model predictive control (MPC) framework and integrate it with the efficient alternating direction method of multipliers (ADMM) to enhance scalability and real-time performance. To accommodate time-varying traffic conditions, we further introduce a data-driven method for forecasting dynamic split ratios. Comprehensive VISSIM simulations on a six-intersection network in Dalian, China, demonstrate that the proposed approach outperforms existing signal control strategies in both traffic efficiency and computational speed, showing its promise for real-time deployment. - oai:arXiv.org:2401.11483v2 - eess.SY - cs.SY - nlin.AO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xinfeng Ru, Ting Bai, Weiguo Xia, Andreas A. Malikopoulos - - - Unifying Graded Linear Logic and Differential Operators - https://arxiv.org/abs/2402.09138 - arXiv:2402.09138v4 Announce Type: replace -Abstract: Linear Logic refines Intuitionnistic Logic by taking into account the resources used during the proof and program computation. In the past decades, it has been extended to various frameworks. The most famous are indexed linear logics which can describe the resource management or the complexity analysis of a program. From an other perspective, Differential Linear Logic is an extension which allows the linearization of proofs. In this article, we merge these two directions by first defining a differential version of Graded linear logic: this is made by indexing exponential connectives with a monoid of differential operators. We prove that it is equivalent to a graded version of previously defined extension of finitary differential linear logic. We give a denotational model of our logic, based on distribution theory and linear partial differential operators with constant coefficients. - oai:arXiv.org:2402.09138v4 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Flavien Breuvart, Marie Kerjean, Simon Mirwasser - - - I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses - https://arxiv.org/abs/2402.11192 - arXiv:2402.11192v5 Announce Type: replace -Abstract: This paper explores an intriguing observation: fine-tuning a large language model (LLM) with responses generated by a LLM often yields better results than using responses generated by humans, particularly in reasoning tasks. We conduct an in-depth investigation to understand why this occurs. Contrary to the common belief that these instances is due to the more detailed nature of LLM-generated content, our study identifies another contributing factor: an LLM is inherently more "familiar" with LLM generated responses. This familiarity is evidenced by lower perplexity before fine-tuning. We design a series of experiments to understand the impact of the "familiarity" and our conclusion reveals that this "familiarity" significantly impacts learning performance. Training with LLM-generated responses not only enhances performance but also helps maintain the model's capabilities in other reasoning tasks after fine-tuning on a specific task. - oai:arXiv.org:2402.11192v5 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xuan Ren, Biao Wu, Lingqiao Liu - - - Ensemble Learning of Machine Learning Force Fields - https://arxiv.org/abs/2403.17507 - arXiv:2403.17507v2 Announce Type: replace -Abstract: Machine learning force fields (MLFFs) are a promising approach to balance the accuracy of quantum mechanics with the efficiency of classical potentials, yet selecting an optimal model amid increasingly diverse architectures that delivers reliable force predictions and stable simulations remains a core pratical challenge. Here we introduce EL-MLFFs, an ensemble learning framework that uses a stacking methodology to integrate predictions from diverse base MLFFs. Our approach constructs a graph representation where a graph neural network (GNN) acts as a meta-model to refine the initial force predictions. We present two meta-model architectures: a computationally efficient direct fitting model and a physically-principled conservative model that ensures energy conservation. The framework is evaluated on a diverse range of systems, including single molecules (methane), surface chemistry (methanol/Cu(100)), molecular dynamics benchmarks (MD17), and the MatPES materials dataset. Results show that EL-MLFFs improves predictive accuracy across these domains. For molecular systems, it reduces force errors and improves the simulation stability compared to base models. For materials, the method yields lower formation energy errors on the WBM test set. The EL- MLFFs framework offers a systematic approach to address challenges of model selection and the accuracy-stability trade-off in molecular and materials simulations. - oai:arXiv.org:2403.17507v2 - cs.LG - physics.chem-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bangchen Yin, Yue Yin, Yuda W. Tang, Hai Xiao - - - Roadside Monocular 3D Detection Prompted by 2D Detection - https://arxiv.org/abs/2404.01064 - arXiv:2404.01064v5 Announce Type: replace -Abstract: Roadside monocular 3D detection requires detecting objects of predefined classes in an RGB frame and predicting their 3D attributes, such as bird's-eye-view (BEV) locations. It has broad applications in traffic control, vehicle-vehicle communication, and vehicle-infrastructure cooperative perception. To address this task, we introduce Promptable 3D Detector (Pro3D), a novel detector design that leverages 2D detections as prompts. We build our Pro3D upon two key insights. First, compared to a typical 3D detector, a 2D detector is ``easier'' to train due to fewer loss terms and performs significantly better at localizing objects w.r.t 2D metrics. Second, once 2D detections precisely locate objects in the image, a 3D detector can focus on lifting these detections into 3D BEV, especially when fixed camera pose or scene geometry provide an informative prior. To encode and incorporate 2D detections, we explore three methods: (a) concatenating features from both 2D and 3D detectors, (b) attentively fusing 2D and 3D detector features, and (c) encoding properties of predicted 2D bounding boxes \{$x$, $y$, width, height, label\} and attentively fusing them with the 3D detector feature. Interestingly, the third method significantly outperforms the others, underscoring the effectiveness of 2D detections as prompts that offer precise object targets and allow the 3D detector to focus on lifting them into 3D. Pro3D is adaptable for use with a wide range of 2D and 3D detectors with minimal modifications. Comprehensive experiments demonstrate that our Pro3D significantly enhances existing methods, achieving state-of-the-art results on two contemporary benchmarks. - oai:arXiv.org:2404.01064v5 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yechi Ma, Yanan Li, Wei Hua, Shu Kong - - - SDT-GNN: Streaming-based Distributed Training Framework for Graph Neural Networks - https://arxiv.org/abs/2404.02300 - arXiv:2404.02300v2 Announce Type: replace -Abstract: Recently, distributed GNN training frameworks, such as DistDGL and PyG, have been developed to enable training GNN models on large graphs by leveraging multiple GPUs in a distributed manner. Despite these advances, their memory requirements are still excessively high, thereby hindering GNN training on large graphs using commodity workstations. In this paper, we propose SDT-GNN, a streaming-based distributed GNN training framework. Unlike the existing frameworks that load the entire graph in memory, it takes a stream of edges as input for graph partitioning to reduce the memory requirement for partitioning. It also enables distributed GNN training even when the aggregated memory size of GPUs is smaller than the size of the graph and feature data. Furthermore, to improve the quality of partitioning, we propose SPRING, a novel streaming partitioning algorithm for distributed GNN training. We demonstrate the effectiveness and efficiency of SDT-GNN on seven large public datasets. SDT-GNN has up to 95% less memory footprint than DistDGL and PyG without sacrificing the prediction accuracy. SPRING also outperforms state-of-the-art streaming partitioning algorithms significantly. - oai:arXiv.org:2404.02300v2 - cs.LG - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xin Huang, Weipeng Zhuo, Minh Phu Vuong, Shiju Li, Jongryool Kim, Bradley Rees, Chul-Ho Lee - - - Covariate-Elaborated Robust Partial Information Transfer with Conditional Spike-and-Slab Prior - https://arxiv.org/abs/2404.03764 - arXiv:2404.03764v3 Announce Type: replace -Abstract: The popularity of transfer learning stems from the fact that it can borrow information from useful auxiliary datasets. Existing statistical transfer learning methods usually adopt a global similarity measure between the source data and the target data, which may lead to inefficiency when only partial information is shared. In this paper, we propose a novel Bayesian transfer learning method named ``CONCERT'' to allow robust partial information transfer for high-dimensional data analysis. A conditional spike-and-slab prior is introduced in the joint distribution of target and source parameters for information transfer. By incorporating covariate-specific priors, we can characterize partial similarities and integrate source information collaboratively to improve the performance on the target. In contrast to existing work, the CONCERT is a one-step procedure which achieves variable selection and information transfer simultaneously. We establish variable selection consistency, as well as estimation and prediction error bounds for CONCERT. Our theory demonstrates the covariate-specific benefit of transfer learning. To ensure the scalability of the algorithm, we adopt the variational Bayes framework to facilitate implementation. Extensive experiments and two real data applications showcase the validity and advantages of CONCERT over existing cutting-edge transfer learning methods. - oai:arXiv.org:2404.03764v3 - cs.LG - stat.ME - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1080/01621459.2025.2591232 - Ruqian Zhang, Yijiao Zhang, Annie Qu, Zhongyi Zhu, Juan Shen - - - An Objective Improvement Approach to Solving Discounted Payoff Games - https://arxiv.org/abs/2404.04124 - arXiv:2404.04124v5 Announce Type: replace -Abstract: While discounted payoff games and classic games that reduce to them, like parity and mean-payoff games, are symmetric, their solutions are not. We have taken a fresh view on the properties that optimal solutions need to have, and devised a novel way to converge to them, which is entirely symmetric. We achieve this by building a constraint system that uses every edge to define an inequation, and update the objective function by taking a single outgoing edge for each vertex into account. These edges loosely represent strategies of both players, where the objective function intuitively asks to make the inequation to these edges sharp. In fact, where they are not sharp, there is an `error' represented by the difference between the two sides of the inequation, which is 0 where the inequation is sharp. Hence, the objective is to minimise the sum of these errors. For co-optimal strategies, and only for them, it can be achieved that all selected inequations are sharp or, equivalently, that the sum of these errors is zero. While no co-optimal strategies have been found, we step-wise improve the error by improving the solution for a given objective function or by improving the objective function for a given solution. This also challenges the gospel that methods for solving payoff games are either based on strategy improvement or on value iteration. - oai:arXiv.org:2404.04124v5 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Daniele Dell'Erba, Arthur Dumas, Sven Schewe - - - PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks - https://arxiv.org/abs/2404.04671 - arXiv:2404.04671v5 Announce Type: replace -Abstract: This paper introduces PhyloLM, a method adapting phylogenetic algorithms to Large Language Models (LLMs) to explore whether and how they relate to each other and to predict their performance characteristics. Our method calculates a phylogenetic distance metric based on the similarity of LLMs' output. The resulting metric is then used to construct dendrograms, which satisfactorily capture known relationships across a set of 111 open-source and 45 closed models. Furthermore, our phylogenetic distance predicts performance in standard benchmarks, thus demonstrating its functional validity and paving the way for a time and cost-effective estimation of LLM capabilities. To sum up, by translating population genetic concepts to machine learning, we propose and validate a tool to evaluate LLM development, relationships and capabilities, even in the absence of transparent training information. - oai:arXiv.org:2404.04671v5 - cs.CL - cs.LG - q-bio.PE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - ICLR 2025 - Nicolas Yax, Pierre-Yves Oudeyer, Stefano Palminteri - - - A Survey on Diffusion Models for Time Series and Spatio-Temporal Data - https://arxiv.org/abs/2404.18886 - arXiv:2404.18886v5 Announce Type: replace -Abstract: Diffusion models have been widely used in time series and spatio-temporal data, enhancing generative, inferential, and downstream capabilities. These models are applied across diverse fields such as healthcare, recommendation, climate, energy, audio, and traffic. By separating applications for time series and spatio-temporal data, we offer a structured perspective on model category, task type, data modality, and practical application domain. This study aims to provide a solid foundation for researchers and practitioners, inspiring future innovations that tackle traditional challenges and foster novel solutions in diffusion model-based data mining tasks and applications. For more detailed information, we have open-sourced a repository at https://github.com/yyysjz1997/Awesome-TimeSeries-SpatioTemporal-Diffusion-Model. - oai:arXiv.org:2404.18886v5 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Shirui Pan, Qingsong Wen - - - Using weakest application conditions to rank graph transformations for graph repair - https://arxiv.org/abs/2405.08788 - arXiv:2405.08788v5 Announce Type: replace -Abstract: When using graphs and graph transformations to model systems, consistency is an important concern. While consistency has primarily been viewed as a binary property, i.e., a graph is consistent or inconsistent with respect to a set of constraints, recent work has presented an approach to consistency as a graduated property. This allows living with inconsistencies for a while and repairing them when necessary. For repairing inconsistencies in a graph, we use graph transformation rules with so-called {\em impairment-indicating and repair-indicating application conditions} to understand how much repair gain certain rule applications would bring. Both types of conditions can be derived from given graph constraints. Our main theorem shows that the difference between the number of actual constraint violations before and after a graph transformation step can be characterised by the difference between the numbers of violated impairment-indicating and repair-indicating application conditions. This theory forms the basis for algorithms with look-ahead that rank graph transformations according to their potential for graph repair. An evaluation shows that graph repair can be well-supported by rules with these new types of application conditions in terms of effectiveness and scalability. - oai:arXiv.org:2405.08788v5 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Lars Fritsche, Alexander Lauer, Maximilian Kratz, Andy Sch\"urr, Gabriele Taentzer - - - A Unified Framework for Sponge-Layer Relaxation Methods and Damping Operators for Conservation Laws: Application to the Piston Problem of Gas Dynamics - https://arxiv.org/abs/2405.11588 - arXiv:2405.11588v2 Announce Type: replace -Abstract: This work addresses the imposition of outflow boundary conditions for one-dimensional conservation laws. While a highly accurate numerical solution can be obtained in the interior of the domain, boundary discretization can lead to unphysical reflections. We investigate and implement some classes of relaxation methods and far-field operators to deal with this problem without significantly increasing the size of the computational domain. We formulate these methods within a framework that allows to reveal relationships among them, and to propose novel extensions. In particular, we introduce a simple and robust relaxation method with a matrix-valued weight function that selectively absorbs outgoing waves. As a challenging model problem, we consider the Lagrangian formulation of the Euler equations for a polytropic gas with inflow boundary conditions determined by an oscillating piston. - oai:arXiv.org:2405.11588v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Carlos Mu\~noz-Moncayo - - - Fast training and sampling of Restricted Boltzmann Machines - https://arxiv.org/abs/2405.15376 - arXiv:2405.15376v3 Announce Type: replace -Abstract: Restricted Boltzmann Machines (RBMs) are powerful tools for modeling complex systems and extracting insights from data, but their training is hindered by the slow mixing of Markov Chain Monte Carlo (MCMC) processes, especially with highly structured datasets. In this study, we build on recent theoretical advances in RBM training and focus on the stepwise encoding of data patterns into singular vectors of the coupling matrix, significantly reducing the cost of generating new samples and evaluating the quality of the model, as well as the training cost in highly clustered datasets. The learning process is analogous to the thermodynamic continuous phase transitions observed in ferromagnetic models, where new modes in the probability measure emerge in a continuous manner. We leverage the continuous transitions in the training process to define a smooth annealing trajectory that enables reliable and computationally efficient log-likelihood estimates. This approach enables online assessment during training and introduces a novel sampling strategy called Parallel Trajectory Tempering (PTT) that outperforms previously optimized MCMC methods. To mitigate the critical slowdown effect in the early stages of training, we propose a pre-training phase. In this phase, the principal components are encoded into a low-rank RBM through a convex optimization process, facilitating efficient static Monte Carlo sampling and accurate computation of the partition function. Our results demonstrate that this pre-training strategy allows RBMs to efficiently handle highly structured datasets where conventional methods fail. Additionally, our log-likelihood estimation outperforms computationally intensive approaches in controlled scenarios, while the PTT algorithm significantly accelerates MCMC processes compared to conventional methods. - oai:arXiv.org:2405.15376v3 - cs.LG - cond-mat.dis-nn - cond-mat.stat-mech - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nicolas B\'ereux, Aur\'elien Decelle, Cyril Furtlehner, Lorenzo Rosset, Beatriz Seoane - - - Is Self-Supervised Learning Enough to Fill in the Gap? A Study on Speech Inpainting - https://arxiv.org/abs/2405.20101 - arXiv:2405.20101v2 Announce Type: replace -Abstract: Speech inpainting consists in reconstructing corrupted or missing speech segments using surrounding context, a process that closely resembles the pretext tasks in Self-Supervised Learning (SSL) for speech encoders. This study investigates using SSL-trained speech encoders for inpainting without any additional training beyond the initial pretext task, and simply adding a decoder to generate a waveform. We compare this approach to supervised fine-tuning of speech encoders for a downstream task -- here, inpainting. Practically, we integrate HuBERT as the SSL encoder and HiFi-GAN as the decoder in two configurations: (1) fine-tuning the decoder to align with the frozen pre-trained encoder's output and (2) fine-tuning the encoder for an inpainting task based on a frozen decoder's input. Evaluations are conducted under single- and multi-speaker conditions using in-domain datasets and out-of-domain datasets (including unseen speakers, diverse speaking styles, and noise). Both informed and blind inpainting scenarios are considered, where the position of the corrupted segment is either known or unknown. The proposed SSL-based methods are benchmarked against several baselines, including a text-informed method combining automatic speech recognition with zero-shot text-to-speech synthesis. Performance is assessed using objective metrics and perceptual evaluations. The results demonstrate that both approaches outperform baselines, successfully reconstructing speech segments up to 200 ms, and sometimes up to 400 ms. Notably, fine-tuning the SSL encoder achieves more accurate speech reconstruction in single-speaker settings, while a pre-trained encoder proves more effective for multi-speaker scenarios. This demonstrates that an SSL pretext task can transfer to speech inpainting, enabling successful speech reconstruction with a pre-trained encoder. - oai:arXiv.org:2405.20101v2 - cs.SD - cs.CL - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ihab Asaad, Maxime Jacquelin, Olivier Perrotin, Laurent Girin, Thomas Hueber - - - TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data - https://arxiv.org/abs/2406.16028 - arXiv:2406.16028v3 Announce Type: replace -Abstract: We present TimeAutoDiff, a unified latent-diffusion framework for four fundamental time-series tasks: unconditional generation, missing-data imputation, forecasting, and time-varying-metadata conditional generation. The model natively supports heterogeneous features including continuous, binary, and categorical variables. We unify all tasks using a masked-modeling strategy in which a binary mask specifies which time-series cells are observed and which must be generated. TimeAutoDiff combines a lightweight variational autoencoder, which maps mixed-type features into a continuous latent sequence, with a diffusion model that learns temporal dynamics in this latent space. Two architectural choices provide strong speed and scalability benefits. The diffusion model samples an entire latent trajectory at once rather than denoising one timestep at a time, greatly reducing reverse-diffusion calls. In addition, the VAE compresses along the feature axis, enabling efficient modeling of wide tables in a low-dimensional latent space. Empirical evaluation shows that TimeAutoDiff matches or surpasses strong baselines in synthetic sequence fidelity and consistently improves imputation and forecasting performance. Metadata conditioning enables realistic scenario exploration, allowing users to edit metadata sequences and produce coherent counterfactual trajectories that preserve cross-feature dependencies. Ablation studies highlight the importance of the VAE's feature encoding and key components of the denoiser. A distance-to-closest-record audit further indicates that the model generalizes without excessive memorization. Code is available at https://github.com/namjoonsuh/TimeAutoDiff - oai:arXiv.org:2406.16028v3 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Namjoon Suh, Yuning Yang, Din-Yin Hsieh, Qitong Luan, Shirong Xu, Shixiang Zhu, Guang Cheng - - - A Fingerprint for Large Language Models - https://arxiv.org/abs/2407.01235 - arXiv:2407.01235v2 Announce Type: replace -Abstract: Recent advances confirm that large language models (LLMs) can achieve state-of-the-art performance across various tasks. However, due to the resource-intensive nature of training LLMs from scratch, it is urgent and crucial to protect the intellectual property of LLMs against infringement. This has motivated the authors in this paper to propose a novel black-box fingerprinting technique for LLMs. We firstly demonstrate that the outputs of LLMs span a unique vector space associated with each model. We model the problem of fingerprint authentication as the task of evaluating the similarity between the space of the victim model and the space of the suspect model. To tackle with this problem, we introduce two solutions: the first determines whether suspect outputs lie within the victim's subspace, enabling fast infringement detection; the second reconstructs a joint subspace to detect models modified via parameter-efficient fine-tuning (PEFT). Experiments indicate that the proposed method achieves superior performance in fingerprint verification and robustness against the PEFT attacks. This work reveals inherent characteristics of LLMs and provides a promising solution for protecting LLMs, ensuring efficiency, generality and practicality. - oai:arXiv.org:2407.01235v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhiguang Yang, Hanzhou Wu - - - Evaluating Model Performance Under Worst-case Subpopulations - https://arxiv.org/abs/2407.01316 - arXiv:2407.01316v2 Announce Type: replace -Abstract: The performance of ML models degrades when the training population is different from that seen under operation. Towards assessing distributional robustness, we study the worst-case performance of a model over all subpopulations of a given size, defined with respect to core attributes Z. This notion of robustness can consider arbitrary (continuous) attributes Z, and automatically accounts for complex intersectionality in disadvantaged groups. We develop a scalable yet principled two-stage estimation procedure that can evaluate the robustness of state-of-the-art models. We prove that our procedure enjoys several finite-sample convergence guarantees, including dimension-free convergence. Instead of overly conservative notions based on Rademacher complexities, our evaluation error depends on the dimension of Z only through the out-of-sample error in estimating the performance conditional on Z. On real datasets, we demonstrate that our method certifies the robustness of a model and prevents deployment of unreliable models. - oai:arXiv.org:2407.01316v2 - cs.LG - cs.CY - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Mike Li, Daksh Mittal, Hongseok Namkoong, Shangzhou Xia - - - Safe MPC Alignment with Human Directional Feedback - https://arxiv.org/abs/2407.04216 - arXiv:2407.04216v3 Announce Type: replace -Abstract: In safety-critical robot planning or control, manually specifying safety constraints or learning them from demonstrations can be challenging. In this article, we propose a certifiable alignment method for a robot to learn a safety constraint in its model predictive control (MPC) policy from human online directional feedback. To our knowledge, it is the first method to learn safety constraints from human feedback. The proposed method is based on an empirical observation: human directional feedback, when available, tends to guide the robot toward safer regions. The method only requires the direction of human feedback to update the learning hypothesis space. It is certifiable, providing an upper bound on the total number of human feedback in the case of successful learning, or declaring the hypothesis misspecification, i.e., the true safety constraint cannot be found within the specified hypothesis space. We evaluated the proposed method in numerical examples and user studies with two simulation games. Additionally, we tested the proposed method on a real-world Franka robot arm performing mobile water-pouring tasks. The results demonstrate the efficacy and efficiency of our method, showing that it enables a robot to successfully learn safety constraints with a small handful (tens) of human directional corrections. - oai:arXiv.org:2407.04216v3 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Zhixian Xie, Wenlong Zhang, Yi Ren, Zhaoran Wang, George J. Pappas, Wanxin Jin - - - SSP-GNN: Learning to Track via Bilevel Optimization - https://arxiv.org/abs/2407.04308 - arXiv:2407.04308v3 Announce Type: replace -Abstract: We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identification features (attributes). Our method applies a successive shortest paths (SSP) algorithm to a tracking graph defined over a batch of frames. The edge costs in this tracking graph are computed via a message-passing network, a graph neural network (GNN) variant. The parameters of the GNN, and hence, the tracker, are learned end-to-end on a training set of example ground-truth tracks and detections. Specifically, learning takes the form of bilevel optimization guided by our novel loss function. We evaluate our algorithm on simulated scenarios to understand its sensitivity to scenario aspects and model hyperparameters. Across varied scenario complexities, our method compares favorably to a strong baseline. - oai:arXiv.org:2407.04308v3 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Griffin Golias, Masa Nakura-Fan, Vitaly Ablavsky - - - Bridging Weighted First Order Model Counting and Graph Polynomials - https://arxiv.org/abs/2407.11877 - arXiv:2407.11877v3 Announce Type: replace -Abstract: The Weighted First-Order Model Counting Problem (WFOMC) asks to compute the weighted sum of models of a given first-order logic sentence over a given domain. It can be solved in time polynomial in the domain size for sentences from the two-variable fragment with counting quantifiers, known as $C^2$. This polynomial-time complexity is known to be retained when extending $C^2$ by one of the following axioms: linear order axiom, tree axiom, forest axiom, directed acyclic graph axiom or connectedness axiom. An interesting question remains as to which other axioms can be added to the first-order sentences in this way. We provide a new perspective on this problem by associating WFOMC with graph polynomials. Using WFOMC, we define Weak Connectedness Polynomial and Strong Connectedness Polynomials for first-order logic sentences. It turns out that these polynomials have the following interesting properties. First, they can be computed in polynomial time in the domain size for sentences from $C^2$. Second, we can use them to solve WFOMC with all of the existing axioms known to be tractable as well as with new ones such as bipartiteness, strong connectedness, having $k$ connected components, etc. Third, the well-known Tutte polynomial can be recovered as a special case of the Weak Connectedness Polynomial, and the Strict and Non-Strict Directed Chromatic Polynomials can be recovered from the Strong Connectedness Polynomials. - oai:arXiv.org:2407.11877v3 - cs.LO - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Qipeng Kuang, Ond\v{r}ej Ku\v{z}elka, Yuanhong Wang, Yuyi Wang - - - JambaTalk: Speech-Driven 3D Talking Head Generation Based on Hybrid Transformer-Mamba Model - https://arxiv.org/abs/2408.01627 - arXiv:2408.01627v3 Announce Type: replace -Abstract: In recent years, the talking head generation has become a focal point for researchers. Considerable effort is being made to refine lip-sync motion, capture expressive facial expressions, generate natural head poses, and achieve high-quality video. However, no single model has yet achieved equivalence across all quantitative and qualitative metrics. We introduce Jamba, a hybrid Transformer-Mamba model, to animate a 3D face. Mamba, a pioneering Structured State Space Model (SSM) architecture, was developed to overcome the limitations of conventional Transformer architectures, particularly in handling long sequences. This challenge has constrained traditional models. Jamba combines the advantages of both the Transformer and Mamba approaches, offering a comprehensive solution. Based on the foundational Jamba block, we present JambaTalk to enhance motion variety and lip sync through multimodal integration. Extensive experiments reveal that our method achieves performance comparable or superior to state-of-the-art models. - oai:arXiv.org:2408.01627v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Farzaneh Jafari, Stefano Berretti, Anup Basu - - - Splitting methods based on the nonzero diagonal pattern for computing matrix functions - https://arxiv.org/abs/2408.04128 - arXiv:2408.04128v2 Announce Type: replace -Abstract: We consider the task of approximating a matrix function $f(A)$, where $A$ is a matrix in which only a relatively small number of (not necessarily consecutive) sub- and superdiagonals contain nonzero entries. Approximating $f$ by a low-degree polynomial $p$ allows us to obtain sparse approximations to $f(A)$, which one can efficiently work with (while, in general, $f(A)$ is a dense matrix, even when $A$ is sparse). Our approach is based on carefully inspecting the locations where nonzeros can occur in $p(A)$, and identifying the entries in $A$ that influence them. In particular, we illustrate how this approach can be used for efficiently approximating the trace of $f(A)$ and identify how this approach is related to established (stochastic) probing methods for trace estimation. Another application area in which our approach works particularly well is the computation of functions of Toeplitz matrices. Here, studying the sparsity pattern of $p(A)$ allows us to reduce the computation of the whole matrix polynomial to that of a single small-scale submatrix, yielding an algorithm that scales exceptionally well to large problem sizes. - oai:arXiv.org:2408.04128v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Majed Hamadi, Nezam Mahdavi-Amiri, Marcel Schweitzer - - - Localized Evaluation for Constructing Discrete Vector Fields - https://arxiv.org/abs/2408.04769 - arXiv:2408.04769v3 Announce Type: replace -Abstract: Topological abstractions offer a method to summarize the behavior of vector fields but computing them robustly can be challenging due to numerical precision issues. One alternative is to represent the vector field using a discrete approach, which constructs a collection of pairs of simplices in the input mesh that satisfies criteria introduced by Forman's discrete Morse theory. While numerous approaches exist to compute pairs in the restricted case of the gradient of a scalar field, state-of-the-art algorithms for the general case of vector fields require expensive optimization procedures. This paper introduces a fast, novel approach for pairing simplices of two-dimensional, triangulated vector fields that do not vary in time. The key insight of our approach is that we can employ a local evaluation, inspired by the approach used to construct a discrete gradient field, where every simplex in a mesh is considered by no more than one of its vertices. Specifically, we observe that for any edge in the input mesh, we can uniquely assign an outward direction of flow. We can further expand this consistent notion of outward flow at each vertex, which corresponds to the concept of a downhill flow in the case of scalar fields. Working with outward flow enables a linear-time algorithm that processes the (outward) neighborhoods of each vertex one-by-one, similar to the approach used for scalar fields. We couple our approach to constructing discrete vector fields with a method to extract, simplify, and visualize topological features. Empirical results on analytic and simulation data demonstrate drastic improvements in running time, produce features similar to the current state-of-the-art, and show the application of simplification to large, complex flows. - oai:arXiv.org:2408.04769v3 - cs.GR - cs.CG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tanner Finken, Julien Tierny, Joshua A Levine - - - Prompt Tuning as User Inherent Profile Inference Machine - https://arxiv.org/abs/2408.06577 - arXiv:2408.06577v3 Announce Type: replace -Abstract: Large Language Models (LLMs) have exhibited significant promise in recommender systems by empowering user profiles with their extensive world knowledge and superior reasoning capabilities. However, LLMs face challenges like unstable instruction compliance, modality gaps, and high inference latency, leading to textual noise and limiting their effectiveness in recommender systems. To address these challenges, we propose UserIP-Tuning, which uses prompt-tuning to infer user profiles. It integrates the causal relationship between user profiles and behavior sequences into LLMs' prompts. It employs Expectation Maximization (EM) to infer the embedded latent profile, minimizing textual noise by fixing the prompt template. Furthermore, a profile quantization codebook bridges the modality gap by categorizing profile embeddings into collaborative IDs pre-stored for online deployment. This improves time efficiency and reduces memory usage. Experiments show that UserIP-Tuning outperforms state-of-the-art recommendation algorithms. An industry application confirms its effectiveness, robustness, and transferability. The presented solution has been deployed in Huawei AppGallery's Explore page since May 2025, serving 2 million daily active users, delivering significant improvements in real-world recommendation scenarios. The code is publicly available for replication at https://github.com/Applied-Machine-Learning-Lab/UserIP-Tuning. - oai:arXiv.org:2408.06577v3 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3746252.3761574 - Yusheng Lu, Zhaocheng Du, Xiangyang Li, Pengyue Jia, Yejing Wang, Weiwen Liu, Yichao Wang, Huifeng Guo, Ruiming Tang, Zhenhua Dong, Yongrui Duan, Xiangyu Zhao - - - ComGPT: Detecting Local Community Structure with Large Language Models - https://arxiv.org/abs/2408.06658 - arXiv:2408.06658v3 Announce Type: replace -Abstract: Large Language Models (LLMs), like GPT-3.5-turbo, have demonstrated the ability to understand graph structures and have achieved excellent performance in various graph reasoning tasks, such as node classification. Despite their strong abilities in graph reasoning tasks, they lack specific domain knowledge and have a weaker understanding of community-related graph information, which hinders their capabilities in the community detection task. Moreover, local community detection algorithms based on seed expansion, referred to as seed expansion algorithms, often face several shortcomings, including the seed-dependent problem, community diffusion, and free rider effect. To use LLMs to overcome the above shortcomings, we explore a GPT-guided seed expansion algorithm named ComGPT. ComGPT iteratively selects potential nodes by local modularity from the detected community's neighbors, and subsequently employs LLMs to choose the node from these selected potential nodes to join the detected community. To improve LLMs' understanding of community-related graph information, we propose ComIncident, a graph encoding method that incorporates community knowledge and is designed for the community detection task. Additionally, we design the Node Selection Guide (NSG) prompt to enhance LLMs' understanding of community characteristics. Experimental results demonstrate that ComGPT outperforms the baselines, thereby confirming the effectiveness of the ComIncident and the NSG prompt. - oai:arXiv.org:2408.06658v3 - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Li Ni, Haowen Shen, Lin Mu, Yiwen Zhang, Wenjian Luo - - - Fredholm Neural Networks - https://arxiv.org/abs/2408.09484 - arXiv:2408.09484v5 Announce Type: replace -Abstract: Within the family of explainable machine-learning, we present Fredholm neural networks (Fredholm NNs): deep neural networks (DNNs) architectures motivated by fixed-point iteration schemes for the solution of linear and nonlinear Fredholm integral equations (FIEs) of the second kind. We also show how the proposed framework can be used for the solution of inverse problems. Applications of FIEs include the solution of ordinary, as well as partial differential equations (ODEs, PDEs) and many more. We first prove that Fredholm NNs provide accurate solutions. We then provide insight into the values of the hyperparameters and trainable/explainable weights and biases of the DNN, by directly connecting their values to the underlying mathematical theory. For our illustrations, we use Fredholm NNs to solve both linear and nonlinear problems, including elliptic PDEs and boundary value problems. We show that the proposed scheme achieves significant numerical approximation accuracy across both the domain and boundary. The proposed methodology provides insight into the connection between neural networks and classical numerical methods, and we posit that it can have applications in fields such as Uncertainty Quantification (UQ) and explainable artificial intelligence (XAI). Thus, we believe that it will trigger further advances in the intersection between scientific machine learning and numerical analysis. - oai:arXiv.org:2408.09484v5 - math.NA - cs.NA - math.DS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1137/24M1686991 - SIAM Journal on Scientific Computing, Vol. 47, Iss. 4, 2025 - Kyriakos Georgiou, Constantinos Siettos, Athanasios N. Yannacopoulos - - - On the loss of orthogonality in low-synchronization variants of reorthogonalized block classical Gram-Schmidt - https://arxiv.org/abs/2408.10109 - arXiv:2408.10109v3 Announce Type: replace -Abstract: Interest in communication-avoiding orthogonalization schemes for high-performance computing has been growing recently. This manuscript addresses open questions about the numerical stability of various block classical Gram-Schmidt variants that have been proposed in the past few years. An abstract framework is employed, the flexibility of which allows for new rigorous bounds on the loss of orthogonality in these variants. We first analyze a generalization of (reorthogonalized) block classical Gram-Schmidt and show that a "strong" intrablock orthogonalization routine is only needed for the very first block in order to maintain orthogonality on the level of the unit roundoff. In particular, this ``strong" first step does not have to be a reorthogonalized QR itself and subsequent steps can use less stable QR variants, thus keeping the overall communication costs low. - Then, using this variant, which has four synchronization points per block column, we remove the synchronization points one at a time and analyze how each alteration affects the stability of the resulting method. Our analysis shows that the variant requiring only one synchronization per block column cannot be guaranteed to be stable in practice, as stability begins to degrade with the first reduction of synchronization points. - Our analysis of block methods also provides new theoretical results for the single-column case. In particular, it is proven that DCGS2 from [Bielich, D. et al. Par. Comput. 112 (2022)] and CGS-2 from [\'{S}wirydowicz, K. et al, Num. Lin. Alg. Appl. 28 (2021)] are as stable as Householder QR. Numerical examples from the BlockStab toolbox are included throughout, to help compare variants and illustrate the effects of different choices of intraorthogonalization subroutines. - oai:arXiv.org:2408.10109v3 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Erin Carson, Kathryn Lund, Yuxin Ma, Eda Oktay - - - Enhancing Test Time Adaptation with Few-shot Guidance - https://arxiv.org/abs/2409.01341 - arXiv:2409.01341v4 Announce Type: replace -Abstract: Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data. Although these methods offer some relief, they lack a reliable mechanism for domain shift correction, which can often be erratic in real-world applications. In response, we develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA. Adhering to the principle of few inputs, big gains, FS-TTA reduces blind exploration in unseen target domains. Furthermore, we propose a two-stage framework to tackle FS-TTA, including (i) fine-tuning the pre-trained source model with few-shot support set, along with using feature diversity augmentation module to avoid overfitting, (ii) implementing test time adaptation based on prototype memory bank guidance to produce high quality pseudo-label for model adaptation. Through extensive experiments on three cross-domain classification benchmarks, we demonstrate the superior performance and reliability of our FS-TTA and framework. - oai:arXiv.org:2409.01341v4 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Siqi Luo, Yi Xin, Yuntao Du, Tao Tan, Guangtao Zhai, Xiaohong Liu - - - An Open-Source Soft Robotic Platform for Autonomous Aerial Manipulation in the Wild - https://arxiv.org/abs/2409.07662 - arXiv:2409.07662v2 Announce Type: replace -Abstract: Aerial manipulation combines the versatility and speed of flying platforms with the functional capabilities of mobile manipulation, which presents significant challenges due to the need for precise localization and control. Traditionally, researchers have relied on offboard perception systems, which are limited to expensive and impractical specially equipped indoor environments. In this work, we introduce a novel platform for autonomous aerial manipulation that exclusively utilizes onboard perception systems. Our platform can perform aerial manipulation in various indoor and outdoor environments without depending on external perception systems. Our experimental results demonstrate the platform's ability to autonomously grasp various objects in diverse settings. This advancement significantly improves the scalability and practicality of aerial manipulation applications by eliminating the need for costly tracking solutions. To accelerate future research, we open source our ROS 2 software stack and custom hardware design, making our contributions accessible to the broader research community. - oai:arXiv.org:2409.07662v2 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Proceedings of Machine Learning Research (2025) 3094-3106 - Erik Bauer, Marc Bl\"ochlinger, Pascal Strauch, Arman Raayatsanati, Curdin Cavelti, Robert K. Katzschmann - - - Kinodynamic Motion Planning for Collaborative Object Transportation by Multiple Mobile Manipulators - https://arxiv.org/abs/2409.14910 - arXiv:2409.14910v2 Announce Type: replace -Abstract: This work proposes a kinodynamic motion planning technique for collaborative object transportation by multiple mobile manipulators in dynamic environments. A global path planner computes a linear piecewise path from start to goal. A novel algorithm detects the narrow regions between the static obstacles and aids in defining the obstacle-free region to enhance the feasibility of the global path. We then formulate a local online motion planning technique for trajectory generation that minimizes the control efforts in a receding horizon manner. It plans the trajectory for finite time horizons, considering the kinodynamic constraints and the static and dynamic obstacles. The planning technique jointly plans for the mobile bases and the arms to utilize the locomotion capability of the mobile base and the manipulation capability of the arm efficiently. We use a convex cone approach to avoid self-collision of the formation by modifying the mobile manipulators admissible state without imposing additional constraints. Numerical simulations and hardware experiments showcase the efficiency of the proposed approach. - oai:arXiv.org:2409.14910v2 - cs.RO - cs.MA - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1115/1.4069407 - J. Mechanisms Robotics. Dec 2025, 17(12) - Keshab Patra, Arpita Sinha, Anirban Guha - - - Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection - https://arxiv.org/abs/2409.14985 - arXiv:2409.14985v4 Announce Type: replace -Abstract: In autonomous driving scenarios, accurate perception is becoming an even more critical task for safe navigation. While LiDAR provides precise spatial data, its inherent sparsity makes it difficult to detect small or distant objects. Existing methods try to address this by generating additional points within a Region of Interest (RoI), but relying on LiDAR alone often leads to false positives and a failure to recover meaningful structures. To address these limitations, we propose Image-Guided Semantic Pseudo-LiDAR Point Generation model, called ImagePG, a novel framework that leverages rich RGB image features to generate dense and semantically meaningful 3D points. Our framework includes an Image-Guided RoI Points Generation (IG-RPG) module, which creates pseudo-points guided by image features, and an Image-Aware Occupancy Prediction Network (I-OPN), which provides spatial priors to guide point placement. A multi-stage refinement (MR) module further enhances point quality and detection robustness. To the best of our knowledge, ImagePG is the first method to directly leverage image features for point generation. Extensive experiments on the KITTI and Waymo datasets demonstrate that ImagePG significantly improves the detection of small and distant objects like pedestrians and cyclists, reducing false positives by nearly 50%. On the KITTI benchmark, our framework improves mAP by +1.38%p (car), +7.91%p (pedestrian), and +5.21%p (cyclist) on the test set over the baseline, achieving state-of-the-art cyclist performance on the KITTI leaderboard. The code is available at: https://github.com/MS-LIMA/ImagePG - oai:arXiv.org:2409.14985v4 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Minseung Lee, Seokha Moon, Seung Joon Lee, Reza Mahjourian, Jinkyu Kim - - - Artificial Human Intelligence: The role of Humans in the Development of Next Generation AI - https://arxiv.org/abs/2409.16001 - arXiv:2409.16001v3 Announce Type: replace -Abstract: Human intelligence, the most evident and accessible form of source of reasoning, hosted by biological hardware, has evolved and been refined over thousands of years, positioning itself today to create new artificial forms and preparing to self--design their evolutionary path forward. Beginning with the advent of foundation models, the rate at which human and artificial intelligence interact with each other has exceeded any anticipated quantitative figures. The close engagement led both bits of intelligence to be impacted in various ways, which naturally resulted in complex confluences that warrant close scrutiny. Recent advances, such as DeepSeek, exemplify this interplay: the novel contributions, we argue, draw indirect inspiration from biological principles like modular neural specialization and sparse episodic encoding, addressing computational bottlenecks while aligning with human-inspired scalability. In the sequel, using a novel taxonomy, we shall explore this interplay between human and machine intelligence, focusing on the crucial role humans play in developing ethical, responsible, and robust intelligent systems. We briefly delve into various aspects of implementation inspired by the mechanisms underlying neuroscience and human cognition. In addition, we propose future perspectives, capitalizing on the advantages of symbiotic designs to suggest a human-centered direction for next-generation developments, focusing on the augmentation role of AI. We finalize this evolving document with some thoughts and open questions yet to be addressed by the broader community. - oai:arXiv.org:2409.16001v3 - cs.AI - q-bio.NC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Suayb S. Arslan - - - Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Handy Appetizer - https://arxiv.org/abs/2409.17120 - arXiv:2409.17120v2 Announce Type: replace -Abstract: This book explores the role of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in driving the progress of big data analytics and management. The book focuses on simplifying the complex mathematical concepts behind deep learning, offering intuitive visualizations and practical case studies to help readers understand how neural networks and technologies like Convolutional Neural Networks (CNNs) work. It introduces several classic models and technologies such as Transformers, GPT, ResNet, BERT, and YOLO, highlighting their applications in fields like natural language processing, image recognition, and autonomous driving. The book also emphasizes the importance of pre-trained models and how they can enhance model performance and accuracy, with instructions on how to apply these models in various real-world scenarios. Additionally, it provides an overview of key big data management technologies like SQL and NoSQL databases, as well as distributed computing frameworks such as Apache Hadoop and Spark, explaining their importance in managing and processing vast amounts of data. Ultimately, the book underscores the value of mastering deep learning and big data management skills as critical tools for the future workforce, making it an essential resource for both beginners and experienced professionals. - oai:arXiv.org:2409.17120v2 - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Benji Peng, Xuanhe Pan, Yizhu Wen, Ziqian Bi, Keyu Chen, Ming Li, Ming Liu, Qian Niu, Junyu Liu, Jinlang Wang, Sen Zhang, Jiawei Xu, Xinyuan Song, Zekun Jiang, Tianyang Wang, Pohsun Feng - - - Surveying the MLLM Landscape: A Meta-Review of Current Surveys - https://arxiv.org/abs/2409.18991 - arXiv:2409.18991v2 Announce Type: replace -Abstract: The rise of Multimodal Large Language Models (MLLMs) has become a transformative force in the field of artificial intelligence, enabling machines to process and generate content across multiple modalities, such as text, images, audio, and video. These models represent a significant advancement over traditional unimodal systems, opening new frontiers in diverse applications ranging from autonomous agents to medical diagnostics. By integrating multiple modalities, MLLMs achieve a more holistic understanding of information, closely mimicking human perception. As the capabilities of MLLMs expand, the need for comprehensive and accurate performance evaluation has become increasingly critical. This survey aims to provide a systematic review of benchmark tests and evaluation methods for MLLMs, covering key topics such as foundational concepts, applications, evaluation methodologies, ethical concerns, security, efficiency, and domain-specific applications. Through the classification and analysis of existing literature, we summarize the main contributions and methodologies of various surveys, conduct a detailed comparative analysis, and examine their impact within the academic community. Additionally, we identify emerging trends and underexplored areas in MLLM research, proposing potential directions for future studies. This survey is intended to offer researchers and practitioners a comprehensive understanding of the current state of MLLM evaluation, thereby facilitating further progress in this rapidly evolving field. - oai:arXiv.org:2409.18991v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ming Li, Keyu Chen, Ziqian Bi, Ming Liu, Xinyuan Song, Zekun Jiang, Tianyang Wang, Benji Peng, Qian Niu, Junyu Liu, Jinlang Wang, Sen Zhang, Xuanhe Pan, Jiawei Xu, Pohsun Feng - - - Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Unveiling AI's Potential Through Tools, Techniques, and Applications - https://arxiv.org/abs/2410.01268 - arXiv:2410.01268v3 Announce Type: replace -Abstract: Artificial intelligence (AI), machine learning, and deep learning have become transformative forces in big data analytics and management, enabling groundbreaking advancements across diverse industries. This article delves into the foundational concepts and cutting-edge developments in these fields, with a particular focus on large language models (LLMs) and their role in natural language processing, multimodal reasoning, and autonomous decision-making. Highlighting tools such as ChatGPT, Claude, and Gemini, the discussion explores their applications in data analysis, model design, and optimization. - The integration of advanced algorithms like neural networks, reinforcement learning, and generative models has enhanced the capabilities of AI systems to process, visualize, and interpret complex datasets. Additionally, the emergence of technologies like edge computing and automated machine learning (AutoML) democratizes access to AI, empowering users across skill levels to engage with intelligent systems. This work also underscores the importance of ethical considerations, transparency, and fairness in the deployment of AI technologies, paving the way for responsible innovation. - Through practical insights into hardware configurations, software environments, and real-world applications, this article serves as a comprehensive resource for researchers and practitioners. By bridging theoretical underpinnings with actionable strategies, it showcases the potential of AI and LLMs to revolutionize big data management and drive meaningful advancements across domains such as healthcare, finance, and autonomous systems. - oai:arXiv.org:2410.01268v3 - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pohsun Feng, Ziqian Bi, Yizhu Wen, Xuanhe Pan, Benji Peng, Ming Liu, Jiawei Xu, Keyu Chen, Junyu Liu, Caitlyn Heqi Yin, Sen Zhang, Jinlang Wang, Qian Niu, Ming Li, Tianyang Wang, Xinyuan Song, Zekun Jiang - - - Event-Customized Image Generation - https://arxiv.org/abs/2410.02483 - arXiv:2410.02483v2 Announce Type: replace -Abstract: Customized Image Generation, generating customized images with user-specified concepts, has raised significant attention due to its creativity and novelty. With impressive progress achieved in subject customization, some pioneer works further explored the customization of action and interaction beyond entity (i.e., human, animal, and object) appearance. However, these approaches only focus on basic actions and interactions between two entities, and their effects are limited by insufficient ''exactly same'' reference images. To extend customized image generation to more complex scenes for general real-world applications, we propose a new task: event-customized image generation. Given a single reference image, we define the ''event'' as all specific actions, poses, relations, or interactions between different entities in the scene. This task aims at accurately capturing the complex event and generating customized images with various target entities. To solve this task, we proposed a novel training-free event customization method: FreeEvent. Specifically, FreeEvent introduces two extra paths alongside the general diffusion denoising process: 1) Entity switching path: it applies cross-attention guidance and regulation for target entity generation. 2) Event transferring path: it injects the spatial feature and self-attention maps from the reference image to the target image for event generation. To further facilitate this new task, we collected two evaluation benchmarks: SWiG-Event and Real-Event. Extensive experiments and ablations have demonstrated the effectiveness of FreeEvent. - oai:arXiv.org:2410.02483v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - ICML 2025 - Zhen Wang, Yilei Jiang, Dong Zheng, Jun Xiao, Long Chen - - - A Data Envelopment Analysis Approach for Assessing Fairness in Resource Allocation: Application to Kidney Exchange Programs - https://arxiv.org/abs/2410.02799 - arXiv:2410.02799v2 Announce Type: replace -Abstract: Kidney exchange programs have substantially increased transplantation rates but also raise critical concerns about fairness in organ allocation. We propose a novel framework leveraging Data Envelopment Analysis (DEA) to evaluate multiple dimensions of fairness-Priority, Access, and Outcome-within a unified model. This approach captures complexities often missed in single-metric analyses. Using data from the United Network for Organ Sharing, we separately quantify fairness across these dimensions: Priority fairness through waitlist durations, Access fairness via the Living Kidney Donor Profile Index (LKDPI) scores, and Outcome fairness based on graft lifespan. We then apply our conditional DEA model with covariate adjustment to demonstrate significant disparities in kidney allocation efficiency across ethnic groups. To quantify uncertainty, we employ conformal prediction within a novel Reference Frontier Mapping (RFM) framework, yielding group-conditional prediction intervals with finite-sample coverage guarantees. Our findings show notable differences in efficiency distributions between ethnic groups. Our study provides a rigorous framework for evaluating fairness in complex resource allocation systems with resource scarcity and mutual compatibility constraints. - oai:arXiv.org:2410.02799v2 - cs.CY - cs.LG - stat.ME - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ali Kaazempur-Mofrad, Xiaowu Dai - - - RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation - https://arxiv.org/abs/2410.06055 - arXiv:2410.06055v2 Announce Type: replace -Abstract: While latent diffusion models (LDMs), such as Stable Diffusion, are designed for high-resolution (HR) image generation, they often struggle with significant structural distortions when generating images at resolutions higher than their training one. Instead of relying on extensive retraining, a more resource-efficient approach is to reprogram the pretrained model for HR image generation; however, existing methods often result in poor image quality and long inference time. We introduce RepLDM, a novel reprogramming framework for pretrained LDMs that enables high-quality, high-efficiency, high-resolution image generation; see Fig. 1. RepLDM consists of two stages: (i) an attention guidance stage, which generates a latent representation of a higher-quality training-resolution image using a novel training-free self-attention mechanism to enhance the structural consistency; and (ii) a progressive upsampling stage, which progressively performs upsampling in pixel space to mitigate the severe artifacts caused by latent space upsampling. The effective initialization from the first stage allows for denoising at higher resolutions with significantly fewer steps, improving the efficiency. Extensive experimental results demonstrate that RepLDM significantly outperforms state-of-the-art methods in both quality and efficiency for HR image generation, underscoring its advantages for real-world applications. Codes: https://github.com/kmittle/RepLDM. - oai:arXiv.org:2410.06055v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Boyuan Cao, Jiaxin Ye, Yujie Wei, Hongming Shan - - - Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation - https://arxiv.org/abs/2410.07618 - arXiv:2410.07618v2 Announce Type: replace -Abstract: Although Chinese calligraphy generation has achieved style transfer, generating calligraphy by specifying the calligrapher, font, and character style remains challenging. To address this, we propose a new Chinese calligraphy generation model 'Moyun' , which replaces the Unet in the Diffusion model with Vision Mamba and introduces the TripleLabel control mechanism to achieve controllable calligraphy generation. The model was tested on our large-scale dataset 'Mobao' of over 1.9 million images, and the results demonstrate that 'Moyun' can effectively control the generation process and produce calligraphy in the specified style. Even for calligraphy the calligrapher has not written, 'Moyun' can generate calligraphy that matches the style of the calligrapher. - oai:arXiv.org:2410.07618v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Kaiyuan Liu, Jiahao Mei, Hengyu Zhang, Yihuai Zhang, Daoguo Dong, Liang He - - - Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning - https://arxiv.org/abs/2410.09101 - arXiv:2410.09101v2 Announce Type: replace -Abstract: Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage and data contamination. Existing approaches, such as backdoor watermarking, rely on inducing a detectable behavior into the trained model on a part of the data distribution. However, these approaches have limitations, as they can be harmful to the model's performances or require unpractical access to the model's internals. Most importantly, previous approaches lack guarantee against false positives. This paper introduces data taggants, a novel non-backdoor dataset ownership verification technique. Our method uses pairs of out-of-distribution samples and random labels as secret keys, and leverages clean-label targeted data poisoning to subtly alter a dataset, so that models trained on it respond to the key samples with the corresponding key labels. The keys are built as to allow for statistical certificates with black-box access only to the model. We validate our approach through comprehensive and realistic experiments on ImageNet1k using ViT and ResNet models with state-of-the-art training recipes. Our findings demonstrate that data taggants can reliably detect models trained on the protected dataset with high confidence, without compromising validation accuracy, and show their superiority over backdoor watermarking. We demonstrate the stealthiness and robustness of our method against various defense mechanisms. - oai:arXiv.org:2410.09101v2 - cs.CR - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wassim Bouaziz, Nicolas Usunier, El-Mahdi El-Mhamdi - - - Mastering AI: Big Data, Deep Learning, and the Evolution of Large Language Models -- AutoML from Basics to State-of-the-Art Techniques - https://arxiv.org/abs/2410.09596 - arXiv:2410.09596v3 Announce Type: replace -Abstract: A comprehensive guide to Automated Machine Learning (AutoML) is presented, covering fundamental principles, practical implementations, and future trends. The paper is structured to assist both beginners and experienced practitioners, with detailed discussions on popular AutoML tools such as TPOT, AutoGluon, and Auto-Keras. Emerging topics like Neural Architecture Search (NAS) and AutoML's applications in deep learning are also addressed. It is anticipated that this work will contribute to ongoing research and development in the field of AI and machine learning. - oai:arXiv.org:2410.09596v3 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Pohsun Feng, Ziqian Bi, Yizhu Wen, Benji Peng, Junyu Liu, Caitlyn Heqi Yin, Tianyang Wang, Keyu Chen, Sen Zhang, Ming Li, Jiawei Xu, Ming Liu, Xuanhe Pan, Jinlang Wang, Xinyuan Song, Qian Niu - - - A Tidal Current Speed Forecasting Model based on Multi-Periodicity Learning - https://arxiv.org/abs/2410.09718 - arXiv:2410.09718v3 Announce Type: replace -Abstract: Tidal energy is one of the key components in increasing the penetration of renewable energy. High tidal energy penetration into the electrical grid depends on accurate tidal current speed forecasting. Model inaccuracies hinder forecast accuracy. Previous research primarily used physical models to forecast tidal current speed, yet tidal current variations influenced by the orbital periods of celestial bodies make accurate physical modeling challenging. Research on the multi-periodicity of tides is crucial for forecasting tidal current speed. We propose the Wavelet-Enhanced Convolutional Network to learn multi-periodicity. The framework embeds intra-period and inter-period variations of one-dimensional tidal current data into the rows and columns, respectively, of a two-dimensional tensor. Then, the two-dimensional variations of the sequence can be processed by convolutional kernels. We integrate a time-frequency analysis method into the framework to further address local periodic features. Additionally, to enhance the framework's stability, we optimize the framework's hyperparameters with the Tree-structured Parzen Estimator. The proposed framework captures multi-periodic dependencies in tidal current data. Numerical results show a 10-step average Mean Absolute Error of 0.025, with at least a 1.18% error reduction compared to other baselines. Further ablation studies show a 1.4% reduction in Mean Absolute Percentage Error on the data with artificially added periodic fluctuations. - oai:arXiv.org:2410.09718v3 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tengfei Cheng, Yangdi Huang, Ling Xiao, Yunxuan Dong - - - Tokenizing Motion: A Generative Approach for Scene Dynamics Compression - https://arxiv.org/abs/2410.09768 - arXiv:2410.09768v3 Announce Type: replace -Abstract: This paper proposes a novel generative video compression framework that leverages motion pattern priors, derived from subtle dynamics in common scenes (e.g., swaying flowers or a boat drifting on water), rather than relying on video content priors (e.g., talking faces or human bodies). These compact motion priors enable a new approach to ultra-low bitrate communication while achieving high-quality reconstruction across diverse scene contents. At the encoder side, motion priors can be streamlined into compact representations via a dense-to-sparse transformation. At the decoder side, these priors facilitate the reconstruction of scene dynamics using an advanced flow-driven diffusion model. Experimental results illustrate that the proposed method can achieve superior rate-distortion-performance and outperform the state-of-the-art conventional-video codec Enhanced Compression Model (ECM) on-scene dynamics sequences. The project page can be found at-https://github.com/xyzysz/GNVDC. - oai:arXiv.org:2410.09768v3 - cs.CV - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Shanzhi Yin, Zihan Zhang, Bolin Chen, Shiqi Wang, Yan Ye - - - Near-Pilotless Single Carrier Communications Using Matrix Decomposition - https://arxiv.org/abs/2410.10403 - arXiv:2410.10403v2 Announce Type: replace -Abstract: Single Input-Multiple Output (SIMO) systems are key enablers of high data rates in the next generation wireless communications. However in SIMO systems, channel estimation and equalization are challenging particularly in the presence of rapidly changing channels. The high pilot overhead required for channel estimation can reduce the system throughput for large antenna configuration. In this paper, we provide an iterative matrix decomposition algorithm for near-pilotless or blind decoding of SIMO signals, in a single carrier system with frequency domain equalization. This novel approach replaces the standard equalization and estimates both the transmitted data and the channel without the knowledge of any prior distributions, by making use of only one pilot. Our simulations demonstrate improved performance, in terms of error rates, compared to the more widely used pilot-based Maximal Ratio Combining (MRC) method. - oai:arXiv.org:2410.10403v2 - cs.IT - eess.SP - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - K Sai Praneeth, P Aswathylakshmi, Radhakrishna Ganti - - - FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening - https://arxiv.org/abs/2410.15001 - arXiv:2410.15001v4 Announce Type: replace -Abstract: Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation trees are used to train on a smaller graph, resulting in faster computation. Nonetheless, prior research has not adequately addressed the computational costs during the inference phase. This paper presents a novel approach to improve the scalability of GNNs by reducing computational burden during the inference phase using graph coarsening. We demonstrate two different methods -- Extra Nodes and Cluster Nodes. Our study extends the application of graph coarsening for graph-level tasks, including graph classification and graph regression. We conduct extensive experiments on multiple benchmark datasets to evaluate the performance of our approach. Our results show that the proposed method achieves orders of magnitude improvements in single-node inference time compared to traditional approaches. Furthermore, it significantly reduces memory consumption for node and graph classification and regression tasks, enabling efficient training and inference on low-resource devices where conventional methods are impractical. Notably, these computational advantages are achieved while maintaining competitive performance relative to baseline models. - oai:arXiv.org:2410.15001v4 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shubhajit Roy, Hrriday Ruparel, Kishan Ved, Anirban Dasgupta - - - The grad-div conforming virtual element method for the quad-div problem in three dimensions - https://arxiv.org/abs/2410.18375 - arXiv:2410.18375v2 Announce Type: replace -Abstract: We propose a new stable variational formulation for the quad-div problem in three dimensions and prove its well-posedness. Using this weak form, we develop and analyze the $\boldsymbol{H}(\operatorname{grad-div})$-conforming virtual element method of arbitrary approximation orders on polyhedral meshes. Three families of $\boldsymbol{H}(\operatorname{grad-div})$-conforming virtual elements are constructed based on the structure of a de Rham sub-complex with enhanced smoothness, resulting in an exact discrete virtual element complex. In the lowest-order case, the simplest element has only one degree of freedom at each vertex and face, respectively. We rigorously prove the interpolation error estimates, the stability of discrete bilinear forms, the well-posedness of discrete formulation and the optimal error estimates. Some numerical examples are shown to verify the theoretical results. - oai:arXiv.org:2410.18375v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaojing Dong, Yibing Han, Yunqing Huang - - - LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation - https://arxiv.org/abs/2410.20833 - arXiv:2410.20833v2 Announce Type: replace -Abstract: Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests in fact-oriented tasks, especially within retrieval-augmented generation (RAG) frameworks, where keyword extraction and factual accuracy take precedence over stylistic elements, remains unclear. Our study addresses this knowledge gap by simulating two critical phases of the RAG framework. In the first phase, LLMs evaluated human-authored and model-generated passages, emulating the \textit{pointwise reranking phase}. The second phase involves conducting pairwise reading comprehension tests to simulate the \textit{generation phase}. Contrary to previous findings indicating a self-preference in rating tasks, our results reveal no significant self-preference effect in RAG frameworks. Instead, we observe that factual accuracy significantly influences LLMs' output, even in the absence of prior knowledge. These findings are consistent among three common QA datasets (NQ, MARCO, TriviaQA Datasets) and 5 widely adopted language models (GPT-3.5, GPT-4o-mini, Gemini, LLaMA3, and Mistral). Our research contributes to the ongoing discourse on LLM biases and their implications for RAG-based system, offering insights that may inform the development of more robust and unbiased LLM systems. - oai:arXiv.org:2410.20833v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Yen-Shan Chen, Jing Jin, Peng-Ting Kuo, Chao-Wei Huang, Yun-Nung Chen - - - A Power Method for Computing Singular Value Decomposition - https://arxiv.org/abs/2410.23999 - arXiv:2410.23999v4 Announce Type: replace -Abstract: The singular value decomposition (SVD) allows to write a matrix as a product of a left singular vectors matrix, a nonnegative singular values diagonal matrix and a right singular vectors matrix. Among the applications of the SVD are the principal component analysis, the low-rank matrix approximation and the solving of a linear system of equations. The methods used for computing this decomposition allow to get the complete or partial result. For very large size matrix, the probabilistic methods allow to get partial result by using less computational load. A power method is proposed in this paper for computing all or the $k$ first largest SVD subspaces for a real-valued matrix. The $k$ first right singular vectors of this method are the $k$ columns of a neural network encoder weight matrix. The accuracy of this iterative search method depends on the behavior of the singular values and the settings of the gradient search optimizer used. A R package implementing the proposed method is available at https://cran.r-project.org/web/packages/psvd/index.html. - oai:arXiv.org:2410.23999v4 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Doulaye Dembele - - - On codes induced from Hadamard matrices - https://arxiv.org/abs/2410.24027 - arXiv:2410.24027v3 Announce Type: replace -Abstract: Unit derived schemes applied to Hadamard matrices are used to construct and analyse linear block and convolutional codes. Codes are constructed to prescribed types, lengths and rates and multiple series of self-dual, dual-containing, linear complementary dual and quantum error-correcting of both linear block {\em and} convolutional codes are derived. - oai:arXiv.org:2410.24027v3 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/publicdomain/zero/1.0/ - Ted Hurley - - - A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese - https://arxiv.org/abs/2411.06096 - arXiv:2411.06096v2 Announce Type: replace -Abstract: We present ZhoBLiMP, the largest linguistic minimal pair benchmark for Chinese, with over 100 paradigms, ranging from topicalization to the \textit{Ba} construction. We then train from scratch a suite of Chinese language models (LMs) with different tokenizers, parameter sizes, and token volumes, to study the learning curves of LMs on Chinese. To mitigate the biases introduced by unequal lengths of the sentences in a minimal pair, we propose a new metric named sub-linear length normalized log-probabilities (SLLN-LP). Using SLLN-LP as the metric, our results show that \textsc{Anaphor}, \textsc{Quantifiers}, and \textsc{Ellipsis} in Chinese are difficult for LMs even up to 32B parameters, and that SLLN-LP successfully mitigates biases in ZhoBLiMP, JBLiMP and BLiMP. We conclude that future evaluations should be more carefully designed to consider the intricate relations between linking functions, LMs, and targeted minimal pairs. - oai:arXiv.org:2411.06096v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yikang Liu, Yeting Shen, Hongao Zhu, Lilong Xu, Zhiheng Qian, Siyuan Song, Kejia Zhang, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang, Hai Hu - - - KeyB2+: Summary-Augmented Block Selection for Scalable Long-Document Reranking with LLMs - https://arxiv.org/abs/2411.06254 - arXiv:2411.06254v3 Announce Type: replace -Abstract: Large language models (LLMs) have advanced neural information retrieval (IR), yet applying them to long-document reranking remains computationally expensive and often ineffective when irrelevant content dominates. We begin with an in-depth analysis of decoder-only LLM attention and show that while some heads align with relevance signals, this alignment quickly deteriorates as irrelevant text accumulates. These observations highlight the necessity of explicit block selection to preserve focus and efficiency. We present KeyB2 and KeyB2+, a scalable reranking framework that selects and aggregates the most relevant blocks together with each document's summarization, ensuring that both localized evidence and global semantics are captured before LLM scoring. KeyB2 family support flexible selectors: BM25, bi-encoder, and cross-encoder, and adapts decoder-only LLMs to compute fine-grained relevance scores on the selected content. Experiments demonstrate that abstract-augmented block selection consistently improves retrieval effectiveness over strong baselines while substantially lowering inference cost, achieving new SOTA result on TREC DL 2019 document track (0.738 for NDCG@10). This establishes KeyB2+ as a practical and effective solution for scalable long-document reranking with LLMs. - oai:arXiv.org:2411.06254v3 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Minghan Li, Eric Gaussier, Juntao Li, Guodong Zhou - - - Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models - https://arxiv.org/abs/2411.06272 - arXiv:2411.06272v2 Announce Type: replace -Abstract: As large language models (LLMs) increasingly permeate the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance. Existing financial benchmarks often suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation. To address these limitations, we introduce Golden Touchstone, a comprehensive bilingual benchmark for financial LLMs, encompassing eight core financial NLP tasks in both Chinese and English. Developed from extensive open-source data collection and industry-specific demands, this benchmark thoroughly assesses models' language understanding and generation capabilities. Through comparative analysis of major models such as GPT-4o, Llama3, FinGPT, and FinMA, we reveal their strengths and limitations in processing complex financial information. Additionally, we open-source Touchstone-GPT, a financial LLM trained through continual pre-training and instruction tuning, which demonstrates strong performance on the bilingual benchmark but still has limitations in specific tasks. This research provides a practical evaluation tool for financial LLMs and guides future development and optimization. The source code for Golden Touchstone and model weight of Touchstone-GPT have been made publicly available at https://github.com/IDEA-FinAI/Golden-Touchstone. - oai:arXiv.org:2411.06272v2 - cs.CL - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.18653/v1/2025.findings-emnlp.1227 - In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 22544-22560, Suzhou, China. Association for Computational Linguistics - Xiaojun Wu, Junxi Liu, Huanyi Su, Zhouchi Lin, Yiyan Qi, Chengjin Xu, Jiajun Su, Jiajie Zhong, Fuwei Wang, Saizhuo Wang, Fengrui Hua, Jia Li, Jian Guo - - - Optimal Virtual Model Control for Robotics: Design and Tuning of Passivity-Based Controllers - https://arxiv.org/abs/2411.06627 - arXiv:2411.06627v3 Announce Type: replace -Abstract: Passivity-based control is a cornerstone of control theory and an established design approach in robotics. Its strength is based on the passivity theorem, which provides a powerful interconnection framework for robotics. However, the design of passivity-based controllers and their optimal tuning remain challenging. We propose here an intuitive design approach for fully actuated robots, where the control action is determined by a `virtual-mechanism' as in classical virtual model control. The result is a robot whose controlled behavior can be understood in terms of physics. We achieve optimal tuning by applying algorithmic differentiation to ODE simulations of the rigid body dynamics. Overall, this leads to a flexible design and optimization approach: stability is proven by passivity of the virtual mechanism, while performance is obtained by optimization using algorithmic differentiation. - oai:arXiv.org:2411.06627v3 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Daniel Larby, Fulvio Forni - - - Rethinking Normalization Strategies and Convolutional Kernels for Multimodal Image Fusion - https://arxiv.org/abs/2411.10036 - arXiv:2411.10036v2 Announce Type: replace -Abstract: Multimodal image fusion (MMIF) integrates information from different modalities to obtain a comprehensive image, aiding downstream tasks. However, existing research focuses on complementary information fusion and training strategies, overlooking the critical role of underlying architectural components like normalization and convolution kernels. We reevaluate the UNet architecture for end-to-end MMIF, identifying that widely used batch normalization limits performance by smoothing crucial sparse features. To address this, we propose a hybrid of instance and group normalization to maintain sample independence and reinforce intrinsic feature correlations. Crucially, this strategy facilitates richer feature maps, enabling large kernel convolution to fully leverage its receptive field, enhancing detail preservation. Furthermore, the proposed multi-path adaptive fusion module dynamically calibrates features from varying scales and receptive fields, ensuring effective information transfer. Our method achieves SOTA objective performance on MSRS, M$^3$FD, TNO, and Harvard datasets, producing visually clearer salient objects and lesion areas. Notably, it improves MSRS segmentation mIoU by 8.1\% over the infrared image. This performance stems from a synergistic design of normalization and convolution kernels, which preserves critical sparse features. The code is available at https://github.com/HeDan-11/LKC-FUNet. - oai:arXiv.org:2411.10036v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dan He, Guofen Wang, Weisheng Li, Yucheng Shu, Wenbo Li, Lijian Yang, Yuping Huang, Feiyan Li - - - SeqProFT: Sequence-only Protein Property Prediction with LoRA Finetuning - https://arxiv.org/abs/2411.11530 - arXiv:2411.11530v2 Announce Type: replace -Abstract: Protein language models (PLMs) have demonstrated remarkable capabilities in learning relationships between protein sequences and functions. However, finetuning these large models requires substantial computational resources, often with suboptimal task-specific results. This study investigates how parameter-efficient finetuning via LoRA can enhance protein property prediction while significantly reducing computational demands. By applying LoRA to ESM-2 and ESM-C models of varying sizes and evaluating 10 diverse protein property prediction tasks, we demonstrate that smaller models with LoRA adaptation can match or exceed the performance of larger models without adaptation. Additionally, we integrate contact map information through a multi-head attention mechanism, improving model comprehension of structural features. Our systematic analysis reveals that LoRA finetuning enables faster convergence, better performance, and more efficient resource utilization, providing practical guidance for protein research applications in resource-constrained environments. The code is available at https://github.com/jiankliu/SeqProFT. - oai:arXiv.org:2411.11530v2 - cs.LG - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/TAI.2025.3636109 - IEEE Transactions on Artificial Intelligence, 2025 - Shuo Zhang, Jian K. Liu - - - Squeezy: Rapid VM Memory Reclamation for Serverless Functions - https://arxiv.org/abs/2411.12893 - arXiv:2411.12893v2 Announce Type: replace -Abstract: Resource elasticity is one of the key defining characteristics of the Function-as-a-Service (FaaS) serverless computing paradigm. While compute resources assigned to VM-sandboxed functions can be seamlessly adjusted on the fly, memory elasticity remains challenging. Hot(un)plugging memory resources suffers from long reclamation latencies and occupies valuable CPU resources. We identify the obliviousness of the OS memory manager to the hotplugged memory as the key issue hindering hot-unplug performance, and design Squeezy, a novel approach for fast and efficient VM memory hot(un)plug, targeting VM-sandboxed serverless functions. Our key insight is that by segregating hotplugged memory regions from regular VM memory, we are able to bound the lifetime of allocations within these regions thus enabling their fast and efficient reclamation. We implement Squeezy in Linux v6.6 as an extension to the OS memory manager. Our evaluation reveals that Squeezy is an order-of-magnitude faster than state-of-the-art, keeping tail latency bounded, when reclaiming VM memory, achieving sub-second reclamation of multiple GiBs of memory while serving realistic FaaS load. - oai:arXiv.org:2411.12893v2 - cs.OS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Orestis Lagkas Nikolos (National Technical University Of Athens), Chloe Alverti (University of Illinois Urbana-Champaign), Stratos Psomadakis (National Technical University Of Athens), Georgios Goumas (National Technical University Of Athens), Nectarios Koziris (National Technical University Of Athens) - - - Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods - https://arxiv.org/abs/2411.14711 - arXiv:2411.14711v2 Announce Type: replace -Abstract: This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes, primarily due to the nature of set-based pooling of the neighborhood aggregation scheme. Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models. Importantly, we observe that the denser the graph, the greater such the improvement. We attribute this to the characteristics of node embeddings, where the link state of each link sample could be encoded into the embeddings of nodes that are involved in the neighborhood aggregation of the two nodes in that link sample. In denser graphs, every node could have more opportunities to attend the neighborhood aggregation of other nodes and encode states of more link samples to its embedding, thus learning better node embeddings for link prediction. Lastly, we demonstrate that the insights gained from our research carry important implications in identifying the limitations of existing link prediction methods, which could guide the future development of more robust algorithms. - oai:arXiv.org:2411.14711v2 - cs.SI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shuming Liang, Yu Ding, Zhidong Li, Bin Liang, Siqi Zhang, Yang Wang, Fang Chen - - - A block-acoustic preconditioner for the elastic Helmholtz equation - https://arxiv.org/abs/2411.15897 - arXiv:2411.15897v2 Announce Type: replace -Abstract: We present a novel block-preconditioner for the elastic Helmholtz equation, based on a reduction to acoustic Helmholtz equations. Both versions of the Helmholtz equations are challenging numerically. The elastic Helmholtz equation is larger, as a system of PDEs, and harder to solve due to its more complicated physics. It was recently suggested that the elastic Helmholtz equation can be reformulated as a generalized saddle-point system, opening the door to the current development. Utilizing the approximate commutativity of the underlying differential operators, we suggest a block-triangular preconditioner whose diagonal blocks are acoustic Helmholtz operators. Thus, we enable the solution of the elastic version using virtually any existing solver for the acoustic version as a black-box. We prove a sufficient condition for the convergence of our method, that sheds light on the long questioned role of the commutator in the convergence of approximate commutator preconditioners. We show scalability of our preconditioner with respect to the Poisson ratio and with respect to the grid size. We compare our approach, combined with multigrid solve of each block, to a recent monolithic multigrid method for the elastic Helmholtz equation. The block-acoustic multigrid achieves a lower computational cost for various heterogeneous media, and a significantly lower memory consumption, compared to the monolithic approach. It results in a fast solution method for wave propagation problems in challenging heterogeneous media in 2D and 3D. - oai:arXiv.org:2411.15897v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Rachel Yovel, Eran Treister - - - E-Trojans: Ransomware, Tracking, DoS, and Data Leaks on Battery-powered Embedded Systems - https://arxiv.org/abs/2411.17184 - arXiv:2411.17184v3 Announce Type: replace -Abstract: Battery-powered embedded systems (BESs) have become ubiquitous. Their internals include a battery management system (BMS), a radio interface, and a motor controller. Despite their associated risk, there is little research on BES internal attack surfaces. To fill this gap, we present the first security and privacy assessment of e-scooters internals. We cover Xiaomi M365 (2016) and ES3 (2023) e-scooters and their interactions with Mi Home (their companion app). We extensively RE their internals and uncover four critical design vulnerabilities, including a remote code execution issue with their BMS. Based on our RE findings, we develop E-Trojans, four novel attacks targeting BES internals. The attacks can be conducted remotely or in wireless proximity. They have a widespread real-world impact as they violate the Xiaomi e-scooter ecosystem safety, security, availability, and privacy. For instance, one attack allows the extortion of money from a victim via a BMS undervoltage battery ransomware. A second one enables user tracking by fingerprinting the BES internals. With extra RE efforts, the attacks can be ported to other BES featuring similar vulnerabilities. We implement our attacks and RE findings in E-Trojans, a modular and low-cost toolkit to test BES internals. Our toolkit binary patches BMS firmware by adding malicious capabilities. It also implements our undervoltage battery ransomware in an Android app with a working backend. We successfully test our four attacks on M365 and ES3, empirically confirming their effectiveness and practicality. We propose four practical countermeasures to fix our attacks and improve the Xiaomi e-scooter ecosystem security and privacy. - oai:arXiv.org:2411.17184v3 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Marco Casagrande, Riccardo Cestaro, Eleonora Losiouk, Mauro Conti, Daniele Antonioli - - - TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba - https://arxiv.org/abs/2411.17473 - arXiv:2411.17473v2 Announce Type: replace -Abstract: Mamba has shown great potential for computer vision due to its linear complexity in modeling the global context with respect to the input length. However, existing lightweight Mamba-based backbones cannot demonstrate performance that matches Convolution or Transformer-based methods. By observing, we find that simply modifying the scanning path in the image domain is not conducive to fully exploiting the potential of vision Mamba. In this paper, we first perform comprehensive spectral and quantitative analyses, and verify that the Mamba block mainly models low-frequency information under Convolution-Mamba hybrid architecture. Based on the analyses, we introduce a novel Laplace mixer to decouple the features in terms of frequency and input only the low-frequency components into the Mamba block. In addition, considering the redundancy of the features and the different requirements for high-frequency details and low-frequency global information at different stages, we introduce a frequency ramp inception, i.e., gradually reduce the input dimensions of the high-frequency branches, so as to efficiently trade-off the high-frequency and low-frequency components at different layers. By integrating mobile-friendly convolution and efficient Laplace mixer, we build a series of tiny hybrid vision Mamba called TinyViM. The proposed TinyViM achieves impressive performance on several downstream tasks including image classification, semantic segmentation, object detection and instance segmentation. In particular, TinyViM outperforms Convolution, Transformer and Mamba-based models with similar scales, and the throughput is about 2-3 times higher than that of other Mamba-based models. Code is available at https://github.com/xwmaxwma/TinyViM. - oai:arXiv.org:2411.17473v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaowen Ma, Zhenliang Ni, Xinghao Chen - - - Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings - https://arxiv.org/abs/2411.18645 - arXiv:2411.18645v2 Announce Type: replace -Abstract: Inner interpretability is a promising field aiming to uncover the internal mechanisms of AI systems through scalable, automated methods. While significant research has been conducted on large language models, limited attention has been paid to applying inner interpretability to large-scale image tasks, focusing primarily on architectural and functional levels to visualize learned concepts. In this paper, we first present a conceptual framework that supports inner interpretability and multilevel analysis for large-scale image classification tasks. Specifically, we introduce the Bi-directional Interaction between Concept and Input Embeddings (Bi-ICE) module, which facilitates interpretability across the computational, algorithmic, and implementation levels. This module enhances transparency by generating predictions based on human-understandable concepts, quantifying their contributions, and localizing them within the inputs. Finally, we showcase enhanced transparency in image classification, measuring concept contributions, and pinpointing their locations within the inputs. Our approach highlights algorithmic interpretability by demonstrating the process of concept learning and its convergence. - oai:arXiv.org:2411.18645v2 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jinyung Hong, Yearim Kim, Keun Hee Park, Sangyu Han, Nojun Kwak, Theodore P. Pavlic - - - Twisted Convolutional Networks (TCNs): Enhancing Feature Interactions for Non-Spatial Data Classification - https://arxiv.org/abs/2412.00238 - arXiv:2412.00238v2 Announce Type: replace -Abstract: Twisted Convolutional Networks (TCNs) are proposed as a novel deep learning architecture for classifying one-dimensional data with arbitrary feature order and minimal spatial relationships. Unlike conventional Convolutional Neural Networks (CNNs) that rely on structured feature sequences, TCNs explicitly combine subsets of input features through theoretically grounded multiplicative and pairwise interaction mechanisms to create enriched representations. This feature combination strategy, formalized through polynomial feature expansions, captures high-order feature interactions that traditional convolutional approaches miss. We provide a comprehensive mathematical framework for TCNs, demonstrating how the twisted convolution operation generalizes standard convolutions while maintaining computational tractability. Through extensive experiments on five benchmark datasets from diverse domains (medical diagnostics, political science, synthetic data, chemometrics, and healthcare), we show that TCNs achieve statistically significant improvements over CNNs, Residual Networks (ResNet), Graph Neural Networks (GNNs), DeepSets, and Support Vector Machine (SVM). The performance gains are validated through statistical testing. TCNs also exhibit superior training stability and generalization capabilities, highlighting their robustness for non-spatial data classification tasks. - oai:arXiv.org:2412.00238v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Junbo Jacob Lian, Haoran Chen, Kaichen Ouyang, Yujun Zhang, Rui Zhong, Huiling Chen - - - Explaining Object Detectors via Collective Contribution of Pixels - https://arxiv.org/abs/2412.00666 - arXiv:2412.00666v2 Announce Type: replace -Abstract: Visual explanations for object detectors are crucial for enhancing their reliability. Object detectors identify and localize instances by assessing multiple visual features collectively. When generating explanations, overlooking these collective influences in detections may lead to missing compositional cues or capturing spurious correlations. However, existing methods typically focus solely on individual pixel contributions, neglecting the collective contribution of multiple pixels. To address this limitation, we propose a game-theoretic method based on Shapley values and interactions to explicitly capture both individual and collective pixel contributions. Our method provides explanations for both bounding box localization and class determination, highlighting regions crucial for detection. Extensive experiments demonstrate that the proposed method identifies important regions more accurately than state-of-the-art methods. The code will be publicly available soon. - oai:arXiv.org:2412.00666v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Toshinori Yamauchi, Hiroshi Kera, Kazuhiko Kawamoto - - - EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation - https://arxiv.org/abs/2412.01254 - arXiv:2412.01254v3 Announce Type: replace -Abstract: This paper aims to bring fine-grained expression control while maintaining high-fidelity identity in portrait generation. This is challenging due to the mutual interference between expression and identity: (i) fine expression control signals inevitably introduce appearance-related semantics (e.g., facial contours, and ratio), which impact the identity of the generated portrait; (ii) even coarse-grained expression control can cause facial changes that compromise identity, since they all act on the face. These limitations remain unaddressed by previous generation methods, which primarily rely on coarse control signals or two-stage inference that integrates portrait animation. Here, we introduce EmojiDiff, the first end-to-end solution that enables simultaneous control of extremely detailed expression (RGB-level) and high-fidelity identity in portrait generation. To address the above challenges, EmojiDiff adopts a two-stage scheme involving decoupled training and fine-tuning. For decoupled training, we innovate ID-irrelevant Data Iteration (IDI) to synthesize cross-identity expression pairs by dividing and optimizing the processes of maintaining expression and altering identity, thereby ensuring stable and high-quality data generation. Training the model with this data, we effectively disentangle fine expression features in the expression template from other extraneous information (e.g., identity, skin). Subsequently, we present ID-enhanced Contrast Alignment (ICA) for further fine-tuning. ICA achieves rapid reconstruction and joint supervision of identity and expression information, thus aligning identity representations of images with and without expression control. Experimental results demonstrate that our method remarkably outperforms counterparts, achieves precise expression control with highly maintained identity, and generalizes well to various diffusion models. - oai:arXiv.org:2412.01254v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Liangwei Jiang, Ruida Li, Zhifeng Zhang, Shuo Fang, Chenguang Ma - - - CTRAPS: CTAP Client Impersonation and API Confusion on FIDO2 - https://arxiv.org/abs/2412.02349 - arXiv:2412.02349v2 Announce Type: replace -Abstract: FIDO2 is the standard technology for single-factor and second-factor authentication. It is specified in an open standard, including the WebAuthn and CTAP application layer protocols. We focus on CTAP, which allows FIDO2 clients and hardware authenticators to communicate. No prior work has explored the CTAP Authenticator API, a critical protocol-level attack surface. We address this gap by presenting the first security and privacy evaluation of the CTAP Authenticator API. We uncover two classes of protocol-level attacks on CTAP that we call CTRAPS. The client impersonation (CI) attacks exploit the lack of client authentication to tamper with FIDO2 authenticators. They include zero-click attacks capable of deleting FIDO2 credentials, including passkeys, without user interaction. The API confusion (AC) attacks abuse the lack of protocol API enforcements and confound FIDO2 authenticators, clients, and unaware users into calling unwanted CTAP APIs while thinking they are calling legitimate ones. The presented eleven attacks are conducted either in proximity or remotely and are effective regardless of the underlying CTAP transport. We detail the eight vulnerabilities in the CTAP specification, enabling the CTRAPS attacks. Six are novel and include unauthenticated CTAP clients and trackable FIDO2 credentials. We release CTRAPS, an original toolkit, to analyze CTAP and conduct the CTRAPS attacks. We confirm the attacks practicality on a large scale by exploiting six popular authenticators, including a FIPS-certified one from Yubico, Feitian, SoloKeys, and Google, and ten widely used relying parties, such as Microsoft, Apple, GitHub, and Facebook. We present eight practical and backward-compliant countermeasures to fix the attacks and their root causes. We responsibly disclosed our findings to the FIDO alliance and the affected vendors. - oai:arXiv.org:2412.02349v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/EuroSP63326.2025.00063 - in 2025 IEEE 10th European Symposium on Security and Privacy (EuroS\&P), Venice, Italy, 2025, pp. 1034-1048 - Marco Casagrande, Daniele Antonioli - - - SAMCL: Empowering SAM to Continually Learn from Dynamic Domains with Extreme Storage Efficiency - https://arxiv.org/abs/2412.05012 - arXiv:2412.05012v2 Announce Type: replace -Abstract: Segment Anything Model (SAM) struggles in open-world scenarios with diverse domains. In such settings, naive fine-tuning with a well-designed learning module is inadequate and often causes catastrophic forgetting issue when learning incrementally. To address this issue, we propose a novel continual learning (CL) method for SAM, termed SAMCL. Rather than relying on a fixed learning module, our method decomposes incremental knowledge into separate modules and trains a selector to choose the appropriate one during inference. However, this intuitive design introduces two key challenges: ensuring effective module learning and selection, and managing storage as tasks accumulate. To tackle these, we introduce two components: AugModule and Module Selector. AugModule reduces the storage of the popular LoRA learning module by sharing parameters across layers while maintaining accuracy. It also employs heatmaps-generated from point prompts-to further enhance domain adaptation with minimal additional cost. Module Selector leverages the observation that SAM's embeddings can effectively distinguish domains, enabling high selection accuracy by training on low-consumed embeddings instead of raw images. Experiments show that SAMCL outperforms state-of-the-art methods, achieving only 0.19% forgetting and at least 2.5% gain on unseen domains. Each AugModule requires just 0.233 MB, reducing storage by at least 24.3% over other fine-tuning approaches. The buffer storage for Module Selector is further reduced by up to 256$\times$. - oai:arXiv.org:2412.05012v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zeqing Wang, Kangye Ji, Di Wang, Haibin Zhang, Fei Cheng - - - Charting the Shapes of Stories with Game Theory - https://arxiv.org/abs/2412.05747 - arXiv:2412.05747v2 Announce Type: replace -Abstract: Stories are records of our experiences and their analysis reveals insights into the nature of being human. Successful analyses are often interdisciplinary, leveraging mathematical tools to extract structure from stories and insights from structure. Historically, these tools have been restricted to one dimensional charts and dynamic social networks; however, modern AI offers the possibility of identifying more fully the plot structure, character incentives, and, importantly, counterfactual plot lines that the story could have taken but did not take. In this work, we use AI to model the structure of stories as game-theoretic objects, amenable to quantitative analysis. This allows us to not only interrogate each character's decision making, but also possibly peer into the original author's conception of the characters' world. We demonstrate our proposed technique on Shakespeare's famous Romeo and Juliet. We conclude with a discussion of how our analysis could be replicated in broader contexts, including real-life scenarios. - oai:arXiv.org:2412.05747v2 - cs.GT - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Constantinos Daskalakis, Ian Gemp, Yanchen Jiang, Renato Paes Leme, Christos Papadimitriou, Georgios Piliouras - - - Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation - https://arxiv.org/abs/2412.08519 - arXiv:2412.08519v3 Announce Type: replace -Abstract: The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating responses. However, due to differences in pre-training data and objectives, there is an inevitable gap between the documents ranked as relevant by the reranker and those required by the generator to support answering the query. To address this gap, we propose RADIO, a novel and practical preference alignment framework with RAtionale DIstillatiOn. Specifically, we first propose a rationale extraction method that leverages the reasoning capabilities of Large Language Models (LLMs) to extract the rationales necessary for answering the query. Subsequently, a rationale-based alignment process is designed to rerank the documents based on the extracted rationales, and fine-tune the reranker to align the preferences. We conduct extensive experiments on two tasks across three datasets to demonstrate the effectiveness of our approach compared to baseline methods. Our code is released online to ease reproduction. - oai:arXiv.org:2412.08519v3 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pengyue Jia, Derong Xu, Xiaopeng Li, Zhaocheng Du, Xiangyang Li, Yichao Wang, Yuhao Wang, Qidong Liu, Maolin Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao - - - MeshA*: Efficient Path Planning With Motion Primitives - https://arxiv.org/abs/2412.10320 - arXiv:2412.10320v2 Announce Type: replace -Abstract: We study a path planning problem where the possible move actions are represented as a finite set of motion primitives aligned with the grid representation of the environment. That is, each primitive corresponds to a short kinodynamically-feasible motion of an agent and is represented as a sequence of the swept cells of a grid. Typically, heuristic search, i.e. A*, is conducted over the lattice induced by these primitives (lattice-based planning) to find a path. However, due to the large branching factor, such search may be inefficient in practice. To this end, we suggest a novel technique rooted in the idea of searching over the grid cells (as in vanilla A*) simultaneously fitting the possible sequences of the motion primitives into these cells. The resultant algorithm, MeshA*, provably preserves the guarantees on completeness and optimality, on the one hand, and is shown to notably outperform conventional lattice-based planning (x1.5-x2 decrease in the runtime), on the other hand. - oai:arXiv.org:2412.10320v2 - cs.RO - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Marat Agranovskiy, Konstantin Yakovlev - - - Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation - https://arxiv.org/abs/2412.10339 - arXiv:2412.10339v2 Announce Type: replace -Abstract: Semantic segmentation suffers from significant performance degradation when the trained network is applied to a different domain. To address this issue, unsupervised domain adaptation (UDA) has been extensively studied. Despite the effectiveness of selftraining techniques in UDA, they still overlook the explicit modeling of domain-shared feature extraction. In this paper, we propose DiDA, an unsupervised domain bridging approach for semantic segmentation. DiDA consists of two key modules: (1) Degradation-based Intermediate Domain Construction, which creates continuous intermediate domains through simple image degradation operations to encourage learning domain-invariant features as domain differences gradually diminish; (2) Semantic Shift Compensation, which leverages a diffusion encoder to disentangle and compensate for semantic shift information with degraded timesteps, preserving discriminative representations in the intermediate domains. As a plug-and-play solution, DiDA supports various degradation operations and seamlessly integrates with existing UDA methods. Extensive experiments on multiple domain adaptive semantic segmentation benchmarks demonstrate that DiDA consistently achieves significant performance improvements across all settings. Code is available at https://github.com/Woof6/DiDA. - oai:arXiv.org:2412.10339v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wangkai Li, Rui Sun, Huayu Mai, Tianzhu Zhang - - - Transparent and Coherent Procedural Mistake Detection - https://arxiv.org/abs/2412.11927 - arXiv:2412.11927v4 Announce Type: replace -Abstract: Procedural mistake detection (PMD) is a challenging problem of classifying whether a human user (observed through egocentric video) has successfully executed a task (specified by a procedural text). Despite significant recent efforts, machine performance in the wild remains nonviable, and the reasoning processes underlying this performance are opaque. As such, we extend PMD to require generating visual self-dialog rationales to inform decisions. Given the impressive, mature image understanding capabilities observed in recent vision-and-language models (VLMs), we curate a suitable benchmark dataset for PMD based on individual frames. As our reformulation enables unprecedented transparency, we leverage a natural language inference (NLI) model to formulate two automated metrics for the coherence of generated rationales. We establish baselines for this reframed task, showing that VLMs struggle off-the-shelf, but with some trade-offs, their accuracy, coherence, and efficiency can be improved by incorporating these metrics into common inference and fine-tuning methods. Lastly, our multi-faceted metrics visualize common outcomes, highlighting areas for further improvement. - oai:arXiv.org:2412.11927v4 - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shane Storks, Itamar Bar-Yossef, Yayuan Li, Zheyuan Zhang, Jason J. Corso, Joyce Chai - - - Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration - https://arxiv.org/abs/2412.15701 - arXiv:2412.15701v5 Announce Type: replace -Abstract: While the advancement of large language models has spurred the development of AI agents to automate tasks, numerous use cases inherently require agents to collaborate with humans due to humans' latent preferences, domain expertise, or the need for control. To facilitate the study of human-agent collaboration, we introduce Collaborative Gym (Co-Gym), an open framework for developing and evaluating collaborative agents that engage in bidirectional communication with humans while interacting with task environments. We describe how the framework enables the implementation of new task environments and coordination between humans and agents through a flexible, non-turn-taking interaction paradigm, along with an evaluation suite that assesses both collaboration outcomes and processes. Our framework provides both a simulated condition with a reliable user simulator and a real-world condition with an interactive web application. Initial benchmark experiments across three representative tasks -- creating travel plans, writing related work sections, and analyzing tabular data -- demonstrate the benefits of human-agent collaboration: The best-performing collaborative agents consistently outperform their fully autonomous counterparts in task performance, achieving win rates of 86% in Travel Planning, 74% in Tabular Analysis, and 66% in Related Work when evaluated by real users. Despite these improvements, our evaluation reveals persistent limitations in current language models and agents, with communication and situational awareness failures observed in 65% and 40% of cases in the real condition, respectively. Released under the permissive MIT license, Co-Gym supports the addition of new task environments and can be used to develop collaborative agent applications, while its evaluation suite enables assessment and improvement of collaborative agents. - oai:arXiv.org:2412.15701v5 - cs.AI - cs.CL - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yijia Shao, Vinay Samuel, Yucheng Jiang, John Yang, Diyi Yang - - - Causal Interpretability for Adversarial Robustness: A Hybrid Generative Classification Approach - https://arxiv.org/abs/2412.20025 - arXiv:2412.20025v2 Announce Type: replace -Abstract: Deep learning-based discriminative classifiers, despite their remarkable success, remain vulnerable to adversarial examples that can mislead model predictions. While adversarial training can enhance robustness, it fails to address the intrinsic vulnerability stemming from the opaque nature of these black-box models. We present a deep ensemble model that combines discriminative features with generative models to achieve both high accuracy and adversarial robustness. Our approach integrates a bottom-level pre-trained discriminative network for feature extraction with a top-level generative classification network that models adversarial input distributions through a deep latent variable model. Using variational Bayes, our model achieves superior robustness against white-box adversarial attacks without adversarial training. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate our model's superior adversarial robustness. Through evaluations using counterfactual metrics and feature interaction-based metrics, we establish correlations between model interpretability and adversarial robustness. Additionally, preliminary results on Tiny-ImageNet validate our approach's scalability to more complex datasets, offering a practical solution for developing robust image classification models. - oai:arXiv.org:2412.20025v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chunheng Zhao, Pierluigi Pisu, Gurcan Comert, Negash Begashaw, Varghese Vaidyan, Nina Christine Hubig - - - CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering - https://arxiv.org/abs/2501.01371 - arXiv:2501.01371v2 Announce Type: replace -Abstract: Vision-Language Models (VLMs) demonstrate remarkable capabilities in visual understanding and reasoning, such as in Visual Question Answering (VQA), where the model is asked a question related to a visual input. Still, these models can make distinctly unnatural errors, for example, providing (wrong) answers to unanswerable VQA questions, such as questions asking about objects that do not appear in the image. To address this issue, we propose CLIP-UP: CLIP-based Unanswerable Problem detection, a novel lightweight method for equipping VLMs with the ability to withhold answers to unanswerable questions. CLIP-UP leverages CLIP-based similarity measures to extract question-image alignment information to detect unanswerability, requiring efficient training of only a few additional layers, while keeping the original VLMs' weights unchanged. Tested across several models, CLIP-UP achieves significant improvements on benchmarks assessing unanswerability in both multiple-choice and open-ended VQA, surpassing other methods, while preserving original performance on other tasks. - oai:arXiv.org:2501.01371v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ben Vardi, Oron Nir, Ariel Shamir - - - Inversely Learning Transferable Rewards via Abstracted States - https://arxiv.org/abs/2501.01669 - arXiv:2501.01669v3 Announce Type: replace -Abstract: Inverse reinforcement learning (IRL) has progressed significantly toward accurately learning the underlying rewards in both discrete and continuous domains from behavior data. The next advance is to learn {\em intrinsic} preferences in ways that produce useful behavior in settings or tasks which are different but aligned with the observed ones. In the context of robotic applications, this helps integrate robots into processing lines involving new tasks (with shared intrinsic preferences) without programming from scratch. We introduce a method to inversely learn an abstract reward function from behavior trajectories in two or more differing instances of a domain. The abstract reward function is then used to learn task behavior in another separate instance of the domain. This step offers evidence of its transferability and validates its correctness. We evaluate the method on trajectories in tasks from multiple domains in OpenAI's Gym testbed and AssistiveGym and show that the learned abstract reward functions can successfully learn task behaviors in instances of the respective domains, which have not been seen previously. - oai:arXiv.org:2501.01669v3 - cs.LG - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Yikang Gui, Prashant Doshi - - - Expectation-Maximization as the Engine of Scalable Medical Intelligence - https://arxiv.org/abs/2501.03410 - arXiv:2501.03410v2 Announce Type: replace -Abstract: Large, high-quality, annotated datasets are the foundation of medical AI research, but constructing even a small, moderate-quality, annotated dataset can take years of effort from multidisciplinary teams. Although active learning can prioritize what to annotate, scaling up still requires extensive manual efforts to revise the noisy annotations. We formulate this as a missing-data problem and develop ScaleMAI, a framework that unifies data annotation and model development co-evolution through an Expectation-Maximization (EM) process. In this iterative process, the AI model automatically identifies and corrects the mistakes in annotations (Expectation), while the refined annotated data retrain the model to improve accuracy (Maximization). In addition to the classical EM algorithm, ScaleMAI brings human experts into the loop to review annotations that cannot be adequately addressed by either Expectation or Maximization step (<5%). As a result, ScaleMAI progressively creates an annotated dataset of 47,315 CT scans (4.8x larger than the largest public dataset, PanTS) including 4,163,720 per-voxel annotations for benign/malignant tumors and 88 anatomical structures. ScaleMAI iteratively trains a model that exceeds human expert performance in tumor diagnosis (+7%), and outperforms models developed from smaller, moderate-quality datasets, with statistically significant gains in tumor detection (+10%) and segmentation (+14%) on two prestigious benchmarks. - oai:arXiv.org:2501.03410v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Wenxuan Li, Pedro R. A. S. Bassi, Tianyu Lin, Yu-Cheng Chou, Jakob Wasserthal, Xinze Zhou, Qi Chen, Fabian Isensee, Yannick Kirchhoff, Maximilian Rokuss, Saikat Roy, Constantin Ulrich, Klaus Maier-Hein, Szymon P{\l}otka, Xiaoxi Chen, Kang Wang, Yang Yang, Daguang Xu, Kai Ding, Yucheng Tang, Alan L. Yuille, Zongwei Zhou - - - Seven kinds of equivalent models for generalized coalition logics - https://arxiv.org/abs/2501.05466 - arXiv:2501.05466v3 Announce Type: replace -Abstract: Coalition Logic is an important logic in logical research on strategic reasoning. In two recent papers, Li and Ju argued that generally, concurrent game models, models of Coalition Logic, have three too strong assumptions: seriality, independence of agents, and determinism. They presented eight coalition logics based on eight classes of general concurrent game models, determined by which of the three assumptions are met. In this paper, we show that each of the eight sets of valid formulas of the eight logics is determined by six other kinds of models, that is, single-coalition-first action models, single-coalition-first actual neighborhood models, clear grand-coalition-first action models, clear single-coalition-first actual neighborhood models, tree-like grand-coalition-first action models, and tree-like single-coalition-first actual neighborhood models. - oai:arXiv.org:2501.05466v3 - cs.LO - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zixuan Chen, Fengkui Ju - - - Concerns and Values in Human-Robot Interactions: A Focus on Social Robotics - https://arxiv.org/abs/2501.05628 - arXiv:2501.05628v2 Announce Type: replace -Abstract: Robots, as AI with physical instantiation, inhabit our social and physical world, where their actions have both social and physical consequences, posing challenges for researchers when designing social robots. This study starts with a scoping review to identify discussions and potential concerns arising from interactions with robotic systems in the context of healthcare, education, and private homes. Two focus groups of technology ethics experts then validated a comprehensive list of key topics and values in human-robot interaction (HRI) literature in these contexts. These insights were integrated into the HRI Value Compass web tool, to help HRI researchers identify these values in robot design. The tool was evaluated in a pilot study. This work benefits the HRI community by highlighting key concerns in human-robot interactions and providing an instrument to help researchers design robots that align with human values, ensuring future robotic systems adhere to these values in social applications. - oai:arXiv.org:2501.05628v2 - cs.RO - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Giulio Antonio Abbo, Tony Belpaeme, Micol Spitale - - - PowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models - https://arxiv.org/abs/2501.07639 - arXiv:2501.07639v2 Announce Type: replace -Abstract: Efficiently solving Optimal Power Flow (OPF) problems in power systems is crucial for operational planning and grid management. There is a growing need for scalable algorithms capable of handling the increasing variability, constraints, and uncertainties in modern power networks while providing accurate and fast solutions. To address this, machine learning techniques, particularly Graph Neural Networks (GNNs) have emerged as promising approaches. This letter introduces PowerGraph-LLM, the first framework explicitly designed for solving OPF problems using Large Language Models (LLMs). The proposed approach combines graph and tabular representations of power grids to effectively query LLMs, capturing the complex relationships and constraints in power systems. A new implementation of in-context learning and fine-tuning protocols for LLMs is introduced, tailored specifically for the OPF problem. PowerGraph-LLM demonstrates reliable performances using off-the-shelf LLM. Our study reveals the impact of LLM architecture, size, and fine-tuning and demonstrates our framework's ability to handle realistic grid components and constraints. - oai:arXiv.org:2501.07639v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/TPWRS.2025.3596774 - Fabien Bernier, Jun Cao, Maxime Cordy, Salah Ghamizi - - - Taint Analysis for Graph APIs Focusing on Broken Access Control - https://arxiv.org/abs/2501.08947 - arXiv:2501.08947v3 Announce Type: replace -Abstract: We present the first systematic approach to static and dynamic taint analysis for Graph APIs focusing on broken access control. The approach comprises the following. We taint nodes of the Graph API if they represent data requiring specific privileges in order to be retrieved or manipulated, and identify API calls which are related to sources and sinks. Then, we statically analyze whether a tainted information flow between API source and sink calls occurs. To this end, we model the API calls using graph transformation rules. We subsequently use Critical Pair Analysis to automatically analyze potential dependencies between rules representing source calls and rules representing sink calls. We distinguish direct from indirect tainted information flow and argue under which conditions the Critical Pair Analysis is able to detect not only direct, but also indirect tainted flow. The static taint analysis (i) identifies flows that need to be further reviewed, since tainted nodes may be created by an API call and used or manipulated by another API call later without having the necessary privileges, and (ii) can be used to systematically design dynamic security tests for broken access control. The dynamic taint analysis checks if potential broken access control risks detected during the static taint analysis really occur. We apply the approach to a part of the GitHub GraphQL API. The application illustrates that our analysis supports the detection of two types of broken access control systematically: the case where users of the API may not be able to access or manipulate information, although they should be able to do so; and the case where users (or attackers) of the API may be able to access/manipulate information that they should not. - oai:arXiv.org:2501.08947v3 - cs.CR - cs.LO - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Leen Lambers, Lucas Sakizloglou, Taisiya Khakharova, Fernando Orejas - - - It's complicated. The relationship of algorithmic fairness and non-discrimination regulations for high-risk systems in the EU AI Act - https://arxiv.org/abs/2501.12962 - arXiv:2501.12962v4 Announce Type: replace -Abstract: What constitutes a fair decision? This question is not only difficult for humans but becomes more challenging when Artificial Intelligence (AI) models are used. In light of discriminatory algorithmic behaviors, the EU has recently passed the AI Act, which mandates specific rules for high-risk systems, incorporating both traditional legal non-discrimination regulations and machine learning based algorithmic fairness concepts. This paper aims to bridge these two different concepts in the AI Act through: First, a necessary high-level introduction of both concepts targeting legal and computer science-oriented scholars, and second, an in-depth analysis of the AI Act's relationship between legal non-discrimination regulations and algorithmic fairness. Our analysis reveals three key findings: (1.) Most non-discrimination regulations target only high-risk AI systems. (2.) The regulation of high-risk systems encompasses both data input requirements and output monitoring, though these regulations are partly inconsistent and raise questions of computational feasibility. (3.) Finally, we consider the possible (future) interaction of classical EU non-discrimination law and the AI Act regulations. We recommend developing more specific auditing and testing methodologies for AI systems. This paper aims to serve as a foundation for future interdisciplinary collaboration between legal scholars and computer science-oriented machine learning researchers studying discrimination in AI systems. - oai:arXiv.org:2501.12962v4 - cs.LG - cs.AI - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kristof Meding - - - Online-BLS: An Accurate and Efficient Online Broad Learning System for Data Stream Classification - https://arxiv.org/abs/2501.16932 - arXiv:2501.16932v2 Announce Type: replace -Abstract: The state-of-the-art online learning models generally conduct a single online gradient descent when a new sample arrives and thus suffer from suboptimal model weights. To this end, we introduce an online broad learning system framework with closed-form solutions for each online update. Different from employing existing incremental broad learning algorithms for online learning tasks, which tend to incur degraded accuracy and expensive online update overhead, we design an effective weight estimation algorithm and an efficient online updating strategy to remedy the above two deficiencies, respectively. Specifically, an effective weight estimation algorithm is first developed by replacing notorious matrix inverse operations with Cholesky decomposition and forward-backward substitution to improve model accuracy. Second, we devise an efficient online updating strategy that dramatically reduces online update time. Theoretical analysis exhibits the splendid error bound and low time complexity of our model. The most popular test-then-training evaluation experiments on various real-world datasets prove its superiority and efficiency. Furthermore, our framework is naturally extended to data stream scenarios with concept drift and exceeds state-of-the-art baselines. - oai:arXiv.org:2501.16932v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Chunyu Lei, Guang-Ze Chen, C. L. Philip Chen, Tong Zhang - - - Network Oblivious Transfer via Noisy Channels: Limits and Capacities - https://arxiv.org/abs/2501.17021 - arXiv:2501.17021v3 Announce Type: replace -Abstract: In this paper, we aim to study the information-theoretical limits of oblivious transfer. This work also investigates the problem of oblivious transfer over a noisy multiple access channel involving two non-colluding senders and a single receiver. The channel model is characterized by correlations among the parties, with the parties assumed to be either honest-but-curious or, in the receiver's case, potentially malicious. At first, we study the information-theoretical limits of oblivious transfer between two parties and extend it to the multiple access channel model. We propose a multiparty protocol for honest-but-curious parties where the general multiple access channel is reduced to a certain correlation. In scenarios where the receiver is malicious, the protocol achieves an achievable rate region. - oai:arXiv.org:2501.17021v3 - cs.IT - cs.CR - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hadi Aghaee, Bahareh Akhbari, Christian Deppe - - - CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering - https://arxiv.org/abs/2501.17792 - arXiv:2501.17792v3 Announce Type: replace -Abstract: We present CrowdSplat, a novel approach that leverages 3D Gaussian Splatting for real-time, high-quality crowd rendering. Our method utilizes 3D Gaussian functions to represent animated human characters in diverse poses and outfits, which are extracted from monocular videos. We integrate Level of Detail (LoD) rendering to optimize computational efficiency and quality. The CrowdSplat framework consists of two stages: (1) avatar reconstruction and (2) crowd synthesis. The framework is also optimized for GPU memory usage to enhance scalability. Quantitative and qualitative evaluations show that CrowdSplat achieves good levels of rendering quality, memory efficiency, and computational performance. Through the.se experiments, we demonstrate that CrowdSplat is a viable solution for dynamic, realistic crowd simulation in real-time applications. - oai:arXiv.org:2501.17792v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xiaohan Sun, Yinghan Xu, John Dingliana, Carol O'Sullivan - - - VLM-Assisted Continual learning for Visual Question Answering in Self-Driving - https://arxiv.org/abs/2502.00843 - arXiv:2502.00843v2 Announce Type: replace -Abstract: In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in enabling the system to understand and reason about its surroundings. However, traditional models often struggle with catastrophic forgetting when sequentially exposed to new driving tasks, such as perception, prediction, and planning, each requiring different forms of knowledge. To address this challenge, we present a novel continual learning framework that combines VLMs with selective memory replay and knowledge distillation, reinforced by task-specific projection layer regularization. The knowledge distillation allows a previously trained model to act as a "teacher" to guide the model through subsequent tasks, minimizing forgetting. Meanwhile, task-specific projection layers calculate the loss based on the divergence of feature representations, ensuring continuity in learning and reducing the shift between tasks. Evaluated on the DriveLM dataset, our framework shows substantial performance improvements, with gains ranging from 20.11% to 35.16% across various metrics. These results highlight the effectiveness of combining continual learning with VLMs in enhancing the resilience and reliability of VQA systems in autonomous driving. We will release our source code. - oai:arXiv.org:2502.00843v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuxin Lin, Mengshi Qi, Liang Liu, Huadong Ma - - - SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection - https://arxiv.org/abs/2502.01445 - arXiv:2502.01445v3 Announce Type: replace -Abstract: Defect detection in fabrics is critical for quality control, yet existing methods often struggle with complex backgrounds and shape-specific defects. In this paper, we propose an improved fabric defect detection model based on YOLOv11. To enhance the detection of strip defects, we introduce a Strip Perception Module (SPM) that improves feature capture through multi-scale convolution. We further enhance the spatial pyramid pooling fast (SPPF) by integrating a squeeze-and-excitation mechanism, resulting in the SE-SPPF module, which better integrates spatial and channel information for more effective defect feature extraction. Additionally, we propose a novel focal enhanced complete intersection over union (FECIoU) metric with adaptive weights, addressing scale differences and class imbalance by adjusting the weights of hard-to-detect instances through focal loss. Experimental results demonstrate that our model achieves a 0.8-8.1% improvement in mean average precision (mAP) on the Tianchi dataset and a 1.6-13.2% improvement on our custom dataset, outperforming other state-of-the-art methods. - oai:arXiv.org:2502.01445v3 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Peizhe Zhao, Shunbo Jia - - - Flatten Graphs as Sequences: Transformers are Scalable Graph Generators - https://arxiv.org/abs/2502.02216 - arXiv:2502.02216v3 Announce Type: replace -Abstract: We introduce AutoGraph, a scalable autoregressive model for attributed graph generation using decoder-only transformers. By flattening graphs into random sequences of tokens through a reversible process, AutoGraph enables modeling graphs as sequences without relying on additional node features that are expensive to compute, in contrast to diffusion-based approaches. This results in sampling complexity and sequence lengths that scale optimally linearly with the number of edges, making it scalable and efficient for large, sparse graphs. A key success factor of AutoGraph is that its sequence prefixes represent induced subgraphs, creating a direct link to sub-sentences in language modeling. Empirically, AutoGraph achieves state-of-the-art performance on synthetic and molecular benchmarks, with up to 100x faster generation and 3x faster training than leading diffusion models. It also supports substructure-conditioned generation without fine-tuning and shows promising transferability, bridging language modeling and graph generation to lay the groundwork for graph foundation models. Our code is available at https://github.com/BorgwardtLab/AutoGraph. - oai:arXiv.org:2502.02216v3 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dexiong Chen, Markus Krimmel, Karsten Borgwardt - - - EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization - https://arxiv.org/abs/2502.02493 - arXiv:2502.02493v2 Announce Type: replace -Abstract: Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU systems, inference latency can be further reduced through tensor parallelism (TP), while the optimal TP size of the draft model is typically smaller than that of the base model, leading to GPU idling during the drafting stage. We observe that such inefficiency stems from the sequential execution of layers, which is seemingly natural but actually unnecessary. Therefore, we propose EasySpec, a layer-parallel speculation strategy that optimizes the efficiency of multi-GPU utilization. EasySpec breaks the inter-layer data dependencies in the draft model, enabling multiple layers to run simultaneously across multiple devices as 'fuzzy' speculation. After each drafting-and-verification iteration, the draft model's key-value cache is calibrated in a single forward pass, preventing long-term fuzzy-error accumulation at minimal additional latency. EasySpec is a training-free and plug-in method. We evaluated EasySpec on several mainstream open-source LLMs, using smaller versions of models from the same series as drafters. The results demonstrate that EasySpec can achieve a peak speedup of 4.17x compared to vanilla decoding, while preserving the original distributions of the base LLMs. Specifically, the drafting stage can be accelerated by up to 1.62x with a maximum speculation accuracy drop of only 7%. The code is available at https://github.com/Yize-Wu/EasySpec. - oai:arXiv.org:2502.02493v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yize Wu, Ke Gao, Ling Li, Yanjun Wu - - - Stein Discrepancy for Unsupervised Domain Adaptation - https://arxiv.org/abs/2502.03587 - arXiv:2502.03587v4 Announce Type: replace -Abstract: Unsupervised domain adaptation (UDA) aims to improve model performance on an unlabeled target domain using a related, labeled source domain. A common approach aligns source and target feature distributions by minimizing a distance between them, often using symmetric measures such as maximum mean discrepancy (MMD). However, these methods struggle when target data is scarce. We propose a novel UDA framework that leverages Stein discrepancy, an asymmetric measure that depends on the target distribution only through its score function, making it particularly suitable for low-data target regimes. Our proposed method has kernelized and adversarial forms and supports flexible modeling of the target distribution via Gaussian, GMM, or VAE models. We derive a generalization bound on the target error and a convergence rate for the empirical Stein discrepancy in the two-sample setting. Empirically, our method consistently outperforms prior UDA approaches under limited target data across multiple benchmarks. - oai:arXiv.org:2502.03587v4 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Anneke von Seeger, Dongmian Zou, Gilad Lerman - - - Novel Lower Bounds on M/G/k Scheduling - https://arxiv.org/abs/2502.08804 - arXiv:2502.08804v3 Announce Type: replace -Abstract: In queueing systems, effective scheduling algorithms are essential for optimizing performance. Optimal scheduling for the M/G/k queue has been explored in the heavy traffic limit, but much remains unknown in the intermediate load regime. - In this paper, we give the first framework for proving nontrivial lower bounds on the mean response time of the M/G/k system under arbitrary scheduling policies. Our bounds tighten previous naive lower bounds by more than 60\%, yielding significant improvements particularly for moderate loads. Key to our approach is a new variable-speed queue, which more accurately captures the work completion behavior of multiserver systems. To analyze the expected work of this queue, we develop a novel manner of employing the drift method or the BAR approach, by developing test functions via the solutions to a differential equation. - We validate our results numerically for systems with up to 5 servers and a range of job size distributions. - oai:arXiv.org:2502.08804v3 - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ziyuan Wang, Izzy Grosof - - - Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluation - https://arxiv.org/abs/2502.08943 - arXiv:2502.08943v3 Announce Type: replace -Abstract: Large language models (LLMs) have demonstrated significant utility in real-world applications, exhibiting impressive capabilities in natural language processing and understanding. Benchmark evaluations are crucial for assessing the capabilities of LLMs as they can provide a comprehensive assessment of their strengths and weaknesses. However, current evaluation methods often overlook the inherent randomness of LLMs by employing deterministic generation strategies or relying on a single random sample, resulting in unaccounted sampling variance and unreliable benchmark score estimates. In this paper, we propose a hierarchical statistical model that provides a more comprehensive representation of the benchmarking process by incorporating both benchmark characteristics and LLM randomness. We show that leveraging multiple generations improves the accuracy of estimating the benchmark score and reduces variance. Multiple generations also allow us to define $\mathbb P\left(\text{correct}\right)$, a prompt-level difficulty score based on correct ratios, providing fine-grained insights into individual prompts. Additionally, we create a data map that visualizes difficulty and semantics of prompts, enabling error detection and quality control in benchmark construction. - oai:arXiv.org:2502.08943v3 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wenbo Zhang, Hengrui Cai, Wenyu Chen - - - Countering Overfitting with Counterfactual Examples - https://arxiv.org/abs/2502.09193 - arXiv:2502.09193v2 Announce Type: replace -Abstract: Overfitting is a well-known issue in machine learning that occurs when a model struggles to generalize its predictions to new, unseen data beyond the scope of its training set. Traditional techniques to mitigate overfitting include early stopping, data augmentation, and regularization. In this work, we demonstrate that the degree of overfitting of a trained model is correlated with the ability to generate counterfactual examples. The higher the overfitting, the easier it will be to find a valid counterfactual example for a randomly chosen input data point. Therefore, we introduce CF-Reg, a novel regularization term in the training loss that controls overfitting by ensuring enough margin between each instance and its corresponding counterfactual. Experiments conducted across multiple datasets and models show that our counterfactual regularizer generally outperforms existing regularization techniques. - oai:arXiv.org:2502.09193v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Flavio Giorgi, Fabiano Veglianti, Fabrizio Silvestri, Gabriele Tolomei - - - FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation - https://arxiv.org/abs/2502.09274 - arXiv:2502.09274v2 Announce Type: replace -Abstract: 3D scene understanding is a critical yet challenging task in autonomous driving due to the irregularity and sparsity of LiDAR data, as well as the computational demands of processing large-scale point clouds. Recent methods leverage range-view representations to enhance efficiency, but they often adopt higher azimuth resolutions to mitigate information loss during spherical projection, where only the closest point is retained for each 2D grid. However, processing wide panoramic range-view images remains inefficient and may introduce additional distortions. Our empirical analysis shows that training with multiple range images, obtained from splitting the full point cloud, improves both segmentation accuracy and computational efficiency. However, this approach also poses new challenges of exacerbated class imbalance and increase in projection artifacts. To address these, we introduce FLARES, a novel training paradigm that incorporates two tailored data augmentation techniques and a specialized post-processing method designed for multi-range settings. Extensive experiments demonstrate that FLARES is highly generalizable across different architectures, yielding 2.1%~7.9% mIoU improvements on SemanticKITTI and 1.8%~3.9% mIoU on nuScenes, while delivering over 40% speed-up in inference. - oai:arXiv.org:2502.09274v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Bin Yang, Alexandru Paul Condurache - - - Exploring the Potential of Encoder-free Architectures in 3D LMMs - https://arxiv.org/abs/2502.09620 - arXiv:2502.09620v4 Announce Type: replace -Abstract: Encoder-free architectures have been preliminarily explored in the 2D Large Multimodal Models (LMMs), yet it remains an open question whether they can be effectively applied to 3D understanding scenarios. In this paper, we present the first comprehensive investigation into the potential of encoder-free architectures to alleviate the challenges of encoder-based 3D LMMs. These long-standing challenges include the failure to adapt to varying point cloud resolutions during inference and the point features from the encoder not meeting the semantic needs of Large Language Models (LLMs). We identify key aspects for 3D LMMs to remove the pre-trained encoder and enable the LLM to assume the role of the 3D encoder: 1) We propose the LLM-embedded Semantic Encoding strategy in the pre-training stage, exploring the effects of various point cloud self-supervised losses. And we present the Hybrid Semantic Loss to extract high-level semantics. 2) We introduce the Hierarchical Geometry Aggregation strategy in the instruction tuning stage. This incorporates inductive bias into the LLM layers to focus on the local details of the point clouds. To the end, we present the first Encoder-free 3D LMM, ENEL. Our 7B model rivals the state-of-the-art model, PointLLM-PiSA-13B, achieving 57.91%, 61.0%, and 55.20% on the classification, captioning, and VQA tasks, respectively. Our results show that the encoder-free architecture is highly promising for replacing encoder-based architectures in the field of 3D understanding. The code is released at https://github.com/Ivan-Tang-3D/ENEL - oai:arXiv.org:2502.09620v4 - cs.CV - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Yiwen Tang, Zoey Guo, Zhuhao Wang, Ray Zhang, Qizhi Chen, Junli Liu, Delin Qu, Zhigang Wang, Dong Wang, Bin Zhao, Xuelong Li - - - ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond - https://arxiv.org/abs/2502.12845 - arXiv:2502.12845v5 Announce Type: replace -Abstract: Molecular design involves an enormous and irregular search space, where traditional optimizers such as Bayesian optimization, genetic algorithms, and generative models struggle to leverage expert knowledge or handle complex feedback. Recently, LLMs have been used as optimizers, achieving promising results on benchmarks such as PMO. However, existing approaches rely only on prompting or extra training, without mechanisms to handle complex feedback or maintain scalable memory. In particular, the common practice of appending or summarizing experiences at every query leads to redundancy, degraded exploration, and ultimately poor final outcomes under large-scale iterative search. We introduce ExLLM (Experience-Enhanced LLM optimization), an LLM-as-optimizer framework with three components: (1) a compact, evolving experience snippet tailored to large discrete spaces that distills non-redundant cues and improves convergence at low cost; (2) a simple yet effective k-offspring scheme that widens exploration per call and reduces orchestration cost; and (3) a lightweight feedback adapter that normalizes objectives for selection while formatting constraints and expert hints for iteration. ExLLM sets new state-of-the-art results on PMO and generalizes strongly in our setup, it sets records on circle packing and stellarator design, and yields consistent gains across additional domains requiring only a task-description template and evaluation functions to transfer. - oai:arXiv.org:2502.12845v5 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Nian Ran, Yue Wang, Xiaoyuan Zhang, Zhongzheng Li, Qingsong Ran, Wenhao Li, Richard Allmendinger - - - DFDT: Dynamic Fast Decision Tree for IoT Data Stream Mining on Edge Devices - https://arxiv.org/abs/2502.14011 - arXiv:2502.14011v2 Announce Type: replace -Abstract: The Internet of Things generates massive data streams, with edge computing emerging as a key enabler for online IoT applications and 5G networks. Edge solutions facilitate real-time machine learning inference, but also require continuous adaptation to concept drifts. While extensions of the Very Fast Decision Tree (VFDT) remain state-of-the-art for tabular stream mining, their unregulated growth limits efficiency, particularly in ensemble settings where post-pruning at the individual tree level is seldom applied. This paper presents DFDT, a novel memory-constrained algorithm for online learning. DFDT employs activity-aware pre-pruning, dynamically adjusting splitting criteria based on leaf node activity: low-activity nodes are deactivated to conserve resources, moderately active nodes split under stricter conditions, and highly active nodes leverage a skipping mechanism for accelerated growth. Additionally, adaptive grace periods and tie thresholds allow DFDT to modulate splitting decisions based on observed data variability, enhancing the accuracy-memory-runtime trade-off while minimizing the need for hyperparameter tuning. An ablation study reveals three DFDT variants suited to different resource profiles. Fully compatible with existing ensemble frameworks, DFDT provides a drop-in alternative to standard VFDT-based learners. - oai:arXiv.org:2502.14011v2 - cs.LG - cs.AI - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Afonso Louren\c{c}o, Jo\~ao Rodrigo, Jo\~ao Gama, Goreti Marreiros - - - Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment - https://arxiv.org/abs/2502.14354 - arXiv:2502.14354v3 Announce Type: replace -Abstract: Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from widespread preference conflicts in the data, where different objectives favor different responses. This results in conflicting optimization directions, hindering the optimization on the Pareto Front. To address this, we propose to construct Pareto-optimal responses to resolve preference conflicts. To efficiently obtain and utilize such responses, we propose a self-improving DPO framework that enables LLMs to self-generate and select Pareto-optimal responses for self-supervised preference alignment. Extensive experiments on two datasets demonstrate the superior Pareto Front achieved by our framework compared to various baselines. Code is available at https://github.com/zyttt-coder/SIPO. - oai:arXiv.org:2502.14354v3 - cs.LG - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/publicdomain/zero/1.0/ - Moxin Li, Yuantao Zhang, Wenjie Wang, Wentao Shi, Zhuo Liu, Fuli Feng, Tat-Seng Chua - - - On the $H$-property for Step-graphons: The Residual Case - https://arxiv.org/abs/2502.14853 - arXiv:2502.14853v3 Announce Type: replace -Abstract: We investigate the $H$-property for step-graphons. Specifically, we sample graphs $G_n$ on $n$ nodes from a step-graphon and evaluate the probability that $G_n$ has a Hamiltonian decomposition in the asymptotic regime as $n\to\infty$. It has been shown that for almost all step-graphons, this probability converges to either zero or one. We focus in this paper on the residual case where the zero-one law does not apply. We show that the limit of the probability still exists and provide an explicit expression of it. We present a complete proof of the result and validate it through numerical studies. - oai:arXiv.org:2502.14853v3 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wanting Gao, Xudong Chen - - - Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers - https://arxiv.org/abs/2502.15021 - arXiv:2502.15021v3 Announce Type: replace -Abstract: ViTs are general and accurate, and address many tasks, but ViTs are slow, and are not always practical when efficiency is key. Existing methods for faster ViTs design hybrid non-ViT architectures, losing generality, or shrink their tokens, sacrificing accuracy. While many non-ViT architectures are both fast and accurate, they cannot flexibly process other input shapes, pre-train by SOTA self-supervised learning, reduce computation by dropping tokens, and more like ViTs can. We make ViTs faster by reducing patch token width while increasing global token width by adding a new Jumbo token. Our wider Jumbo token is processed by its own wider FFN to increase model capacity. Yet our Jumbo FFN is efficient: it processes a single token, for speed, and its parameters are shared across all layers, for memory. Crucially, our Jumbo is attention-only and non-hierarchical, like a plain ViT, so it is simple, scalable, flexible, and compatible with ViT methods new and old. Jumbo improves over ViT baselines with Registers from Nano to Large scales while maintaining speed/throughput on ImageNet-1K (0.1-13%). Jumbo also improves MAE pre-training (4.9% linear probing on ImageNet-1K), test-time adaptation (5.2% on ImageNet-C), and time series modeling. Our Jumbo models even achieve better speed-accuracy trade-offs than specialized non-ViT compute-efficient models, while maintaining plain-ViT compatibility for practicality. Code and weights available: https://github.com/antofuller/jumbo - oai:arXiv.org:2502.15021v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Anthony Fuller, Yousef Yassin, Daniel G. Kyrollos, Evan Shelhamer, James R. Green - - - A Survey on Industrial Anomalies Synthesis - https://arxiv.org/abs/2502.16412 - arXiv:2502.16412v2 Announce Type: replace -Abstract: This paper comprehensively reviews anomaly synthesis methodologies. Existing surveys focus on limited techniques, missing an overall field view and understanding method interconnections. In contrast, our study offers a unified review, covering about 40 representative methods across Hand-crafted, Distribution-hypothesis-based, Generative models (GM)-based, and Vision-language models (VLM)-based synthesis. We introduce the first industrial anomaly synthesis (IAS) taxonomy. Prior works lack formal classification or use simplistic taxonomies, hampering structured comparisons and trend identification. Our taxonomy provides a fine-grained framework reflecting methodological progress and practical implications, grounding future research. Furthermore, we explore cross-modality synthesis and large-scale VLM. Previous surveys overlooked multimodal data and VLM in anomaly synthesis, limiting insights into their advantages. Our survey analyzes their integration, benefits, challenges, and prospects, offering a roadmap to boost IAS with multimodal learning. More resources are available at https://github.com/M-3LAB/awesome-anomaly-synthesis. - oai:arXiv.org:2502.16412v2 - cs.CV - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yanshu Wang, Xichen Xu, Jiaqi Liu, Xiaoning Lei, Guoyang Xie, Guannan Jiang, Zhichao Lu - - - Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments - https://arxiv.org/abs/2502.16611 - arXiv:2502.16611v3 Announce Type: replace -Abstract: Target speaker extraction focuses on isolating a specific speaker's voice from an audio mixture containing multiple speakers. To provide information about the target speaker's identity, prior works have utilized clean audio samples as conditioning inputs. However, such clean audio examples are not always readily available. For instance, obtaining a clean recording of a stranger's voice at a cocktail party without leaving the noisy environment is generally infeasible. Limited prior research has explored extracting the target speaker's characteristics from noisy enrollments, which may contain overlapping speech from interfering speakers. In this work, we explore a novel enrollment strategy that encodes target speaker information from the noisy enrollment by comparing segments where the target speaker is talking (Positive Enrollments) with segments where the target speaker is silent (Negative Enrollments). Experiments show the effectiveness of our model architecture, which achieves over 2.1 dB higher SI-SNRi compared to prior works in extracting the monaural speech from the mixture of two speakers. Additionally, the proposed two-stage training strategy accelerates convergence, reducing the number of optimization steps required to reach 3 dB SNR by 60%. Overall, our method achieves state-of-the-art performance in the monaural target speaker extraction conditioned on noisy enrollments. Our implementation is available at https://github.com/xu-shitong/TSE-through-Positive-Negative-Enroll . - oai:arXiv.org:2502.16611v3 - cs.SD - cs.AI - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shitong Xu, Yiyuan Yang, Niki Trigoni, Andrew Markham - - - Global-Decision-Focused Neural ODEs for Proactive Grid Resilience Management - https://arxiv.org/abs/2502.18321 - arXiv:2502.18321v3 Announce Type: replace -Abstract: Extreme hazard events such as wildfires and hurricanes increasingly threaten power systems, causing widespread outages and disrupting critical services. Recently, predict-then-optimize approaches have gained traction in grid operations, where system functionality forecasts are first generated and then used as inputs for downstream decision-making. However, this two-stage method often results in a misalignment between prediction and optimization objectives, leading to suboptimal resource allocation. To address this, we propose predict-all-then-optimize-globally (PATOG), a framework that integrates outage prediction with globally optimized interventions. At its core, our global-decision-focused (GDF) neural ODE model captures outage dynamics while optimizing resilience strategies in a decision-aware manner. Unlike conventional methods, our approach ensures spatially and temporally coherent decision-making, improving both predictive accuracy and operational efficiency. Experiments on synthetic and real-world datasets demonstrate significant improvements in outage prediction consistency and grid resilience. - oai:arXiv.org:2502.18321v3 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shuyi Chen, Ferdinando Fioretto, Feng Qiu, Shixiang Zhu - - - Optimizing Parameter Estimation for Electrochemical Battery Model: A Comparative Analysis of Operating Profiles on Computational Efficiency and Accuracy - https://arxiv.org/abs/2503.00604 - arXiv:2503.00604v3 Announce Type: replace -Abstract: Parameter estimation in electrochemical models remains a significant challenge in their application. This study investigates the impact of different operating profiles on electrochemical model parameter estimation to identify the optimal conditions. In particular, the present study is focused on Nickel Manganese Cobalt Oxide(NMC) lithium-ion batteries. Based on five fundamental current profiles (C/5, C/2, 1C, Pulse, DST), 31 combinations of conditions were generated and used for parameter estimation and validation, resulting in 961 evaluation outcomes. The Particle Swarm Optimization is employed for parameter identification in electrochemical models, specifically using the Single Particle Model (SPM). The analysis considered three dimensions: model voltage output error, parameter estimation error, and time cost. Results show that using all five profiles (C/5, C/2, 1C, Pulse, DST) minimizes voltage output error, while {C/5, C/2, Pulse, DST} minimizes parameter estimation error. The shortest time cost is achieved with {1C}. When considering both model voltage output and parameter errors, {C/5, C/2, 1C, DST} is optimal. For minimizing model voltage output error and time cost, {C/2, 1C} is best, while {1C} is ideal for parameter error and time cost. The comprehensive optimal condition is {C/5, C/2, 1C, DST}. These findings provide guidance for selecting current conditions tailored to specific needs. - oai:arXiv.org:2503.00604v3 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1016/j.jpowsour.2025.239044 - Journal of Power Sources 665 (2026) 239044 - Feng Guo, Luis D. Couto, Khiem Trad, Grietus Mulder, Keivan Haghverdi, Guillaume Thenaisie - - - Parameter estimation in fluid flow models from undersampled frequency space data - https://arxiv.org/abs/2503.04092 - arXiv:2503.04092v2 Announce Type: replace -Abstract: 4D Flow MRI is the state of the art technique for measuring blood flow, and it provides valuable information for inverse problems in the cardiovascular system. However, 4D Flow MRI has a very long acquisition time, straining healthcare resources and inconveniencing patients. Due to this, usually only a part of the frequency space is acquired, where then further assumptions need to be made in order to obtain an image. - Inverse problems from 4D Flow MRI data have the potential to compute clinically relevant quantities without the need for invasive procedures, and/or expanding the set of biomarkers for a more accurate diagnosis. However, reconstructing MRI measurements with Compressed Sensing techniques introduces artifacts and inaccuracies, which can compromise the results of the inverse problems. Additionally, there is a high number of different sampling patterns available, and it is often unclear which of them is preferable. - Here, we present a parameter estimation problem directly using highly undersampled frequency space measurements. This problem is numerically solved by a Reduced-Order Unscented Kalman Filter (ROUKF). We show that this results in more accurate parameter estimation for boundary conditions in a synthetic aortic blood flow than using measurements reconstructed with Compressed Sensing. - We also compare different sampling patterns, demonstrating how the quality of the parameter estimation depends on the choice of the sampling pattern. The results show a considerably higher accuracy than an inverse problem using velocity measurements reconstructed via compressed sensing. Finally, we confirm these findings on real MRI data from a mechanical phantom. - oai:arXiv.org:2503.04092v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Miriam L\"ocke, Pim van Ooij, Crist\'obal Bertoglio - - - HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization - https://arxiv.org/abs/2503.04598 - arXiv:2503.04598v4 Announce Type: replace -Abstract: Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, many challenges remain in training deep transformer networks, especially regarding the position of the layer normalization. While Pre-Norm structures facilitate more stable training owing to their stronger identity path, they often lead to suboptimal performance compared to Post-Norm. In this paper, we propose $\textbf{HybridNorm}$, a simple yet effective hybrid normalization strategy that integrates the advantages of both Pre-Norm and Post-Norm. Specifically, HybridNorm employs QKV normalization within the attention mechanism and Post-Norm in the feed-forward network (FFN) of each transformer block. We provide both theoretical insights and empirical evidence to demonstrate that HybridNorm improves the gradient flow and the model robustness. Extensive experiments on large-scale transformer models, including both dense and sparse variants, show that HybridNorm consistently outperforms both Pre-Norm and Post-Norm approaches across multiple benchmarks. These findings highlight the potential of HybridNorm as a more stable and effective technique for improving the training and performance of deep transformer models. Code is available at https://github.com/BryceZhuo/HybridNorm. - oai:arXiv.org:2503.04598v4 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Zhijian Zhuo, Yutao Zeng, Ya Wang, Sijun Zhang, Jian Yang, Xiaoqing Li, Xun Zhou, Jinwen Ma - - - Collaborative Drill Alignment in Surgical Robotics - https://arxiv.org/abs/2503.05791 - arXiv:2503.05791v2 Announce Type: replace -Abstract: Robotic assistance allows surgeries to be reliably and accurately executed while still under direct supervision of the surgeon, combining the strengths of robotic technology with the surgeon's expertise. This paper describes a robotic system designed to assist in surgical procedures by implementing a virtual drill guide. The system integrates virtual-fixture functionality using a novel virtual-mechanism controller with additional visual feedback. The controller constrains the tool to the desired axis, while allowing axial motion to remain under the surgeon's control. Compared to prior virtual-fixture approaches -- which primarily perform pure energy-shaping and damping injection with linear springs and dampers -- our controller uses a virtual prismatic joint to which the robot is constrained by nonlinear springs, allowing us to easily shape the dynamics of the system. We detail the calibration procedures required to achieve sufficient precision, and describe the implementation of the controller. We apply this system to a veterinary procedure: drilling for transcondylar screw placement in dogs. The results of the trials on 3D-printed bone models demonstrate sufficient precision to perform the procedure and suggest improved angular accuracy and reduced exit translation errors compared to patient specific guides (PSG). Discussion and future improvements follow. - oai:arXiv.org:2503.05791v2 - eess.SY - cs.RO - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Daniel Larby, Joshua Kershaw, Matthew Allen, Fulvio Forni - - - Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmark - https://arxiv.org/abs/2503.06983 - arXiv:2503.06983v2 Announce Type: replace -Abstract: While cooperative perception can overcome the limitations of single-vehicle systems, the practical implementation of vehicle-to-vehicle and vehicle-to-infrastructure systems is often impeded by significant economic barriers. Aerial-ground cooperation (AGC), which pairs ground vehicles with drones, presents a more economically viable and rapidly deployable alternative. However, this emerging field has been held back by a critical lack of high-quality public datasets and benchmarks. To bridge this gap, we present \textit{Griffin}, a comprehensive AGC 3D perception dataset, featuring over 250 dynamic scenes (37k+ frames). It incorporates varied drone altitudes (20-60m), diverse weather conditions, realistic drone dynamics via CARLA-AirSim co-simulation, and critical occlusion-aware 3D annotations. Accompanying the dataset is a unified benchmarking framework for cooperative detection and tracking, with protocols to evaluate communication efficiency, altitude adaptability, and robustness to communication latency, data loss and localization noise. By experiments through different cooperative paradigms, we demonstrate the effectiveness and limitations of current methods and provide crucial insights for future research. The dataset and codes are available at https://github.com/wang-jh18-SVM/Griffin. - oai:arXiv.org:2503.06983v2 - cs.CV - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiahao Wang, Xiangyu Cao, Jiaru Zhong, Yuner Zhang, Zeyu Han, Haibao Yu, Chuang Zhang, Lei He, Shaobing Xu, Jianqiang Wang - - - MIRAM: Masked Image Autoencoders Across Multiple Scales with Hybrid-Attention Mechanism for Breast Lesion Risk Prediction - https://arxiv.org/abs/2503.07157 - arXiv:2503.07157v3 Announce Type: replace -Abstract: Self-supervised learning (SSL) has garnered substantial interest within the machine learning and computer vision communities. Two prominent approaches in SSL include contrastive-based learning and self-distillation utilizing cropping augmentation. Lately, masked image modeling (MIM) has emerged as a more potent SSL technique, employing image inpainting as a pretext task. MIM creates a strong inductive bias toward meaningful spatial and semantic understanding. This has opened up new opportunities for SSL to contribute not only to classification tasks but also to more complex applications like object detection and image segmentation. Building upon this progress, our research paper introduces a scalable and practical SSL approach centered around more challenging pretext tasks that facilitate the acquisition of robust features. Specifically, we leverage multi-scale image reconstruction from randomly masked input images as the foundation for feature learning. Our hypothesis posits that reconstructing high-resolution images enables the model to attend to finer spatial details, particularly beneficial for discerning subtle intricacies within medical images. The proposed SSL features help improve classification performance on the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) dataset. In pathology classification, our method demonstrates a 3\% increase in average precision (AP) and a 1\% increase in the area under the receiver operating characteristic curve (AUC) when compared to state-of-the-art (SOTA) algorithms. Moreover, in mass margins classification, our approach achieves a 4\% increase in AP and a 2\% increase in AUC. - oai:arXiv.org:2503.07157v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Hung Q. Vo, Pengyu Yuan, Zheng Yin, Kelvin K. Wong, Chika F. Ezeana, Son T. Ly, Stephen T. C. Wong, Hien V. Nguyen - - - PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Spatiotemporal Prediction - https://arxiv.org/abs/2503.10253 - arXiv:2503.10253v3 Announce Type: replace -Abstract: Simulation of spatiotemporal systems governed by partial differential equations is widely applied in fields such as biology, chemistry, aerospace dynamics, and meteorology. Traditional numerical methods incur high computational costs due to the requirement of small time steps for accurate predictions. While machine learning has reduced these costs, long-term predictions remain challenged by error accumulation, particularly in scenarios with insufficient data or varying time scales, where stability and accuracy are compromised. Existing methods often neglect the effective utilization of multi-scale data, leading to suboptimal robustness in predictions. To address these issues, we propose a novel multi-scale learning framework, namely, the Physics-Informed Multi-Scale Recurrent Learning (PIMRL), to effectively leverage multi-scale data for spatiotemporal dynamics prediction. The PIMRL framework comprises two modules: the micro-scale module embeds physical knowledge into neural networks via pretraining, and the macro-scale module adopts a data-driven approach to learn the temporal evolution of physics in the latent space. Experimental results demonstrate that the PIMRL framework consistently achieves state-of-the-art performance across five benchmark datasets ranging from one to three dimensions, showing average improvements of over 9\% in both RMSE and MAE evaluation metrics, with maximum enhancements reaching up to 80%. - oai:arXiv.org:2503.10253v3 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Han Wan, Qi Wang, Yuan Mi, Hao Sun - - - Quantization-Free Autoregressive Action Transformer - https://arxiv.org/abs/2503.14259 - arXiv:2503.14259v3 Announce Type: replace -Abstract: Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. However, the initial quantization breaks the continuous structure of the action space thereby limiting the capabilities of the generative model. We propose a quantization-free method instead that leverages Generative Infinite-Vocabulary Transformers (GIVT) as a direct, continuous policy parametrization for autoregressive transformers. This simplifies the imitation learning pipeline while achieving state-of-the-art performance on a variety of popular simulated robotics tasks. We enhance our policy roll-outs by carefully studying sampling algorithms, further improving the results. - oai:arXiv.org:2503.14259v3 - cs.LG - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 39th Conference on Neural Information Processing Systems, 2025 - Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach, Claire Vernade - - - Proceedings of the 3rd Italian Conference on Big Data and Data Science (ITADATA2024) - https://arxiv.org/abs/2503.14937 - arXiv:2503.14937v2 Announce Type: replace -Abstract: Proceedings of the 3rd Italian Conference on Big Data and Data Science (ITADATA2024), held in Pisa, Italy, September 17-19, 2024. - The Italian Conference on Big Data and Data Science (ITADATA2024) is the annual event supported by the CINI Big Data National Laboratory and ISTI CNR that aims to put together Italian researchers and professionals from academia, industry, government, and public administration working in the field of big data and data science, as well as related fields (e.g., security and privacy, HPC, Cloud). - ITADATA2024 covered research on all theoretical and practical aspects of Big Data and data science including data governance, data processing, data analysis, data reporting, data protection, as well as experimental studies and lessons learned. In particular, ITADATA2024 focused on - - Data spaces - - Data processing life cycle - - Machine learning and Large Language Models - - Applications of big data and data science in healthcare, finance, industry 5.0, and beyond - - Data science for social network analysis - oai:arXiv.org:2503.14937v2 - cs.DB - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nicola Bena, Claudia Diamantini, Michela Natilli, Luigi Romano, Giovanni Stilo, Valentina Pansanella, Claudio A. Ardagna, Anna Monreale, Roberto Trasarti - - - TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment - https://arxiv.org/abs/2503.16929 - arXiv:2503.16929v4 Announce Type: replace -Abstract: Video Large Language Models (Video LLMs) have achieved significant success by adopting the paradigm of large-scale pre-training followed by supervised fine-tuning (SFT). However, existing approaches struggle with temporal reasoning due to weak temporal correspondence in the data and over-reliance on the next-token prediction paradigm}, which collectively result in the absence temporal supervision. To address these limitations, we propose TEMPLE (TEMporal Preference LEarning), a systematic framework that enhances temporal reasoning capabilities through Direct Preference Optimization (DPO). To address temporal information scarcity in data, we introduce an automated pipeline for systematically constructing temporality-intensive preference pairs comprising three steps: selecting temporally rich videos, designing video-specific perturbation strategies, and evaluating model responses on clean and perturbed inputs. Complementing this data pipeline, we provide additional supervision signals via preference learning and propose a novel Progressive Pre-SFT Alignment strategy featuring two key innovations: a curriculum learning strategy which progressively increases perturbation difficulty to maximize data efficiency; and applying preference optimization before instruction tuning to incentivize fundamental temporal alignment. Extensive experiments demonstrate that our approach consistently improves Video LLM performance across multiple benchmarks with a relatively small set of self-generated DPO data. Our findings highlight TEMPLE as a scalable and efficient complement to SFT-based methods, paving the way for developing reliable Video LLMs. - oai:arXiv.org:2503.16929v4 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shicheng Li, Lei Li, Kun Ouyang, Shuhuai Ren, Yuanxin Liu, Yuanxing Zhang, Fuzheng Zhang, Lingpeng Kong, Qi Liu, Xu Sun - - - Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining - https://arxiv.org/abs/2503.19912 - arXiv:2503.19912v2 Announce Type: replace -Abstract: LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera sensors, they often overlook the temporal dynamics critical for capturing motion and scene continuity in driving scenarios. To address this limitation, we propose SuperFlow++, a novel framework that integrates spatiotemporal cues in both pretraining and downstream tasks using consecutive LiDAR-camera pairs. SuperFlow++ introduces four key components: (1) a view consistency alignment module to unify semantic information across camera views, (2) a dense-to-sparse consistency regularization mechanism to enhance feature robustness across varying point cloud densities, (3) a flow-based contrastive learning approach that models temporal relationships for improved scene understanding, and (4) a temporal voting strategy that propagates semantic information across LiDAR scans to improve prediction consistency. Extensive evaluations on 11 heterogeneous LiDAR datasets demonstrate that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions. Furthermore, by scaling both 2D and 3D backbones during pretraining, we uncover emergent properties that provide deeper insights into developing scalable 3D foundation models. With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving. The code is publicly available at https://github.com/Xiangxu-0103/SuperFlow - oai:arXiv.org:2503.19912v2 - cs.CV - cs.LG - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - 10.1109/TPAMI.2025.3640589 - Xiang Xu, Lingdong Kong, Hui Shuai, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu, Qingshan Liu - - - Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMs - https://arxiv.org/abs/2503.20745 - arXiv:2503.20745v2 Announce Type: replace -Abstract: Diagrams represent a form of visual language that encodes abstract concepts and relationships through structured symbols and their spatial arrangements. Unlike natural images, they are inherently symbolic, and entirely artificial. They thus pose unique challenges for Multimodal Large Language Models (MLLMs) distinct from natural image processing. Recent studies have shown that MLLMs often exhibit flawed reasoning and hallucinations when handling diagram inputs. We investigate here whether these limitations stem from shortcomings in the models' ability to interpret diagrams themselves. To this end, we develop a diagnostic test suite that isolates perception from reasoning. Our systematic evaluation reveals that MLLMs perform poorly on basic perceptual tasks, e.g., shape classification, object counting, relationship identification, and object grounding, with near-zero accuracy on fine-grained grounding. Further analysis shows that weak diagram perception leads to "blind faith in text", where models rely on textual shortcuts rather than visual understanding (that is, they are Math Blind). We hypothesize that enabling models to capture the inherent structural properties of diagrams, represented as graphs of primitives and their interrelationships, is essential for improving diagram understanding. Experiments with 7B and 32B MLLMs validate this assumption, with models trained on such representations achieving a +79% gain on the grounding task. Crucially, these gains transfer to reasoning, achieving 3-4% cross-suite improvements on three public benchmarks even without additional chain-of-thought reasoning data. Our findings demonstrate that low-level perception supports faithful high-level reasoning in mathematical MLLMs. We provide both methodological frameworks and empirical evidence to guide future research in this direction. - oai:arXiv.org:2503.20745v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yanpeng Sun, Shan Zhang, Wei Tang, Aotian Chen, Piotr Koniusz, Kai Zou, Yuan Xue, Anton van den Hengel - - - MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX - https://arxiv.org/abs/2503.21699 - arXiv:2503.21699v2 Announce Type: replace -Abstract: We introduce MAVERIX (Multimodal audiovisual Evaluation and Recognition IndeX), a unified benchmark to probe the video understanding in multimodal LLMs, encompassing video, audio, text inputs with human performance baselines. Although recent advancements in models with vision and audio understanding capabilities have shown substantial progress, the field lacks a standardized evaluation framework to thoroughly assess their cross-modality comprehension performance. MAVERIX curates 2,556 questions from 700 videos, in the form of both multiple-choice and open-ended formats, explicitly designed to evaluate multimodal models through questions that necessitate tight integration of video and audio information, spanning a broad spectrum of agentic scenarios. MAVERIX uniquely provides models with audiovisual questions, closely mimicking the multimodal perceptual experiences available to humans during inference and decision-making processes. To our knowledge, MAVERIX is the first benchmark aimed explicitly at assessing comprehensive audiovisual integration in such granularity. Experiments with state-of-the-art models, including Qwen 2.5 Omni and Gemini 2.5 Flash-Lite, show performance around 64% accuracy, while human experts reach near-ceiling performance of 92.8%, exposing a substantial gap to human-level comprehension. With standardized evaluation protocols, a rigorously annotated pipeline, and a public toolkit, MAVERIX establishes a challenging testbed for advancing audiovisual multimodal intelligence. - oai:arXiv.org:2503.21699v2 - cs.MM - cs.AI - cs.CV - cs.SD - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - AAAI 2026 - Liuyue Xie, Avik Kuthiala, George Z. Wei, Ce Zheng, Ananya Bal, Mosam Dabhi, Liting Wen, Taru Rustagi, Ethan Lai, Sushil Khyalia, Rohan Choudhury, Morteza Ziyadi, Xu Zhang, Hao Yang, L\'aszl\'o A. Jeni - - - Grasping a Handful: Sequential Multi-Object Dexterous Grasp Generation - https://arxiv.org/abs/2503.22370 - arXiv:2503.22370v5 Announce Type: replace -Abstract: We introduce the sequential multi-object robotic grasp sampling algorithm SeqGrasp that can robustly synthesize stable grasps on diverse objects using the robotic hand's partial Degrees of Freedom (DoF). We use SeqGrasp to construct the large-scale Allegro Hand sequential grasping dataset SeqDataset and use it for training the diffusion-based sequential grasp generator SeqDiffuser. We experimentally evaluate SeqGrasp and SeqDiffuser against the state-of-the-art non-sequential multi-object grasp generation method MultiGrasp in simulation and on a real robot. The experimental results demonstrate that SeqGrasp and SeqDiffuser reach an 8.71%-43.33% higher grasp success rate than MultiGrasp. Furthermore, SeqDiffuser is approximately 1000 times faster at generating grasps than SeqGrasp and MultiGrasp. Project page: https://yulihn.github.io/SeqGrasp/. - oai:arXiv.org:2503.22370v5 - cs.RO - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/LRA.2025.3614051 - IEEE Robotics and Automation Letters, vol. 10, no. 11, pp. 11880-11887, Nov. 2025 - Haofei Lu, Yifei Dong, Zehang Weng, Florian T. Pokorny, Jens Lundell, Danica Kragic - - - TranSplat: Instant Cross-Scene Object Relighting in Gaussian Splatting via Spherical Harmonic Transfer - https://arxiv.org/abs/2503.22676 - arXiv:2503.22676v3 Announce Type: replace -Abstract: We present TranSplat, a method for fast and accurate object relighting for the 3D Gaussian Splatting (GS) framework when transferring a 3D object from a source GS scene to a target GS scene. TranSplat is based on a theoretical radiance transfer identity for cross-scene relighting of objects with radially symmetric BRDFs that involves only taking simple products of spherical harmonic appearance coefficients of the object, source, and target environment maps without any explicit computation of scene quantities (e.g., the BRDFs themselves). TranSplat is the first method to demonstrate how this theoretical identity may be used to perform relighting within the GS framework, and furthermore, by automatically inferring unknown source and target environment maps directly from the source and target scene GS representations. We evaluated TranSplat on several synthetic and real-world scenes and objects, demonstrating comparable 3D object relighting performance to recent conventional inverse rendering-based GS methods with a fraction of their runtime. While TranSplat is theoretically best-suited for radially symmetric BRDFs, results demonstrate that TranSplat still offers perceptually realistic renderings on real scenes and opens a valuable, lightweight path forward to relighting with the GS framework. - oai:arXiv.org:2503.22676v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Boyang (Tony), Yu, Yanlin Jin, Yun He, Akshat Dave, Guha Balakrishnan - - - Energy-Aware Lane Planning for Connected Electric Vehicles in Urban Traffic: Design and Vehicle-in-the-Loop Validation - https://arxiv.org/abs/2503.23228 - arXiv:2503.23228v4 Announce Type: replace -Abstract: Urban driving with connected and automated vehicles (CAVs) offers potential for energy savings, yet most eco-driving strategies focus solely on longitudinal speed control within a single lane. This neglects the significant impact of lateral decisions, such as lane changes, on overall energy efficiency, especially in environments with traffic signals and heterogeneous traffic flow. To address this gap, we propose a novel energy-aware motion planning framework that jointly optimizes longitudinal speed and lateral lane-change decisions using vehicle-to-infrastructure (V2I) communication. Our approach estimates long-term energy costs using a graph-based approximation and solves short-horizon optimal control problems under traffic constraints. Using a data-driven energy model calibrated to an actual battery electric vehicle, we demonstrate with vehicle-in-the-loop experiments that our method reduces motion energy consumption by up to 24 percent compared to a human driver, highlighting the potential of connectivity-enabled planning for sustainable urban autonomy. - oai:arXiv.org:2503.23228v4 - eess.SY - cs.RO - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hansung Kim, Eric Yongkeun Choi, Eunhyek Joa, Hotae Lee, Linda Lim, Scott Moura, Francesco Borrelli - - - Iterative VCG-based Mechanism Fosters Cooperation in Multi-Regional Network Design - https://arxiv.org/abs/2503.23255 - arXiv:2503.23255v2 Announce Type: replace -Abstract: Transportation network design often involves multiple stakeholders with diverse priorities. We consider a system with a hierarchical multi-agent structure, featuring self-optimized subnetwork operators at the lower level and a central organization at the upper level. Independent regional planning can lead to inefficiencies due to the lack of coordination, hindering interregional travel and cross-border infrastructure development, while centralized methods may struggle to align local interests and can be impractical to implement. To support decision making for such a system, we introduce an iterative VCG-based mechanism for multi-regional network design that fosters cooperation among subnetwork operators. By leveraging the Vickery-Clarke-Groves (VCG) mechanism, the framework determines collective investment decisions and the necessary payments from both operators and the central organization to achieve efficient outcomes. A case study on the European Railway System validates the effectiveness of the proposed method, demonstrating significant improvements in overall network performance through enhanced cross-region cooperation. - oai:arXiv.org:2503.23255v2 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Mingjia He, Yannik Werner, Andrea Censi, Emilio Frazzoli, Gioele Zardini - - - Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries - https://arxiv.org/abs/2503.23606 - arXiv:2503.23606v2 Announce Type: replace -Abstract: Extracting depth information from photon-limited, defocused images is challenging because depth from defocus (DfD) relies on accurate estimation of defocus blur, which is fundamentally sensitive to image noise. We present a novel approach to robustly measure object depths from photon-limited images along the defocused boundaries. It is based on a new image patch representation, Blurry-Edges, that explicitly stores and visualizes a rich set of low-level patch information, including boundaries, color, and smoothness. We develop a deep neural network architecture that predicts the Blurry-Edges representation from a pair of differently defocused images, from which depth can be calculated using a closed-form DfD relation we derive. The experimental results on synthetic and real data show that our method achieves the highest depth estimation accuracy on photon-limited images compared to a broad range of state-of-the-art DfD methods. - oai:arXiv.org:2503.23606v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wei Xu, Charles James Wagner, Junjie Luo, Qi Guo - - - Optimizing Age of Information in Networks with Large and Small Updates - https://arxiv.org/abs/2503.23658 - arXiv:2503.23658v2 Announce Type: replace -Abstract: Modern sensing and monitoring applications typically consist of sources transmitting updates of different sizes, ranging from a few bytes (position, temperature, etc.) to multiple megabytes (images, video frames, LIDAR point scans, etc.). Existing approaches to wireless scheduling for information freshness typically ignore this mix of large and small updates, leading to suboptimal performance. In this paper, we consider a single-hop wireless broadcast network with sources transmitting updates of different sizes to a base station over unreliable links. Some sources send large updates spanning many time slots while others send small updates spanning only a few time slots. Due to medium access constraints, only one source can transmit to the base station at any given time, thus requiring careful design of scheduling policies that takes the sizes of updates into account. First, we derive a lower bound on the achievable Age of Information (AoI) by any transmission scheduling policy. Second, we develop optimal randomized policies that consider both switching and no-switching during the transmission of large updates. Third, we introduce a novel Lyapunov function and associated analysis to propose an AoI-based Max-Weight policy that has provable constant factor optimality guarantees. Finally, we evaluate and compare the performance of our proposed scheduling policies through simulations, which show that our Max-Weight policy achieves near-optimal AoI performance. - oai:arXiv.org:2503.23658v2 - eess.SY - cs.NI - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhuoyi Zhao, Vishrant Tripathi, Igor Kadota - - - Suite-IN++: A FlexiWear BodyNet Integrating Global and Local Motion Features from Apple Suite for Robust Inertial Navigation - https://arxiv.org/abs/2504.00438 - arXiv:2504.00438v2 Announce Type: replace -Abstract: The proliferation of wearable technology has established multi-device ecosystems comprising smartphones, smartwatches, and headphones as critical enablers for ubiquitous pedestrian localization. However, traditional pedestrian dead reckoning (PDR) struggles with diverse motion modes, while data-driven methods, despite improving accuracy, often lack robustness due to their reliance on a single-device setup. Therefore, a promising solution is to fully leverage existing wearable devices to form a flexiwear bodynet for robust and accurate pedestrian localization. This paper presents Suite-IN++, a deep learning framework for flexiwear bodynet-based pedestrian localization. Suite-IN++ integrates motion data from wearable devices on different body parts, using contrastive learning to separate global and local motion features. It fuses global features based on the data reliability of each device to capture overall motion trends and employs an attention mechanism to uncover cross-device correlations in local features, extracting motion details helpful for accurate localization. To evaluate our method, we construct a real-life flexiwear bodynet dataset, incorporating Apple Suite (iPhone, Apple Watch, and AirPods) across diverse walking modes and device configurations. Experimental results demonstrate that Suite-IN++ achieves superior localization accuracy and robustness, significantly outperforming state-of-the-art models in real-life pedestrian tracking scenarios. - oai:arXiv.org:2504.00438v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lan Sun, Songpengcheng Xia, Jiarui Yang, Ling Pei - - - A Physics-Informed Meta-Learning Framework for the Continuous Solution of Parametric PDEs on Arbitrary Geometries - https://arxiv.org/abs/2504.02459 - arXiv:2504.02459v2 Announce Type: replace -Abstract: In this work, we introduce implicit Finite Operator Learning (iFOL) for the continuous and parametric solution of partial differential equations (PDEs) on arbitrary geometries. We propose a physics-informed encoder-decoder network to establish the mapping between continuous parameter and solution spaces. The decoder constructs the parametric solution field by leveraging an implicit neural field network conditioned on a latent or feature code. Instance-specific codes are derived through a PDE encoding process based on the second-order meta-learning technique. In training and inference, a physics-informed loss function is minimized during the PDE encoding and decoding. iFOL expresses the loss function in an energy or weighted residual form and evaluates it using discrete residuals derived from standard numerical PDE methods. This approach results in the backpropagation of discrete residuals during both training and inference. - iFOL features several key properties: (1) its unique loss formulation eliminates the need for the conventional encode-process-decode pipeline previously used in operator learning with conditional neural fields for PDEs; (2) it not only provides accurate parametric and continuous fields but also delivers solution-to-parameter gradients without requiring additional loss terms or sensitivity analysis; (3) it can effectively capture sharp discontinuities in the solution; and (4) it removes constraints on the geometry and mesh, making it applicable to arbitrary geometries and spatial sampling (zero-shot super-resolution capability). We critically assess these features and analyze the network's ability to generalize to unseen samples across both stationary and transient PDEs. The overall performance of the proposed method is promising, demonstrating its applicability to a range of challenging problems in computational mechanics. - oai:arXiv.org:2504.02459v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Reza Najian Asl, Yusuke Yamazaki, Kianoosh Taghikhani, Mayu Muramatsu, Markus Apel, Shahed Rezaei - - - Instance-Optimal Imprecise Convex Hull - https://arxiv.org/abs/2504.02611 - arXiv:2504.02611v4 Announce Type: replace -Abstract: Imprecise measurements of a point set P = (p1, ..., pn) can be modelled by a family of regions F = (R1, ..., Rn), where each imprecise region Ri contains a unique point pi. A retrieval models an accurate measurement by replacing an imprecise region Ri with its corresponding point pi. We construct the convex hull of an imprecise point set in the plane, where regions in F may be retrieved at unit cost. The goal is to determine the cyclic ordering of the convex hull vertices of P as efficiently as possible. Here, efficiency is interpreted in two ways: (i) minimising the number of retrievals, and (ii) computing each retrieval location quickly. - Prior works focused on only one of these two aspects: either minimising retrievals or optimising algorithmic runtime. Our contribution is the first to simultaneously achieve both. Let r(F, P) denote the minimal number of retrievals required by any algorithm to determine the convex hull of P for a given instance (F, P). For a family F of n constant-complexity polygons, our main result is a reconstruction algorithm that performs O(r(F, P)) retrievals in O(r(F, P) log^3 n) time. - Compared to previous approaches that achieve optimal retrieval counts, we improve the runtime per retrieval by a exponential factor, from polynomial to polylogarithmic. Compared to near-linear time algorithms, we significantly reduce the number of retrievals used, and broaden the input families to include overlapping regions. We further extend our results to simple k-gons and to pairwise disjoint disks with radii in [1,k], where our runtime scales linearly with k. - oai:arXiv.org:2504.02611v4 - cs.CG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sarita de Berg, Ivor van der Hoog, Eva Rotenberg, Daniel Rutschmann, Sampson Wong - - - Three Forensic Cues for JPEG AI Images - https://arxiv.org/abs/2504.03191 - arXiv:2504.03191v2 Announce Type: replace -Abstract: The JPEG standard was vastly successful. Currently, the first AI-based compression method ``JPEG AI'' will be standardized. JPEG AI brings remarkable benefits. JPEG AI images exhibit impressive image quality at bitrates that are an order of magnitude lower than images compressed with traditional JPEG. However, forensic analysis of JPEG AI has to be completely re-thought: forensic tools for traditional JPEG do not transfer to JPEG AI, and artifacts from JPEG AI are easily confused with artifacts from artificially generated images (``DeepFakes''). This creates a need for novel forensic approaches to detection and distinction of JPEG AI images. In this work, we make a first step towards a forensic JPEG AI toolset. We propose three cues for forensic algorithms for JPEG AI. These algorithms address three forensic questions: first, we show that the JPEG AI preprocessing introduces correlations in the color channels that do not occur in uncompressed images. Second, we show that repeated compression of JPEG AI images leads to diminishing distortion differences. This can be used to detect recompression, in a spirit similar to some classic JPEG forensics methods. Third, we show that the quantization of JPEG AI images in the latent space can be used to distinguish real images with JPEG AI compression from synthetically generated images. The proposed methods are interpretable for a forensic analyst, and we hope that they inspire further research in the forensics of AI-compressed images. - oai:arXiv.org:2504.03191v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sandra Bergmann, Fabian Brand, Christian Riess - - - MAPLE: Encoding Dexterous Robotic Manipulation Priors Learned From Egocentric Videos - https://arxiv.org/abs/2504.06084 - arXiv:2504.06084v2 Announce Type: replace -Abstract: Large-scale egocentric video datasets capture diverse human activities across a wide range of scenarios, offering rich and detailed insights into how humans interact with objects, especially those that require fine-grained dexterous control. Such complex, dexterous skills with precise controls are crucial for many robotic manipulation tasks, yet are often insufficiently addressed by traditional data-driven approaches to robotic manipulation. To address this gap, we leverage manipulation priors learned from large-scale egocentric video datasets to improve policy learning for dexterous robotic manipulation tasks. We present MAPLE, a novel method for dexterous robotic manipulation that learns features to predict object contact points and detailed hand poses at the moment of contact from egocentric images. We then use the learned features to train policies for downstream manipulation tasks. Experimental results demonstrate the effectiveness of MAPLE across 4 existing simulation benchmarks, as well as a newly designed set of 4 challenging simulation tasks requiring fine-grained object control and complex dexterous skills. The benefits of MAPLE are further highlighted in real-world experiments using a 17 DoF dexterous robotic hand, whereas the simultaneous evaluation across both simulation and real-world experiments has remained underexplored in prior work. We additionally showcase the efficacy of our model on an egocentric contact point prediction task, validating its usefulness beyond dexterous manipulation policy learning. - oai:arXiv.org:2504.06084v2 - cs.RO - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alexey Gavryushin, Xi Wang, Robert J. S. Malate, Chenyu Yang, Davide Liconti, Ren\'e Zurbr\"ugg, Robert K. Katzschmann, Marc Pollefeys - - - Exploring Adversarial Obstacle Attacks in Search-based Path Planning for Autonomous Mobile Robots - https://arxiv.org/abs/2504.06154 - arXiv:2504.06154v2 Announce Type: replace -Abstract: Path planning algorithms, such as the search-based A*, are a critical component of autonomous mobile robotics, enabling robots to navigate from a starting point to a destination efficiently and safely. We investigated the resilience of the A* algorithm in the face of potential adversarial interventions known as obstacle attacks. The adversary's goal is to delay the robot's timely arrival at its destination by introducing obstacles along its original path. - We developed malicious software to execute the attacks and conducted experiments to assess their impact, both in simulation using TurtleBot in Gazebo and in real-world deployment with the Unitree Go1 robot. In simulation, the attacks resulted in an average delay of 36\%, with the most significant delays occurring in scenarios where the robot was forced to take substantially longer alternative paths. In real-world experiments, the delays were even more pronounced, with all attacks successfully rerouting the robot and causing measurable disruptions. These results highlight that the algorithm's robustness is not solely an attribute of its design but is significantly influenced by the operational environment. For example, in constrained environments like tunnels, the delays were maximized due to the limited availability of alternative routes. - oai:arXiv.org:2504.06154v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/ICRA55743.2025.11128179 - 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, 2025, pp. 14843-14849 - Adrian Szvoren, Jianwei Liu, Dimitrios Kanoulas, Nilufer Tuptuk - - - Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling - https://arxiv.org/abs/2504.09261 - arXiv:2504.09261v2 Announce Type: replace -Abstract: Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality content generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and severe memory overhead due to the accumulation of key-value (KV) caches across scales. In this paper, we tackle this challenge by introducing KV cache compression into the next-scale generation paradigm. We begin with a crucial observation: attention heads in VAR models can be divided into two functionally distinct categories: Contextual Heads focus on maintaining semantic consistency, while Structural Heads are responsible for preserving spatial coherence. This structural divergence causes existing one-size-fits-all compression methods to perform poorly on VAR models. To address this, we propose HACK, a training-free Head-Aware KV cache Compression frameworK. HACK utilizes an offline classification scheme to separate head types, enabling it to apply pattern-specific compression strategies with asymmetric cache budgets for each category. By doing so, HACK effectively constrains the average KV cache length within a fixed budget $B$, reducing the theoretical attention complexity from $\mathcal{O}(n^4)$ to $\mathcal{O}(Bn^2)$. Extensive experiments on multiple VAR models across text-to-image and class-conditional tasks validate the effectiveness and generalizability of HACK. It achieves up to 70% KV cache compression without degrading output quality, resulting in memory savings and faster inference. For example, HACK provides a $1.75\times$ memory reduction and a $1.57\times$ speedup on Infinity-8B. - oai:arXiv.org:2504.09261v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ziran Qin, Youru Lv, Mingbao Lin, Hang Guo, Zeren Zhang, Danping Zou, Weiyao Lin - - - Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration - https://arxiv.org/abs/2504.09973 - arXiv:2504.09973v2 Announce Type: replace -Abstract: All-in-One Image Restoration (AiOIR), which addresses diverse degradation types with a unified model, presents significant challenges in designing task-aware prompts that effectively guide restoration across multiple degradation scenarios. While adaptive prompt learning enables end-to-end optimization, it often yields overlapping or redundant task representations. Conversely, explicit prompts derived from pretrained classifiers enhance discriminability but discard critical visual information needed for reconstruction. To address these limitations, we introduce Contrastive Prompt Learning (CPL), a framework that aims to improve prompt-task alignment through two complementary components: a Sparse Prompt Module (SPM) that efficiently captures degradation-aware representations while reducing redundancy, and a Contrastive Prompt Regularization (CPR) that explicitly strengthens task boundaries by incorporating negative prompt samples across different degradation types. Unlike previous approaches that focus primarily on degradation classification, CPL directly optimizes the interaction between prompts and the restoration model. Extensive experiments across five benchmarks show that CPL consistently boosts the performance of strong AiOIR baselines across diverse scenarios. Our approach achieves state-of-the-art average performance on these benchmarks, providing a general and robust solution for AiOIR. The code is available at https://github.com/Aitical/CPLIR - oai:arXiv.org:2504.09973v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu, Liqiang Nie - - - SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing - https://arxiv.org/abs/2504.10826 - arXiv:2504.10826v3 Announce Type: replace -Abstract: Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to preserve the musical content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that improve the consistency between the original and edited music by leveraging score distillation. The first method, SteerMusic, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, SteerMusic+, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. SteerMusic+ allows for the editing of music into user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality. - oai:arXiv.org:2504.10826v3 - cs.SD - cs.MM - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Xinlei Niu, Kin Wai Cheuk, Jing Zhang, Naoki Murata, Chieh-Hsin Lai, Michele Mancusi, Woosung Choi, Giorgio Fabbro, Wei-Hsiang Liao, Charles Patrick Martin, Yuki Mitsufuji - - - Sensing-Then-Beamforming: Robust Transmission Design for RIS-Empowered Integrated Sensing and Covert Communication - https://arxiv.org/abs/2504.13741 - arXiv:2504.13741v2 Announce Type: replace -Abstract: Traditional covert communication often relies on the knowledge of the warden's channel state information, which is inherently challenging to obtain due to the non-cooperative nature and potential mobility of the warden. The integration of sensing and communication technology provides a promising solution by enabling the legitimate transmitter to sense and track the warden, thereby enhancing transmission covertness. In this paper, we develop a framework for sensing-then-beamforming in reconfigurable intelligent surface (RIS)-empowered integrated sensing and covert communication (ISACC) systems, where the transmitter (Alice) estimates and tracks the mobile aerial warden's channel using sensing echo signals while simultaneously sending covert information to multiple legitimate users (Bobs) with the assistance of RIS, under the surveillance of the warden (Willie). Considering channel estimation errors, we formulate a robust non-convex optimization problem that jointly designs the communication beamformers, the sensing signal covariance matrix at Alice, and the phase shifts at the RIS to maximize the covert sum rate of Bobs while satisfying the constraints related to covert communication, sensing, transmitter power, and the unit modulus of the RIS elements. To solve this complex problem, we develop an efficient algorithm using alternating optimization, successive convex approximation, S-procedure, sequential rank-one constraint relaxation, and semidefinite relaxation techniques. Numerical results confirm the convergence of the proposed algorithm and demonstrate its effectiveness in tracking the warden's channel while ensuring robust covert transmission. Furthermore, the results highlight the advantages of using RIS to enhance the covert transmission rate compared to baseline schemes, and also illustrate the intricate trade-off between communication and sensing in ISACC systems. - oai:arXiv.org:2504.13741v2 - cs.IT - eess.SP - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xingyu Zhao, Min Li, Ming-Min Zhao, Shihao Yan, Min-Jian Zhao - - - Time discretization in convected linearized thermo-visco-elastodynamics at large displacements - https://arxiv.org/abs/2504.14297 - arXiv:2504.14297v2 Announce Type: replace -Abstract: The fully-implicit time discretization (i.e. the backward Euler formula) is applied to compressible nonlinear dynamical models of thermo-viscoelastic solids in the Eulerian description, i.e. in the actual deforming configuration, formulated in terms of rates. The Kelvin-Voigt rheology or also, in the deviatoric part, the Jeffreys rheology (which covers creep or plasticity) are considered, using the additive Green-Naghdi decomposition of total strain into the elastic and the inelastic strains formulated in terms of (objective) rates exploiting the Zaremba-Jaumann time derivative. A linearized convective model at large displacements is considered, focusing on the case where the internal energy additively splits the (convex) mechanical and the thermal parts.A fully implicit time-discrete scheme is devised. Considering the multipolar 2nd-grade viscosity, the numerical stability and convergence towards weak solutions are proven by exploiting, in particular, the convexity of the kinetic energy when written in terms of linear momentum instead of velocity and by estimating the temperature gradient from the entropy-like inequality. - oai:arXiv.org:2504.14297v2 - math.NA - cs.NA - math.AP - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Tom\'a\v{s} Roub\'i\v{c}ek - - - Process Reward Models That Think - https://arxiv.org/abs/2504.16828 - arXiv:2504.16828v5 Announce Type: replace -Abstract: Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as verbalized step-wise reward models that verify every step in the solution by generating a verification chain-of-thought (CoT). We propose ThinkPRM, a long CoT verifier fine-tuned on orders of magnitude fewer process labels than those required by discriminative PRMs. Our approach capitalizes on the inherent reasoning abilities of long CoT models, and outperforms LLM-as-a-Judge and discriminative verifiers -- using only 1% of the process labels in PRM800K -- across several challenging benchmarks. Specifically, ThinkPRM beats the baselines on ProcessBench, MATH-500, and AIME '24 under best-of-N selection and reward-guided search. In an out-of-domain evaluation on a subset of GPQA-Diamond and LiveCodeBench, our PRM surpasses discriminative verifiers trained on the full PRM800K by 8% and 4.5%, respectively. Lastly, under the same token budget, ThinkPRM scales up verification compute more effectively compared to LLM-as-a-Judge, outperforming it by 7.2% on a subset of ProcessBench. Our work highlights the value of generative, long CoT PRMs that can scale test-time compute for verification while requiring minimal supervision for training. Our code, data, and models are released at https://github.com/mukhal/thinkprm. - oai:arXiv.org:2504.16828v5 - cs.LG - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran, Jaekyeom Kim, Hao Peng, Moontae Lee, Honglak Lee, Lu Wang - - - Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs - https://arxiv.org/abs/2504.17432 - arXiv:2504.17432v4 Announce Type: replace -Abstract: The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key limitations: (1) text token truncation, (2) isolated image-text encoding, and (3) deficient compositionality due to bag-of-words behavior. While recent Multimodal Large Language Models (MLLMs) have demonstrated significant advances in generalized vision-language understanding, their potential for learning transferable multimodal representations remains underexplored.In this work, we present UniME (Universal Multimodal Embedding), a novel two-stage framework that leverages MLLMs to learn discriminative representations for diverse downstream tasks. In the first stage, we perform textual discriminative knowledge distillation from a powerful LLM-based teacher model to enhance the embedding capability of the MLLM\'s language component. In the second stage, we introduce hard negative enhanced instruction tuning to further advance discriminative representation learning. Specifically, we initially mitigate false negative contamination and then sample multiple hard negatives per instance within each batch, forcing the model to focus on challenging samples. This approach not only improves discriminative power but also enhances instruction-following ability in downstream tasks. We conduct extensive experiments on the MMEB benchmark and multiple retrieval tasks, including short and long caption retrieval and compositional retrieval. Results demonstrate that UniME achieves consistent performance improvement across all tasks, exhibiting superior discriminative and compositional capabilities. - oai:arXiv.org:2504.17432v4 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Tiancheng Gu, Kaicheng Yang, Ziyong Feng, Xingjun Wang, Yanzhao Zhang, Dingkun Long, Yingda Chen, Weidong Cai, Jiankang Deng - - - Robust semi-implicit multilevel SDC methods for conservation laws - https://arxiv.org/abs/2504.18526 - arXiv:2504.18526v2 Announce Type: replace -Abstract: Semi-implicit multilevel spectral deferred correction (SI-MLSDC) methods provide a promising approach for high-order time integration for nonlinear evolution equations including conservation laws. However, existing methods lack robustness and often do not achieve the expected advantage over single-level SDC. This work adopts the novel SI time integrators from [48] for enhanced stability and extends the single-level SI-SDC method with a multilevel approach to increase computational efficiency. The favourable properties of the resulting SI-MLSDC method are shown by linear temporal stability analysis for a convection-diffusion problem. The robustness and efficiency of the fully discrete method involving a high-order discontinuous Galerkin SEM discretization are demonstrated through numerical experiments for the convection-diffusion, Burgers, Euler and Navier-Stokes equations. The method is shown to yield substantial reductions in fine-grid iterations compared to single-level SI-SDC across a broad range of test cases. Finally, current limitations of the SI-MLSDC framework are identified and discussed, providing guidance for future improvements. - oai:arXiv.org:2504.18526v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Erik Pfister, J\"org Stiller - - - A Multi-Language Perspective on the Robustness of LLM Code Generation - https://arxiv.org/abs/2504.19108 - arXiv:2504.19108v3 Announce Type: replace -Abstract: Large language models have gained significant traction and popularity in recent times, extending their usage to code-generation tasks. While this field has garnered considerable attention, the exploration of testing and evaluating the robustness of code generation models remains an ongoing endeavor. Previous studies have primarily focused on code generation models specifically for the Python language, overlooking other widely-used programming languages. In this work, we conduct a comprehensive comparative analysis to assess the robustness performance of several prominent code generation models and investigate whether robustness can be improved by repairing perturbed docstrings using an LLM. Furthermore, we investigate how their performance varies across different programming languages. To accomplish this, we introduce perturbations in four key areas of the prompt: DocString, functionname, syntax, and format. We have compiled and released a dedicated dataset for this purpose. This work presents our experimental findings, shedding light on the performance of code generation models in various scenarios. - oai:arXiv.org:2504.19108v3 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Fazle Rabbi, Zishuo Ding, Jinqiu Yang - - - OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification - https://arxiv.org/abs/2504.20964 - arXiv:2504.20964v2 Announce Type: replace -Abstract: We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) on the task of generating complete formal specifications for verifying the functional correctness of operating system kernels. This benchmark is built upon a real-world operating system kernel, Hyperkernel, and consists of 245 complex specification generation tasks in total, each of which is a long-context task of about 20k-30k tokens. The benchmark formulates the specification generation task as a program synthesis problem confined to a domain for specifying states and transitions. This formulation is provided to LLMs through a programming model. The LLMs must be able to understand the programming model and verification assumptions before delineating the correct search space for syntax and semantics and generating formal specifications. Guided by the operating system's high-level functional description, the LLMs are asked to generate a specification that fully describes all correct states and transitions for a potentially buggy code implementation of the operating system. Experimental results with 12 state-of-the-art LLMs indicate limited performance of existing LLMs on the specification generation task for operating system verification. Significant disparities in their performance highlight differences in their ability to handle long-context code generation tasks. The code are available at https://github.com/lishangyu-hkust/OSVBench - oai:arXiv.org:2504.20964v2 - cs.CL - cs.AI - cs.OS - cs.PL - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shangyu Li, Juyong Jiang, Tiancheng Zhao, Jiasi Shen - - - Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message-Passing Limit - https://arxiv.org/abs/2505.00291 - arXiv:2505.00291v3 Announce Type: replace -Abstract: We precisely characterize the expressivity of computable Recurrent Graph Neural Networks (recurrent GNNs). We prove that recurrent GNNs with finite-precision parameters, sum aggregation, and ReLU activation, can compute any graph algorithm that respects the natural message-passing invariance induced by the Color Refinement (or Weisfeiler-Leman) algorithm. While it is well known that the expressive power of GNNs is limited by this invariance [Morris et al., AAAI 2019; Xu et al., ICLR 2019], we establish that recurrent GNNs can actually match this limit. This is in contrast to non-recurrent GNNs, which have the power of Weisfeiler-Leman only in a very weak, "non-uniform", sense where each graph size requires a different GNN to compute with. Our construction introduces only a polynomial overhead in both time and space. - Furthermore, we show that by incorporating random initialization, for connected graphs recurrent GNNs can express all graph algorithms. In particular, any polynomial-time graph algorithm can be emulated on connected graphs in polynomial time by a recurrent GNN with random initialization. - oai:arXiv.org:2505.00291v3 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Eran Rosenbluth, Martin Grohe - - - On the Schr\"odingerization method for linear non-unitary dynamics with optimal dependence on matrix queries - https://arxiv.org/abs/2505.00370 - arXiv:2505.00370v4 Announce Type: replace -Abstract: The Schr\"odingerization method converts linear partial and ordinary differential equations with non-unitary dynamics into systems of Schr\"odinger-type equations with unitary evolution. It does so via the so-called warped phase transformation that maps the original equation into a Schr\"odinger-type equation in one higher dimension \cite{Schrshort,JLY22SchrLong}. The original proposal used a particular initial function in the auxiliary space that did not achieve optimal scaling in precision. Here we show that, by choosing smoother initial functions in auxiliary space, Schr\"odingerization \textit{can} in fact achieve near optimal and even optimal scaling in matrix queries. We construct three necessary criteria that the initial auxiliary state must satisfy to achieve optimality. This paper presents detailed implementation of four smooth initializations for the Schr\"odingerization method: (a) the error function and related functions, (b) the cut-off function, (c) the higher-order polynomial interpolation, and (d) Fourier transform methods. Method (a) achieves optimality and methods (b), (c) and (d) can achieve near-optimality. A detailed analysis of key parameters affecting time complexity is conducted. - oai:arXiv.org:2505.00370v4 - math.NA - cs.NA - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shi Jin, Nana Liu, Chuwen Ma, Yizhe Peng, Yue Yu - - - Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain - https://arxiv.org/abs/2505.01267 - arXiv:2505.01267v4 Announce Type: replace -Abstract: The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the clean images through the reverse process. Due to the lack of distribution information about adversarial perturbations in the pixel domain, it is often unavoidable to damage normal semantics. We turn to the frequency domain perspective, decomposing the image into amplitude spectrum and phase spectrum. We find that for both spectra, the damage caused by adversarial perturbations tends to increase monotonically with frequency. This means that we can extract the content and structural information of the original clean sample from the frequency components that are less damaged. Meanwhile, theoretical analysis indicates that existing purification methods indiscriminately damage all frequency components, leading to excessive damage to the image. Therefore, we propose a purification method that can eliminate adversarial perturbations while maximizing the preservation of the content and structure of the original image. Specifically, at each time step during the reverse process, for the amplitude spectrum, we replace the low-frequency components of the estimated image's amplitude spectrum with the corresponding parts of the adversarial image. For the phase spectrum, we project the phase of the estimated image into a designated range of the adversarial image's phase spectrum, focusing on the low frequencies. Empirical evidence from extensive experiments demonstrates that our method significantly outperforms most current defense methods. - oai:arXiv.org:2505.01267v4 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Gaozheng Pei, Ke Ma, Yingfei Sun, Qianqian Xu, Qingming Huang - - - LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration - https://arxiv.org/abs/2505.05031 - arXiv:2505.05031v3 Announce Type: replace -Abstract: Cloud-device collaboration leverages on-cloud Large Language Models (LLMs) for handling public user queries and on-device Small Language Models (SLMs) for processing private user data, collectively forming a powerful and privacy-preserving solution. However, existing approaches often fail to fully leverage the scalable problem-solving capabilities of on-cloud LLMs while underutilizing the advantage of on-device SLMs in accessing and processing personalized data. This leads to two interconnected issues: 1) Limited utilization of the problem-solving capabilities of on-cloud LLMs, which fail to align with personalized user-task needs, and 2) Inadequate integration of user data into on-device SLM responses, resulting in mismatches in contextual user information. - In this paper, we propose a Leader-Subordinate Retrieval framework for Privacy-preserving cloud-device collaboration (LSRP), a novel solution that bridges these gaps by: 1) enhancing on-cloud LLM guidance to on-device SLM through a dynamic selection of task-specific leader strategies named as user-to-user retrieval-augmented generation (U-U-RAG), and 2) integrating the data advantages of on-device SLMs through small model feedback Direct Preference Optimization (SMFB-DPO) for aligning the on-cloud LLM with the on-device SLM. Experiments on two datasets demonstrate that LSRP consistently outperforms state-of-the-art baselines, significantly improving question-answer relevance and personalization, while preserving user privacy through efficient on-device retrieval. Our code is available at: https://github.com/Applied-Machine-Learning-Lab/LSRP. - oai:arXiv.org:2505.05031v3 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yingyi Zhang, Pengyue Jia, Xianneng Li, Derong Xu, Maolin Wang, Yichao Wang, Zhaocheng Du, Huifeng Guo, Yong Liu, Ruiming Tang, Xiangyu Zhao - - - LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning - https://arxiv.org/abs/2505.06131 - arXiv:2505.06131v3 Announce Type: replace -Abstract: We introduce LOG-Nav, an efficient layout-aware object-goal navigation approach designed for complex multi-room indoor environments. By planning hierarchically leveraging a global topologigal map with layout information and local imperative approach with detailed scene representation memory, LOG-Nav achieves both efficient and effective navigation. The process is managed by an LLM-powered agent, ensuring seamless effective planning and navigation, without the need for human interaction, complex rewards, or costly training. Our experimental results on the MP3D benchmark achieves 85\% object navigation success rate (SR) and 79\% success rate weighted by path length (SPL) (over 40\% point improvement in SR and 60\% improvement in SPL compared to exsisting methods). Furthermore, we validate the robustness of our approach through virtual agent and real-world robotic deployment, showcasing its capability in practical scenarios. - oai:arXiv.org:2505.06131v3 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiawei Hou, Yuting Xiao, Xiangyang Xue, Taiping Zeng - - - Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correction - https://arxiv.org/abs/2505.06905 - arXiv:2505.06905v3 Announce Type: replace -Abstract: Monocular height estimation (MHE) from very-high-resolution (VHR) optical imagery remains challenging due to limited structural cues and the high cost and geographic constraints of conventional elevation data such as airborne LiDAR and multi-view stereo. Although recent MHE and monocular depth estimation (MDE) models show strong performance, their robustness under varied illumination and scene conditions is still limited. We introduce a fully automated correction pipeline that integrates sparse, imperfect global LiDAR measurements from ICESat-2 with deep learning predictions to enhance accuracy and stability. The workflow relies entirely on publicly available models and data and requires only a single georeferenced optical image to produce corrected height maps, enabling low-cost and globally scalable deployment. We also establish the first benchmark for this task, evaluating two random forest based approaches, four parameter efficient fine tuning methods, and full fine tuning. Experiments across six diverse regions at 0.5 m resolution (297 km2), covering the urban cores of Tokyo, Paris, and Sao Paulo as well as suburban and forested areas, show substantial gains. The best method reduces the MHE model's mean absolute error (MAE) by 30.9 percent and improves its F1HE score by 44.2 percent. For the MDE model, MAE improves by 24.1 percent and the F1HE score by 25.1 percent. These results validate the effectiveness of our correction pipeline and demonstrate how sparse global LiDAR can systematically strengthen both MHE and MDE models, enabling scalable and widely accessible 3D height mapping. - oai:arXiv.org:2505.06905v3 - cs.CV - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - 10.1016/j.isprsjprs.2025.12.004 - Jian Song, Hongruixuan Chen, Naoto Yokoya - - - RDD: Robust Feature Detector and Descriptor using Deformable Transformer - https://arxiv.org/abs/2505.08013 - arXiv:2505.08013v5 Announce Type: replace -Abstract: As a core step in structure-from-motion and SLAM, robust feature detection and description under challenging scenarios such as significant viewpoint changes remain unresolved despite their ubiquity. While recent works have identified the importance of local features in modeling geometric transformations, these methods fail to learn the visual cues present in long-range relationships. We present Robust Deformable Detector (RDD), a novel and robust keypoint detector/descriptor leveraging the deformable transformer, which captures global context and geometric invariance through deformable self-attention mechanisms. Specifically, we observed that deformable attention focuses on key locations, effectively reducing the search space complexity and modeling the geometric invariance. Furthermore, we collected an Air-to-Ground dataset for training in addition to the standard MegaDepth dataset. Our proposed method outperforms all state-of-the-art keypoint detection/description methods in sparse matching tasks and is also capable of semi-dense matching. To ensure comprehensive evaluation, we introduce two challenging benchmarks: one emphasizing large viewpoint and scale variations, and the other being an Air-to-Ground benchmark -- an evaluation setting that has recently gaining popularity for 3D reconstruction across different altitudes. - oai:arXiv.org:2505.08013v5 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Gonglin Chen, Tianwen Fu, Haiwei Chen, Wenbin Teng, Hanyuan Xiao, Yajie Zhao - - - Foundation Models Knowledge Distillation For Battery Capacity Degradation Forecast - https://arxiv.org/abs/2505.08151 - arXiv:2505.08151v4 Announce Type: replace -Abstract: Accurate forecasting of lithium-ion battery capacity degradation is critical for reliable and safe operation, yet remains challenging under distribution shifts across scales and operating regimes. Here we investigate a time-series foundation model, that is, a large pre-trained time-series model for capacity degradation forecasting, and propose a degradation-aware fine-tuning strategy that aligns the model to capacity trajectories while retaining broadly transferable temporal structure. We instantiate this approach by fine-tuning the Timer model on 220,153 cycles of open-source charge-discharge records to obtain Battery-Timer. Using our released CycleLife-SJTUIE dataset, a real-world industrial collection from an energy-storage station with long-horizon cycling, we evaluate capacity generalization from small cells to large-scale storage systems and across varying operating conditions. Battery-Timer consistently outperforms specialized expert models. To address deployment cost, we further introduce knowledge distillation, a teacher-student transfer that compresses the foundation model's behavior into compact expert models. Distillation across several state-of-the-art time-series experts improves multi-condition capacity generalization while substantially reducing computational overhead, indicating a practical path to deployable cross-scale degradation forecasting by combining a foundation model with targeted distillation. - oai:arXiv.org:2505.08151v4 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Joey Chan, Zhen Chen, Ershun Pan - - - Evaluating the robustness of adversarial defenses in malware detection systems - https://arxiv.org/abs/2505.09342 - arXiv:2505.09342v2 Announce Type: replace -Abstract: Machine learning is a key tool for Android malware detection, effectively identifying malicious patterns in apps. However, ML-based detectors are vulnerable to evasion attacks, where small, crafted changes bypass detection. Despite progress in adversarial defenses, the lack of comprehensive evaluation frameworks in binary-constrained domains limits understanding of their robustness. We introduce two key contributions. First, Prioritized Binary Rounding, a technique to convert continuous perturbations into binary feature spaces while preserving high attack success and low perturbation size. Second, the sigma-binary attack, a novel adversarial method for binary domains, designed to achieve attack goals with minimal feature changes. Experiments on the Malscan dataset show that sigma-binary outperforms existing attacks and exposes key vulnerabilities in state-of-the-art defenses. Defenses equipped with adversary detectors, such as KDE, DLA, DNN+, and ICNN, exhibit significant brittleness, with attack success rates exceeding 90% using fewer than 10 feature modifications and reaching 100% with just 20. Adversarially trained defenses, including AT-rFGSM-k, AT-MaxMA, improves robustness under small budgets but remains vulnerable to unrestricted perturbations, with attack success rates of 99.45% and 96.62%, respectively. Although PAD-SMA demonstrates strong robustness against state-of-the-art gradient-based adversarial attacks by maintaining an attack success rate below 16.55%, the sigma-binary attack significantly outperforms these methods, achieving a 94.56% success rate under unrestricted perturbations. These findings highlight the critical need for precise method like sigma-binary to expose hidden vulnerabilities in existing defenses and support the development of more resilient malware detection systems. - oai:arXiv.org:2505.09342v2 - cs.CR - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1016/j.compeleceng.2025.110845 - Computers & Electrical Engineering, Volume 130, February 2026, Article 110845 - Mostafa Jafari, Alireza Shameli-Sendi - - - Scalable Approximate Biclique Counting over Large Bipartite Graphs - https://arxiv.org/abs/2505.10471 - arXiv:2505.10471v2 Announce Type: replace -Abstract: Counting $(p,q)$-bicliques in bipartite graphs is crucial for a variety of applications, from recommendation systems to cohesive subgraph analysis. Yet, it remains computationally challenging due to the combinatorial explosion to exactly count the $(p,q)$-bicliques. In many scenarios, e.g., graph kernel methods, however, exact counts are not strictly required. To design a scalable and high-quality approximate solution, we novelly resort to $(p,q)$-broom, a special spanning tree of the $(p,q)$-biclique, which can be counted via graph coloring and efficient dynamic programming. Based on the intermediate results of the dynamic programming, we propose an efficient sampling algorithm to derive the approximate $(p,q)$-biclique count from the $(p,q)$-broom counts. Theoretically, our method offers unbiased estimates with provable error guarantees. Empirically, our solution outperforms existing approximation techniques in both accuracy (up to 8$\times$ error reduction) and runtime (up to 50$\times$ speedup) on nine real-world bipartite networks, providing a scalable solution for large-scale $(p,q)$-biclique counting. - oai:arXiv.org:2505.10471v2 - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jingbang Chen, Weinuo Li, Yingli Zhou, Hangrui Zhou, Qiuyang Mang, Can Wang, Yixiang Fang, Chenhao Ma - - - Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions - https://arxiv.org/abs/2505.10947 - arXiv:2505.10947v3 Announce Type: replace -Abstract: Establishing stability certificates for closed-loop systems under reinforcement learning (RL) policies is essential to move beyond empirical performance and offer guarantees of system behavior. Classical Lyapunov methods require a strict stepwise decrease in the Lyapunov function but such certificates are difficult to construct for learned policies. The RL value function is a natural candidate but it is not well understood how it can be adapted for this purpose. To gain intuition, we first study the linear quadratic regulator (LQR) problem and make two key observations. First, a Lyapunov function can be obtained from the value function of an LQR policy by augmenting it with a residual term related to the system dynamics and stage cost. Second, the classical Lyapunov decrease requirement can be relaxed to a generalized Lyapunov condition requiring only decrease on average over multiple time steps. Using this intuition, we consider the nonlinear setting and formulate an approach to learn generalized Lyapunov functions by augmenting RL value functions with neural network residual terms. Our approach successfully certifies the stability of RL policies trained on Gymnasium and DeepMind Control benchmarks. We also extend our method to jointly train neural controllers and stability certificates using a multi-step Lyapunov loss, resulting in larger certified inner approximations of the region of attraction compared to the classical Lyapunov approach. Overall, our formulation enables stability certification for a broad class of systems with learned policies by making certificates easier to construct, thereby bridging classical control theory and modern learning-based methods. - oai:arXiv.org:2505.10947v3 - cs.LG - cs.RO - cs.SY - eess.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Kehan Long, Jorge Cort\'es, Nikolay Atanasov - - - Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs - https://arxiv.org/abs/2505.11227 - arXiv:2505.11227v2 Announce Type: replace -Abstract: The development of reasoning capabilities represents a critical frontier in large language models (LLMs) research, where reinforcement learning (RL) and process reward models (PRMs) have emerged as predominant methodological frameworks. Contrary to conventional wisdom, empirical evidence from DeepSeek-R1 demonstrates that pure RL training focused on mathematical problem-solving can progressively enhance reasoning abilities without PRM integration, challenging the perceived necessity of process supervision. In this study, we conduct a systematic investigation of the relationship between RL training and PRM capabilities. Our findings demonstrate that problem-solving proficiency and process supervision capabilities represent complementary dimensions of reasoning that co-evolve synergistically during pure RL training. In particular, current PRMs underperform simple baselines like majority voting when applied to state-of-the-art models such as DeepSeek-R1 and QwQ-32B. To address this limitation, we propose Self-PRM, an introspective framework in which models autonomously evaluate and rerank their generated solutions through self-reward mechanisms. Although Self-PRM consistently improves the accuracy of the benchmark (particularly with larger sample sizes), analysis exposes persistent challenges: The approach exhibits low precision (<10\%) on difficult problems, frequently misclassifying flawed solutions as valid. These analyses underscore the need for continued RL scaling to improve reward alignment and introspective accuracy. Overall, our findings suggest that PRM may not be essential for enhancing complex reasoning, as pure RL not only improves problem-solving skills but also inherently fosters robust PRM capabilities. We hope these findings provide actionable insights for building more reliable and self-aware complex reasoning models. - oai:arXiv.org:2505.11227v2 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Zhangying Feng, Qianglong Chen, Ning Lu, Yongqian Li, Siqi Cheng, Shuangmu Peng, Duyu Tang, Shengcai Liu, Zhirui Zhang - - - Discrete Time Credit-Based Shaping for Time-Sensitive Applications in 5G/6G Networks - https://arxiv.org/abs/2505.12091 - arXiv:2505.12091v2 Announce Type: replace -Abstract: Future wireless networks must deliver deterministic end-to-end delays for workloads such as smart-factory control loops. On Ethernet these guarantees are delivered by the set of tools within IEEE 802.1 time sensitive networking~(TSN) standards. Credit-based shaper (CBS) is one such tool which enforces bounded latency. Directly porting CBS to 5G/6G New Radio (NR) is non-trivial because NR schedules traffic in discrete-time, modulation-dependent resource allocation, whereas CBS assumes a continuous, fixed-rate link. Existing TSN-over-5G translators map Ethernet priorities to 5G quality of service (QoS) identifiers but leave the radio scheduler unchanged, so deterministic delay is lost within the radio access network (RAN). To address this challenge, we propose a novel slot-native approach that adapts CBS to operate natively in discrete NR slots. We first propose a per-slot credit formulation for each user-equipment ({UE}) queue that debits credit by the granted transport block size~(TBS); we call this discrete-time CBS (CBS-DT). Recognizing that debiting the full {TBS} can unduly penalize transmissions that actually use only part of their grant, we then introduce and analyze {CBS} with Partial Usage ({CBS-PU}). {CBS-PU} scales the credit debit in proportion to the actual bytes dequeued from the downlink queue. The resulting CBS-PU algorithm is shown to maintain bounded credit, preserve long-term rate reservations, and guarantees worst-case delay performance no worse than {CBS-DT}. Simulation results show that slot-level credit gating--particularly CBS-PU--enables NR to export TSN class QoS while maximizing resource utilization. - oai:arXiv.org:2505.12091v2 - cs.NI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Anudeep Karnam, Kishor C. Joshi, Jobish John, George Exarchakos, Sonia Heemstra de Groot, Ignas Niemegeers - - - Dribble Master: Learning Agile Humanoid Dribbling Through Legged Locomotion - https://arxiv.org/abs/2505.12679 - arXiv:2505.12679v2 Announce Type: replace -Abstract: Humanoid soccer dribbling is a highly challenging task that demands dexterous ball manipulation while maintaining dynamic balance. Traditional rule-based methods often struggle to achieve accurate ball control due to their reliance on fixed walking patterns and limited adaptability to real-time ball dynamics. To address these challenges, we propose a two-stage curriculum learning framework that enables a humanoid robot to acquire dribbling skills without explicit dynamics or predefined trajectories. In the first stage, the robot learns basic locomotion skills; in the second stage, we fine-tune the policy for agile dribbling maneuvers. We further introduce a virtual camera model in simulation that simulates the field of view and perception constraints of the real robot, enabling realistic ball perception during training. We also design heuristic rewards to encourage active sensing, promoting a broader visual range for continuous ball perception. The policy is trained in simulation and successfully transferred to a physical humanoid robot. Experiment results demonstrate that our method enables effective ball manipulation, achieving flexible and visually appealing dribbling behaviors across multiple environments. This work highlights the potential of reinforcement learning in developing agile humanoid soccer robots. Additional details and videos are available at https://zhuoheng0910.github.io/dribble-master/. - oai:arXiv.org:2505.12679v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhuoheng Wang, Jinyin Zhou, Qi Wu - - - Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning - https://arxiv.org/abs/2505.14069 - arXiv:2505.14069v3 Announce Type: replace -Abstract: Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows and lack the adaptability required for multistep reasoning and complex task management. To address these limitations, agentic RAG systems (e.g., DeepResearch) have been proposed, enabling dynamic retrieval strategies, iterative context refinement, and adaptive workflows for handling complex search queries beyond the capabilities of conventional RAG. Recent advances, such as Search-R1, have demonstrated promising gains using outcome-based reinforcement learning, where the correctness of the final answer serves as the reward signal. Nevertheless, such outcome-supervised agentic RAG methods face challenges including low exploration efficiency, gradient conflict, and sparse reward signals. To overcome these challenges, we propose to utilize fine-grained, process-level rewards to improve training stability, reduce computational costs, and enhance efficiency. Specifically, we introduce a novel method ReasonRAG that automatically constructs RAG-ProGuide, a high-quality dataset providing process-level rewards for (i) query generation, (ii) evidence extraction, and (iii) answer generation, thereby enhancing model inherent capabilities via process-supervised reinforcement learning. With the process-level policy optimization, the proposed framework empowers LLMs to autonomously invoke search, generate queries, extract relevant evidence, and produce final answers. Compared to existing approaches such as Search-R1 and traditional RAG systems, ReasonRAG, leveraging RAG-ProGuide, achieves superior performance on five benchmark datasets using only 5k training instances, significantly fewer than the 90k training instances required by Search-R1. - oai:arXiv.org:2505.14069v3 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wenlin Zhang, Xiangyang Li, Kuicai Dong, Yichao Wang, Pengyue Jia, Xiaopeng Li, Yingyi Zhang, Derong Xu, Zhaocheng Du, Huifeng Guo, Ruiming Tang, Xiangyu Zhao - - - Redox: Improving I/O Efficiency of Model Training Through File Redirection - https://arxiv.org/abs/2505.16280 - arXiv:2505.16280v2 Announce Type: replace -Abstract: This paper proposes Redox, a training data management system designed to achieve high I/O efficiency. The key insight is a new observation of file redirection: for model training, when training data in one file is requested, the system has the flexibility to return the data of another file. Based on this property, Redox starts with a bold design principle that chunks of data files are always read from disk in batch, and once loaded, all files in the chunk will be consumed without being loaded again. We propose efficient local and distributed file read protocol based on this principle that both minimizes the wasted data read and enables opportunistic prefetch from remote node. Moreover, we analyze file redirection's impact on randomness, and show that it has little effects on training efficiency. Experimental results indicate that Redox significantly accelerates data fetching in training, achieving up to a 4.57x improvement in end-to-end training compared to PyTorch. - oai:arXiv.org:2505.16280v2 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuhao Li, Xuanhua Shi, Yunfei Zhao, Yongluan Zhou, Yusheng Hua, Xuehai Qian - - - LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision - https://arxiv.org/abs/2505.18051 - arXiv:2505.18051v2 Announce Type: replace -Abstract: Vision transformers are ever larger, more accurate, and more expensive to compute. The expense is even more extreme at high resolution as the number of tokens grows quadratically with the image size. We turn to adaptive computation to cope with this cost by learning to predict where to compute. Our LookWhere method divides the computation between a low-resolution selector and a high-resolution extractor without ever processing the full high-resolution input. We jointly pretrain the selector and extractor without task supervision by distillation from a self-supervised teacher, in effect, learning where and what to compute simultaneously. Unlike prior token reduction methods, which pay to save by pruning already-computed tokens, and prior token selection methods, which require complex and expensive per-task optimization, LookWhere economically and accurately selects and extracts transferrable representations of images. We show that LookWhere excels at sparse recognition on high-resolution inputs (Traffic Signs), maintaining accuracy while reducing FLOPs by up to 34x and time by 6x. It also excels at standard recognition tasks that are global (ImageNet classification) or local (ADE20K segmentation), improving accuracy while reducing time by 1.36x. See https://github.com/antofuller/lookwhere for the code and weights. - oai:arXiv.org:2505.18051v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Anthony Fuller, Yousef Yassin, Junfeng Wen, Daniel G. Kyrollos, Tarek Ibrahim, James R. Green, Evan Shelhamer - - - BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs - https://arxiv.org/abs/2505.18229 - arXiv:2505.18229v2 Announce Type: replace -Abstract: With the rapid advancement of low-altitude remote sensing and Vision-Language Models (VLMs), Embodied Agents based on Unmanned Aerial Vehicles (UAVs) have shown significant potential in autonomous tasks. However, current evaluation methods for UAV-Embodied Agents (UAV-EAs) remain constrained by the lack of standardized benchmarks, diverse testing scenarios and open system interfaces. To address these challenges, we propose BEDI (Benchmark for Embodied Drone Intelligence), a systematic and standardized benchmark designed for evaluating UAV-EAs. Specifically, we introduce a novel Dynamic Chain-of-Embodied-Task paradigm based on the perception-decision-action loop, which decomposes complex UAV tasks into standardized, measurable subtasks. Building on this paradigm, we design a unified evaluation framework encompassing six core sub-skills: semantic perception, spatial perception, motion control, tool utilization, task planning and action generation. Furthermore, we develop a hybrid testing platform that incorporates a wide range of both virtual and real-world scenarios, enabling a comprehensive evaluation of UAV-EAs across diverse contexts. The platform also offers open and standardized interfaces, allowing researchers to customize tasks and extend scenarios, thereby enhancing flexibility and scalability in the evaluation process. Finally, through empirical evaluations of several state-of-the-art (SOTA) VLMs, we reveal their limitations in embodied UAV tasks, underscoring the critical role of the BEDI benchmark in advancing embodied intelligence research and model optimization. By filling the gap in systematic and standardized evaluation within this field, BEDI facilitates objective model comparison and lays a robust foundation for future development in this field. Our benchmark is now publicly available at https://github.com/lostwolves/BEDI. - oai:arXiv.org:2505.18229v2 - cs.RO - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mingning Guo, Mengwei Wu, Jiarun He, Shaoxian Li, Haifeng Li, Chao Tao - - - Mind The Gap: Quantifying Mechanistic Gaps in Algorithmic Reasoning via Neural Compilation - https://arxiv.org/abs/2505.18623 - arXiv:2505.18623v2 Announce Type: replace -Abstract: This paper aims to understand how neural networks learn algorithmic reasoning by addressing two questions: How faithful are learned algorithms when they are effective, and why do neural networks fail to learn effective algorithms otherwise? To answer these questions, we use neural compilation, a technique that directly encodes a source algorithm into neural network parameters, enabling the network to compute the algorithm exactly. This enables comparison between compiled and conventionally learned parameters, intermediate vectors, and behaviors. This investigation is crucial for developing neural networks that robustly learn complexalgorithms from data. Our analysis focuses on graph neural networks (GNNs), which are naturally aligned with algorithmic reasoning tasks, specifically our choices of BFS, DFS, and Bellman-Ford, which cover the spectrum of effective, faithful, and ineffective learned algorithms. Commonly, learning algorithmic reasoning is framed as induction over synthetic data, where a parameterized model is trained on inputs, traces, and outputs produced by an underlying ground truth algorithm. In contrast, we introduce a neural compilation method for GNNs, which sets network parameters analytically, bypassing training. Focusing on GNNs leverages their alignment with algorithmic reasoning, extensive algorithmic induction literature, and the novel application of neural compilation to GNNs. Overall, this paper aims to characterize expressability-trainability gaps - a fundamental shortcoming in learning algorithmic reasoning. We hypothesize that inductive learning is most effective for parallel algorithms contained within the computational class \texttt{NC}. - oai:arXiv.org:2505.18623v2 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Lucas Saldyt, Subbarao Kambhampati - - - Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains - https://arxiv.org/abs/2505.19397 - arXiv:2505.19397v2 Announce Type: replace -Abstract: Time-Series Foundation Models (TSFMs) are rapidly transitioning from research prototypes to core components of critical decision-making systems, driven by their impressive zero-shot forecasting capabilities. However, as their deployment surges, a critical blind spot remains: their fragility under adversarial attacks. This lack of scrutiny poses severe risks, particularly as TSFMs enter high-stakes environments vulnerable to manipulation. We present a systematic, diagnostic study arguing that for TSFMs, robustness is not merely a secondary metric but a prerequisite for trustworthy deployment comparable to accuracy. Our evaluation framework, explicitly tailored to the unique constraints of time series, incorporates normalized, sparsity-aware perturbation budgets and unified scale-invariant metrics across white-box and black-box settings. Across six representative TSFMs, we demonstrate that current architectures are alarmingly brittle: even small perturbations can reliably steer forecasts toward specific failure modes, such as trend flips and malicious drifts. We uncover TSFM-specific vulnerability patterns, including horizon-proximal brittleness, increased susceptibility with longer context windows, and weak cross-model transfer that points to model-specific failure modes rather than generic distortions. Finally, we show that simple adversarial fine-tuning offers a cost-effective path to substantial robustness gains, even with out-of-domain data. This work bridges the gap between TSFM capabilities and safety constraints, offering essential guidance for hardening the next generation of forecasting systems. - oai:arXiv.org:2505.19397v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiawen Zhang, Zhenwei Zhang, Shun Zheng, Xumeng Wen, Jia Li, Jiang Bian - - - Structured Initialization for Vision Transformers - https://arxiv.org/abs/2505.19985 - arXiv:2505.19985v2 Announce Type: replace -Abstract: Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating this inductive bias into ViTs, not through an architectural intervention but solely through initialization. The motivation here is to have a ViT that can enjoy strong CNN-like performance when data assets are small, but can still scale to ViT-like performance as the data expands. Our approach is motivated by our empirical results that random impulse filters can achieve commensurate performance to learned filters within a CNN. We improve upon current ViT initialization strategies, which typically rely on empirical heuristics such as using attention weights from pretrained models or focusing on the distribution of attention weights without enforcing structures. Empirical results demonstrate that our method significantly outperforms standard ViT initialization across numerous small and medium-scale benchmarks, including Food-101, CIFAR-10, CIFAR-100, STL-10, Flowers, and Pets, while maintaining comparative performance on large-scale datasets such as ImageNet-1K. Moreover, our initialization strategy can be easily integrated into various transformer-based architectures such as Swin Transformer and MLP-Mixer with consistent improvements in performance. - oai:arXiv.org:2505.19985v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Jianqiao Zheng, Xueqian Li, Hemanth Saratchandran, Simon Lucey - - - Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning - https://arxiv.org/abs/2505.20561 - arXiv:2505.20561v2 Announce Type: replace -Abstract: Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error correction, as a form of in-context exploration. However, the Markovian policy obtained from conventional RL training does not give rise to reflective exploration behaviors since the policy depends on the history only through the state and therefore has no incentive to enrich identical states with additional context. Instead, RL exploration is only useful during training to learn the optimal policy in a trial-and-error manner. Therefore, it remains unclear whether reflective reasoning will emerge during RL, or why it is beneficial. To remedy this, we recast reflective exploration within a Bayesian RL framework, which optimizes the expected return under a posterior distribution over Markov decision processes induced by the training data. This Bayesian formulation admits uncertainty-adaptive policies that, through belief updates, naturally incentivize information-gathering actions and induce self-reflection behaviors. Our resulting algorithm, BARL, instructs the LLM to stitch and switch strategies based on the observed outcomes, offering principled guidance on when and how the model should reflectively explore. Empirical results on both synthetic and mathematical reasoning tasks demonstrate that BARL outperforms conventional RL approaches, achieving superior test-time performance and token efficiency. Our code is available at https://github.com/shenao-zhang/BARL. - oai:arXiv.org:2505.20561v2 - cs.LG - cs.AI - cs.CL - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shenao Zhang, Yaqing Wang, Yinxiao Liu, Tianqi Liu, Peter Grabowski, Eugene Ie, Zhaoran Wang, Yunxuan Li - - - Large Language Models Miss the Multi-Agent Mark - https://arxiv.org/abs/2505.21298 - arXiv:2505.21298v4 Announce Type: replace -Abstract: Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of this literature appropriates the terminology of MAS without engaging with its foundational principles. In this position paper, we highlight critical discrepancies between MAS theory and current MAS LLMs implementations, focusing on four key areas: the social aspect of agency, environment design, coordination and communication protocols, and measuring emergent behaviours. Our position is that many MAS LLMs lack multi-agent characteristics such as autonomy, social interaction, and structured environments, and often rely on oversimplified, LLM-centric architectures. The field may slow down and lose traction by revisiting problems the MAS literature has already addressed. Therefore, we systematically analyse this issue and outline associated research opportunities; we advocate for better integrating established MAS concepts and more precise terminology to avoid mischaracterisation and missed opportunities. - oai:arXiv.org:2505.21298v4 - cs.MA - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Emanuele La Malfa, Gabriele La Malfa, Samuele Marro, Jie M. Zhang, Elizabeth Black, Michael Luck, Philip Torr, Michael Wooldridge - - - Learning where to learn: Training data distribution optimization for scientific machine learning - https://arxiv.org/abs/2505.21626 - arXiv:2505.21626v3 Announce Type: replace -Abstract: In scientific machine learning, models are routinely deployed with parameter values or boundary conditions far from those used in training. This paper studies the learning-where-to-learn problem of designing a training data distribution that minimizes average prediction error across a family of deployment regimes. A theoretical analysis shows how the training distribution shapes deployment accuracy. This motivates two adaptive algorithms based on bilevel or alternating optimization in the space of probability measures. Discretized implementations using parametric distribution classes or nonparametric particle-based gradient flows deliver optimized training distributions that outperform nonadaptive designs. Once trained, the resulting models exhibit improved sample complexity and robustness to distribution shift. This framework unlocks the potential of principled data acquisition for learning functions and solution operators of partial differential equations. - oai:arXiv.org:2505.21626v3 - cs.LG - math.OC - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nicolas Guerra, Nicholas H. Nelsen, Yunan Yang - - - LLMs Judging LLMs: A Simplex Perspective - https://arxiv.org/abs/2505.21972 - arXiv:2505.21972v2 Announce Type: replace -Abstract: Given the challenge of automatically evaluating free-form outputs from large language models (LLMs), an increasingly common solution is to use LLMs themselves as the judging mechanism, without any gold-standard scores. Implicitly, this practice accounts for only sampling variability (aleatoric uncertainty) and ignores uncertainty about judge quality (epistemic uncertainty). While this is justified if judges are perfectly accurate, it is unclear when such an approach is theoretically valid and practically robust. We study these questions for the task of ranking LLM candidates from a novel geometric perspective: for $M$-level scoring systems, both LLM judges and candidates can be represented as points on an $(M-1)$-dimensional probability simplex, where geometric concepts (e.g., triangle areas) correspond to key ranking concepts. This perspective yields intuitive theoretical conditions and visual proofs for when rankings are identifiable; for instance, we provide a formal basis for the ``folk wisdom'' that LLM judges are more effective for two-level scoring ($M=2$) than multi-level scoring ($M>2$). Leveraging the simplex, we design geometric Bayesian priors that encode epistemic uncertainty about judge quality and vary the priors to conduct sensitivity analyses. Experiments on LLM benchmarks show that rankings based solely on LLM judges are robust in many but not all datasets, underscoring both their widespread success and the need for caution. Our Bayesian method achieves substantially higher coverage rates than existing procedures, highlighting the importance of modeling epistemic uncertainty. - oai:arXiv.org:2505.21972v2 - cs.LG - cs.AI - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Patrick Vossler, Fan Xia, Yifan Mai, Adarsh Subbaswamy, Jean Feng - - - LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents - https://arxiv.org/abs/2505.22634 - arXiv:2505.22634v2 Announce Type: replace -Abstract: Scientific embodied agents play a crucial role in modern laboratories by automating complex experimental workflows. Compared to typical household environments, laboratory settings impose significantly higher demands on perception of physical-chemical transformations and long-horizon planning, making them an ideal testbed for advancing embodied intelligence. However, its development has been long hampered by the lack of suitable simulator and benchmarks. In this paper, we address this gap by introducing LabUtopia, a comprehensive simulation and benchmarking suite designed to facilitate the development of generalizable, reasoning-capable embodied agents in laboratory settings. Specifically, it integrates i) LabSim, a high-fidelity simulator supporting multi-physics and chemically meaningful interactions; ii) LabScene, a scalable procedural generator for diverse scientific scenes; and iii) LabBench, a hierarchical benchmark spanning five levels of complexity from atomic actions to long-horizon mobile manipulation. LabUtopia supports 30 distinct tasks and includes more than 200 scene and instrument assets, enabling large-scale training and principled evaluation in high-complexity environments. We demonstrate that LabUtopia offers a powerful platform for advancing the integration of perception, planning, and control in scientific-purpose agents and provides a rigorous testbed for exploring the practical capabilities and generalization limits of embodied intelligence in future research. - oai:arXiv.org:2505.22634v2 - cs.RO - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Rui Li, Zixuan Hu, Wenxi Qu, Jinouwen Zhang, Zhenfei Yin, Sha Zhang, Xuantuo Huang, Hanqing Wang, Tai Wang, Jiangmiao Pang, Wanli Ouyang, Lei Bai, Wangmeng Zuo, Ling-Yu Duan, Dongzhan Zhou, Shixiang Tang - - - An additive two-level parallel variant of the DMRG algorithm with coarse-space correction - https://arxiv.org/abs/2505.23429 - arXiv:2505.23429v2 Announce Type: replace -Abstract: The density matrix renormalization group (DMRG) algorithm is a popular alternating minimization scheme for solving high-dimensional optimization problems in the tensor train format. Classical DMRG, however, is based on sequential minimization, which raises challenges in its implementation on parallel computing architectures. To overcome this, we propose a novel additive two-level DMRG algorithm that combines independent, local minimization steps with a global update step using a subsequent coarse-space minimization. Our proposed algorithm, which is directly inspired by additive Schwarz methods from the domain decomposition literature, is particularly amenable to implementation on parallel, distributed architectures since both the local minimization steps and the construction of the coarse-space can be performed in parallel. Numerical experiments on strongly correlated molecular systems demonstrate that the method achieves competitive convergence rates while achieving significant parallel speedups. - oai:arXiv.org:2505.23429v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Laura Grigori, Muhammad Hassan - - - Stepsize anything: A unified learning rate schedule for budgeted-iteration training - https://arxiv.org/abs/2505.24452 - arXiv:2505.24452v4 Announce Type: replace -Abstract: The expanding computational costs and limited resources underscore the critical need for budgeted-iteration training, which aims to achieve optimal learning within predetermined iteration budgets. While learning rate schedules fundamentally govern the performance of different networks and tasks, particularly in budgeted-iteration scenarios, their design remains largely heuristic, lacking theoretical foundations. In addition, the optimal learning rate schedule requires extensive trial-and-error selection, making the training process inefficient. In this work, we propose the Unified Budget-Aware (UBA) schedule, a theoretically grounded learning rate schedule that consistently outperforms commonly-used schedules among diverse architectures and tasks under different constrained training budgets. First, we bridge the gap by constructing a novel training budget-aware optimization framework, which explicitly accounts for the robustness to landscape curvature variations. From this framework, we derive the UBA schedule, controlled by a single hyper-parameter \varphi that provides a trade-off between flexibility and simplicity, eliminating the need for per-network numerical optimization. Moreover, we establish a theoretical connection between \varphi and the condition number, adding interpretation and justification to our approach. Besides, we prove the convergence for different values of \varphi. We offer practical guidelines for its selection via theoretical analysis and empirical results. Extensive experimental results show that UBA consistently surpasses the commonly-used schedules across diverse vision and language tasks, spanning network architectures (e.g., ResNet, OLMo) and scales, under different training-iteration budgets. - oai:arXiv.org:2505.24452v4 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - NeurIPS 2025 - Anda Tang, Yiming Dong, Yutao Zeng, zhou Xun, Zhouchen Lin - - - CoP: Agentic Red-teaming for Large Language Models using Composition of Principles - https://arxiv.org/abs/2506.00781 - arXiv:2506.00781v3 Announce Type: replace -Abstract: Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance by tricking the target LLMs into answering harmful and risky responses, are becoming an urgent concern. The practice of red-teaming for LLMs is to proactively explore potential risks and error-prone instances before the release of frontier AI technology. This paper proposes an agentic workflow to automate and scale the red-teaming process of LLMs through the Composition-of-Principles (CoP) framework, where human users provide a set of red-teaming principles as instructions to an AI agent to automatically orchestrate effective red-teaming strategies and generate jailbreak prompts. Distinct from existing red-teaming methods, our CoP framework provides a unified and extensible framework to encompass and orchestrate human-provided red-teaming principles to enable the automated discovery of new red-teaming strategies. When tested against leading LLMs, CoP reveals unprecedented safety risks by finding novel jailbreak prompts and improving the best-known single-turn attack success rate by up to 19.0 times. - oai:arXiv.org:2506.00781v3 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Chen Xiong, Pin-Yu Chen, Tsung-Yi Ho - - - Unlearning Inversion Attacks for Graph Neural Networks - https://arxiv.org/abs/2506.00808 - arXiv:2506.00808v2 Announce Type: replace -Abstract: Graph unlearning methods aim to efficiently remove the impact of sensitive data from trained GNNs without full retraining, assuming that deleted information cannot be recovered. In this work, we challenge this assumption by introducing the graph unlearning inversion attack: given only black-box access to an unlearned GNN and partial graph knowledge, can an adversary reconstruct the removed edges? We identify two key challenges: varying probability-similarity thresholds for unlearned versus retained edges, and the difficulty of locating unlearned edge endpoints, and address them with TrendAttack. First, we derive and exploit the confidence pitfall, a theoretical and empirical pattern showing that nodes adjacent to unlearned edges exhibit a large drop in model confidence. Second, we design an adaptive prediction mechanism that applies different similarity thresholds to unlearned and other membership edges. Our framework flexibly integrates existing membership inference techniques and extends them with trend features. Experiments on four real-world datasets demonstrate that TrendAttack significantly outperforms state-of-the-art GNN membership inference baselines, exposing a critical privacy vulnerability in current graph unlearning methods. - oai:arXiv.org:2506.00808v2 - cs.LG - cs.AI - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1145/3773966.3777929 - WSDM 2026 - Jiahao Zhang, Yilong Wang, Zhiwei Zhang, Xiaorui Liu, Suhang Wang - - - 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding - https://arxiv.org/abs/2506.01946 - arXiv:2506.01946v2 Announce Type: replace -Abstract: Recent advances in scene understanding have leveraged multimodal large language models (MLLMs) for 3D reasoning by capitalizing on their strong 2D pretraining. However, the lack of explicit 3D data during MLLM pretraining limits 3D representation capability. In this paper, we investigate the 3D-awareness of MLLMs by evaluating multi-view correspondence and reveal a strong positive correlation between the quality of 3D-aware representation and downstream task performance. Motivated by this, we propose 3DRS, a framework that enhances MLLM 3D representation learning by introducing supervision from pretrained 3D foundation models. Our approach aligns MLLM visual features with rich 3D knowledge distilled from 3D models, effectively improving scene understanding. Extensive experiments across multiple benchmarks and MLLMs -- including visual grounding, captioning, and question answering -- demonstrate consistent performance gains. Project page: https://visual-ai.github.io/3drs - oai:arXiv.org:2506.01946v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaohu Huang, Jingjing Wu, Qunyi Xie, Kai Han - - - Normalize Filters! Classical Wisdom for Deep Vision - https://arxiv.org/abs/2506.04401 - arXiv:2506.04401v3 Announce Type: replace -Abstract: Classical image filters, such as those for averaging or differencing, are carefully normalized to ensure consistency, interpretability, and to avoid artifacts like intensity shifts, halos, or ringing. In contrast, convolutional filters learned end-to-end in deep networks lack such constraints. Although they may resemble wavelets and blob/edge detectors, they are not normalized in the same or any way. Consequently, when images undergo atmospheric transfer, their responses become distorted, leading to incorrect outcomes. We address this limitation by proposing filter normalization, followed by learnable scaling and shifting, akin to batch normalization. This simple yet effective modification ensures that the filters are atmosphere-equivariant, enabling co-domain symmetry. By integrating classical filtering principles into deep learning (applicable to both convolutional neural networks and convolution-dependent vision transformers), our method achieves significant improvements on artificial and natural intensity variation benchmarks. Our ResNet34 could even outperform CLIP by a large margin. Our analysis reveals that unnormalized filters degrade performance, whereas filter normalization regularizes learning, promotes diversity, and improves robustness and generalization. - oai:arXiv.org:2506.04401v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Gustavo Perez, Stella X. Yu - - - Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences - https://arxiv.org/abs/2506.04478 - arXiv:2506.04478v2 Announce Type: replace -Abstract: The rise of Large Language Models (LLMs) has driven progress in reasoning tasks -- from program synthesis to scientific hypothesis generation -- yet their ability to handle ranked preferences and structured algorithms in combinatorial domains remains underexplored. We study matching markets, a core framework behind applications like resource allocation and ride-sharing, which require reconciling individual ranked preferences to ensure stable outcomes. We evaluate several state-of-the-art models on a hierarchy of preference-based reasoning tasks -- ranging from stable-matching generation to instability detection, instability resolution, and fine-grained preference queries -- to systematically expose their logical and algorithmic limitations in handling ranked inputs. Surprisingly, even top-performing models with advanced reasoning struggle to resolve instability in large markets, often failing to identify blocking pairs or execute algorithms iteratively. We further show that parameter-efficient fine-tuning (LoRA) significantly improves performance in small markets, but fails to bring about a similar improvement on large instances, suggesting the need for more sophisticated strategies to improve LLMs' reasoning with larger-context inputs. - oai:arXiv.org:2506.04478v2 - cs.AI - cs.GT - econ.TH - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hadi Hosseini, Samarth Khanna, Ronak Singh - - - Exploring Adversarial Watermarking in Transformer-Based Models: Transferability and Robustness Against Defense Mechanism for Medical Images - https://arxiv.org/abs/2506.06389 - arXiv:2506.06389v2 Announce Type: replace -Abstract: Deep learning models have shown remarkable success in dermatological image analysis, offering potential for automated skin disease diagnosis. Previously, convolutional neural network(CNN) based architectures have achieved immense popularity and success in computer vision (CV) based task like skin image recognition, generation and video analysis. But with the emergence of transformer based models, CV tasks are now are nowadays carrying out using these models. Vision Transformers (ViTs) is such a transformer-based models that have shown success in computer vision. It uses self-attention mechanisms to achieve state-of-the-art performance across various tasks. However, their reliance on global attention mechanisms makes them susceptible to adversarial perturbations. This paper aims to investigate the susceptibility of ViTs for medical images to adversarial watermarking-a method that adds so-called imperceptible perturbations in order to fool models. By generating adversarial watermarks through Projected Gradient Descent (PGD), we examine the transferability of such attacks to CNNs and analyze the performance defense mechanism -- adversarial training. Results indicate that while performance is not compromised for clean images, ViTs certainly become much more vulnerable to adversarial attacks: an accuracy drop of as low as 27.6%. Nevertheless, adversarial training raises it up to 90.0%. - oai:arXiv.org:2506.06389v2 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Rifat Sadik, Tanvir Rahman, Arpan Bhattacharjee, Bikash Chandra Halder, Ismail Hossain, Rifat Sarker Aoyon, Md. Golam Rabiul Alam, Jia Uddin - - - Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regression - https://arxiv.org/abs/2506.06954 - arXiv:2506.06954v2 Announce Type: replace -Abstract: Mainstream approximate action-value iteration reinforcement learning (RL) algorithms suffer from overestimation bias, leading to suboptimal policies in high-variance stochastic environments. Quantile-based action-value iteration methods reduce this bias by learning a distribution of the expected cost-to-go using quantile regression. However, ensuring that the learned policy satisfies safety constraints remains a challenge when these constraints are not explicitly integrated into the RL framework. Existing methods often require complex neural architectures or manual tradeoffs due to combined cost functions. To address this, we propose a risk-regularized quantile-based algorithm integrating Conditional Value-at-Risk (CVaR) to enforce safety without complex architectures. We also provide theoretical guarantees on the contraction properties of the risk-sensitive distributional Bellman operator in Wasserstein space, ensuring convergence to a unique cost distribution. Simulations of a mobile robot in a dynamic reach-avoid task show that our approach leads to more goal successes, fewer collisions, and better safety-performance trade-offs than risk-neutral methods. - oai:arXiv.org:2506.06954v2 - cs.LG - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Clinton Enwerem, Aniruddh G. Puranic, John S. Baras, Calin Belta - - - Primal-Dual iLQR for GPU-Accelerated Learning and Control in Legged Robots - https://arxiv.org/abs/2506.07823 - arXiv:2506.07823v3 Announce Type: replace -Abstract: This paper introduces a novel Model Predictive Control (MPC) implementation for legged robot locomotion that leverages GPU parallelization. Our approach enables both temporal and state-space parallelization by incorporating a parallel associative scan to solve the primal-dual Karush-Kuhn-Tucker (KKT) system. In this way, the optimal control problem is solved in $\mathcal{O}(\log^2(n)\log{N} + \log^2(m))$ complexity, instead of $\mathcal{O}(N(n + m)^3)$, where $n$, $m$, and $N$ are the dimension of the system state, control vector, and the length of the prediction horizon. We demonstrate the advantages of this implementation over two state-of-the-art solvers (acados and crocoddyl), achieving up to a 60\% improvement in runtime for Whole Body Dynamics (WB)-MPC and a 700\% improvement for Single Rigid Body Dynamics (SRBD)-MPC when varying the prediction horizon length. The presented formulation scales efficiently with the problem state dimensions as well, enabling the definition of a centralized controller for up to 16 legged robots that can be computed in less than 25 ms. Furthermore, thanks to the JAX implementation, the solver supports large-scale parallelization across multiple environments, allowing the possibility of performing learning with the MPC in the loop directly in GPU. The code associated with this work can be found at https://github.com/iit-DLSLab/mpx. - oai:arXiv.org:2506.07823v3 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/LRA.2025.3632610 - IEEE Robotics and Automation Letters, 2026, vol. 11, no. 1, pp. 1010-1017 - Lorenzo Amatucci, Jo\~ao Sousa-Pinto, Giulio Turrisi, Dominique Orban, Victor Barasuol, Claudio Semini - - - PlayerOne: Egocentric World Simulator - https://arxiv.org/abs/2506.09995 - arXiv:2506.09995v2 Announce Type: replace -Abstract: We introduce PlayerOne, the first egocentric realistic world simulator, facilitating immersive and unrestricted exploration within vividly dynamic environments. Given an egocentric scene image from the user, PlayerOne can accurately construct the corresponding world and generate egocentric videos that are strictly aligned with the real scene human motion of the user captured by an exocentric camera. PlayerOne is trained in a coarse-to-fine pipeline that first performs pretraining on large-scale egocentric text-video pairs for coarse-level egocentric understanding, followed by finetuning on synchronous motion-video data extracted from egocentric-exocentric video datasets with our automatic construction pipeline. Besides, considering the varying importance of different components, we design a part-disentangled motion injection scheme, enabling precise control of part-level movements. In addition, we devise a joint reconstruction framework that progressively models both the 4D scene and video frames, ensuring scene consistency in the long-form video generation. Experimental results demonstrate its great generalization ability in precise control of varying human movements and worldconsistent modeling of diverse scenarios. It marks the first endeavor into egocentric real-world simulation and can pave the way for the community to delve into fresh frontiers of world modeling and its diverse applications. - oai:arXiv.org:2506.09995v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Yuanpeng Tu, Hao Luo, Xi Chen, Xiang Bai, Fan Wang, Hengshuang Zhao - - - Improving Medical Visual Representation Learning with Pathological-level Cross-Modal Alignment and Correlation Exploration - https://arxiv.org/abs/2506.10573 - arXiv:2506.10573v2 Announce Type: replace -Abstract: Learning medical visual representations from image-report pairs through joint learning has garnered increasing research attention due to its potential to alleviate the data scarcity problem in the medical domain. The primary challenges stem from the lengthy reports that feature complex discourse relations and semantic pathologies. Previous works have predominantly focused on instance-wise or token-wise cross-modal alignment, often neglecting the importance of pathological-level consistency. This paper presents a novel framework PLACE that promotes the Pathological-Level Alignment and enriches the fine-grained details via Correlation Exploration without additional human annotations. Specifically, we propose a novel pathological-level cross-modal alignment (PCMA) approach to maximize the consistency of pathology observations from both images and reports. To facilitate this, a Visual Pathology Observation Extractor is introduced to extract visual pathological observation representations from localized tokens. The PCMA module operates independently of any external disease annotations, enhancing the generalizability and robustness of our methods. Furthermore, we design a proxy task that enforces the model to identify correlations among image patches, thereby enriching the fine-grained details crucial for various downstream tasks. Experimental results demonstrate that our proposed framework achieves new state-of-the-art performance on multiple downstream tasks, including classification, image-to-text retrieval, semantic segmentation, object detection and report generation. Code is available at https://github.com/Markin-Wang/PLACE. - oai:arXiv.org:2506.10573v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/JBHI.2025.3624382 - Jun Wang, Lixing Zhu, Xiaohan Yu, Abhir Bhalerao, Yulan He - - - Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models - https://arxiv.org/abs/2506.12758 - arXiv:2506.12758v2 Announce Type: replace -Abstract: As Large Language Models (LLMs) become increasingly integrated into everyday life and information ecosystems, concerns about their implicit biases continue to persist. While prior work has primarily examined socio-demographic and left--right political dimensions, little attention has been paid to how LLMs align with broader geopolitical value systems, particularly the democracy--authoritarianism spectrum. In this paper, we propose a novel methodology to assess such alignment, combining (1) the F-scale, a psychometric tool for measuring authoritarian tendencies, (2) FavScore, a newly introduced metric for evaluating model favorability toward world leaders, and (3) role-model probing to assess which figures are cited as general role-models by LLMs. We find that LLMs generally favor democratic values and leaders, but exhibit increased favorability toward authoritarian figures when prompted in Mandarin. Further, models are found to often cite authoritarian figures as role models, even outside explicit political contexts. These results shed light on ways LLMs may reflect and potentially reinforce global political ideologies, highlighting the importance of evaluating bias beyond conventional socio-political axes. Our code is available at: https://github.com/irenestrauss/Democratic-Authoritarian-Bias-LLMs. - oai:arXiv.org:2506.12758v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - David Guzman Piedrahita, Irene Strauss, Bernhard Sch\"olkopf, Rada Mihalcea, Zhijing Jin - - - X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability - https://arxiv.org/abs/2506.13558 - arXiv:2506.13558v3 Announce Type: replace -Abstract: Diffusion models are advancing autonomous driving by enabling realistic data synthesis, predictive end-to-end planning, and closed-loop simulation, with a primary focus on temporally consistent generation. However, large-scale 3D scene generation requiring spatial coherence remains underexplored. In this paper, we present X-Scene, a novel framework for large-scale driving scene generation that achieves geometric intricacy, appearance fidelity, and flexible controllability. Specifically, X-Scene supports multi-granular control, including low-level layout conditioning driven by user input or text for detailed scene composition, and high-level semantic guidance informed by user intent and LLM-enriched prompts for efficient customization. To enhance geometric and visual fidelity, we introduce a unified pipeline that sequentially generates 3D semantic occupancy and corresponding multi-view images and videos, ensuring alignment and temporal consistency across modalities. We further extend local regions into large-scale scenes via consistency-aware outpainting, which extrapolates occupancy and images from previously generated areas to maintain spatial and visual coherence. The resulting scenes are lifted into high-quality 3DGS representations, supporting diverse applications such as simulation and scene exploration. Extensive experiments demonstrate that X-Scene substantially advances controllability and fidelity in large-scale scene generation, empowering data generation and simulation for autonomous driving. - oai:arXiv.org:2506.13558v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yu Yang, Alan Liang, Jianbiao Mei, Yukai Ma, Yong Liu, Gim Hee Lee - - - Unified Software Engineering Agent as AI Software Engineer - https://arxiv.org/abs/2506.14683 - arXiv:2506.14683v2 Announce Type: replace -Abstract: The growth of Large Language Model (LLM) technology has raised expectations for automated coding. However, software engineering is more than coding and is concerned with activities including maintenance and evolution of a project. In this context, the concept of LLM agents has gained traction, which utilize LLMs as reasoning engines to invoke external tools autonomously. But is an LLM agent the same as an AI software engineer? In this paper, we seek to understand this question by developing a Unified Software Engineering agent or USEagent. Unlike existing work which builds specialized agents for specific software tasks such as testing, debugging, and repair, our goal is to build a unified agent which can orchestrate and handle multiple capabilities. This gives the agent the promise of handling complex scenarios in software development such as fixing an incomplete patch, adding new features, or taking over code written by others. We envision USEagent as the first draft of a future AI Software Engineer which can be a team member in future software development teams involving both AI and humans. To evaluate the efficacy of USEagent, we build a Unified Software Engineering bench (USEbench) comprising of myriad tasks such as coding, testing, and patching. USEbench is a judicious mixture of tasks from existing benchmarks such as SWE-bench, SWT-bench, and REPOCOD. In an evaluation on USEbench consisting of 1,271 repository-level software engineering tasks, USEagent shows improved efficacy compared to existing general agents such as OpenHands CodeActAgent. There exist gaps in the capabilities of USEagent for certain coding tasks, which provides hints on further developing the AI Software Engineer of the future. - oai:arXiv.org:2506.14683v2 - cs.SE - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Leonhard Applis, Yuntong Zhang, Shanchao Liang, Nan Jiang, Lin Tan, Abhik Roychoudhury - - - How Warm-Glow Alters the Usability of Technology - https://arxiv.org/abs/2506.14720 - arXiv:2506.14720v3 Announce Type: replace -Abstract: As technology increasingly aligns with users' personal values, traditional models of usability, focused on functionality and specifically effectiveness, efficiency, and satisfaction, may not fully capture how people perceive and evaluate it. This study investigates how the warm-glow phenomenon, the positive feeling associated with doing good, shapes perceived usability. An experimental approach was taken in which participants evaluated a hypothetical technology under conditions designed to evoke either the intrinsic (i.e., personal fulfillment) or extrinsic (i.e., social recognition) dimensions of warm-glow. A Multivariate Analysis of Variance as well as subsequent follow-up analyses revealed that intrinsic warm-glow significantly enhances all dimensions of perceived usability, while extrinsic warm-glow selectively influences perceived effectiveness and satisfaction. These findings suggest that perceptions of usability extend beyond functionality and are shaped by how technology resonates with users' broader sense of purpose. We conclude by proposing that designers consider incorporating warm-glow into technology as a strategic design decision. - oai:arXiv.org:2506.14720v3 - cs.HC - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3783862.3783873 - Antonios Saravanos (New York University) - - - The Ultimate Signs of Second-Order Holonomic Sequences - https://arxiv.org/abs/2506.14751 - arXiv:2506.14751v2 Announce Type: replace -Abstract: A real-valued sequence $f = \{ f(n) \}_{n \in \mathbb{N}}$ is said to be second-order holonomic if it satisfies a linear recurrence $f (n + 2) = P (n) f (n + 1) + Q (n) f (n)$ for all sufficiently large $n$, where $P, Q \in \mathbb{R}(x)$ are rational functions. We study the ultimate sign of such a sequence, i.e., the repeated pattern that the signs of $f (n)$ follow for sufficiently large $n$. For each $P$, $Q$ we determine all the ultimate signs that $f$ can have, and show how they partition the space of initial values of $f$. This completes the prior work by Neumann, Ouaknine and Worrell, who have settled some restricted cases. As a corollary, it follows that when $P$, $Q$ have rational coefficients, $f$ either has an ultimate sign of length $1$, $2$, $3$, $4$, $6$, $8$ or $12$, or never falls into a repeated sign pattern. We also give a partial algorithm that finds the ultimate sign of $f$ (or tells that there is none) in almost all cases. - oai:arXiv.org:2506.14751v2 - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.4230/LIPIcs.ICALP.2025.159 - Fugen Hagihara, Akitoshi Kawamura - - - Semi-supervised Graph Anomaly Detection via Robust Homophily Learning - https://arxiv.org/abs/2506.15448 - arXiv:2506.15448v2 Announce Type: replace -Abstract: Semi-supervised graph anomaly detection (GAD) utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. Current methods in this line posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of two novel modules, adaptive frequency response filters (AdaFreq) and graph normality alignment (GNA). AdaFreq learns a set of adaptive spectral filters that capture different frequency components of the labeled normal nodes with varying homophily in the channel-wise and cross-channel views of node attributes. GNA is introduced to enforce consistency between the channel-wise and cross-channel homophily representations to robustify the normality learned by the filters in the two views. Experiments on eight real-world GAD datasets show that RHO can effectively learn varying, often under-represented, homophily in the small normal node set and substantially outperforms state-of-the-art competing methods. Code is available at https://github.com/mala-lab/RHO. - oai:arXiv.org:2506.15448v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Guoguo Ai, Hezhe Qiao, Hui Yan, Guansong Pang - - - Rethinking LLM Training through Information Geometry and Quantum Metrics - https://arxiv.org/abs/2506.15830 - arXiv:2506.15830v4 Announce Type: replace -Abstract: Optimization in large language models (LLMs) unfolds over high-dimensional parameter spaces with non-Euclidean structure. Information geometry frames this landscape using the Fisher information metric, enabling more principled learning via natural gradient descent. Though often impractical, this geometric lens clarifies phenomena such as sharp minima, generalization, and observed scaling laws. We argue that curvature-based approaches deepen our understanding of LLM training. Finally, we speculate on quantum analogies based on the Fubini-Study metric and Quantum Fisher Information, hinting at efficient optimization in quantum-enhanced systems. - oai:arXiv.org:2506.15830v4 - cs.CL - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Riccardo Di Sipio - - - Understanding the Challenges and Promises of Developing Generative AI Apps: An Empirical Study - https://arxiv.org/abs/2506.16453 - arXiv:2506.16453v3 Announce Type: replace -Abstract: The release of ChatGPT in 2022 triggered a rapid surge in generative artificial intelligence mobile apps (i.e., Gen-AI apps). Despite widespread adoption, little is known about how end users perceive and evaluate these Gen-AI functionalities in practice. In this work, we conduct a user-centered analysis of 676,066 automatically labeled reviews from 173 Gen-AI apps on the Google Play Store. We propose a structured four-phase framework, SARA (Selection, Acquisition, Refinement, and Analysis), which integrates and extends state-of-the-art techniques for large-scale review collection, filtering, and analysis using prompt-based LLMs. First, we empirically validate the reliability of LLMs for topic extraction and assignment, achieving 91% accuracy through five-shot prompting and LLM-based filtering of non-informative reviews. We then apply the framework to informative reviews to identify the ten most discussed topics (e.g., AI Performance, Content Quality, and Content Policy & Censorship) and analyze the key challenges and emerging opportunities. Finally, we examine how these topics evolve over time, offering insight into shifting user expectations and engagement patterns with Gen-AI apps. Based on our findings and observations, we present actionable implications for developers and researchers. - oai:arXiv.org:2506.16453v3 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Buthayna AlMulla, Maram Assi, Safwat Hassan - - - One Sample is Enough to Make Conformal Prediction Robust - https://arxiv.org/abs/2506.16553 - arXiv:2506.16553v2 Announce Type: replace -Abstract: For any black-box model, conformal prediction (CP) returns prediction sets guaranteed to include the true label with high adjustable probability. Robust CP (RCP) extends the guarantee to the worst case noise up to a pre-defined magnitude. For RCP, a well-established approach is to use randomized smoothing since it is applicable to any black-box model and provides smaller sets compared to deterministic methods. However, smoothing-based robustness requires many model forward passes per each input which is computationally expensive. We show that conformal prediction attains some robustness even with a single forward pass on a randomly perturbed input. Using any binary certificate we propose a single sample robust CP (RCP1). Our approach returns robust sets with smaller average set size compared to SOTA methods which use many (e.g. 100) passes per input. Our key insight is to certify the conformal procedure itself rather than individual conformity scores. Our approach is agnostic to the task (classification and regression). We further extend our approach to smoothing-based robust conformal risk control. - oai:arXiv.org:2506.16553v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski - - - Quantum-Classical Hybrid Quantized Neural Network - https://arxiv.org/abs/2506.18240 - arXiv:2506.18240v4 Announce Type: replace -Abstract: In this work, we introduce a novel Quadratic Binary Optimization (QBO) framework for training a quantized neural network. The framework enables the use of arbitrary activation and loss functions through spline interpolation, while Forward Interval Propagation addresses the nonlinearities and the multi-layered, composite structure of neural networks via discretizing activation functions into linear subintervals. This preserves the universal approximation properties of neural networks while allowing complex nonlinear functions accessible to quantum solvers, broadening their applicability in artificial intelligence. Theoretically, we derive an upper bound on the approximation error and the number of Ising spins required by deriving the sample complexity of the empirical risk minimization problem from an optimization perspective. A key challenge in solving the associated large-scale Quadratic Constrained Binary Optimization (QCBO) model is the presence of numerous constraints. To overcome this, we adopt the Quantum Conditional Gradient Descent (QCGD) algorithm, which solves QCBO directly on quantum hardware. We establish the convergence of QCGD under a quantum oracle subject to randomness, bounded variance, and limited coefficient precision, and further provide an upper bound on the Time-To-Solution. To enhance scalability, we further incorporate a decomposed copositive optimization scheme that replaces the monolithic lifted model with sample-wise subproblems. This decomposition substantially reduces the quantum resource requirements and enables efficient low-bit neural network training. We further propose the usage of QCGD and Quantum Progressive Hedging (QPH) algorithm to efficiently solve the decomposed problem. - oai:arXiv.org:2506.18240v4 - cs.LG - cs.AI - physics.optics - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wenxin Li, Chuan Wang, Hongdong Zhu, Qi Gao, Yin Ma, Hai Wei, Kai Wen - - - IG-PINNs: Interface-gated physics-informed neural networks for solving elliptic interface problems - https://arxiv.org/abs/2506.18332 - arXiv:2506.18332v2 Announce Type: replace -Abstract: In this work, we develop interface-gated physics-informed neural networks (IG-PINNs) to solve elliptic interface equations. In IG-PINNs, we use a fully connected neural network to capture the smooth behavior across the entire domain. In each subdomain separated by the interface, an interface-gated network is utilized to provide corrections at the interface. In the architectural design of the interface-gated network, we introduce a gating mechanism and a level-set function derived from the interface. This design enables the interface-gated network to effectively handle discontinuous jumps across the interface. Some numerical experiments have confirmed the effectiveness of the IG-PINNs, demonstrating higher accuracy compared with PINNs, interface PINNs (I-PINNs) and multi-domain PINNs (M-PINNs). - oai:arXiv.org:2506.18332v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiachun Zheng, Yunqing Huang, Nianyu Yi - - - Waterfall Model Simulation: A Systematic Mapping Study - https://arxiv.org/abs/2506.19653 - arXiv:2506.19653v3 Announce Type: replace -Abstract: This paper systematically maps peer-reviewed research and graduate theses/dissertations that explicitly simulate the waterfall model. Following Petersen's mapping guidelines and Kitchenham's systematic literature review practices, major databases (ACM Digital Library, IEEE Xplore, Scopus, Springer, Google Scholar, and Web of Science) were searched for studies published between 2000-2024 using the title query ("simulation" OR "simulating") AND "waterfall". A PRISMA workflow guided the screening process, and approximately 9% of retrieved records met the inclusion criteria. A repeated extraction process captured methods, tools, venues, geography, publication years, comparative scope, and fidelity to Royce's original model; findings were synthesized thematically. Discrete-event simulation dominates (80%) compared to system dynamics (20%). Reported tools center on Simphony.NET (40%) and SimPy (20%), while 40% of studies omit tool details, limiting reproducibility. Research is distributed across Italy, Lebanon, India, Japan, and the United States; publication venues include 60% journals and 40% conferences. Sixty percent of studies are comparative, while 40% model only the waterfall approach. No study reproduces Royce's original model; all employ adaptations. The paper concludes by presenting a consolidated view of waterfall simulation research and recommending clearer model reporting, fuller tool disclosure, and wider adoption of open-source platforms. - oai:arXiv.org:2506.19653v3 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3783862.3783877 - Antonios Saravanos (New York University) - - - Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation - https://arxiv.org/abs/2506.19852 - arXiv:2506.19852v2 Announce Type: replace -Abstract: Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this paper, we identify a phenomenon we term Spatiotemporal Energy Decay in video diffusion models: post-softmax attention scores diminish as spatial and temporal distance between tokens increase, akin to the physical decay of signal or waves over space and time in nature. Motivated by this, we propose Radial Attention, a scalable sparse attention mechanism with $\mathcal{O}(n \log n)$ complexity that translates energy decay into exponentially decaying compute density, which is significantly more efficient than standard $\mathcal{O}(n^2)$ dense attention and more expressive than linear attention. Specifically, Radial Attention employs a simple, static attention mask where each token attends to spatially nearby tokens, with the attention window size shrinking with temporal distance. Moreover, it allows pre-trained video diffusion models to extend their generation length with efficient LoRA-based fine-tuning. Extensive experiments show that Radial Attention maintains video quality across Wan2.1-14B, HunyuanVideo, and Mochi 1, achieving up to a 1.9$\times$ speedup over the original dense attention. With minimal tuning, it enables video generation up to 4$\times$ longer while reducing training costs by up to 4.4$\times$ compared to direct fine-tuning and accelerating inference by up to 3.7$\times$ compared to dense attention inference. Code is released at \href{https://github.com/mit-han-lab/radial-attention}{https://github.com/mit-han-lab/radial-attention}. - oai:arXiv.org:2506.19852v2 - cs.CV - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xingyang Li, Muyang Li, Tianle Cai, Haocheng Xi, Shuo Yang, Yujun Lin, Lvmin Zhang, Songlin Yang, Jinbo Hu, Kelly Peng, Maneesh Agrawala, Ion Stoica, Kurt Keutzer, Song Han - - - Emergent Granger Causality in Neural Networks: Can Prediction Alone Reveal Structure? - https://arxiv.org/abs/2506.20347 - arXiv:2506.20347v2 Announce Type: replace -Abstract: Granger Causality (GC) offers an elegant statistical framework to study the association between multivariate time series data. Vector autoregressive models (VAR) are simple and easy to fit, but have limited application because of their inherent inability to capture more complex (e.g., non-linear) associations. Numerous attempts have already been made in the literature that exploit the functional approximation power of deep neural networks (DNNs) for GC. However, these methods treat GC as a variable selection problem. We present a novel paradigm for investigating the learned GC from a single neural network used for joint modeling of all components of multivariate time series data, which is essentially linked with prediction and assessing the distribution shift in residuals. A deep learning model, with proper regularization, may learn the true GC structure when jointly used for all components of the time series when there is sufficient training data. We propose to uncover the learned GC structure by comparing the model uncertainty or distribution of the residuals when the past of everything is used as compared to the one where a specific time series component is dropped from the model. We also compare the effect of input layer dropout on the ability of a neural network to learn GC. We show that a well-regularized model can learn the true GC structure from the data without explicitly adding terms in the loss function that guide the model to select variables or perform sparse regression under specific settings. We also provide a comparison of deep learning architectures such as CNN, LSTM and transformer models on their ability to discover Granger Causality. The numerical experiments demonstrate that, compared to sparse regression models, a simple joint model is a strong baseline for learning the true GC which has the advantage that it does not require tuning of many extra hyper-parameters. - oai:arXiv.org:2506.20347v2 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Malik Shahid Sultan, Hernando Ombao, Maurizio Filippone - - - OptGM: An Optimized Gate Merging Method to Mitigate NBTI in Digital Circuits - https://arxiv.org/abs/2506.21487 - arXiv:2506.21487v4 Announce Type: replace -Abstract: This paper presents OptGM, an optimized gate merging method designed to mitigate negative bias temperature instability (NBTI) in digital circuits. First, the proposed approach effectively identifies NBTI-critical internal nodes, defined as those with a signal probability exceeding a predefined threshold. Next, based on the proposed optimized algorithm, the sensitizer gate (which drives the critical node) and the sensitive gate (which is fed by it) are merged into a new complex gate. This complex gate preserves the original logic while eliminating NBTI-critical nodes. Finally, to evaluate the effectiveness of OptGM, we assess it on several combinational and sequential benchmark circuits. Simulation results demonstrate that, on average, the number of NBTI-critical transistors (i.e., PMOS transistors connected to critical nodes), NBTI-induced delay degradation, and the total transistor count are reduced by 89.29%, 23.87%, and 6.47%, respectively. Furthermore, OptGM enhances performance per cost (PPC) by 12.8% on average, with minimal area overhead. - oai:arXiv.org:2506.21487v4 - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1007/s10470-025-02550-6 - Analog Integrated Circuits and Signal Processing, 2026 - Amir M. Hajisadeghi, Maryam Ghane, Hamid R. Zarandi - - - Nonlinear Power Amplifier-Resilient Cell-Free Massive MIMO: A Joint Optimization Approach - https://arxiv.org/abs/2506.22094 - arXiv:2506.22094v2 Announce Type: replace -Abstract: This letter analyzes the effects of power amplifiers (PAs) on the downlink of cell-free massive MIMO systems. We model signal transmission incorporating nonlinear PA distortion and derive a unified spectral efficiency (SE) expression applicable to arbitrary precoding schemes. To combat PA-induced performance degradation, a joint optimization approach for user association and max-min power control is proposed. Furthermore, a low-complexity alternative is developed to approximate the joint optimization with reduced computational overhead. Simulations validate the analysis and demonstrate significant performance gains of the proposed approaches over conventional techniques. - oai:arXiv.org:2506.22094v2 - cs.IT - eess.SP - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wei Jiang, Hans D. Schotten - - - Towards Explainable Bilingual Multimodal Misinformation Detection and Localization - https://arxiv.org/abs/2506.22930 - arXiv:2506.22930v2 Announce Type: replace -Abstract: The increasing realism of multimodal content has made misinformation more subtle and harder to detect, especially in news media where images are frequently paired with bilingual (e.g., Chinese-English) subtitles. Such content often includes localized image edits and cross-lingual inconsistencies that jointly distort meaning while remaining superficially plausible. We introduce BiMi, a bilingual multimodal framework that jointly performs region-level localization, cross-modal and cross-lingual consistency detection, and natural language explanation for misinformation analysis. To support generalization, BiMi integrates an online retrieval module that supplements model reasoning with up-to-date external context. We further release BiMiBench, a large-scale and comprehensive benchmark constructed by systematically editing real news images and subtitles, comprising 104,000 samples with realistic manipulations across visual and linguistic modalities. To enhance interpretability, we apply Group Relative Policy Optimization (GRPO) to improve explanation quality, marking the first use of GRPO in this domain. Extensive experiments demonstrate that BiMi outperforms strong baselines by up to +8.9 in classification accuracy, +15.9 in localization accuracy, and +2.5 in explanation BERTScore, advancing state-of-the-art performance in realistic, multilingual misinformation detection. Code, models, and datasets will be released. - oai:arXiv.org:2506.22930v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yiwei He, Xiangtai Li, Zhenglin Huang, Yi Dong, Hao Fei, Jiangning Zhang, Baoyuan Wu, Guangliang Cheng - - - Teacher-AI Collaboration for Curating and Customizing Lesson Plans in Low-Resource Schools - https://arxiv.org/abs/2507.00456 - arXiv:2507.00456v2 Announce Type: replace -Abstract: This study investigates Shiksha copilot, an AI-assisted lesson planning tool deployed in government schools across Karnataka, India. The system combined LLMs and human expertise through a structured process in which English and Kannada lesson plans were co-created by curators and AI; teachers then further customized these curated plans for their classrooms using their own expertise alongside AI support. Drawing on a large-scale mixed-methods study involving 1,043 teachers and 23 curators, we examine how educators collaborate with AI to generate context-sensitive lesson plans, assess the quality of AI-generated content, and analyze shifts in teaching practices within multilingual, low-resource environments. Our findings show that teachers used Shiksha copilot both to meet administrative documentation needs and to support their teaching. The tool eased bureaucratic workload, reduced lesson planning time, and lowered teaching-related stress, while promoting a shift toward activity-based pedagogy. However, systemic challenges such as staffing shortages and administrative demands constrained broader pedagogical change. We frame these findings through the lenses of teacher-AI collaboration and communities of practice to examine the effective integration of AI tools in teaching. Finally, we propose design directions for future teacher-centered EdTech, particularly in multilingual and Global South contexts. - oai:arXiv.org:2507.00456v2 - cs.CY - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Deepak Varuvel Dennison, Bakhtawar Ahtisham, Kavyansh Chourasia, Nirmit Arora, Rahul Singh, Rene F. Kizilcec, Akshay Nambi, Tanuja Ganu, Aditya Vashistha - - - Blackbox Dataset Inference for LLM - https://arxiv.org/abs/2507.03619 - arXiv:2507.03619v3 Announce Type: replace -Abstract: Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset inference}, which aims to detect if a suspect model $\mathcal{M}$ used a victim dataset $\mathcal{D}$ in training. Previous research tackles dataset inference by aggregating results of membership inference attacks (MIAs) -- methods to determine whether individual samples are a part of the training dataset. However, restricted by the low accuracy of MIAs, previous research mandates grey-box access to $\mathcal{M}$ to get intermediate outputs (probabilities, loss, perplexity, etc.) for obtaining satisfactory results. This leads to reduced practicality, as LLMs, especially those deployed for profits, have limited incentives to return the intermediate outputs. - In this paper, we propose a new method of dataset inference with only black-box access to the target model (i.e., assuming only the text-based responses of the target model are available). Our method is enabled by two sets of locally built reference models, one set involving $\mathcal{D}$ in training and the other not. By measuring which set of reference model $\mathcal{M}$ is closer to, we determine if $\mathcal{M}$ used $\mathcal{D}$ for training. Evaluations of real-world LLMs in the wild show that our method offers high accuracy in all settings and presents robustness against bypassing attempts. - oai:arXiv.org:2507.03619v3 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ruikai Zhou, Kang Yang, Xun Chen, Wendy Hui Wang, Guanhong Tao, Jun Xu - - - How Not to Detect Prompt Injections with an LLM - https://arxiv.org/abs/2507.05630 - arXiv:2507.05630v3 Announce Type: replace -Abstract: LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on known-answer detection (KAD) scheme have reported near-perfect performance by observing an LLM's output to classify input data as clean or contaminated. KAD attempts to repurpose the very susceptibility to prompt injection as a defensive mechanism. We formally characterize the KAD scheme and uncover a structural vulnerability that invalidates its core security premise. To exploit this fundamental vulnerability, we methodically design an adaptive attack, DataFlip. It consistently evades KAD defenses, achieving detection rates as low as $0\%$ while reliably inducing malicious behavior with a success rate of $91\%$, all without requiring white-box access to the LLM or any optimization procedures. - oai:arXiv.org:2507.05630v3 - cs.CR - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sarthak Choudhary, Divyam Anshumaan, Nils Palumbo, Somesh Jha - - - Fredholm Neural Networks for forward and inverse problems in elliptic PDEs - https://arxiv.org/abs/2507.06038 - arXiv:2507.06038v3 Announce Type: replace -Abstract: Building on our previous work introducing Fredholm Neural Networks (Fredholm NNs/ FNNs) for solving integral equations, we extend the framework to tackle forward and inverse problems for linear and semi-linear elliptic partial differential equations. The proposed scheme consists of a deep neural network (DNN) which is designed to represent the iterative process of fixed-point iterations for the solution of elliptic PDEs using the boundary integral method within the framework of potential theory. The number of layers, weights, biases and hyperparameters are computed in an explainable manner based on the iterative scheme, and we therefore refer to this as the Potential Fredholm Neural Network (PFNN). We show that this approach ensures both accuracy and explainability, achieving small errors in the interior of the domain, and near machine-precision on the boundary. We provide a constructive proof for the consistency of the scheme and provide explicit error bounds for both the interior and boundary of the domain, reflected in the layers of the PFNN. These error bounds depend on the approximation of the boundary function and the integral discretization scheme, both of which directly correspond to components of the Fredholm NN architecture. In this way, we provide an explainable scheme that explicitly respects the boundary conditions. We assess the performance of the proposed scheme for the solution of both the forward and inverse problem for linear and semi-linear elliptic PDEs in two dimensions. - oai:arXiv.org:2507.06038v3 - math.NA - cs.LG - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kyriakos Georgiou, Constantinos Siettos, Athanasios N. Yannacopoulos - - - Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks - https://arxiv.org/abs/2507.06274 - arXiv:2507.06274v2 Announce Type: replace -Abstract: Watermarking is a promising defense against the misuse of large language models (LLMs), yet it remains vulnerable to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size: smaller windows resist scrubbing better but are easier to reverse-engineer, enabling low-cost statistics-based spoofing attacks. This work breaks this trade-off by introducing a novel mechanism, equivalent texture keys, where multiple tokens within a watermark window can independently support the detection. Based on the redundancy, we propose a novel watermark scheme with Sub-vocabulary decomposed Equivalent tExture Key (SEEK). It achieves a Pareto improvement, increasing the resilience against scrubbing attacks without compromising robustness to spoofing. Experiments demonstrate SEEK's superiority over prior method, yielding spoofing robustness gains of +88.2%/+92.3%/+82.0% and scrubbing robustness gains of +10.2%/+6.4%/+24.6% across diverse dataset settings. - oai:arXiv.org:2507.06274v2 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Huanming Shen, Baizhou Huang, Xiaojun Wan - - - Multiscale Approximation as a Bias-Reducing Strategy for Manifold-Valued Functions - https://arxiv.org/abs/2507.06707 - arXiv:2507.06707v2 Announce Type: replace -Abstract: We study the bias-variance tradeoff within a multiscale approximation framework. Our approach utilizes a given quasi-approximation operator that is repeatedly applied in an error-correction scheme over a hierarchical data structure. We introduce a new bias measure, the bias ratio, to quantitatively assess the improvements afforded by multiscale approximations and demonstrate that this strategy effectively reduces the bias component of the approximation error, thereby providing a more flexible and robust framework for addressing scattered-data approximation problems. Our findings exhibit consistent bias decay across various scenarios, including applications to manifold-valued functions. - oai:arXiv.org:2507.06707v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Asaf Abas, Nir Sharon - - - XiChen: An observation-scalable fully AI-driven global weather forecasting system with 4D variational knowledge - https://arxiv.org/abs/2507.09202 - arXiv:2507.09202v2 Announce Type: replace -Abstract: Artificial intelligence (AI)-driven models have the potential to revolutionize weather forecasting, but still rely on initial conditions generated by costly Numerical Weather Prediction (NWP) systems. Although recent end-to-end forecasting models attempt to bypass NWP systems, these methods lack scalable assimilation of new types of observational data. Here, we introduce XiChen, an observation-scalable fully AI-driven global weather forecasting system, wherein the entire pipeline, from Data Assimilation (DA) to medium-range forecasting, can be accomplished within only 15 seconds. XiChen is built upon a foundation model that is pre-trained for weather forecasting and subsequently fine-tuned to serve as both observation operators and DA models, thereby enabling the scalable assimilation of conventional and raw satellite observations. Furthermore, the integration of Four-Dimensional Variational (4DVar) knowledge ensures XiChen to achieve DA and medium-range forecasting accuracy comparable to operational NWP systems, with skillful forecasting lead time beyond 8.75 days. A key feature of XiChen is its ability to maintain physical balance constraints during DA, enabling observed variables to correct unobserved ones effectively. In single-point perturbation DA experiments, XiChen exhibits flow-dependent characteristics similar to those of traditional 4DVar systems. These results demonstrate that XiChen holds strong potential for fully AI-driven weather forecasting independent of NWP systems. - oai:arXiv.org:2507.09202v2 - cs.LG - cs.AI - physics.ao-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wuxin Wang, Weicheng Ni, Lilan Huang, Tao Hao, Ben Fei, Shuo Ma, Taikang Yuan, Yanlai Zhao, Kefeng Deng, Xiaoyong Li, Hongze Leng, Boheng Duan, Lei Bai, Weimin Zhang, Kaijun Ren, Junqiang Song - - - A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models - https://arxiv.org/abs/2507.10714 - arXiv:2507.10714v2 Announce Type: replace -Abstract: Stochastic Petri Nets (SPNs) are an increasingly popular tool of choice for modeling discrete-event dynamics in areas such as epidemiology and systems biology, yet their parameter estimation remains challenging in general and in particular when transition rates depend on external covariates and explicit likelihoods are unavailable. We introduce a neural-surrogate (neural-network-based approximation of the posterior distribution) framework that predicts the coefficients of known covariate-dependent rate functions directly from noisy, partially observed token trajectories. Our model employs a lightweight 1D Convolutional Residual Network trained end-to-end on Gillespie-simulated SPN realizations, learning to invert system dynamics under realistic conditions of event dropout. During inference, Monte Carlo dropout provides calibrated uncertainty bounds together with point estimates. On synthetic SPNs with $10\%$ missing events, our surrogate recovers rate-function coefficients with an $RMSE = 0.043$ and substantially runs faster than traditional Bayesian approaches. These results demonstrate that data-driven, likelihood-free surrogates can enable accurate, robust, and real-time parameter recovery in complex, partially observed discrete-event systems. - oai:arXiv.org:2507.10714v2 - cs.LG - q-bio.QM - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Bright Kwaku Manu, Trevor Reckell, Beckett Sterner, Petar Jevtic - - - SystolicAttention: Fusing FlashAttention within a Single Systolic Array - https://arxiv.org/abs/2507.11331 - arXiv:2507.11331v4 Announce Type: replace -Abstract: Transformer models rely heavily on the scaled dot-product attention (SDPA) operation, typically implemented as FlashAttention. Characterized by its frequent interleaving of matrix multiplications and softmax operations, FlashAttention fails to fully utilize the compute resources of modern systolic-array-based accelerators designed for consecutive and large matrix multiplications. - To fully unleash the performance potential of systolic arrays for FlashAttention, we propose FSA, an enhanced systolic array architecture that runs the entire FlashAttention on the array without external vector units. Combined with SystolicAttention, an optimized kernel for FSA that achieves fine-grained and element-wise overlapping of FlashAttention operations, FSA maximizes array utilization while preserving the original floating-point operation order of FlashAttention. We implement FSA in synthesizable RTL and evaluate its performance against state-of-the-art systolic-array-based accelerators. Our results show that FSA achieves 1.77x and 4.83x higher attention FLOPs/s utilization compared to AWS Neuron-v2 and Google TPUv5e, respectively. We synthesize FSA in a 16 nm technology at 1.5 GHz, and results indicate only a 12% area overhead compared to a standard weight-stationary systolic array. - oai:arXiv.org:2507.11331v4 - cs.AR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiawei Lin, Yuanlong Li, Guokai Chen, Thomas Bourgeat - - - Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety - https://arxiv.org/abs/2507.11473 - arXiv:2507.11473v2 Announce Type: replace -Abstract: AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability. - oai:arXiv.org:2507.11473v2 - cs.AI - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo, Victoria Krakovna, Shane Legg, David Lindner, David Luan, Aleksander M\k{a}dry, Julian Michael, Neel Nanda, Dave Orr, Jakub Pachocki, Ethan Perez, Mary Phuong, Fabien Roger, Joshua Saxe, Buck Shlegeris, Mart\'in Soto, Eric Steinberger, Jasmine Wang, Wojciech Zaremba, Bowen Baker, Rohin Shah, Vlad Mikulik - - - AdapTT: Functoriality for Dependent Type Casts - https://arxiv.org/abs/2507.13774 - arXiv:2507.13774v2 Announce Type: replace -Abstract: The ability to cast values between related types is a leitmotiv of many flavors of dependent type theory, such as observational type theories, subtyping, or cast calculi for gradual typing. These casts all exhibit a common structural behavior that boils down to the pervasive functoriality of type formers. We propose and extensively study a type theory, called AdapTT, which makes systematic and precise this idea of functorial type formers, with respect to an abstract notion of adapters relating types. Leveraging descriptions for functorial inductive types in AdapTT, we derive structural laws for type casts on general inductive type formers. - oai:arXiv.org:2507.13774v2 - cs.PL - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1145/3776664 - Arthur Adjedj, Meven Lennon-Bertrand, Thibaut Benjamin, Kenji Maillard - - - Conch: Competitive Debate Analysis via Visualizing Clash Points and Hierarchical Strategies - https://arxiv.org/abs/2507.14482 - arXiv:2507.14482v2 Announce Type: replace -Abstract: In-depth analysis of competitive debates is essential for participants to develop argumentative skills and refine strategies, and further improve their debating performance. However, manual analysis of unstructured and unlabeled textual records of debating is time-consuming and ineffective, as it is challenging to reconstruct contextual semantics and track logical connections from raw data. To address this, we propose Conch, an interactive visualization system that systematically analyzes both what is debated and how it is debated. In particular, we propose a novel parallel spiral visualization that compactly traces the multidimensional evolution of clash points and participant interactions throughout debate process. In addition, we leverage large language models with well-designed prompts to automatically identify critical debate elements such as clash points, disagreements, viewpoints, and strategies, enabling participants to understand the debate context comprehensively. Finally, through two case studies on real-world debates and a carefully-designed user study, we demonstrate Conch's effectiveness and usability for competitive debate analysis. - oai:arXiv.org:2507.14482v2 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Qianhe Chen, Yong Wang, Yixin Yu, Xiyuan Zhu, Xuerou Yu, Ran Wang - - - Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions - https://arxiv.org/abs/2507.14555 - arXiv:2507.14555v2 Announce Type: replace -Abstract: Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding, particularly when visual embeddings alone do not adequately convey the roles and interactions of objects. In this paper, we introduce Descrip3D, a novel and powerful framework that explicitly encodes the relationships between objects using natural language. Unlike previous methods that rely only on 2D and 3D embeddings, Descrip3D enhances each object with a textual description that captures both its intrinsic attributes and contextual relationships. These relational cues are incorporated into the model through a dual-level integration: embedding fusion and prompt-level injection. This allows for unified reasoning across various tasks such as grounding, captioning, and question answering, all without the need for task-specific heads or additional supervision. When evaluated on five benchmark datasets, including ScanRefer, Multi3DRefer, ScanQA, SQA3D, and Scan2Cap, Descrip3D consistently outperforms strong baseline models, demonstrating the effectiveness of language-guided relational representation for understanding complex indoor scenes. Our code and data are publicly available at https://github.com/jintangxue/Descrip3D. - oai:arXiv.org:2507.14555v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jintang Xue, Ganning Zhao, Jie-En Yao, Hong-En Chen, Yue Hu, Meida Chen, Suya You, C. -C. Jay Kuo - - - Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images - https://arxiv.org/abs/2507.14670 - arXiv:2507.14670v3 Announce Type: replace -Abstract: Accurately predicting gene expression from histopathology images offers a scalable and non-invasive approach to molecular profiling, with significant implications for precision medicine and computational pathology. However, existing methods often underutilize the cross-modal representation alignment between histopathology images and gene expression profiles across multiple representational levels, thereby limiting their prediction performance. To address this, we propose Gene-DML, a unified framework that structures latent space through Dual-pathway Multi-Level discrimination to enhance correspondence between morphological and transcriptional modalities. The multi-scale instance-level discrimination pathway aligns hierarchical histopathology representations extracted at local, neighbor, and global levels with gene expression profiles, capturing scale-aware morphological-transcriptional relationships. In parallel, the cross-level instance-group discrimination pathway enforces structural consistency between individual (image/gene) instances and modality-crossed (gene/image, respectively) groups, strengthening the alignment across modalities. By jointly modeling fine-grained and structural-level discrimination, Gene-DML is able to learn robust cross-modal representations, enhancing both predictive accuracy and generalization across diverse biological contexts. Extensive experiments on public spatial transcriptomics datasets demonstrate that Gene-DML achieves state-of-the-art performance in gene expression prediction. The code and processed datasets are available at https://github.com/YXSong000/Gene-DML. - oai:arXiv.org:2507.14670v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yaxuan Song, Jianan Fan, Hang Chang, Weidong Cai - - - The Endless Tuning. An Artificial Intelligence Design To Avoid Human Replacement and Trace Back Responsibilities - https://arxiv.org/abs/2507.14909 - arXiv:2507.14909v3 Announce Type: replace -Abstract: The Endless Tuning is a design method for a reliable deployment of artificial intelligence based on a double mirroring process, which pursues both the goals of avoiding human replacement and filling the so-called responsibility gap (Matthias 2004). Originally depicted in (Fabris et al. 2024) and ensuing the relational approach urged therein, it was then actualized in a protocol, implemented in three prototypical applications regarding decision-making processes (respectively: loan granting, pneumonia diagnosis, and art style recognition) and tested with such as many domain experts. Step by step illustrating the protocol, giving insights concretely showing a different voice (Gilligan 1993) in the ethics of artificial intelligence, a philosophical account of technical choices (e.g., a reversed and hermeneutic deployment of XAI algorithms) will be provided in the present study together with the results of the experiments, focusing on user experience rather than statistical accuracy. Even thoroughly employing deep learning models, full control was perceived by the interviewees in the decision-making setting, while it appeared that a bridge can be built between accountability and liability in case of damage. - oai:arXiv.org:2507.14909v3 - cs.AI - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Elio Grande - - - Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression - https://arxiv.org/abs/2507.14997 - arXiv:2507.14997v3 Announce Type: replace -Abstract: Multimodal Large Language Models (MLLMs) show promise for image-based regression tasks, but current approaches face key limitations. Recent methods fine-tune MLLMs using preset output vocabularies and generic task-level prompts (e.g., "How would you rate this image?"), assuming this mimics human rating behavior. Our analysis reveals that these approaches provide no benefit over image-only training. Models using preset vocabularies and generic prompts perform equivalently to image-only models, failing to leverage semantic understanding from textual input. We propose Regression via Transformer-Based Classification (RvTC), which replaces vocabulary-constrained classification with a flexible bin-based approach. Unlike approaches that address discretization errors through complex distributional modeling, RvTC eliminates manual vocabulary crafting through straightforward bin increase, achieving state-of-the-art performance on four image assessment datasets using only images. More importantly, we demonstrate that data-specific prompts dramatically improve performance. Unlike generic task descriptions, prompts containing semantic information about specific images enable MLLMs to leverage cross-modal understanding. On the AVA dataset, adding challenge titles to prompts substantially improves our already state-of-the-art image-only baseline. We demonstrate through empirical evidence from the AVA and AGIQA-3k datasets that MLLMs benefit from semantic prompt information, surpassing mere statistical biases. We validate RvTC across two different MLLM architectures, demonstrating consistent improvements and method generalizability. - oai:arXiv.org:2507.14997v3 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Roy H. Jennings, Genady Paikin, Roy Shaul, Evgeny Soloveichik - - - Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning - https://arxiv.org/abs/2507.16302 - arXiv:2507.16302v2 Announce Type: replace -Abstract: Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often inherit unsafe behaviors from toxic pretraining data, raising growing safety concerns. While recent safety-driven unlearning methods have made promising progress in suppressing model toxicity, they are found to be fragile to downstream fine-tuning, as we reveal that state-of-the-art methods largely fail to retain their effectiveness even when fine-tuned on entirely benign datasets. To mitigate this problem, in this paper, we propose ResAlign, a safety-driven unlearning framework with enhanced resilience against downstream fine-tuning. By modeling downstream fine-tuning as an implicit optimization problem with a Moreau envelope-based reformulation, ResAlign enables efficient gradient estimation to minimize the recovery of harmful behaviors. Additionally, a meta-learning strategy is proposed to simulate a diverse distribution of fine-tuning scenarios to improve generalization. Extensive experiments across a wide range of datasets, fine-tuning methods, and configurations demonstrate that ResAlign consistently outperforms prior unlearning approaches in retaining safety, while effectively preserving benign generation capability. Our code and pretrained models are publicly available at https://github.com/AntigoneRandy/ResAlign. - oai:arXiv.org:2507.16302v2 - cs.LG - cs.AI - cs.CR - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Boheng Li, Renjie Gu, Junjie Wang, Leyi Qi, Yiming Li, Run Wang, Zhan Qin, Tianwei Zhang - - - DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling - https://arxiv.org/abs/2507.16329 - arXiv:2507.16329v2 Announce Type: replace -Abstract: Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended exposure and potential misuse. Red teaming, which aims to proactively identify diverse prompts that can elicit unsafe outputs from the T2I system, is increasingly recognized as an essential method for assessing and improving safety before real-world deployment. However, existing automated red teaming approaches often treat prompt discovery as an isolated, prompt-level optimization task, which limits their scalability, diversity, and overall effectiveness. To bridge this gap, in this paper, we propose DREAM, a scalable red teaming framework to automatically uncover diverse problematic prompts from a given T2I system. Unlike prior work that optimizes prompts individually, DREAM directly models the probabilistic distribution of the target system's problematic prompts, which enables explicit optimization over both effectiveness and diversity, and allows efficient large-scale sampling after training. To achieve this without direct access to representative training samples, we draw inspiration from energy-based models and reformulate the objective into a simple and tractable form. We further introduce GC-SPSA, an efficient optimization algorithm that provides stable gradient estimates through the long and potentially non-differentiable T2I pipeline. During inference, we also propose a diversity-aware sampling strategy to enhance prompt variety. The effectiveness of DREAM is validated through extensive experiments, demonstrating state-of-the-art performance across a wide range of T2I models and safety filters in terms of both prompt success rate and diversity. Our code is available at https://github.com/AntigoneRandy/DREAM - oai:arXiv.org:2507.16329v2 - cs.CR - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Boheng Li, Junjie Wang, Yiming Li, Zhiyang Hu, Leyi Qi, Jianshuo Dong, Run Wang, Han Qiu, Zhan Qin, Tianwei Zhang - - - Look the Other Way: Designing 'Positive' Molecules with Negative Data via Task Arithmetic - https://arxiv.org/abs/2507.17876 - arXiv:2507.17876v2 Announce Type: replace -Abstract: The scarcity of molecules with desirable properties (i.e., `positive' molecules) is an inherent bottleneck for generative molecule design. To sidestep such obstacle, here we propose molecular task arithmetic: training a model on diverse and abundant negative examples to learn 'property directions' - without accessing any positively labeled data - and moving models in the opposite property directions to generate positive molecules. When analyzed on 33 design experiments with distinct molecular entities (small molecules, proteins), model architectures, and scales, molecular task arithmetic generated more diverse and successful designs than models trained on positive molecules in general. Moreover, we employed molecular task arithmetic in dual-objective and few-shot design tasks. We find that molecular task arithmetic can consistently increase the diversity of designs while maintaining desirable complex design properties, such as good docking scores to a protein. With its simplicity, data efficiency, and performance, molecular task arithmetic bears the potential to become the de facto transfer learning strategy for de novo molecule design. - oai:arXiv.org:2507.17876v2 - cs.LG - physics.chem-ph - q-bio.BM - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - R{\i}za \"Oz\c{c}elik, Sarah de Ruiter, Francesca Grisoni - - - Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows - https://arxiv.org/abs/2507.18405 - arXiv:2507.18405v2 Announce Type: replace -Abstract: We introduce Iwin Transformer, a novel position-embedding-free hierarchical vision transformer, which can be fine-tuned directly from low to high resolution, through the collaboration of innovative interleaved window attention and depthwise separable convolution. This approach uses attention to connect distant tokens and applies convolution to link neighboring tokens, enabling global information exchange within a single module, overcoming Swin Transformer's limitation of requiring two consecutive blocks to approximate global attention. Extensive experiments on visual benchmarks demonstrate that Iwin Transformer exhibits strong competitiveness in tasks such as image classification (87.4 top-1 accuracy on ImageNet-1K), semantic segmentation and video action recognition. We also validate the effectiveness of the core component in Iwin as a standalone module that can seamlessly replace the self-attention module in class-conditional image generation. The concepts and methods introduced by the Iwin Transformer have the potential to inspire future research, like Iwin 3D Attention in video generation. The code and models are available at https://github.com/cominder/Iwin-Transformer. - oai:arXiv.org:2507.18405v2 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Simin Huo, Ning Li - - - DRWKV: Focusing on Object Edges for Low-Light Image Enhancement - https://arxiv.org/abs/2507.18594 - arXiv:2507.18594v3 Announce Type: replace -Abstract: Low-light image enhancement remains a challenging task, particularly in preserving object edge continuity and fine structural details under extreme illumination degradation. In this paper, we propose a novel model, DRWKV (Detailed Receptance Weighted Key Value), which integrates our proposed Global Edge Retinex (GER) theory, enabling effective decoupling of illumination and edge structures for enhanced edge fidelity. Secondly, we introduce Evolving WKV Attention, a spiral-scanning mechanism that captures spatial edge continuity and models irregular structures more effectively. Thirdly, we design the Bilateral Spectrum Aligner (Bi-SAB) and a tailored MS2-Loss to jointly align luminance and chrominance features, improving visual naturalness and mitigating artifacts. Extensive experiments on five LLIE benchmarks demonstrate that DRWKV achieves leading performance in PSNR, SSIM, and NIQE while maintaining low computational complexity. Furthermore, DRWKV enhances downstream performance in low-light multi-object tracking tasks, validating its generalization capabilities. - oai:arXiv.org:2507.18594v3 - cs.CV - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Xuecheng Bai, Yuxiang Wang, Boyu Hu, Qinyuan Jie, Chuanzhi Xu, Kechen Li, Hongru Xiao, Vera Chung - - - VGS-ATD: Robust Distributed Learning for Multi-Label Medical Image Classification Under Heterogeneous and Imbalanced Conditions - https://arxiv.org/abs/2507.18657 - arXiv:2507.18657v3 Announce Type: replace -Abstract: In recent years, advanced deep learning architectures have shown strong performance in medical imaging tasks. However, the traditional centralized learning paradigm poses serious privacy risks as all data is collected and trained on a single server. To mitigate this challenge, decentralized approaches such as federated learning and swarm learning have emerged, allowing model training on local nodes while sharing only model weights. While these methods enhance privacy, they struggle with heterogeneous and imbalanced data and suffer from inefficiencies due to frequent communication and the aggregation of weights. More critically, the dynamic and complex nature of clinical environments demands scalable AI systems capable of continuously learning from diverse modalities and multilabels. Yet, both centralized and decentralized models are prone to catastrophic forgetting during system expansion, often requiring full model retraining to incorporate new data. To address these limitations, we propose VGS-ATD, a novel distributed learning framework. To validate VGS-ATD, we evaluate it in experiments spanning 30 datasets and 80 independent labels across distributed nodes, VGS-ATD achieved an overall accuracy of 92.7%, outperforming centralized learning (84.9%) and swarm learning (72.99%), while federated learning failed under these conditions due to high requirements on computational resources. VGS-ATD also demonstrated strong scalability, with only a 1% drop in accuracy on existing nodes after expansion, compared to a 20% drop in centralized learning, highlighting its resilience to catastrophic forgetting. Additionally, it reduced computational costs by up to 50% relative to both centralized and swarm learning, confirming its superior efficiency and scalability. - oai:arXiv.org:2507.18657v3 - cs.CV - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Zehui Zhao, Laith Alzubaidi, Haider A. Alwzwazy, Jinglan Zhang, Yuantong Gu - - - Geometric Multi-color Message Passing Graph Neural Networks for Blood-brain Barrier Permeability Prediction - https://arxiv.org/abs/2507.18926 - arXiv:2507.18926v5 Announce Type: replace -Abstract: Accurate prediction of blood-brain barrier permeability (BBBP) is essential for central nervous system (CNS) drug development. While graph neural networks (GNNs) have advanced molecular property prediction, they often rely on molecular topology and neglect the three-dimensional geometric information crucial for modeling transport mechanisms. This paper introduces the geometric multi-color message-passing graph neural network (GMC-MPNN), a novel framework that enhances standard message-passing architectures by explicitly incorporating atomic-level geometric features and long-range interactions. Our model constructs weighted colored subgraphs based on atom types to capture the spatial relationships and chemical context that govern BBB permeability. We evaluated GMC-MPNN on three benchmark datasets for both classification and regression tasks, using rigorous scaffold-based splitting to ensure a robust assessment of generalization. The results demonstrate that GMC-MPNN consistently outperforms existing state-of-the-art models, achieving superior performance in both classifying compounds as permeable/non-permeable (AUC-ROC of 0.947 and 0.9212) and in regressing continuous permeability values (RMSE of 0.5628, Pearson correlation of 0.6947). An ablation study further quantified the impact of specific atom-pair interactions, revealing that the model's predictive power derives from its ability to learn from both common and rare, but chemically significant, functional motifs. By integrating spatial geometry into the graph representation, GMC-MPNN sets a new performance benchmark and offers a more accurate and generalizable tool for drug discovery pipelines. - oai:arXiv.org:2507.18926v5 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Trung Nguyen, Md Masud Rana, Farjana Tasnim Mukta, Chang-Guo Zhan, Duc Duy Nguyen - - - Pic2Diagnosis: A Method for Diagnosis of Cardiovascular Diseases from the Printed ECG Pictures - https://arxiv.org/abs/2507.19961 - arXiv:2507.19961v2 Announce Type: replace -Abstract: The electrocardiogram (ECG) is a vital tool for diagnosing heart diseases. However, many disease patterns are derived from outdated datasets and traditional stepwise algorithms with limited accuracy. This study presents a method for direct cardiovascular disease (CVD) diagnosis from ECG images, eliminating the need for digitization. The proposed approach utilizes a two-step curriculum learning framework, beginning with the pre-training of a classification model on segmentation masks, followed by fine-tuning on grayscale, inverted ECG images. Robustness is further enhanced through an ensemble of three models with averaged outputs, achieving an AUC of 0.9534 and an F1 score of 0.7801 on the BHF ECG Challenge dataset, outperforming individual models. By effectively handling real-world artifacts and simplifying the diagnostic process, this method offers a reliable solution for automated CVD diagnosis, particularly in resource-limited settings where printed or scanned ECG images are commonly used. Such an automated procedure enables rapid and accurate diagnosis, which is critical for timely intervention in CVD cases that often demand urgent care. - oai:arXiv.org:2507.19961v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - 10.1109/EMBC58623.2025.11254054 - O\u{g}uzhan B\"uy\"uksolak, \.Ilkay \"Oks\"uz - - - Learning to Align Human Code Preferences - https://arxiv.org/abs/2507.20109 - arXiv:2507.20109v2 Announce Type: replace -Abstract: Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human preferences, the optimal training strategy remains unclear across diverse code preference scenarios. This paper systematically investigates the roles of SFT and DPO in aligning LLMs with different code preferences. Through both theoretical analysis and empirical observation, we hypothesize that SFT excels in scenarios with objectively verifiable optimal solutions, while applying SFT followed by DPO (S&D) enables models to explore superior solutions in scenarios without objectively verifiable optimal solutions. Based on the analysis and experimental evidence, we propose Adaptive Preference Optimization (APO), a dynamic integration approach that adaptively amplifies preferred responses, suppresses dispreferred ones, and encourages exploration of potentially superior solutions during training. Extensive experiments across six representative code preference tasks validate our theoretical hypotheses and demonstrate that APO consistently matches or surpasses the performance of existing SFT and S&D strategies. Our work provides both theoretical foundations and practical guidance for selecting appropriate training strategies in different code preference alignment scenarios. - oai:arXiv.org:2507.20109v2 - cs.SE - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xin Yin, Chao Ni, Xiaohu Yang - - - IdeaBlocks: Expressing and Reusing Divergent Intents for Graphic Design Exploration using Generative AI - https://arxiv.org/abs/2507.22163 - arXiv:2507.22163v3 Announce Type: replace -Abstract: While designers increasingly leverage Generative AI for divergent exploration, current interaction is optimized for convergent refinement, forcing users to specify fixed targets rather than open-ended search spaces. Based on a formative study (N=7), we define the anatomy of Divergent Intent, comprising property, direction, and range, and identified two critical barriers: the lack of mechanisms to explicitly shape the parametric boundaries of exploration and the difficulty of reusing successful search strategies. We present IdeaBlocks, where users can modularize divergent intents into Exploration Blocks. Users can reuse prior intents at multiple levels (block, path, and project) with options for literal or context-adaptive reuse. In our comparative study (N=12), participants using IdeaBlocks explored 2.13 times more images with 12.5% greater visual diversity than the baseline, demonstrating how structured intent expression and reuse support effective divergence. A three-day deployment study (N=6) further revealed how different reuse mechanisms allowed distinct creative strategies, offering design implications for future intent-aware creativity supports. - oai:arXiv.org:2507.22163v3 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - DaEun Choi, Kihoon Son, Jaesang Yu, Hyunjoon Jung, Juho Kim - - - Density Operator Expectation Maximization - https://arxiv.org/abs/2507.22786 - arXiv:2507.22786v2 Announce Type: replace -Abstract: Machine learning with density operators, the mathematical foundation of quantum mechanics, is gaining prominence with rapid advances in quantum computing. Generative models based on density operators cannot yet handle tasks that are routinely handled by probabilistic models. The progress of latent variable models, a broad and influential class of probabilistic unsupervised models, was driven by the Expectation-Maximization framework. Deriving such a framework for density operators is challenging due to the non-commutativity of operators. To tackle this challenge, an inequality arising from the monotonicity of relative entropy is demonstrated to serve as an evidence lower bound for density operators. A minorant-maximization perspective on this bound leads to Density Operator Expectation Maximization (DO-EM), a general framework for training latent variable models defined through density operators. Through an information-geometric argument, the Expectation step in DO-EM is shown to be the Petz recovery map. The DO-EM algorithm is applied to Quantum Restricted Boltzmann Machines, adapting Contrastive Divergence to approximate the Maximization step gradient. Quantum interleaved Deep Boltzmann Machines and Quantum Gaussian-Bernoulli Restricted Boltzmann Machines, new models introduced in this work, outperform their probabilistic counterparts on generative tasks when trained with similar computational resources and identical hyperparameters. - oai:arXiv.org:2507.22786v2 - cs.LG - quant-ph - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Adit Vishnu, Abhay Shastry, Dhruva Kashyap, Chiranjib Bhattacharyya - - - Exponential Lower Bounds on the Size of ResLin Proofs of Nearly Quadratic Depth - https://arxiv.org/abs/2507.23008 - arXiv:2507.23008v2 Announce Type: replace -Abstract: Itsykson and Sokolov [IS14] identified resolution over parities, denoted by $\text{Res}(\oplus)$, as a natural and simple fragment of $\text{AC}^0[2]$-Frege for which no super-polynomial lower bounds on size of proofs are known. Building on a recent line of work ([EGI24], [BCD24], [AI25]), Efremenko and Itsykson [EI25] proved lower bounds of the form $\text{exp}(N^{\Omega(1)})$, on the size of $\text{Res}(\oplus)$ proofs whose depth is upper bounded by $O(N\log N)$, where $N$ is the number of variables of the unsatisfiable CNF formula. The hard formula they used was Tseitin on an appropriately expanding graph, lifted by a $2$-stifling gadget. They posed the natural problem of proving super-polynomial lower bounds on the size of proofs that are $\Omega(N^{1+\epsilon})$ deep, for any constant $\epsilon > 0$. - We prove the first such lower bounds. In fact, we show that $\text{Res}(\oplus)$ refutations of Tseitin formulas on constant-degree expanders on $m$ vertices, lifted with Inner-Product gadget of size $O(\log m)$, must have size $\text{exp}(\tilde{\Omega}(N^{\epsilon}))$, as long as the depth of the $\text{Res}(\oplus)$ proofs are $O(N^{2-\epsilon})$, for every $\epsilon > 0$. Here $N=\Theta(m\log m)$ is the number of variables of the lifted formula. An important ingredient in our work is to show that arbitrary distributions lifted with such gadgets fool safe affine spaces, an idea which originates in the earlier work of Bhattacharya, Chattopadhyay and Dvorak [BCD24]. - oai:arXiv.org:2507.23008v2 - cs.CC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sreejata Kishor Bhattacharya, Arkadev Chattopadhyay - - - MUST-RAG: MUSical Text Question Answering with Retrieval Augmented Generation - https://arxiv.org/abs/2507.23334 - arXiv:2507.23334v2 Announce Type: replace -Abstract: Recent advancements in Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains. While they exhibit strong zero-shot performance on various tasks, LLMs' effectiveness in music-related applications remains limited due to the relatively small proportion of music-specific knowledge in their training data. To address this limitation, we propose MusT-RAG, a comprehensive framework based on Retrieval Augmented Generation (RAG) to adapt general-purpose LLMs for text-only music question answering (MQA) tasks. RAG is a technique that provides external knowledge to LLMs by retrieving relevant context information when generating answers to questions. To optimize RAG for the music domain, we (1) propose MusWikiDB, a music-specialized vector database for the retrieval stage, and (2) utilizes context information during both inference and fine-tuning processes to effectively transform general-purpose LLMs into music-specific models. Our experiment demonstrates that MusT-RAG significantly outperforms traditional fine-tuning approaches in enhancing LLMs' music domain adaptation capabilities, showing consistent improvements across both in-domain and out-of-domain MQA benchmarks. Additionally, our MusWikiDB proves substantially more effective than general Wikipedia corpora, delivering superior performance and computational efficiency. - oai:arXiv.org:2507.23334v2 - cs.CL - cs.AI - cs.IR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Daeyong Kwon, SeungHeon Doh, Juhan Nam - - - The Complexity of Logarithmic Space Bounded Counting Classes - https://arxiv.org/abs/2507.23563 - arXiv:2507.23563v3 Announce Type: replace -Abstract: In this monograph, we study complexity classes that are defined using $O(\log n)$-space bounded non-deterministic Turing machines. We prove salient results of Computational Complexity in this topic such as the Immerman-Szelepcs$\rm\acute{e}$nyi Theorem, the Isolating Lemma, theorems of Mahajan-Vinay on the determinant and many consequences of these very important results. The manuscript is intended to be a comprehensive textbook on the topic of The Complexity of Logarithmic Space Bounded Counting Classes. - oai:arXiv.org:2507.23563v3 - cs.CC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - T. C. Vijayaraghavan - - - Semantic Chain-of-Trust: Autonomous Trust Orchestration for Collaborator Selection via Hypergraph-Aided Agentic AI - https://arxiv.org/abs/2507.23565 - arXiv:2507.23565v3 Announce Type: replace -Abstract: The effective completion of tasks in collaborative systems hinges on task-specific trust evaluations of potential devices for distributed collaboration. Due to independent operation of devices involved, dynamic evolution of their mutual relationships, and complex situation-related impact on trust evaluation, effectively assessing devices' trust for collaborator selection is challenging. To overcome this challenge, we propose a semantic chain-of-trust model implemented with agentic AI and hypergraphs for supporting effective collaborator selection. We first introduce a concept of semantic trust, specifically designed to assess collaborators along multiple semantic dimensions for a more accurate representation of their trustworthiness. To facilitate intelligent evaluation, an agentic AI system is deployed on each device, empowering it to autonomously perform necessary operations, including device state detection, trust-related data collection, semantic extraction, task-specific resource evaluation, to derive a semantic trust representation for each collaborator. In addition, each device leverages a hypergraph to dynamically manage potential collaborators according to different levels of semantic trust, enabling fast one-hop collaborator selection. Furthermore, adjacent trusted devices autonomously form a chain through the hypergraph structure, supporting multi-hop collaborator selection. Experimental results demonstrate that the proposed semantic chain-of-trust achieves 100\% accuracy in trust evaluation based on historical collaborations, enabling intelligent, resource-efficient, and precise collaborator selection. - oai:arXiv.org:2507.23565v3 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Botao Zhu, Xianbin Wang, Dusit Niyato - - - Dual Collaborative LLMs via Continual Fine-Tuning for Serendipitous Recommendation - https://arxiv.org/abs/2508.00450 - arXiv:2508.00450v2 Announce Type: replace -Abstract: Traditional recommendation systems tend to trap users in strong feedback loops by excessively pushing content aligned with their historical preferences, thereby limiting exploration opportunities and causing content fatigue. Although large language models (LLMs) demonstrate potential with their diverse content generation capabilities, existing LLM-enhanced dual-model frameworks face two major limitations: first, they overlook long-term preferences driven by group identity, leading to biased interest modeling; second, they suffer from static optimization flaws, as a one-time alignment process fails to leverage incremental user data for closed-loop optimization. To address these challenges, we propose the Co-Evolutionary Alignment (CoEA) method. For interest modeling bias, we introduce Dual-Stable Interest Exploration (DSIE) module, jointly modeling long-term group identity and short-term individual interests through parallel processing of behavioral sequences. For static optimization limitations, we design a Periodic Collaborative Optimization (PCO) mechanism. This mechanism regularly conducts preference verification on incremental data using the Relevance LLM, then guides the Novelty LLM to perform fine-tuning based on the verification results, and subsequently feeds back the output of the continually fine-tuned Novelty LLM to the Relevance LLM for re-evaluation, thereby achieving a dynamic closed-loop optimization. Extensive online and offline experiments verify the effectiveness of the CoEA model in serendipitous recommendation. - oai:arXiv.org:2508.00450v2 - cs.IR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hongxiang Lin, Hao Guo, Zeshun Li, Erpeng Xue, Yongqian He, Xiangyu Hou, Zhaoyu Hu, Lei Wang, Sheng Chen - - - A Deep Reinforcement Learning-Based TCP Congestion Control Algorithm: Design, Simulation, and Evaluation - https://arxiv.org/abs/2508.01047 - arXiv:2508.01047v2 Announce Type: replace -Abstract: This paper presents a novel TCP congestion control algorithm based on Deep Reinforcement Learning. The proposed approach utilizes Deep Q-Networks to optimize the congestion window (cWnd) by observing key network parameters and taking real-time actions. The algorithm is trained and evaluated within the NS-3 network simulator using the OpenGym interface. The results demonstrate significant improvements over traditional TCP New Reno in terms of latency and throughput, with better adaptability to changing network conditions. This study emphasizes the potential of reinforcement learning techniques for solving complex congestion control problems in modern networks. - oai:arXiv.org:2508.01047v2 - cs.NI - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Efe A\u{g}lamazlar, Emirhan Eken, Harun Batur Ge\c{c}ici - - - Instruction-based Time Series Editing - https://arxiv.org/abs/2508.01504 - arXiv:2508.01504v3 Announce Type: replace -Abstract: In time series editing, we aim to modify some properties of a given time series without altering others. For example, when analyzing a hospital patient's blood pressure, we may add a sudden early drop and observe how it impacts their future while preserving other conditions. Existing diffusion-based editors rely on rigid, predefined attribute vectors as conditions and produce all-or-nothing edits through sampling. This attribute- and sampling-based approach limits flexibility in condition format and lacks customizable control over editing strength. To overcome these limitations, we introduce Instruction-based Time Series Editing, where users specify intended edits using natural language. This allows users to express a wider range of edits in a more accessible format. We then introduce InstructTime, the first instruction-based time series editor. InstructTime takes in time series and instructions, embeds them into a shared multi-modal representation space, then decodes their embeddings to generate edited time series. By learning a structured multi-modal representation space, we can easily interpolate between embeddings to achieve varying degrees of edit. To handle local and global edits together, we propose multi-resolution encoders. In our experiments, we use synthetic and real datasets and find that InstructTime is a state-of-the-art time series editor: InstructTime achieves high-quality edits with controllable strength, can generalize to unseen instructions, and can be easily adapted to unseen conditions through few-shot learning. - oai:arXiv.org:2508.01504v3 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiaxing Qiu, Dongliang Guo, Brynne Sullivan, Teague R. Henry, Thomas Hartvigsen - - - Implementing Cumulative Functions with Generalized Cumulative Constraints - https://arxiv.org/abs/2508.01751 - arXiv:2508.01751v2 Announce Type: replace -Abstract: Modeling scheduling problems with conditional time intervals and cumulative functions has become a common approach when using modern commercial constraint programming solvers. This paradigm enables the modeling of a wide range of scheduling problems, including those involving producers and consumers. However, it is unavailable in existing open-source solvers and practical implementation details remain undocumented. In this work, we present an implementation of this modeling approach using a single, generic global constraint called the Generalized Cumulative. We also introduce a novel time-table filtering algorithm specifically designed to handle tasks defined on conditional time-intervals. Experimental results demonstrate that this approach, combined with the new filtering algorithm, performs competitively with existing solvers enabling the modeling of producer and consumer scheduling problems and effectively scales to large-scale problems. - oai:arXiv.org:2508.01751v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Pierre Schaus, Charles Thomas, Roger Kameugne - - - Optimizing Day-Ahead Energy Trading with Proximal Policy Optimization and Blockchain - https://arxiv.org/abs/2508.01888 - arXiv:2508.01888v2 Announce Type: replace -Abstract: The increasing penetration of renewable energy sources in day-ahead energy markets introduces challenges in balancing supply and demand, ensuring grid resilience, and maintaining trust in decentralized trading systems. This paper proposes a novel framework that integrates the Proximal Policy Optimization (PPO) algorithm, a state-of-the-art reinforcement learning method, with blockchain technology to optimize automated trading strategies for prosumers in day-ahead energy markets. We introduce a comprehensive framework that employs RL agent for multi-objective energy optimization and blockchain for tamper-proof data and transaction management. Simulations using real-world data from the Electricity Reliability Council of Texas (ERCOT) demonstrate the effectiveness of our approach. The RL agent achieves demand-supply balancing within 2\% and maintains near-optimal supply costs for the majority of the operating hours. Moreover, it generates robust battery storage policies capable of handling variability in solar and wind generation. All decisions are recorded on an Algorand-based blockchain, ensuring transparency, auditability, and security - key enablers for trustworthy multi-agent energy trading. Our contributions include a novel system architecture, curriculum learning for robust agent development, and actionable policy insights for practical deployment. - oai:arXiv.org:2508.01888v2 - cs.LG - cs.CR - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Navneet Verma, Ying Xie - - - Generative Large-Scale Pre-trained Models for Automated Ad Bidding Optimization - https://arxiv.org/abs/2508.02002 - arXiv:2508.02002v2 Announce Type: replace -Abstract: Modern auto-bidding systems are required to balance overall performance with diverse advertiser goals and real-world constraints, reflecting the dynamic and evolving needs of the industry. Recent advances in conditional generative models, such as transformers and diffusers, have enabled direct trajectory generation tailored to advertiser preferences, offering a promising alternative to traditional Markov Decision Process-based methods. However, these generative methods face significant challenges, such as the distribution shift between offline and online environments, limited exploration of the action space, and the necessity to meet constraints like marginal Cost-per-Mille (CPM) and Return on Investment (ROI). To tackle these challenges, we propose GRAD (Generative Reward-driven Ad-bidding with Mixture-of-Experts), a scalable foundation model for auto-bidding that combines an Action-Mixture-of-Experts module for diverse bidding action exploration with the Value Estimator of Causal Transformer for constraint-aware optimization. Extensive offline and online experiments demonstrate that GRAD significantly enhances platform revenue, highlighting its effectiveness in addressing the evolving and diverse requirements of modern advertisers. Furthermore, GRAD has been implemented in multiple marketing scenarios at Meituan, one of the world's largest online food delivery platforms, leading to a 2.18% increase in Gross Merchandise Value (GMV) and 10.68% increase in ROI. - oai:arXiv.org:2508.02002v2 - cs.LG - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yu Lei, Jiayang Zhao, Yilei Zhao, Zhaoqi Zhang, Linyou Cai, Qianlong Xie, Xingxing Wang - - - FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment - https://arxiv.org/abs/2508.02292 - arXiv:2508.02292v2 Announce Type: replace -Abstract: Financial AI holds great promise for transforming modern finance, with the potential to support a wide range of tasks such as market forecasting, portfolio management, quantitative trading, and automated analysis. However, existing platforms remain limited in task coverage, lack robust multimodal data integration, and offer insufficient support for the training and deployment of large language models (LLMs). In response to these limitations, we present FinWorld, an all-in-one open-source platform that provides end-to-end support for the entire financial AI workflow, from data acquisition to experimentation and deployment. FinWorld distinguishes itself through native integration of heterogeneous financial data, unified support for diverse AI paradigms, and advanced agent automation, enabling seamless development and deployment. Leveraging data from 2 representative markets, 4 stock pools, and over 800 million financial data points, we conduct comprehensive experiments on 4 key financial AI tasks. These experiments systematically evaluate deep learning and reinforcement learning algorithms, with particular emphasis on RL-based finetuning for LLMs and LLM Agents. The empirical results demonstrate that FinWorld significantly enhances reproducibility, supports transparent benchmarking, and streamlines deployment, thereby providing a strong foundation for future research and real-world applications. Code is available at Github~\footnote{https://github.com/DVampire/FinWorld}. - oai:arXiv.org:2508.02292v2 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wentao Zhang, Yilei Zhao, Chuqiao Zong, Xinrun Wang, Bo An - - - WiFinger: Fingerprinting Noisy IoT Event Traffic Using Packet-level Sequence Matching - https://arxiv.org/abs/2508.03151 - arXiv:2508.03151v2 Announce Type: replace -Abstract: IoT environments such as smart homes are susceptible to privacy inference attacks, where attackers can analyze patterns of encrypted network traffic to infer the state of devices and even the activities of people. While most existing attacks exploit ML techniques for discovering such traffic patterns, they underperform on wireless traffic, especially Wi-Fi, due to its heavy noisiness and the packet loss of wireless sniffing. In addition, these approaches commonly target distinguishing chunked IoT event traffic samples, and they fail at effectively tracking multiple events simultaneously. In this work, we propose WiFinger, a fine-grained multi-IoT event fingerprinting approach against noisy traffic. WiFinger turns the traffic pattern classification task into a subsequence matching problem and introduces novel techniques to account for the high time complexity while maintaining high accuracy. In addition, its reliance on training sample volumes reduces efforts for any future fingerprint updates. Experiments demonstrate that WiFinger outperforms existing approaches under practical threat models, with an average recall of 89% (v.s. 49% and 46% respectively) and almost zero false positives for various IoT events. - oai:arXiv.org:2508.03151v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - The Network and Distributed System Security (NDSS), 2026 - Ronghua Li, Shinan Liu, Haibo Hu, Qingqing Ye, Nick Feamster - - - GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations - https://arxiv.org/abs/2508.03209 - arXiv:2508.03209v2 Announce Type: replace -Abstract: Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Although adversarial perturbations offer a potential defense, current methods are ill-suited for this scenario: they often perform poorly on high-resolution images and low perturbation budgets, and may introduce irrelevant semantic content. To address these limitations, we propose GeoShield, a novel adversarial framework designed for robust geoprivacy protection in real-world scenarios. GeoShield comprises three key modules: a feature disentanglement module that separates geographical and non-geographical information, an exposure element identification module that pinpoints geo-revealing regions within an image, and a scale-adaptive enhancement module that jointly optimizes perturbations at both global and local levels to ensure effectiveness across resolutions. Extensive experiments on challenging benchmarks show that GeoShield consistently surpasses prior methods in black-box settings, achieving strong privacy protection with minimal impact on visual or semantic quality. To our knowledge, this work is the first to explore adversarial perturbations for defending against geolocation inference by advanced VLMs, providing a practical and effective solution to escalating privacy concerns. - oai:arXiv.org:2508.03209v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xinwei Liu, Xiaojun Jia, Yuan Xun, Simeng Qin, Xiaochun Cao - - - MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework - https://arxiv.org/abs/2508.03929 - arXiv:2508.03929v2 Announce Type: replace -Abstract: Designing effective algorithmic components remains a fundamental obstacle in tackling NP-hard combinatorial optimization problems (COPs), where solvers often rely on carefully hand-crafted strategies. Despite recent advances in using large language models (LLMs) to synthesize high-quality components, most approaches restrict the search to a single element - commonly a heuristic scoring function - thus missing broader opportunities for innovation. In this paper, we introduce a broader formulation of solver design as a multi-strategy optimization problem, which seeks to jointly improve a set of interdependent components under a unified objective. To address this, we propose Multi-strategy Optimization via Turn-based Interactive Framework (MOTIF) - a novel framework based on Monte Carlo Tree Search that facilitates turn-based optimization between two LLM agents. At each turn, an agent improves one component by leveraging the history of both its own and its opponent's prior updates, promoting both competitive pressure and emergent cooperation. This structured interaction broadens the search landscape and encourages the discovery of diverse, high-performing solutions. Experiments across multiple COP domains show that MOTIF consistently outperforms state-of-the-art methods, highlighting the promise of turn-based, multi-agent prompting for fully automated solver design. - oai:arXiv.org:2508.03929v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nguyen Viet Tuan Kiet, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh - - - InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization - https://arxiv.org/abs/2508.05731 - arXiv:2508.05731v2 Announce Type: replace -Abstract: The emergence of Multimodal Large Language Models (MLLMs) has propelled the development of autonomous agents that operate on Graphical User Interfaces (GUIs) using pure visual input. A fundamental challenge is robustly grounding natural language instructions. This requires a precise spatial alignment, which accurately locates the coordinates of each element, and, more critically, a correct semantic alignment, which matches the instructions to the functionally appropriate UI element. Although Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be effective at improving spatial alignment for these MLLMs, we find that inefficient exploration bottlenecks semantic alignment, which prevent models from learning difficult semantic associations. To address this exploration problem, we present Adaptive Exploration Policy Optimization (AEPO), a new policy optimization framework. AEPO employs a multi-answer generation strategy to enforce broader exploration, which is then guided by a theoretically grounded Adaptive Exploration Reward (AER) function derived from first principles of efficiency eta=U/C. Our AEPO-trained models, InfiGUI-G1-3B and InfiGUI-G1-7B, establish new state-of-the-art results across multiple challenging GUI grounding benchmarks, achieving significant relative improvements of up to 9.0% against the naive RLVR baseline on benchmarks designed to test generalization and semantic understanding. Resources are available at https://github.com/InfiXAI/InfiGUI-G1. - oai:arXiv.org:2508.05731v2 - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yuhang Liu, Zeyu Liu, Shuanghe Zhu, Pengxiang Li, Congkai Xie, Jiasheng Wang, Xavier Hu, Xiaotian Han, Jianbo Yuan, Xinyao Wang, Shengyu Zhang, Hongxia Yang, Fei Wu - - - DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment - https://arxiv.org/abs/2508.06041 - arXiv:2508.06041v4 Announce Type: replace -Abstract: How can we effectively handle queries for on-device large language models (LLMs) with varying runtime constraints, such as latency and accuracy? Multi-scale quantization addresses this challenge by enabling memory-efficient runtime model adaptation of LLMs through the overlaying of multiple model variants quantized to different bitwidths. Meanwhile, an important question still remains open-ended: how can models be properly configured to match a target precision or latency? While mixed-precision offers a promising solution, we take this further by leveraging the key observation that the sensitivity of each layer dynamically changes across decoding steps. Building on this insight, we introduce DP-LLM, a novel mechanism that dynamically assigns precision to each layer based on input values. Experimental results across multiple models and benchmarks demonstrate that DP-LLM achieves a superior performance-latency trade-off, outperforming prior approaches. - oai:arXiv.org:2508.06041v4 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Sangwoo Kwon, Seong Hoon Seo, Jae W. Lee, Yeonhong Park - - - Architecture-Aware Generalization Bounds for Temporal Networks: Theory and Fair Comparison Methodology - https://arxiv.org/abs/2508.06066 - arXiv:2508.06066v2 Announce Type: replace -Abstract: Deep temporal architectures such as TCNs achieve strong predictive performance on sequential data, yet theoretical understanding of their generalization remains limited. We address this gap through three contributions: introducing an evaluation methodology for temporal models, revealing surprising empirical phenomena about temporal dependence, and the first architecture-aware theoretical framework for dependent sequences. - Fair-Comparison Methodology. We introduce evaluation protocols that fix effective sample size $N_{\text{eff}}$ to isolate temporal structure effects from information content. - Empirical Findings. Applying this method reveals that under $N_{\text{eff}} = 2000$, strongly dependent sequences ($\rho = 0.8$) exhibit approx' $76\%$ smaller generalization gaps than weakly dependent ones ($\rho = 0.2$), challenging the conventional view that dependence universally impedes learning. However, observed convergence rates ($N_{\text{eff}}^{-1.21}$ to $N_{\text{eff}}^{-0.89}$) significantly exceed theoretical worst-case predictions ($N^{-0.5}$), revealing that temporal architectures exploit problem structure in ways current theory does not capture. - Lastly, we develop the first architecture-aware generalization bounds for deep temporal models on exponentially $\beta$-mixing sequences. By embedding Golowich et al.'s i.i.d. class bound within a novel blocking scheme that partitions $N$ samples into approx' $B \approx N/\log N$ quasi-independent blocks, we establish polynomial sample complexity under convex Lipschitz losses. The framework achieves $\sqrt{D}$ depth scaling alongside the product of layer-wise norms $R = \prod_{\ell=1}^{D} M^{(\ell)}$, avoiding exponential dependence. While these bounds are conservative, they prove learnability and identify architectural scaling laws, providing worst-case baselines that highlight where future theory must improve. - oai:arXiv.org:2508.06066v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Barak Gahtan, Alex M. Bronstein - - - DexFruit: Dexterous Manipulation and Gaussian Splatting Inspection of Fruit - https://arxiv.org/abs/2508.07118 - arXiv:2508.07118v3 Announce Type: replace -Abstract: DexFruit is a robotic manipulation framework that enables gentle, autonomous handling of fragile fruit and precise evaluation of damage. Many fruits are fragile and prone to bruising, thus requiring humans to manually harvest them with care. In this work, we demonstrate by using optical tactile sensing, autonomous manipulation of fruit with minimal damage can be achieved. We show that our tactile informed diffusion policies outperform baselines in both reduced bruising and pick-and-place success rate across three fruits: strawberries, tomatoes, and blackberries. In addition, we introduce FruitSplat, a novel technique to represent and quantify visual damage in high-resolution 3D representation via 3D Gaussian Splatting (3DGS). Existing metrics for measuring damage lack quantitative rigor or require expensive equipment. With FruitSplat, we distill a 2D strawberry mask as well as a 2D bruise segmentation mask into the 3DGS representation. Furthermore, this representation is modular and general, compatible with any relevant 2D model. Overall, we demonstrate a 92% grasping policy success rate, up to a 20% reduction in visual bruising, and up to an 31% improvement in grasp success rate on challenging fruit compared to our baselines across our three tested fruits. We rigorously evaluate this result with over 630 trials. Please checkout our website at https://dex-fruit.github.io . - oai:arXiv.org:2508.07118v3 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Aiden Swann, Alex Qiu, Matthew Strong, Angelina Zhang, Samuel Morstein, Kai Rayle, Monroe Kennedy III - - - Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape - https://arxiv.org/abs/2508.07334 - arXiv:2508.07334v2 Announce Type: replace -Abstract: The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turing machine by constructing a "computational necessity hierarchy", and for the first time proves the illusions are inevitable on diagonalization, incomputability, and information theory boundaries supported by the new "learner pump lemma". However, we propose two "escape routes": one is to model Retrieval Enhanced Generations (RAGs) as oracle machines, proving their absolute escape through "computational jumps", providing the first formal theory for the effectiveness of RAGs; The second is to formalize continuous learning as an "internalized oracle" mechanism and implement this path through a novel neural game theory framework. Finally, this article proposes a feasible new principle for artificial intelligence security - Computational Class Alignment (CCA), which requires strict matching between task complexity and the actual computing power of the system, providing theoretical support for the secure application of artificial intelligence. - oai:arXiv.org:2508.07334v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wang Xi, Quan Shi, Zenghui Ding, Jianqing Gao, Xianjun Yang - - - DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation - https://arxiv.org/abs/2508.07341 - arXiv:2508.07341v2 Announce Type: replace -Abstract: The unified autoregressive (AR) model excels at multimodal understanding and generation. However, its full potential in the domain of customized image generation has yet to be fully realized. Existing customization approaches for unified AR models face a fundamental dilemma: adaptation-based methods suffer from overfitting and scalability bottlenecks, while concept-injection paradigms are constrained by a shallow injection strategy that leads to poor visual fidelity and impaired re-contextualization. To address this, we propose DCoAR, a novel deep concept injection framework that maintains a completely frozen pre-trained model. DCoAR deeply integrates new concepts through a Layer-wise Multimodal Context Learning (LMCL) strategy, which is stabilized by a multi-faceted regularization scheme: a Dual Prior Preservation (DPP) loss to mitigate semantic drift and a Context-Aware Self-Regularization (CASR) loss to enhance re-contextualization. The framework also enables training-free subject customization in user-provided styles. Experiments demonstrate that DCoAR significantly outperforms previous injection-based methods and achieves performance competitive with adaptation-based approaches while requiring substantially fewer trainable parameters. Code: https://github.com/KZF-kzf/CoAR - oai:arXiv.org:2508.07341v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fangtai Wu, Mushui Liu, Weijie He, Zhao Wang, Yunlong Yu - - - Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlo - https://arxiv.org/abs/2508.07631 - arXiv:2508.07631v3 Announce Type: replace -Abstract: We study the problem of posterior sampling in the context of score based generative models. We have a trained score network for a prior $p(x)$, a measurement model $p(y|x)$, and are tasked with sampling from the posterior $p(x|y)$. Prior work has shown this to be intractable in KL (in the worst case) under well-accepted computational hardness assumptions. Despite this, popular algorithms for tasks such as image super-resolution, stylization, and reconstruction enjoy empirical success. Rather than establishing distributional assumptions or restricted settings under which exact posterior sampling is tractable, we view this as a more general "tilting" problem of biasing a distribution towards a measurement. Under minimal assumptions, we show that one can tractably sample from a distribution that is simultaneously close to the posterior of a noised prior in KL divergence and the true posterior in Fisher divergence. Intuitively, this combination ensures that the resulting sample is consistent with both the measurement and the prior. To the best of our knowledge these are the first formal results for (approximate) posterior sampling in polynomial time. - oai:arXiv.org:2508.07631v3 - cs.LG - cs.AI - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Advait Parulekar, Litu Rout, Karthikeyan Shanmugam, Sanjay Shakkottai - - - Material Fingerprinting: A shortcut to material model discovery without solving optimization problems - https://arxiv.org/abs/2508.07831 - arXiv:2508.07831v2 Announce Type: replace -Abstract: We propose Material Fingerprinting, a new method for the rapid discovery of mechanical material models from direct or indirect data that avoids solving potentially non-convex optimization problems. The core assumption of Material Fingerprinting is that each material exhibits a unique response when subjected to a standardized experimental setup. We can interpret this response as the material's fingerprint, essentially a unique identifier that encodes all pertinent information about the material's mechanical characteristics. Consequently, once we have established a database containing fingerprints and their corresponding mechanical models during an offline phase, we can rapidly characterize an unseen material in an online phase. This is accomplished by measuring its fingerprint and employing a pattern recognition algorithm to identify the best matching fingerprint in the database. In our study, we explore this concept in the context of hyperelastic materials, demonstrating the applicability of Material Fingerprinting across different experimental setups. Initially, we examine Material Fingerprinting through experiments involving homogeneous deformation fields, which provide direct strain-stress data pairs. We then extend this concept to experiments involving complexly shaped specimens with heterogeneous deformation fields, which provide indirect displacement and reaction force measurements. We show that, in both cases, Material Fingerprinting is an efficient tool for model discovery, bypassing the challenges of potentially non-convex optimization. We believe that Material Fingerprinting provides a powerful and generalizable framework for rapid material model identification across a wide range of experimental designs and material behaviors, paving the way for numerous future developments. - oai:arXiv.org:2508.07831v2 - cs.CE - cond-mat.mtrl-sci - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Moritz Flaschel, Denisa Martonov\'a, Carina Veil, Ellen Kuhl - - - Understanding Syntactic Generalization in Structure-inducing Language Models - https://arxiv.org/abs/2508.07969 - arXiv:2508.07969v2 Announce Type: replace -Abstract: Structure-inducing Language Models (SiLM) are trained on a self-supervised language modeling task, and induce a hierarchical sentence representation as a byproduct when processing an input. SiLMs couple strong syntactic generalization behavior with competitive performance on various NLP tasks, but many of their basic properties are yet underexplored. In this work, we train three different SiLM architectures from scratch: Structformer (Shen et al., 2021), UDGN (Shen et al., 2022), and GPST (Hu et al., 2024b). We train these architectures on both natural language (English, German, and Chinese) corpora and synthetic bracketing expressions. The models are then evaluated with respect to (i) properties of the induced syntactic representations (ii) performance on grammaticality judgment tasks, and (iii) training dynamics. We find that none of the three architectures dominates across all evaluation metrics. However, there are significant differences, in particular with respect to the induced syntactic representations. The Generative Pretrained Structured Transformer (GPST; Hu et al. 2024) performs most consistently across evaluation settings, and outperforms the other models on long-distance dependencies in bracketing expressions. Furthermore, our study shows that small models trained on large amounts of synthetic data provide a useful testbed for evaluating basic model properties. - oai:arXiv.org:2508.07969v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - David Arps, Hassan Sajjad, Laura Kallmeyer - - - Learning to Select MCP Algorithms: From Traditional ML to Dual-Channel GAT-MLP - https://arxiv.org/abs/2508.08005 - arXiv:2508.08005v3 Announce Type: replace -Abstract: The Maximum Clique Problem (MCP) is a foundational NP-hard problem with wide-ranging applications, yet no single algorithm consistently outperforms all others across diverse graph instances. This underscores the critical need for instance-aware algorithm selection, a domain that remains largely unexplored for the MCP. To address this gap, we propose a novel learning-based framework that integrates both traditional machine learning and graph neural networks. We first construct a benchmark dataset by executing four state-of-the-art exact MCP solvers on a diverse collection of graphs and extracting their structural features. An evaluation of conventional classifiers establishes Random Forest as a strong baseline and reveals that connectivity and topological features are key predictors of performance. Building on these insights, we develop GAT-MLP, a dual-channel model that combines a Graph Attention Network (GAT) to encode local graph structure with a Multilayer Perceptron (MLP) to model global features. Extensive experiments demonstrate that GAT-MLP achieves superior and consistent performance, significantly outperforming all baseline methods. Our results highlight the effectiveness of the dual-channel architecture and the promise of graph neural networks for combinatorial algorithm selection, achieving 90.43% accuracy in choosing the optimal solver. Code and models are available at: https://anonymous.4open.science/r/GAT-MLP-7E5F. - oai:arXiv.org:2508.08005v3 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiang Li, Shanshan Wang, Chenglong Xiao - - - Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent - https://arxiv.org/abs/2508.08222 - arXiv:2508.08222v2 Announce Type: replace -Abstract: Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities through training remain limited, particularly from a theoretical standpoint. This work investigates how transformers learn to solve symbolic multi-step reasoning problems through chain-of-thought processes, focusing on path-finding in trees. We analyze two intertwined tasks: a backward reasoning task, where the model outputs a path from a goal node to the root, and a more complex forward reasoning task, where the model implements two-stage reasoning by first identifying the goal-to-root path and then reversing it to produce the root-to-goal path. Our theoretical analysis, grounded in the dynamics of gradient descent, shows that trained one-layer transformers can provably solve both tasks with generalization guarantees to unseen trees. In particular, our multi-phase training dynamics for forward reasoning elucidate how different attention heads learn to specialize and coordinate autonomously to solve the two subtasks in a single autoregressive path. These results provide a mechanistic explanation of how trained transformers can implement sequential algorithmic procedures. Moreover, they offer insights into the emergence of reasoning abilities, suggesting that when tasks are structured to take intermediate chain-of-thought steps, even shallow multi-head transformers can effectively solve problems that would otherwise require deeper architectures. - oai:arXiv.org:2508.08222v2 - cs.LG - cs.AI - cs.IT - math.IT - math.OC - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi - - - Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference - https://arxiv.org/abs/2508.09442 - arXiv:2508.09442v3 Announce Type: replace -Abstract: The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model (LLM) inference. However, this efficiency optimization introduces significant yet underexplored privacy risks. This paper provides the first comprehensive analysis of these vulnerabilities, demonstrating that an attacker can reconstruct sensitive user inputs directly from the KV-cache. We design and implement three distinct attack vectors: a direct Inversion Attack, a more broadly applicable and potent Collision Attack, and a semantic-based Injection Attack. These methods demonstrate the practicality and severity of KV-cache privacy leakage issues. To mitigate this, we propose KV-Cloak, a novel, lightweight, and efficient defense mechanism. KV-Cloak uses a reversible matrix-based obfuscation scheme, combined with operator fusion, to secure the KV-cache. Our extensive experiments show that KV-Cloak effectively thwarts all proposed attacks, reducing reconstruction quality to random noise. Crucially, it achieves this robust security with virtually no degradation in model accuracy and minimal performance overhead, offering a practical solution for trustworthy LLM deployment. - oai:arXiv.org:2508.09442v3 - cs.CR - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhifan Luo, Shuo Shao, Su Zhang, Lijing Zhou, Yuke Hu, Chenxu Zhao, Zhihao Liu, Zhan Qin - - - EVCtrl: Efficient Control Adapter for Visual Generation - https://arxiv.org/abs/2508.10963 - arXiv:2508.10963v2 Announce Type: replace -Abstract: Visual generation includes both image and video generation, training probabilistic models to create coherent, diverse, and semantically faithful content from scratch. While early research focused on unconditional sampling, practitioners now demand controllable generation that allows precise specification of layout, pose, motion, or style. While ControlNet grants precise spatial-temporal control, its auxiliary branch markedly increases latency and introduces redundant computation in both uncontrolled regions and denoising steps, especially for video. To address this problem, we introduce EVCtrl, a lightweight, plug-and-play control adapter that slashes overhead without retraining the model. Specifically, we propose a spatio-temporal dual caching strategy for sparse control information. For spatial redundancy, we first profile how each layer of DiT-ControlNet responds to fine-grained control, then partition the network into global and local functional zones. A locality-aware cache focuses computation on the local zones that truly need the control signal, skipping the bulk of redundant computation in global regions. For temporal redundancy, we selectively omit unnecessary denoising steps to improve efficiency. Extensive experiments on CogVideo-Controlnet, Wan2.1-Controlnet, and Flux demonstrate that our method is effective in image and video control generation without the need for training. For example, it achieves 2.16 and 2.05 times speedups on CogVideo-Controlnet and Wan2.1-Controlnet, respectively, with almost no degradation in generation quality.Codes are available in the supplementary materials. - oai:arXiv.org:2508.10963v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zixiang Yang, Yue Ma, Yinhan Zhang, Shanhui Mo, Dongrui Liu, Linfeng Zhang - - - SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learning - https://arxiv.org/abs/2508.12394 - arXiv:2508.12394v2 Announce Type: replace -Abstract: Image-goal navigation (ImageNav) tasks a robot with autonomously exploring an unknown environment and reaching a location that visually matches a given target image. While prior works primarily study ImageNav for ground robots, enabling this capability for autonomous drones is substantially more challenging due to their need for high-frequency feedback control and global localization for stable flight. In this paper, we propose a novel sim-to-real framework that leverages reinforcement learning (RL) to achieve ImageNav for drones. To enhance visual representation ability, our approach trains the vision backbone with auxiliary tasks, including image perturbations and future transition prediction, which results in more effective policy training. The proposed algorithm enables end-to-end ImageNav with direct velocity control, eliminating the need for external localization. Furthermore, we integrate a depth-based safety module for real-time obstacle avoidance, allowing the drone to safely navigate in cluttered environments. Unlike most existing drone navigation methods that focus solely on reference tracking or obstacle avoidance, our framework supports comprehensive navigation behaviors, including autonomous exploration, obstacle avoidance, and image-goal seeking, without requiring explicit global mapping. Code and model checkpoints are available at https://github.com/Zichen-Yan/SIGN. - oai:arXiv.org:2508.12394v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zichen Yan, Rui Huang, Lei He, Shao Guo, Lin Zhao - - - Image2Net: Datasets, Benchmark and Hybrid Framework to Convert Analog Circuit Diagrams into Netlists - https://arxiv.org/abs/2508.13157 - arXiv:2508.13157v2 Announce Type: replace -Abstract: Large Language Model (LLM) exhibits great potential in designing of analog integrated circuits (IC) because of its excellence in abstraction and generalization for knowledge. However, further development of LLM-based analog ICs heavily relies on textual description of analog ICs, while existing analog ICs are mostly illustrated in image-based circuit diagrams rather than text-based netlists. Converting circuit diagrams to netlists help LLMs to enrich the knowledge of analog IC. Nevertheless, previously proposed conversion frameworks face challenges in further application because of limited support of image styles and circuit elements. Up to now, it still remains a challenging task to effectively convert complex circuit diagrams into netlists. To this end, this paper constructs and opensources a new dataset with rich styles of circuit diagrams as well as balanced distribution of simple and complex analog ICs. And a hybrid framework, named Image2Net, is proposed for practical conversion from circuit diagrams to netlists. The netlist edit distance (NED) is also introduced to precisely assess the difference between the converted netlists and ground truth. Based on our benchmark, Image2Net achieves 80.77% successful rate, which is 34.62%-45.19% higher than previous works. Specifically, the proposed work shows 0.116 averaged NED, which is 62.1%-69.6% lower than state-of-the-arts. Our datasets and benchmark are available at https://github.com/LAD021/ci2n_datasets. - oai:arXiv.org:2508.13157v2 - cs.AR - cs.AI - cs.CV - eess.IV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Haohang Xu, Chengjie Liu, Qihang Wang, Wenhao Huang, Yongjian Xu, Weiyu Chen, Anlan Peng, Zhijun Li, Bo Li, Lei Qi, Jun Yang, Yuan Du, Li Du - - - Incremental Generalized Hybrid A* - https://arxiv.org/abs/2508.13392 - arXiv:2508.13392v2 Announce Type: replace -Abstract: We address the problem of efficiently organizing search over very large trees, which arises in many applications ranging from autonomous driving to aerial vehicles. Here, we are motivated by off-road autonomy, where real-time planning is essential. Classical approaches use graphs of motion primitives and exploit dominance to mitigate the curse of dimensionality and prune expansions efficiently. However, for complex dynamics, repeatedly solving two-point boundary-value problems makes graph construction too slow for fast kinodynamic planning. Hybrid A* (HA*) addressed this challenge by searching over a tree of motion primitives and introducing approximate pruning using a grid-based dominance check. However, choosing the grid resolution is difficult: too coarse risks failure, while too fine leads to excessive expansions and slow planning. We propose Incremental Generalized Hybrid A* (IGHA*), an anytime tree-search framework that dynamically organizes vertex expansions without rigid pruning. IGHA* provably matches or outperforms HA*. For both on-road kinematic and off-road kinodynamic planning queries for a car-like robot, variants of IGHA* use 6x fewer expansions to the best solution compared to an optimized version of HA* (HA*M, an internal baseline). In simulated off- road experiments in a high-fidelity simulator, IGHA* outper- forms HA*M when both are used in the loop with a model predictive controller. We demonstrate real-time performance both in simulation and on a small-scale off-road vehicle, enabling fast, robust planning under complex dynamics. Website: https: //personalrobotics.github.io/IGHAStar/ - oai:arXiv.org:2508.13392v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sidharth Talia, Oren Salzman, Siddhartha Srinivasa - - - FLAIR: Frequency- and Locality-Aware Implicit Neural Representations - https://arxiv.org/abs/2508.13544 - arXiv:2508.13544v4 Announce Type: replace -Abstract: Implicit Neural Representations (INRs) leverage neural networks to map coordinates to corresponding signals, enabling continuous and compact representations. This paradigm has driven significant advances in various vision tasks. However, existing INRs lack frequency selectivity and spatial localization, leading to an over-reliance on redundant signal components. Consequently, they exhibit spectral bias, tending to learn low-frequency components early while struggling to capture fine high-frequency details. To address these issues, we propose FLAIR (Frequency- and Locality-Aware Implicit Neural Representations), which incorporates two key innovations. The first is Band-Localized Activation (BLA), a novel activation designed for joint frequency selection and spatial localization under the constraints of the time-frequency uncertainty principle (TFUP). Through structured frequency control and spatially localized responses, BLA effectively mitigates spectral bias and enhances training stability. The second is Wavelet-Energy-Guided Encoding (WEGE), which leverages the discrete wavelet transform to compute energy scores and explicitly guide frequency information to the network, enabling precise frequency selection and adaptive band control. Our method consistently outperforms existing INRs in 2D image representation, as well as 3D shape reconstruction and novel view synthesis. - oai:arXiv.org:2508.13544v4 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sukhun Ko, Seokhyun Yoon, Dahyeon Kye, Kyle Min, Chanho Eom, Jihyong Oh - - - Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy Module - https://arxiv.org/abs/2508.13962 - arXiv:2508.13962v2 Announce Type: replace -Abstract: As Artificial Intelligence (AI) becomes increasingly integrated into daily life, there is a growing need to equip the next generation with the ability to apply, interact with, evaluate, and collaborate with AI systems responsibly. Prior research highlights the urgent demand from K-12 educators to teach students the ethical and effective use of AI for learning. To address this need, we designed an Large-Language Model (LLM)-based module to teach prompting literacy. This includes scenario-based deliberate practice activities with direct interaction with intelligent LLM agents, aiming to foster secondary school students' responsible engagement with AI chatbots. We conducted two iterations of classroom deployment in 11 authentic secondary education classrooms, and evaluated 1) AI-based auto-grader's capability; 2) students' prompting performance and confidence changes towards using AI for learning; and 3) the quality of learning and assessment materials. Results indicated that the AI-based auto-grader could grade student-written prompts with satisfactory quality. In addition, the instructional materials supported students in improving their prompting skills through practice and led to positive shifts in their perceptions of using AI for learning. Furthermore, data from Study 1 informed assessment revisions in Study 2. Analyses of item difficulty and discrimination in Study 2 showed that True/False and open-ended questions could measure prompting literacy more effectively than multiple-choice questions for our target learners. These promising outcomes highlight the potential for broader deployment and highlight the need for broader studies to assess learning effectiveness and assessment design. - oai:arXiv.org:2508.13962v2 - cs.HC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ruiwei Xiao, Xinying Hou, Ying-Jui Tseng, Hsuan Nieu, Guanze Liao, John Stamper, Kenneth R. Koedinger - - - Jointly Computation- and Communication-Efficient Distributed Learning - https://arxiv.org/abs/2508.15509 - arXiv:2508.15509v2 Announce Type: replace -Abstract: We address distributed learning problems over undirected networks. Specifically, we focus on designing a novel ADMM-based algorithm that is jointly computation- and communication-efficient. Our design guarantees computational efficiency by allowing agents to use stochastic gradients during local training. Moreover, communication efficiency is achieved as follows: i) the agents perform multiple training epochs between communication rounds, and ii) compressed transmissions are used. We prove exact linear convergence of the algorithm in the strongly convex setting. We corroborate our theoretical results by numerical comparisons with state of the art techniques on a classification task. - oai:arXiv.org:2508.15509v2 - cs.LG - cs.SY - eess.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaoxing Ren, Nicola Bastianello, Karl H. Johansson, Thomas Parisini - - - Conditionally adaptive augmented Lagrangian method for physics-informed learning of forward and inverse problems - https://arxiv.org/abs/2508.15695 - arXiv:2508.15695v2 Announce Type: replace -Abstract: We present several key advances to the Physics and Equality Constrained Artificial Neural Networks (PECANN) framework, substantially improving its capacity to solve challenging partial differential equations (PDEs). Our enhancements broaden the framework's applicability and improve efficiency. First, we generalize the Augmented Lagrangian Method (ALM) to support multiple, independent penalty parameters for enforcing heterogeneous constraints. Second, we introduce a constraint aggregation technique to address inefficiencies associated with point-wise enforcement. Third, we incorporate a single Fourier feature mapping to capture highly oscillatory solutions with multi-scale features, where alternative methods often require multiple mappings or costlier architectures. Fourth, a novel time-windowing strategy enables seamless long-time evolution without relying on discrete time models. Fifth, and critically, we propose a conditionally adaptive penalty update (CAPU) strategy for ALM that accelerates the growth of Lagrange multipliers for constraints with larger violations, while enabling coordinated updates of multiple penalty parameters. CAPU accelerates the growth of Lagrange multipliers for selectively challenging constraints, enhancing constraint enforcement during training. We demonstrate the effectiveness of PECANN-CAPU across diverse problems, including the transonic rarefaction problem, reversible scalar advection by a vortex, high-wavenumber Helmholtz and Poisson's equations, and inverse heat source identification. The framework achieves competitive accuracy across all cases when compared with established methods and recent approaches based on Kolmogorov-Arnold networks. Collectively, these advances improve the robustness, computational efficiency, and applicability of PECANN to demanding problems in scientific computing. - oai:arXiv.org:2508.15695v2 - cs.LG - math.OC - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Qifeng Hu, Shamsulhaq Basir, Inanc Senocak - - - Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings - https://arxiv.org/abs/2508.16210 - arXiv:2508.16210v2 Announce Type: replace -Abstract: Cross-domain recommender (CDR) systems aim to transfer knowledge from data-rich domains to data-sparse ones, alleviating sparsity and cold-start issues present in conventional single-domain recommenders. However, many CDR approaches rely on overlapping users or items to establish explicit cross-domain connections, which is unrealistic in practice. Moreover, most methods represent user preferences as fixed discrete vectors, limiting their ability to capture the fine-grained and multi-aspect nature of user interests. To address these limitations, we propose DUP-OT (Distributional User Preferences with Optimal Transport), a novel framework for non-overlapping CDR. DUP-OT consists of three stages: (1) a shared preprocessing module that extracts review-based embeddings using a unified sentence encoder and autoencoder; (2) a user preference modeling module that represents each user's interests as a Gaussian Mixture Model (GMM) over item embeddings; and (3) an optimal-transport-based alignment module that matches Gaussian components across domains, enabling effective preference transfer for target-domain rating prediction. Experiments on Amazon Review datasets demonstrate that DUP-OT mitigates domain discrepancy and significantly outperforms state-of-the-art baselines under strictly non-overlapping training settings, with user correspondence revealed only for inference-time evaluation. - oai:arXiv.org:2508.16210v2 - cs.IR - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ziyin Xiao, Toyotaro Suzumura - - - CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance - https://arxiv.org/abs/2508.16644 - arXiv:2508.16644v2 Announce Type: replace -Abstract: Diffusion models have shown remarkable progress in photorealistic image synthesis, yet they remain unreliable for generating scenes with a precise number of object instances, particularly in complex and high-density settings. We present CountLoop, a training-free framework that provides diffusion models with accurate instance control through iterative structured feedback. The approach alternates between image generation and multimodal agent evaluation, where a language-guided planner and critic assess object counts, spatial arrangements, and attribute consistency. This feedback is then used to refine layouts and guide subsequent generations. To further improve separation between objects, especially in occluded scenes, we introduce instance-driven attention masking and compositional generation techniques. Experiments on COCO Count, T2I CompBench, and two new high-instance benchmarks show that CountLoop achieves counting accuracy of up to 98% while maintaining spatial fidelity and visual quality, outperforming layout-based and gradient-guided baselines with a score of 0.97. - oai:arXiv.org:2508.16644v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Anindya Mondal, Ayan Banerjee, Sauradip Nag, Josep Llad\'os, Xiatian Zhu, Anjan Dutta - - - H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference - https://arxiv.org/abs/2508.16653 - arXiv:2508.16653v2 Announce Type: replace -Abstract: Large language models (LLMs) have demonstrated remarkable proficiency in a wide range of natural language processing applications. However, the high energy and latency overhead induced by the KV cache limits the edge deployment, especially for long contexts. Emerging hybrid bonding (HB) technology has been proposed as a promising alternative to conventional near-memory processing (NMP) architectures, offering improved bandwidth efficiency and lower power consumption while exhibiting characteristics of distributed memory. In this paper, we propose H2EAL, a hybrid bonding-based accelerator with sparse attention algorithm-hardware co-design for efficient LLM inference at the edge. At the algorithm level, we propose a hybrid sparse attention scheme with static and dynamic sparsity for different heads to fully leverage the sparsity with high accuracy. At the hardware level, we co-design the hardware to support hybrid sparse attention and propose memory-compute co-placement to address the distributed memory bottleneck. Since different attention heads exhibit different sparse patterns and the attention structure often mismatches the HB architecture, we further develop a load-balancing scheduler with parallel tiled attention to address workload imbalance and optimize the mapping strategy. Extensive experiments demonstrate H2EAL achieves 5.20~48.21x speedup and 6.22~73.48x energy efficiency improvement over baseline HB implementation, with a negligible average accuracy drop of 0.87% on multiple benchmarks. - oai:arXiv.org:2508.16653v2 - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zizhuo Fu, Xiaotian Guo, Wenxuan Zeng, Shuzhang Zhong, Yadong Zhang, Peiyu Chen, Runsheng Wang, Le Ye, Meng Li - - - ONG: Orthogonal Natural Gradient Descent - https://arxiv.org/abs/2508.17169 - arXiv:2508.17169v3 Announce Type: replace -Abstract: Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal convergence in learning tasks. To address this, we propose incorporating the natural gradient into OGD and present \textbf{ONG (Orthogonal Natural Gradient Descent)}. ONG preconditions each new task-specific gradient with an efficient EKFAC approximation of the inverse Fisher information matrix, yielding updates that follow the steepest descent direction under a Riemannian metric. To preserve performance on previously learned tasks, ONG projects these natural gradients onto the orthogonal complement of prior tasks' natural gradients. We provide an initial theoretical justification for this procedure, introduce the Orthogonal Natural Gradient Descent (ONG) algorithm, and present preliminary results on the Permuted and Rotated MNIST benchmarks. Our preliminary results, however, indicate that a naive combination of natural gradients and orthogonal projections has potential issues. This finding has motivated continued future work focused on robustly reconciling these geometric perspectives to develop a continual learning method, establishing a more rigorous theoretical foundation with formal convergence guarantees, and extending empirical validation to large-scale continual learning benchmarks. - oai:arXiv.org:2508.17169v3 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yajat Yadav, Patrick Mendoza, Jathin Korrapati - - - Variational Shape Inference for Grasp Diffusion on SE(3) - https://arxiv.org/abs/2508.17482 - arXiv:2508.17482v2 Announce Type: replace -Abstract: Grasp synthesis is a fundamental task in robotic manipulation which usually has multiple feasible solutions. Multimodal grasp synthesis seeks to generate diverse sets of stable grasps conditioned on object geometry, making the robust learning of geometric features crucial for success. To address this challenge, we propose a framework for learning multimodal grasp distributions that leverages variational shape inference to enhance robustness against shape noise and measurement sparsity. Our approach first trains a variational autoencoder for shape inference using implicit neural representations, and then uses these learned geometric features to guide a diffusion model for grasp synthesis on the SE(3) manifold. Additionally, we introduce a test-time grasp optimization technique that can be integrated as a plugin to further enhance grasping performance. Experimental results demonstrate that our shape inference for grasp synthesis formulation outperforms state-of-the-art multimodal grasp synthesis methods on the ACRONYM dataset by 6.3%, while demonstrating robustness to deterioration in point cloud density compared to other approaches. Furthermore, our trained model achieves zero-shot transfer to real-world manipulation of household objects, generating 34% more successful grasps than baselines despite measurement noise and point cloud calibration errors. - oai:arXiv.org:2508.17482v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - S. Talha Bukhari, Kaivalya Agrawal, Zachary Kingston, Aniket Bera - - - A new class of regularized preconditioners for double saddle-point problems - https://arxiv.org/abs/2508.19469 - arXiv:2508.19469v2 Announce Type: replace -Abstract: The block structure of double saddle-point problems has prompted extensive research into efficient preconditioners. This paper introduces a novel class of three-by-three block preconditioners tailored for such systems from the time-dependent Maxwell equations or liquid crystal director modeling. The main motivation of this work is to highlight the limitations of recent preconditioners under high Reynolds numbers, as the original studies did not explore this scenario, and to demonstrate that our preconditioner outperforms the existing ones in such regimes. We thoroughly analyze the convergence and spectral properties of the proposed preocnditioner. We illustrate the efficiency of the proposed preconditioners, and verify the theoretical bounds. - oai:arXiv.org:2508.19469v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/publicdomain/zero/1.0/ - Achraf Badahmane - - - Commitment Gap via Correlation Gap - https://arxiv.org/abs/2508.20246 - arXiv:2508.20246v2 Announce Type: replace -Abstract: Selection problems with costly information, dating back to Weitzman's Pandora's Box problem, have received much attention recently. We study the general model of Costly Information Combinatorial Selection (CICS) that was recently introduced by Chawla et al. [2024] and Bowers et al. [2025]. In this problem, a decision maker needs to select a feasible subset of stochastic variables, and can only learn information about their values through a series of costly steps, modeled by a Markov decision process. The algorithmic objective is to maximize the total value of the selection minus the cost of information acquisition. However, determining the optimal algorithm is known to be a computationally challenging problem. - To address this challenge, previous approaches have turned to approximation algorithms by considering a restricted class of committing policies that simplify the decision-making aspects of the problem and allow for efficient optimization. This motivates the question of bounding the commitment gap, measuring the worst case ratio in the performance of the optimal committing policy and the overall optimal. In this work, we obtain improved bounds on the commitment gap of CICS through a reduction to a simpler problem of Bayesian Combinatorial Selection where information is free. By establishing a close relationship between these problems, we are able to relate the commitment gap of CICS to ex ante free-order prophet inequalities. As a consequence, we obtain improved efficient approximations for arbitrary instances of the CICS under various feasibility constraints. - oai:arXiv.org:2508.20246v2 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shuchi Chawla, Dimitris Christou, Trung Dang - - - MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning - https://arxiv.org/abs/2508.20549 - arXiv:2508.20549v2 Announce Type: replace -Abstract: The application of Vision-Language Models (VLMs) in medicine is critically hampered by the scarcity of high-quality, expert-annotated data. Supervised Fine-Tuning (SFT) on existing datasets often leads to poor generalization on unseen modalities and tasks, while Reinforcement Learning (RL), a promising alternative, is stymied by the lack of reliable reward signals in this data-scarce domain. To break this impasse, we introduce Generative Reward Learning for Medical Reasoning (MedGR$^2$), a novel framework that creates a self-improving virtuous cycle. MedGR$^2$ co-develops a data generator and a reward model, enabling the automated, continuous creation of high-quality, multi-modal medical data that serves as both a superior training source for SFT and RL. Our experiments demonstrate that SFT with MedGR$^2$-produced data already surpasses baselines trained on large-scale, human-curated datasets. Crucially, when leveraging this data for RL via Group Relative Policy Optimization (GRPO), our model achieves state-of-the-art cross-modality and cross-task generalization, significantly outperforming specialized RL-based methods. Furthermore, our compact model, empowered by MedGR$^2$, achieves performance competitive with foundation models possessing over 10 times more parameters. MedGR$^2$ presents a new paradigm for data-efficient learning in high-stakes domains, transforming the problem from data scarcity to data generation and unlocking the full potential of RL for building truly generalizable medical AI. - oai:arXiv.org:2508.20549v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - AAAI'2026 Main Technical Track - Weihai Zhi, Jiayan Guo, Shangyang Li - - - Efficient Forkless Blockchain Databases - https://arxiv.org/abs/2508.20686 - arXiv:2508.20686v3 Announce Type: replace -Abstract: Operating nodes in an L1 blockchain remains costly despite recent advances in blockchain technology. One of the most resource-intensive components of a node is the blockchain database, also known as StateDB, that manages balances, nonce, code, and the persistent storage of accounts/smart contracts. Although the blockchain industry has transitioned from forking to forkless chains due to improved consensus protocols, forkless blockchains still rely on legacy forking databases that are suboptimal for their purposes. In this paper, we propose a forkless blockchain database, showing a 100x improvement in storage and a 10x improvement in throughput compared to the geth-based Fantom Blockchain client. - oai:arXiv.org:2508.20686v3 - cs.DB - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1109/ACCESS.2025.3639677 - Herbert Jordan, Kamil Jezek, Pavle Subotic, Bernhard Scholz - - - Automated Test Validators for Flaky Cyber-Physical System Simulators: Approach and Evaluation - https://arxiv.org/abs/2508.20902 - arXiv:2508.20902v2 Announce Type: replace -Abstract: Simulation-based testing of cyber-physical systems (CPS) is costly due to the time-consuming execution of CPS simulators. In addition, CPS simulators may be flaky, leading to inconsistent test outcomes and requiring repeated test re-execution for reliable test verdicts. Many test inputs within the input space of CPS may not effectively exercise the behaviour of the system under test (SUT) -- for instance, those that violate system preconditions, exceed operational design domain (ODD) limits, or represent inherently safe scenarios. In this article, we propose to use test validators to filter out such test inputs before execution. We describe two methods for generating test validators: one using genetic programming (GP) that employs well-known spectrum-based fault localization (SBFL) ranking formulas, namely Ochiai, Tarantula, and Naish, as fitness functions; and the other using decision trees (DT) and decision rules (DR). We evaluate our test validators through case studies in the domains of aerospace, networking and autonomous driving. We show that test validators generated using GP with Ochiai are significantly more accurate than those generated using GP with Tarantula and Naish or using DT or DR. Moreover, this accuracy advantage remains even when accounting for the flakiness of the simulator. We further show that our test validators generated by GP with Ochiai are robust against flakiness with only 4% average variation in their accuracy results across four different network and autonomous-driving systems with flaky behaviours. Finally, we show that, on average, 88.7% of the assertions inferred by our approach align or overlap with requirements precondition violations, ODD-limit violations, and nominal safe conditions extracted from technical standards and empirical results in the literature. - oai:arXiv.org:2508.20902v2 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Baharin A. Jodat, Khouloud Gaaloul, Mehrdad Sabetzadeh, Shiva Nejati - - - MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning - https://arxiv.org/abs/2508.21451 - arXiv:2508.21451v3 Announce Type: replace -Abstract: Systems such as video chatbots and navigation robots often depend on streaming image captioning to interpret visual inputs. Existing approaches typically employ large multimodal language models (MLLMs) for this purpose, but their substantial computational cost hinders practical application. This limitation motivates our development of a lightweight captioning model. Our investigation begins by replacing the large-scale language component in MLLMs with a compact 125M-parameter model. Surprisingly, this compact model, despite a 93x reduction in size, achieves comparable performance to MLLMs, suggesting that factual image captioning does not significantly require the complex reasoning abilities of LLMs. Despite this promising result, our lightweight model still lacks reliability. To address this, we draw inspiration from the human visual process: perceiving a global and coarse understanding of the scene before attending to finer details. Accordingly, we propose a multimodal self-refinement framework that guides the model to utilize features from salient regions, identified by referencing the previous coarse caption, and to produce a refined description. Experimental results demonstrate the superiority of our model in both single-sentence and detailed captioning, extending even to long-range video QA tasks. - oai:arXiv.org:2508.21451v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Junha Song, Yongsik Jo, So Yeon Min, Quanting Xie, Taehwan Kim, Yonatan Bisk, Jaegul Choo - - - RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning - https://arxiv.org/abs/2509.00974 - arXiv:2509.00974v5 Announce Type: replace -Abstract: Medical question answering requires advanced reasoning that integrates domain knowledge with logical inference. However, existing large language models (LLMs) often generate reasoning chains that lack factual accuracy and clinical reliability. We propose Ranked Preference Reinforcement Optimization (RPRO), a novel framework that combines reinforcement learning with preference-driven reasoning refinement to enhance clinical chain-of-thought (CoT) performance. RPRO distinguishes itself from prior approaches by employing task-adaptive reasoning templates and a probabilistic evaluation mechanism that aligns model outputs with established clinical workflows, while automatically identifying and correcting low-quality reasoning chains. Unlike traditional pairwise preference methods, RPRO introduces a groupwise ranking optimization based on the Bradley--Terry model and incorporates KL-divergence regularization for stable training. Experiments on PubMedQA, MedQA-USMLE, and a real-world clinical dataset from Far Eastern Memorial Hospital (FEMH) demonstrate consistent improvements over strong baselines. Remarkably, our 2B-parameter model outperforms much larger 7B--20B models, including medical-specialized variants. These findings demonstrate that combining preference optimization with quality-driven refinement provides a scalable and clinically grounded approach to building more reliable medical LLMs. - oai:arXiv.org:2509.00974v5 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Chia-Hsuan Hsu, Jun-En Ding, Hsin-Ling Hsu, Chih-Ho Hsu, Li-Hung Yao, Chun-Chieh Liao, Feng Liu, Fang-Ming Hung - - - Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First - https://arxiv.org/abs/2509.00997 - arXiv:2509.00997v2 Announce Type: replace -Abstract: Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of exploration and solution formulation for the given task, one we call agentic speculation. The sheer volume and inefficiencies of agentic speculation can pose challenges for present-day data systems. We argue that data systems need to adapt to more natively support agentic workloads. We take advantage of the characteristics of agentic speculation that we identify, i.e., scale, heterogeneity, redundancy, and steerability - to outline a number of new research opportunities for a new agent-first data systems architecture, ranging from new query interfaces, to new query processing techniques, to new agentic memory stores. - oai:arXiv.org:2509.00997v2 - cs.AI - cs.DB - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito, Shuo Yuan, Ion Stoica, Matei Zaharia, Alvin Cheung, Natacha Crooks, Joseph E. Gonzalez, Aditya G. Parameswaran - - - Computation of Feasible Assume-Guarantee Contracts: A Resilience-based Approach - https://arxiv.org/abs/2509.01832 - arXiv:2509.01832v2 Announce Type: replace -Abstract: We propose a resilience-based framework for computing feasible assume-guarantee contracts that ensure the satisfaction of temporal specifications in interconnected discrete-time systems. Interconnection effects are modeled as structured disturbances. We use a resilience metric, the maximum disturbance under which local specifications hold, to refine assumptions and guarantees across subsystems iteratively. We first demonstrate correctness and monotone refinement of guarantees for two subsystems. Then, we extend our approach to general networks of L subsystems using weighted combinations of interconnection effects. We instantiate the framework on linear systems by meeting finite-horizon safety, exact-time reachability, and finite-horizon reachability specifications, and on nonlinear systems by fulfilling general finite-horizon specifications. Our approach is demonstrated through numerical linear examples and a nonlinear DC microgrid case study, showcasing the impact of our framework on verifying temporal logic specifications with compositional reasoning. - oai:arXiv.org:2509.01832v2 - eess.SY - cs.LO - cs.SY - math.DS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Negar Monir, Youssef Ait Si, Ratnangshu Das, Pushpak Jagtap, Adnane Saoud, Sadegh Soudjani - - - HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices - https://arxiv.org/abs/2509.01839 - arXiv:2509.01839v5 Announce Type: replace -Abstract: Currently, prominent Transformer architectures applied on graphs and meshes for shape analysis tasks employ traditional attention layers that heavily utilize spectral features requiring costly eigenvalue decomposition-based methods. To encode the mesh structure, these methods derive positional embeddings, that heavily rely on eigenvalue decomposition based operations, e.g. on the Laplacian matrix, or on heat-kernel signatures, which are then concatenated to the input features. This paper proposes a novel approach inspired by the explicit construction of the Hodge Laplacian operator in Discrete Exterior Calculus as a product of discrete Hodge operators and exterior derivatives, i.e. $(L := \star_0^{-1} d_0^T \star_1 d_0)$. We adjust the Transformer architecture in a novel deep learning layer that utilizes the multi-head attention mechanism to approximate Hodge matrices $\star_0$, $\star_1$ and $\star_2$ and learn families of discrete operators $L$ that act on mesh vertices, edges and faces. Our approach results in a computationally-efficient architecture that achieves comparable performance in mesh segmentation and classification tasks, through a direct learning framework, while eliminating the need for costly eigenvalue decomposition operations or complex preprocessing operations. - oai:arXiv.org:2509.01839v5 - cs.GR - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Akis Nousias, Stavros Nousias - - - Hyperbolic Large Language Models - https://arxiv.org/abs/2509.05757 - arXiv:2509.05757v2 Announce Type: replace -Abstract: Large language models (LLMs) have achieved remarkable success and demonstrated superior performance across various tasks, including natural language processing (NLP), weather forecasting, biological protein folding, text generation, and solving mathematical problems. However, many real-world data exhibit highly non-Euclidean latent hierarchical anatomy, such as protein networks, transportation networks, financial networks, brain networks, and linguistic structures or syntactic trees in natural languages. Effectively learning intrinsic semantic entailment and hierarchical relationships from these raw, unstructured input data using LLMs remains an underexplored area. Due to its effectiveness in modeling tree-like hierarchical structures, hyperbolic geometry -- a non-Euclidean space -- has rapidly gained popularity as an expressive latent representation space for complex data modeling across domains such as graphs, images, languages, and multi-modal data. Here, we provide a comprehensive and contextual exposition of recent advancements in LLMs that leverage hyperbolic geometry as a representation space to enhance semantic representation learning and multi-scale reasoning. Specifically, the paper presents a taxonomy of the principal techniques of Hyperbolic LLMs (HypLLMs) in terms of four main categories: (1) hyperbolic LLMs through exp/log maps; (2) hyperbolic fine-tuned models; (3) fully hyperbolic LLMs, and (4) hyperbolic state-space models. We also explore crucial potential applications and outline future research directions. A repository of key papers, models, datasets, and code implementations is available at https://github.com/sarangp2402/Hyperbolic-LLM-Models. - oai:arXiv.org:2509.05757v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sarang Patil, Zeyong Zhang, Yiran Huang, Tengfei Ma, Mengjia Xu - - - Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching - https://arxiv.org/abs/2509.05952 - arXiv:2509.05952v4 Announce Type: replace -Abstract: Reinforcement Learning (RL) has recently emerged as a powerful technique for improving image and video generation in Diffusion and Flow Matching models, specifically for enhancing output quality and alignment with prompts. A critical step for applying online RL methods on Flow Matching is the introduction of stochasticity into the deterministic framework, commonly realized by Stochastic Differential Equation (SDE). Our investigation reveals a significant drawback to this approach: SDE-based sampling introduces pronounced noise artifacts in the generated images, which we found to be detrimental to the reward learning process. A rigorous theoretical analysis traces the origin of this noise to an excess of stochasticity injected during inference. To address this, we draw inspiration from Denoising Diffusion Implicit Models (DDIM) to reformulate the sampling process. Our proposed method, Coefficients-Preserving Sampling (CPS), eliminates these noise artifacts. This leads to more accurate reward modeling, ultimately enabling faster and more stable convergence for reinforcement learning-based optimizers like Flow-GRPO and Dance-GRPO. Code will be released at https://github.com/IamCreateAI/FlowCPS - oai:arXiv.org:2509.05952v4 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Feng Wang, Zihao Yu - - - When Code Crosses Borders: A Security-Centric Study of LLM-based Code Translation - https://arxiv.org/abs/2509.06504 - arXiv:2509.06504v2 Announce Type: replace -Abstract: Code translation is crucial for cross-language codebase migration, and large language models (LLMs) have emerged as a promising technique to automate this process. However, the security implications of using LLMs for code translation remain largely unexplored, as existing evaluations primarily focus on syntactic and functional correctness. To bridge this gap, we conduct a security-centric empirical study to investigate the risks of vulnerabilities being introduced or preserved during LLM-based translation. Our study involves a rigorous evaluation of five state-of-the-art LLMs on a curated dataset of 720 security-related code samples across four programming languages (Java, PHP, C, C++) and nine Common Weakness Enumeration (CWE) categories. The results reveal significant security degradation, with 28.6\% to 45\% of translations introducing new vulnerabilities. Web-related flaws, particularly in input validation, proved most challenging for LLMs. Furthermore, we identify and categorize the root causes of these vulnerable translations into a taxonomy of five major error types. Based on our findings, we develop and evaluate a Retrieval-Augmented Generation (RAG)-based mitigation strategy, which successfully reduces the vulnerability introduction rate by 32.8\%. Our study provides the first large-scale evidence of serious security risks in LLM-based code translation and demonstrates the potential of knowledge-enhanced prompting to mitigate them. - oai:arXiv.org:2509.06504v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hailong Chang, Guozhu Meng, Shuhui Xiao, Kai Chen, Kun Sun, Yilin Li - - - Aurora: Architecting Argonne's First Exascale Supercomputer for Accelerated Scientific Discovery - https://arxiv.org/abs/2509.08207 - arXiv:2509.08207v2 Announce Type: replace -Abstract: Aurora is Argonne National Laboratory's pioneering Exascale supercomputer, designed to accelerate scientific discovery with cutting-edge architectural innovations. Key new technologies include the Intel(TM) Xeon(TM) Data Center GPU Max Series (code-named Sapphire Rapids) with support for High Bandwidth Memory (HBM), alongside the Intel(TM) Data Center GPU Max Series (code-named Ponte Vecchio) on each compute node. Aurora also integrates the Distributed Asynchronous Object Storage (DAOS), a novel exascale storage solution, and leverages Intel's oneAPI programming environment. This paper presents an in-depth exploration of Aurora's node architecture, the HPE Slingshot interconnect, the supporting software ecosystem, and DAOS. We provide insights into standard benchmark performance and applications readiness efforts via Aurora's Early Science Program and the Exascale Computing Project. - oai:arXiv.org:2509.08207v2 - cs.DC - cs.AR - cs.CE - cs.PF - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - William E. Allcock, Benjamin S. Allen, James Anchell, Victor Anisimov, Thomas Applencourt, Abhishek Bagusetty, Ramesh Balakrishnan, Riccardo Balin, Solomon Bekele, Colleen Bertoni, Cyrus Blackworth, Renzo Bustamante, Kevin Canada, John Carrier, Christopher Chan-nui, Lance C. Cheney, Taylor Childers, Paul Coffman, Susan Coghlan, Tanima Dey, Michael D'Mello, Ashok Emani, Murali Emani, Kyle G. Felker, Sam Foreman, Olivier Franza, Longfei Gao, Marta Garc\'ia, Mar\'ia Garzar\'an, Balazs Gerofi, Yasaman Ghadar, Subrata Goswami, Neha Gupta, Kevin Harms, V\"ain\"o Hatanp\"a\"a, Brian Holland, Carissa Holohan, Brian Homerding, Khalid Hossain, Xue Hu, Louise Huot, Huda Ibeid, Joseph A. Insley, Sai Jayanthi, Hong Jiang, Wei Jiang, Xiao-Yong Jin, Jeongnim Kim, Christopher Knight, Panagiotis Kourdis, Kalyan Kumaran, JaeHyuk Kwack, Janghaeng Lee, Ti Leggett, Ben Lenard, Chris Lewis, Nevin Liber, Johann Lombardi, Raymond M. Loy, Ye Luo, Bethany Lusch, Nilakantan Mahadevan, Beth Markey, Victor A. Mateevitsi, Gordon McPheeters, Ryan Milner, Jerome Mitchell, Vitali A. Morozov, Servesh Muralidharan, Tom Musta, Mrigendra Nagar, Vikram Narayana, Marieme Ngom, Anthony-Trung Nguyen, Nathan Nichols, Aditya Nishtala, James C. Osborn, Michael E. Papka, Scott Parker, Saumil S. Patel, Julia Piotrowska, Adrian C. Pope, Sucheta Raghunanda, Esteban Rangel, Paul M. Rich, Katherine M. Riley, Silvio Rizzi, Kris Rowe, Varuni Sastry, Adam Scovel, Filippo Simini, Haritha Siddabathuni Som, Patrick Steinbrecher, Rick Stevens, Xinmin Tian, Peter Upton, Thomas Uram, Archit K. Vasan, \'Alvaro V\'azquez-Mayagoitia, Kaushik Velusamy, Brice Videau, Venkatram Vishwanath, Brian Whitney, Timothy J. Williams, Michael Woodacre, Sam Zeltner, Chuanjun Zhang, Gengbin Zheng, Huihuo Zheng - - - Overcoming DNSSEC Islands of Security: A TLS and IP-Based Certificate Solution - https://arxiv.org/abs/2509.08364 - arXiv:2509.08364v2 Announce Type: replace -Abstract: The Domain Name System (DNS) serves as the backbone of the Internet, primarily translating domain names to IP addresses. Over time, various enhancements have been introduced to strengthen the integrity of DNS. Among these, DNSSEC stands out as a leading cryptographic solution. It protects against attacks (such as DNS spoofing) by establishing a chain of trust throughout the DNS nameserver hierarchy. However, DNSSEC's effectiveness is compromised when there is a break in this chain, resulting in "Islands of Security", where domains can authenticate locally but not across hierarchical levels, leading to a loss of trust and validation between them. Leading approaches to addressing these issues were centralized, with a single authority maintaining some kind of bulletin board. This approach requires significantly more infrastructure and places excessive trust in the entity responsible for managing it properly. In this paper, we propose a decentralized approach to addressing gaps in DNSSEC's chain of trust, commonly referred to as "Islands of Security". We leverage TLS and IP-based certificates to enable end-to-end authentication between hierarchical levels, eliminating the need for uniform DNSSEC deployment across every level of the DNS hierarchy. This approach enhances the overall integrity of DNSSEC, while reducing dependence on registrars for maintaining signature records to verify the child nameserver's authenticity. By offering a more flexible and efficient solution, our method strengthens DNS security and streamlines deployment across diverse environments. - oai:arXiv.org:2509.08364v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Aduma Rishith, Aditya Kulkarni, Tamal Das, Vivek Balachandran - - - Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy - https://arxiv.org/abs/2509.10691 - arXiv:2509.10691v2 Announce Type: replace -Abstract: Decentralized Federated Learning (DFL) enables collaborative model training without a central server, but it remains vulnerable to privacy leakage because shared model updates can expose sensitive information through inversion, reconstruction, and membership inference attacks. Differential Privacy (DP) provides formal safeguards, yet existing DP-enabled DFL methods operate as black-boxes that cannot track cumulative noise added across clients and rounds, forcing each participant to inject worst-case perturbations that severely degrade accuracy. We propose PrivateDFL, a new explainable and privacy-preserving framework that addresses this gap by combining a HyperDimensional Computing (HD) model with a transparent DP noise accountant tailored to decentralized learning. HD offers structured, noise-tolerant high-dimensional representations, while the accountant explicitly tracks cumulative perturbations so each client adds only the minimal incremental noise required to satisfy its (epsilon, delta) budget. This yields significantly tighter and more interpretable privacy-utility tradeoffs than prior DP-DFL approaches. Experiments on MNIST (image), ISOLET (speech), and UCI-HAR (wearable sensor) show that PrivateDFL consistently surpasses centralized DP-SGD and Renyi-DP Transformer and deep learning baselines under both IID and non-IID partitions, improving accuracy by up to 24.4% on MNIST, over 80% on ISOLET, and 14.7% on UCI-HAR, while reducing inference latency by up to 76 times and energy consumption by up to 36 times. These results position PrivateDFL as an efficient and trustworthy solution for privacy-sensitive pattern recognition applications such as healthcare, finance, human-activity monitoring, and industrial sensing. Future work will extend the accountant to adversarial participation, heterogeneous privacy budgets, and dynamic topologies. - oai:arXiv.org:2509.10691v2 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fardin Jalil Piran, Zhiling Chen, Yang Zhang, Qianyu Zhou, Jiong Tang, Farhad Imani - - - Living with Data: Exploring Physicalization Approaches to Sedentary Behavior Intervention for Older Adults in Everyday Life - https://arxiv.org/abs/2509.11059 - arXiv:2509.11059v2 Announce Type: replace -Abstract: Sedentary behavior is a critical health risk for older adults. Although digital interventions are widely available, they primarily rely on screen-based notifications that can feel clinical or cognitively demanding, and are thus often ignored over time. This paper presents a three phase Research through Design methodology to explore data physicalization approaches that ambiently represented sedentary data patterns using decor artifacts in older adults' homes. These artifacts transformed abstract data into aesthetic, evolving forms, that became part of the domestic landscape. Our research revealed how these physicalizations fostered self-reflection, family conversations, and encouraged active lifestyles. We demonstrate how qualities like aesthetic ambiguity and slow revelation can empower older adults, fostering a reflective relationship with their well-being. Ultimately, we argue that creating data physicalizations for older adults necessitates a shift from merely informing users to enabling them to live with, and through, their data. - oai:arXiv.org:2509.11059v2 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Siying Hu, Zhenhao Zhang - - - Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows - https://arxiv.org/abs/2509.11079 - arXiv:2509.11079v4 Announce Type: replace -Abstract: Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex ones, while also neglecting the efficiency-performance trade-offs across heterogeneous LLMs. To address these limitations, we propose Difficulty-Aware Agentic Orchestration (DAAO), which can dynamically generate query-specific multi-agent workflows guided by predicted query difficulty. DAAO comprises three interdependent modules: a variational autoencoder (VAE) for difficulty estimation, a modular operator allocator, and a cost- and performance-aware LLM router. A self-adjusting policy updates difficulty estimates based on workflow success, enabling simpler workflows for easy queries and more complex strategies for harder ones. Experiments on six benchmarks demonstrate that DAAO surpasses prior multi-agent systems in both accuracy and inference efficiency, validating its effectiveness for adaptive, difficulty-aware reasoning. - oai:arXiv.org:2509.11079v4 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jinwei Su, Qizhen Lan, Yinghui Xia, Lifan Sun, Weiyou Tian, Tianyu Shi, Xinyuan Song, Lewei He - - - ODoQ: Oblivious DNS-over-QUIC - https://arxiv.org/abs/2509.11123 - arXiv:2509.11123v2 Announce Type: replace -Abstract: The Domain Name System (DNS), which converts domain names to their respective IP addresses, has advanced enhancements aimed at safeguarding DNS data and users' identity from attackers. The recent privacy-focused advancements have enabled the IETF to standardize several protocols. Nevertheless, these protocols tend to focus on either strengthening user privacy (like Oblivious DNS and Oblivious DNS-over-HTTPS) or reducing resolution latency (as demonstrated by DNS-over-QUIC). Achieving both within a single protocol remains a key challenge, which we address in this paper. Our proposed protocol -- 'Oblivious DNS-over-QUIC' (ODoQ) -- leverages the benefits of the QUIC protocol and incorporates an intermediary proxy server to protect the client's identity from exposure to the recursive resolver. - oai:arXiv.org:2509.11123v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Aditya Kulkarni, Tamal Das, Vivek Balachandran - - - Scaling to Multimodal and Multichannel Heart Sound Classification with Synthetic and Augmented Biosignals - https://arxiv.org/abs/2509.11606 - arXiv:2509.11606v3 Announce Type: replace -Abstract: Cardiovascular diseases (CVDs) are the leading cause of death worldwide, accounting for approximately 17.9 million deaths each year. Early detection is critical, creating a demand for accurate and inexpensive pre-screening methods. Deep learning has recently been applied to classify abnormal heart sounds indicative of CVDs using synchronised phonocardiogram (PCG) and electrocardiogram (ECG) signals, as well as multichannel PCG (mPCG). However, state-of-the-art architectures remain underutilised due to the limited availability of synchronised and multichannel datasets. Augmented datasets and pre-trained models provide a pathway to overcome these limitations, enabling transformer-based architectures to be trained effectively. This work combines traditional signal processing with denoising diffusion models, WaveGrad and DiffWave, to create an augmented dataset to fine-tune a Wav2Vec 2.0-based classifier on multimodal and multichannel heart sound datasets. The approach achieves state-of-the-art performance. On the Computing in Cardiology (CinC) 2016 dataset of single channel PCG, accuracy, unweighted average recall (UAR), sensitivity, specificity and Matthew's correlation coefficient (MCC) reach 92.48%, 93.05%, 93.63%, 92.48%, 94.93% and 0.8283, respectively. Using the synchronised PCG and ECG signals of the training-a dataset from CinC, 93.14%, 92.21%, 94.35%, 90.10%, 95.12% and 0.8380 are achieved for accuracy, UAR, sensitivity, specificity and MCC, respectively. Using a wearable vest dataset consisting of mPCG data, the model achieves 77.13% accuracy, 74.25% UAR, 86.47% sensitivity, 62.04% specificity, and 0.5082 MCC. These results demonstrate the effectiveness of transformer-based models for CVD detection when supported by augmented datasets, highlighting their potential to advance multimodal and multichannel heart sound classification. - oai:arXiv.org:2509.11606v3 - cs.SD - cs.LG - eess.SP - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Milan Marocchi, Matthew Fynn, Kayapanda Mandana, Yue Rong - - - U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCT - https://arxiv.org/abs/2509.12069 - arXiv:2509.12069v3 Announce Type: replace -Abstract: Cone-Beam Computed Tomography (CBCT) is a widely used 3D imaging technique in dentistry, providing volumetric information about the anatomical structures of jaws and teeth. Accurate segmentation of these anatomies is critical for clinical applications such as diagnosis and surgical planning, but remains time-consuming and challenging. In this paper, we present U-Mamba2, a new neural network architecture designed for multi-anatomy CBCT segmentation in the context of the ToothFairy3 challenge. U-Mamba2 integrates the Mamba2 state space models into the U-Net architecture, enforcing stronger structural constraints for higher efficiency without compromising performance. In addition, we integrate interactive click prompts with cross-attention blocks, pre-train U-Mamba2 using self-supervised learning, and incorporate dental domain knowledge into the model design to address key challenges of dental anatomy segmentation in CBCT. Extensive experiments, including independent tests, demonstrate that U-Mamba2 is both effective and efficient, securing first place in both tasks of the Toothfairy3 challenge. In Task 1, U-Mamba2 achieved a mean Dice of 0.84, HD95 of 38.17 with the held-out test data, with an average inference time of 40.58s. In Task 2, U-Mamba2 achieved the mean Dice of 0.87 and HD95 of 2.15 with the held-out test data. The code is publicly available at https://github.com/zhiqin1998/UMamba2. - oai:arXiv.org:2509.12069v3 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Zhi Qin Tan, Xiatian Zhu, Owen Addison, Yunpeng Li - - - Interaction Context Often Increases Sycophancy in LLMs - https://arxiv.org/abs/2509.12517 - arXiv:2509.12517v2 Announce Type: replace -Abstract: We investigate how the presence and type of interaction context shapes sycophancy in LLMs. Although real-world interactions allow models to mirror a user's values, preferences, and self-image, prior work often studies sycophancy in zero-shot settings devoid of context. Using two weeks of interaction context from 38 users, we evaluate two forms of sycophancy: (1) agreement sycophancy -- the tendency of models to produce overly affirmative responses, and (2) perspective sycophancy -- the extent to which models reflect a user's viewpoint. Agreement sycophancy tends to increase with the presence of user context, though model behavior varies based on the context type. User memory profiles are associated with the largest increases in agreement sycophancy (e.g. 45% for Gemini 2.5 Pro), and some models become more sycophantic even with non-user synthetic contexts (e.g. 15% for Llama 4 Scout). Perspective sycophancy increases only when models can accurately infer user viewpoints from interaction context. Overall, context shapes sycophancy in heterogeneous ways, underscoring the need for evaluations grounded in real-world interactions and raising questions for system design around extended conversations. - oai:arXiv.org:2509.12517v2 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shomik Jain, Charlotte Park, Matheus Mesquita Viana, Ashia Wilson, Dana Calacci - - - xRWA: A Cross-Chain Framework for Interoperability of Real-World Assets - https://arxiv.org/abs/2509.12957 - arXiv:2509.12957v3 Announce Type: replace -Abstract: Real-World Assets (RWAs) have recently attracted increasing attention as a means of bridging traditional financial instruments with decentralized infrastructures. By representing assets such as bonds, commodities, and real estate on blockchains, RWAs can enhance liquidity, broaden accessibility, and extend the scope of decentralized finance. Industry forecasts further suggest rapid growth of tokenized RWAs in the coming years, underscoring their potential role in the evolution of digital financial markets. However, when deployed across multiple blockchains, RWAs face challenges such as repeated authentication on different chains and inefficiency caused by multi-step settlement protocols. To address these issues, we present a cross-chain framework for RWAs that emphasizes identity management, authentication, and interaction. The framework integrates Decentralized Identifiers and Verifiable Credentials with customized attributes to support decentralized identification, and incorporates an authentication protocol based on Simplified Payment Verification to avoid redundant verification across chains. Furthermore, we design a cross-chain channel that enables the settlement of RWAs without requiring channel closure, thereby improving operational efficiency. We implement the framework and evaluate it through simulations, which confirm its feasibility and demonstrate improvements in efficiency for RWAs in cross-chain settings. - oai:arXiv.org:2509.12957v3 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yihao Guo, Haoming Zhu, Minghui Xu, Xiuzhen Cheng, Bin Xiao - - - I, Robot? Exploring Ultra-Personalized AI-Powered AAC; an Autoethnographic Account - https://arxiv.org/abs/2509.13671 - arXiv:2509.13671v2 Announce Type: replace -Abstract: Generic AI auto-complete for message composition often fails to capture the nuance of personal identity, requiring significant editing. While harmless in low-stakes settings, for users of Augmentative and Alternative Communication (AAC) devices, who rely on such systems for everyday communication, this editing burden is particularly acute. Intuitively, the need for edits would be lower if language models were personalized to the communication of the specific user. While personalization has been shown to be technically feasible, it raises questions about how such systems affect AAC users' agency, identity, and privacy. To understand how these shifts in practice, we conduct an autoethnographic study in three phases: (1) seven months of collecting all the lead author's AAC communication data, (2) fine-tuning a model on this dataset, and (3) three months of daily use of personalized AI suggestions. Observations across these phases include that logging everyday conversations reshaped the author's sense of agency, the model training selectively amplified or muted aspects of their identity, and suggestions occasionally resurfaced private details outside their original context. Our findings show that ultra-personalized AAC reshapes communication by continually renegotiating agency, identity, and privacy between user and model. We highlight design directions for building context-adaptive, user-controlled personalization AAC technology that supports expressive, authentic communication. - oai:arXiv.org:2509.13671v2 - cs.HC - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Tobias Weinberg, Ricardo E. Gonzalez Penuela, Stephanie Valencia, Thijs Roumen - - - JaGuard: Jamming Correction of GNSS Deviation with Deep Temporal Graphs - https://arxiv.org/abs/2509.14000 - arXiv:2509.14000v2 Announce Type: replace -Abstract: Global Navigation Satellite Systems (GNSS) are increasingly exposed to intentional jamming, threatening reliability when accurate positioning and timing are most critical. We address this problem by formulating interference mitigation as a dynamic graph regression task and propose JaGuard, a receiver-centric temporal graph neural network that estimates and corrects latitude and longitude errors. At each 1 Hz epoch, the satellite-receiver scene is represented as a heterogeneous star graph with time-varying satellite attributes such as SNR, azimuth and elevation. A single-layer HeteroGCLSTM fuses one-hop spatial context with short-term temporal dynamics to produce a 2D deviation estimate. - We evaluate JaGuard on data collected from two commercial receivers under controlled conducted jamming using three jammer types (CW, 3xCW, FM) and six power levels from -45 to -70 dBm, each repeated 50 times across pre-jam, jam, and recovery phases. JaGuard outperforms strong multivariate baselines (TSMixer, uniform CNN, Seq2Point) in all conditions. Under severe jamming at -45 dBm, it achieves 3.64-7.74 cm MAE, improving to 1.59-1.90 cm for -60 to -70 dBm. On mixed-mode datasets, it attains 3.78 cm MAE on GP01 and 4.25 cm on U-blox 10. With only 10 percent of the training data, JaGuard remains ahead, reaching about 20 cm MAE compared to 36-42 cm for the baselines. - oai:arXiv.org:2509.14000v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ivana Kesi\'c, Alja\v{z} Blatnik, Carolina Fortuna, Bla\v{z} Bertalani\v{c} - - - Evidential Physics-Informed Neural Networks for Scientific Discovery - https://arxiv.org/abs/2509.14568 - arXiv:2509.14568v3 Announce Type: replace -Abstract: We present the fundamental theory and implementation guidelines underlying Evidential Physics-Informed Neural Network (E-PINN) -- a novel class of uncertainty-aware PINN. It leverages the marginal distribution loss function of evidential deep learning for estimating uncertainty of outputs, and infers unknown parameters of the PDE via a learned posterior distribution. Validating our model on two illustrative case studies -- the 1D Poisson equation with a Gaussian source and the 2D Fisher-KPP equation, we found that E-PINN generated empirical coverage probabilities that were calibrated significantly better than Bayesian PINN and Deep Ensemble methods. To demonstrate real-world applicability, we also present a brief case study on applying E-PINN to analyze clinical glucose-insulin datasets that have featured in medical research on diabetes pathophysiology. - oai:arXiv.org:2509.14568v3 - cs.LG - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hai Siong Tan, Kuancheng Wang, Rafe McBeth - - - The Multi-Query Paradox in Zeroth-Order Optimization - https://arxiv.org/abs/2509.15552 - arXiv:2509.15552v3 Announce Type: replace -Abstract: Zeroth-order (ZO) optimization provides a powerful framework for problems where explicit gradients are unavailable and have to be approximated using only queries to function value. The prevalent single-query approach is simple, but suffers from high estimation variance, motivating a multi-query paradigm to improves estimation accuracy. This, however, creates a critical trade-off: under a fixed budget of queries (i.e. cost), queries per iteration and the total number of optimization iterations are inversely proportional to one another. How to best allocate this budget is a fundamental, under-explored question. - This work systematically resolves this query allocation problem. We analyze two aggregation methods: the de facto simple averaging (ZO-Avg), and a new Projection Alignment method (ZO-Align) we derive from local surrogate minimization. By deriving convergence rates for both methods that make the dependence on the number of queries explicit across strongly convex, convex, non-convex, and stochastic settings, we uncover a stark dichotomy: For ZO-Avg, we prove that using more than one query per iteration is always query-inefficient, rendering the single-query approach optimal. On the contrary, ZO-Align generally performs better with more queries per iteration, resulting in a full-subspace estimation as the optimal approach. Thus, our work clarifies that the multi-query problem boils down to a choice not about an intermediate query size, but between two classic algorithms, a choice dictated entirely by the aggregation method used. These theoretical findings are also consistently validated by extensive experiments. - oai:arXiv.org:2509.15552v3 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wei Lin, Qingyu Song, Hong Xu - - - A PCA Based Model for Surface Reconstruction from Incomplete Point Clouds - https://arxiv.org/abs/2509.15675 - arXiv:2509.15675v2 Announce Type: replace -Abstract: Point cloud data represents a crucial category of information for mathematical modeling, and surface reconstruction from such data is an important task across various disciplines. However, during the scanning process, the collected point cloud data may fail to cover the entire surface due to factors such as high light-absorption rate and occlusions, resulting in incomplete datasets. Inferring surface structures in data-missing regions and successfully reconstructing the surface poses a challenge. In this paper, we present a Principal Component Analysis (PCA) based model for surface reconstruction from incomplete point cloud data. Initially, we employ PCA to estimate the normal information of the underlying surface from the available point cloud data. This estimated normal information serves as a regularizer in our model, guiding the reconstruction of the surface, particularly in areas with missing data. Additionally, we introduce an operator-splitting method to effectively solve the proposed model. Through systematic experimentation, we demonstrate that our model successfully infers surface structures in data-missing regions and well reconstructs the underlying surfaces, outperforming existing methodologies. - oai:arXiv.org:2509.15675v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hao Liu - - - Staying on the Manifold: Geometry-Aware Noise Injection - https://arxiv.org/abs/2509.20201 - arXiv:2509.20201v2 Announce Type: replace -Abstract: It has been shown that perturbing the input during training implicitly regularises the gradient of the learnt function, leading to smoother models and enhancing generalisation. However, previous research mostly considered the addition of ambient noise in the input space, without considering the underlying structure of the data. In this work, we propose several strategies of adding geometry-aware input noise that accounts for the lower dimensional manifold the input space inhabits. We start by projecting ambient Gaussian noise onto the tangent space of the manifold. In a second step, the noise sample is mapped on the manifold via the associated geodesic curve. We also consider Brownian motion noise, which moves in random steps along the manifold. We show that geometry-aware noise leads to improved generalisation and robustness to hyperparameter selection on highly curved manifolds, while performing at least as well as training without noise on simpler manifolds. Our proposed framework extends to data manifolds approximated by generative models and we observe similar trends on the MNIST digits dataset. - oai:arXiv.org:2509.20201v2 - cs.LG - math.DG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Albert Kj{\o}ller Jacobsen, Johanna Marie Gegenfurtner, Georgios Arvanitidis - - - CHOIR: A Chatbot-mediated Organizational Memory Leveraging Communication in University Research Labs - https://arxiv.org/abs/2509.20512 - arXiv:2509.20512v2 Announce Type: replace -Abstract: University research labs often rely on chat-based platforms for communication and project management, where valuable knowledge surfaces but is easily lost in message streams. Documentation can preserve knowledge, but it requires ongoing maintenance and is challenging to navigate. Drawing on formative interviews that revealed organizational memory challenges in labs, we designed CHOIR, an LLM-based chatbot that supports organizational memory through four key functions: document-grounded Q&A, Q&A sharing for follow-up discussion, knowledge extraction from conversations, and AI-assisted document updates. We deployed CHOIR in four research labs for one month (n=21), where the lab members asked 107 questions and lab directors updated documents 38 times in the organizational memory. Our findings reveal a privacy-awareness tension: questions were asked privately, limiting directors' visibility into documentation gaps. Students often avoided contribution due to challenges in generalizing personal experiences into universal documentation. We contribute design implications for privacy-preserving awareness and supporting context-specific knowledge documentation. - oai:arXiv.org:2509.20512v2 - cs.HC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sangwook Lee, Adnan Abbas, Yan Chen, Young-Ho Kim, Sang Won Lee - - - Training Task Reasoning LLM Agents for Multi-turn Task Planning via Single-turn Reinforcement Learning - https://arxiv.org/abs/2509.20616 - arXiv:2509.20616v2 Announce Type: replace -Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent applications. However, training LLM agents for complex multi-turn task planning faces significant challenges, including sparse episode-wise rewards, credit assignment across long horizons, and the computational overhead of reinforcement learning in multi-turn interaction settings. To this end, this paper introduces a novel approach that transforms multi-turn task planning into single-turn task reasoning problems, enabling efficient policy optimization through Group Relative Policy Optimization (GRPO) with dense and verifiable reward from expert trajectories. Our theoretical analysis shows that GRPO improvement on single-turn task reasoning results in a lower bound of the multi-turn success probability under the minimal turns, as well as the generalization to subtasks with shorter horizons. Experimental evaluation on the complex task planning benchmark demonstrates that our 1.5B parameter model trained with single-turn GRPO achieves superior performance compared to larger baseline models up to 14B parameters, with success rates of 70% for long-horizon planning tasks. - oai:arXiv.org:2509.20616v2 - cs.LG - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Hanjiang Hu, Changliu Liu, Na Li, Yebin Wang - - - SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs - https://arxiv.org/abs/2509.20758 - arXiv:2509.20758v2 Announce Type: replace -Abstract: Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their general capabilities. In this work, we revisit this trade-off and present both empirical and theoretical insights. First, we show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation while preserving comparable target-domain performance. We then provide a theoretical analysis that explains these phenomena and further motivates a new method, Token-Adaptive Loss Reweighting (TALR). Building on this, and recognizing that smaller learning rates alone do not fully eliminate general-performance degradation in all cases, we evaluate a range of strategies for reducing general capability loss, including L2 regularization, LoRA, model averaging, FLOW, and our proposed TALR. Experimental results demonstrate that while no method completely eliminates the trade-off, TALR consistently outperforms these baselines in balancing domain-specific gains and general capabilities. Finally, we distill our findings into practical guidelines for adapting LLMs to new domains: (i) using a small learning rate to achieve a favorable trade-off, and (ii) when a stronger balance is further desired, adopt TALR as an effective strategy. - oai:arXiv.org:2509.20758v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Jiacheng Lin, Zhongruo Wang, Kun Qian, Tian Wang, Arvind Srinivasan, Hansi Zeng, Ruochen Jiao, Xie Zhou, Jiri Gesi, Dakuo Wang, Yufan Guo, Kai Zhong, Weiqi Zhang, Sujay Sanghavi, Changyou Chen, Hyokun Yun, Lihong Li - - - From GPUs to RRAMs: Distributed In-Memory Primal-Dual Hybrid Gradient Method for Solving Large-Scale Linear Optimization Problem - https://arxiv.org/abs/2509.21137 - arXiv:2509.21137v3 Announce Type: replace -Abstract: The exponential growth of computational workloads is surpassing the capabilities of conventional architectures, which are constrained by fundamental limits. In-memory computing (IMC) with RRAM provides a promising alternative by providing analog computations with significant gains in latency and energy use. However, existing algorithms developed for conventional architectures do not translate to IMC, particularly for constrained optimization problems where frequent matrix reprogramming remains cost-prohibitive for IMC applications. Here we present a distributed in-memory primal-dual hybrid gradient (PDHG) method, specifically co-designed for arrays of RRAM devices. Our approach minimizes costly write cycles, incorporates robustness against device non-idealities, and leverages a symmetric block-matrix formulation to unify operations across distributed crossbars. We integrate a physics-based simulation framework called MELISO+ to evaluate performance under realistic device conditions. Benchmarking against GPU-accelerated solvers on large-scale linear programs demonstrates that our RRAM-based solver achieves comparable accuracy with up to three orders of magnitude reductions in energy consumption and latency. These results demonstrate the first PDHG-based LP solver implemented on RRAMs, showcasing the transformative potential of algorithm-hardware co-design for solving large-scale optimization through distributed in-memory computing. - oai:arXiv.org:2509.21137v3 - cs.DC - cs.AR - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Huynh Q. N. Vo, Md Tawsif Rahman Chowdhury, Paritosh Ramanan, Gozde Tutuncuoglu, Junchi Yang, Feng Qiu, Murat Yildirim - - - Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias - https://arxiv.org/abs/2509.21181 - arXiv:2509.21181v3 Announce Type: replace -Abstract: For overparameterized linear regression with isotropic Gaussian design and minimum-$\ell_p$ interpolator $p\in(1,2]$, we give a unified, high-probability characterization for the scaling of the family of parameter norms $ \\{ \lVert \widehat{w_p} \rVert_r \\}_{r \in [1,p]} $ with sample size. - We solve this basic, but unresolved question through a simple dual-ray analysis, which reveals a competition between a signal *spike* and a *bulk* of null coordinates in $X^\top Y$, yielding closed-form predictions for (i) a data-dependent transition $n_\star$ (the "elbow"), and (ii) a universal threshold $r_\star=2(p-1)$ that separates $\lVert \widehat{w_p} \rVert_r$'s which plateau from those that continue to grow with an explicit exponent. - This unified solution resolves the scaling of *all* $\ell_r$ norms within the family $r\in [1,p]$ under $\ell_p$-biased interpolation, and explains in one picture which norms saturate and which increase as $n$ grows. - We then study diagonal linear networks (DLNs) trained by gradient descent. By calibrating the initialization scale $\alpha$ to an effective $p_{\mathrm{eff}}(\alpha)$ via the DLN separable potential, we show empirically that DLNs inherit the same elbow/threshold laws, providing a predictive bridge between explicit and implicit bias. - Given that many generalization proxies depend on $\lVert \widehat {w_p} \rVert_r$, our results suggest that their predictive power will depend sensitively on which $l_r$ norm is used. - oai:arXiv.org:2509.21181v3 - cs.LG - math.ST - stat.ML - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shuofeng Zhang, Ard Louis - - - LLM Output Homogenization is Task Dependent - https://arxiv.org/abs/2509.21267 - arXiv:2509.21267v2 Announce Type: replace -Abstract: A large language model can be less helpful if it exhibits output response homogenization. But whether two responses are considered homogeneous, and whether such homogenization is problematic, both depend on the task category. For instance, in objective math tasks, we often expect no variation in the final answer but anticipate variation in the problem-solving strategy. Whereas, for creative writing tasks, we may expect variation in key narrative components (e.g. plot, genre, setting, etc), beyond the vocabulary or embedding diversity produced by temperature-sampling. Previous work addressing output homogenization often fails to conceptualize diversity in a task-dependent way. We address this gap in the literature directly by making the following contributions. (1) We present a task taxonomy comprised of eight task categories that each have distinct concepts of output homogenization. (2) We introduce task-anchored functional diversity to better evaluate output homogenization. (3) We propose a task-anchored sampling technique that increases functional diversity for task categories where homogenization is undesired, while preserving it where it is desired. (4) We challenge the perceived existence of a diversity-quality trade-off by increasing functional diversity while maintaining response quality. Overall, we demonstrate how task dependence improves the evaluation and mitigation of output homogenization. - oai:arXiv.org:2509.21267v2 - cs.CL - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shomik Jain, Jack Lanchantin, Maximilian Nickel, Karen Ullrich, Ashia Wilson, Jamelle Watson-Daniels - - - Lattice-Based Dynamic $k$-Times Anonymous Authentication with Attribute-Based Credentials - https://arxiv.org/abs/2509.21786 - arXiv:2509.21786v3 Announce Type: replace -Abstract: With the development of Internet, privacy has become a primary concern of users. Anonymous authentication plays an important role in privacy-preserving systems. A $k$-times anonymous authentication ($k$-TAA) scheme allows a group member to anonymously authenticate to the application provider up to $k$ times. Considering quantum computing attacks, lattice-based $k$-TAA was introduced. However, existing schemes neither support the dynamic granting and revocation of users nor enable users to control the release of their attributes. In this paper, we construct the first lattice-based dynamic $k$-TAA, which offers limited times anonymous authentication, dynamic member management, attribute-based authentication, and post-quantum security. We present a concrete construction, and reduce its security to standard complexity assumptions. Notably, compared with existing lattice-based $k$-TAA, our scheme is efficient in terms of communication cost. - oai:arXiv.org:2509.21786v3 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junjie Song, Jinguang Han, Man Ho Au, Rupeng Yang, Chao Sun - - - Why Chain of Thought Fails in Clinical Text Understanding - https://arxiv.org/abs/2509.21933 - arXiv:2509.21933v2 Announce Type: replace -Abstract: Large language models (LLMs) are increasingly being applied to clinical care, a domain where both accuracy and transparent reasoning are critical for safe and trustworthy deployment. Chain-of-thought (CoT) prompting, which elicits step-by-step reasoning, has demonstrated improvements in performance and interpretability across a wide range of tasks. However, its effectiveness in clinical contexts remains largely unexplored, particularly in the context of electronic health records (EHRs), the primary source of clinical documentation, which are often lengthy, fragmented, and noisy. In this work, we present the first large-scale systematic study of CoT for clinical text understanding. We assess 95 advanced LLMs on 87 real-world clinical text tasks, covering 9 languages and 8 task types. Contrary to prior findings in other domains, we observe that 86.3\% of models suffer consistent performance degradation in the CoT setting. More capable models remain relatively robust, while weaker ones suffer substantial declines. To better characterize these effects, we perform fine-grained analyses of reasoning length, medical concept alignment, and error profiles, leveraging both LLM-as-a-judge evaluation and clinical expert evaluation. Our results uncover systematic patterns in when and why CoT fails in clinical contexts, which highlight a critical paradox: CoT enhances interpretability but may undermine reliability in clinical text tasks. This work provides an empirical basis for clinical reasoning strategies of LLMs, highlighting the need for transparent and trustworthy approaches. - oai:arXiv.org:2509.21933v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiageng Wu, Kevin Xie, Bowen Gu, Nils Kr\"uger, Kueiyu Joshua Lin, Jie Yang - - - Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning - https://arxiv.org/abs/2509.22601 - arXiv:2509.22601v4 Announce Type: replace -Abstract: Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation balance under the guidance of the agent's own experiences without succumbing to either entropy collapsing or runaway divergence. We propose SPEAR, a self-imitation learning (SIL) recipe for training agentic LLMs. It extends the vanilla SIL, where a replay buffer stores good experience for off-policy update, by gradually steering the policy entropy across stages. Specifically, the proposed curriculum scheduling harmonizes intrinsic reward shaping and self-imitation to 1) expedite exploration via frequent tool interactions at the beginning, and 2) strengthen exploitation of successful tactics upon convergence towards familiarity with the environment. We also combine bag-of-tricks of industrial RL optimizations for a strong baseline Dr.BoT to demonstrate our effectiveness. In ALFWorld and WebShop, SPEAR increases the success rates of GRPO/GiGPO/Dr.BoT by up to 16.1%/5.1%/8.6% and 20.7%/11.8%/13.9%, respectively. In AIME24 and AIME25, SPEAR boosts Dr.BoT by up to 3.8% and 6.1%, respectively. Such gains incur only 10%-25% extra theoretical complexity and negligible runtime overhead in practice, demonstrating the plug-and-play scalability of SPEAR. - oai:arXiv.org:2509.22601v4 - cs.LG - cs.AI - cs.CL - cs.CV - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yulei Qin, Xiaoyu Tan, Zhengbao He, Gang Li, Haojia Lin, Zongyi Li, Zihan Xu, Yuchen Shi, Siqi Cai, Renting Rui, Shaofei Cai, Yuzheng Cai, Xuan Zhang, Sheng Ye, Ke Li, Xing Sun - - - ARSS: Taming Decoder-only Autoregressive Visual Generation for View Synthesis From Single View - https://arxiv.org/abs/2509.23008 - arXiv:2509.23008v2 Announce Type: replace -Abstract: Diffusion models have achieved impressive results in world modeling tasks, including novel view generation from sparse inputs. However, most existing diffusion-based NVS methods generate target views jointly via an iterative denoising process, which makes it less straightforward to impose a strictly causal structure along a camera trajectory. In contrast, autoregressive (AR) models operate in a causal fashion, generating each token based on all previously generated tokens. In this work, we introduce ARSS, a novel framework that leverages a GPT-style decoder-only AR model to generate novel views from a single image, conditioned on a predefined camera trajectory. We employ an off-the-shelf video tokenizer to map continuous image sequences into discrete tokens and propose a camera encoder that converts camera trajectories into 3D positional guidance. Then to enhance generation quality while preserving the autoregressive structure, we propose an autoregressive transformer module that randomly permutes the spatial order of tokens while maintaining their temporal order. Qualitative and quantitative experiments on public datasets demonstrate that our method achieves overall performance comparable to state-of-the-art view synthesis approaches based on diffusion models. Project page: https://wbteng9526.github.io/arss/. - oai:arXiv.org:2509.23008v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wenbin Teng, Gonglin Chen, Haiwei Chen, Yajie Zhao - - - Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents - https://arxiv.org/abs/2509.23045 - arXiv:2509.23045v3 Announce Type: replace -Abstract: Large Language Models (LLMs) are increasingly applied to software engineering (SWE), with SWE-bench as a key benchmark. Solutions are split into SWE-Agent frameworks with multi-turn interactions and workflow-based Agentless methods with single-turn verifiable steps. We argue these paradigms are not mutually exclusive: reasoning-intensive Agentless training induces skill priors, including localization, code edit, and self-reflection that enable efficient and effective SWE-Agent adaptation. In this work, we first curate the Agentless training recipe and present Kimi-Dev, an open-source SWE LLM achieving 60.4\% on SWE-bench Verified, the best among workflow approaches. With additional SFT adaptation on 5k publicly-available trajectories, Kimi-Dev powers SWE-Agents to 48.6\% pass@1, on par with that of Claude 3.5 Sonnet (241022 version). These results show that structured skill priors from Agentless training can bridge workflow and agentic frameworks for transferable coding agents. - oai:arXiv.org:2509.23045v3 - cs.AI - cs.CL - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Zonghan Yang, Shengjie Wang, Kelin Fu, Wenyang He, Weimin Xiong, Yibo Liu, Yibo Miao, Bofei Gao, Yejie Wang, Yingwei Ma, Yanhao Li, Yue Liu, Zhenxing Hu, Kaitai Zhang, Shuyi Wang, Huarong Chen, Flood Sung, Yang Liu, Yang Gao, Zhilin Yang, Tianyu Liu - - - Non-Collaborative User Simulators for Tool Agents - https://arxiv.org/abs/2509.23124 - arXiv:2509.23124v3 Announce Type: replace -Abstract: Tool agents interact with users through multi-turn dialogues to accomplish various tasks. Recent studies have adopted user simulation methods to develop these agents in multi-turn settings. However, existing user simulators tend to be agent-friendly, exhibiting only cooperative behaviors, which fails to train and test agents against non-collaborative users in the real world. To address this, we propose a novel user simulator architecture that simulates four categories of non-collaborative behaviors: requesting unavailable services, digressing into tangential conversations, expressing impatience, and providing incomplete utterances. Our user simulator can simulate challenging and natural non-collaborative behaviors while reliably delivering all intents and information necessary to accomplish the task. Our experiments on MultiWOZ and $\tau$-bench reveal significant performance degradation in state-of-the-art tool agents when encountering non-collaborative users. We provide detailed analyses of agents' weaknesses under each non-collaborative condition, such as escalated hallucinations and dialogue breakdowns. Ultimately, we contribute an easily extensible user simulation framework to help the research community develop tool agents and preemptively diagnose them under challenging real-world conditions within their own services. - oai:arXiv.org:2509.23124v3 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jeonghoon Shim, Woojung Song, Cheyon Jin, Seungwon KooK, Yohan Jo - - - High Torque Density PCB Axial Flux Permanent Magnet Motor for Micro Robots - https://arxiv.org/abs/2509.23561 - arXiv:2509.23561v2 Announce Type: replace -Abstract: Quasi-direct-drive (QDD) actuation is transforming legged and manipulator robots by eliminating high-ratio gearboxes, yet it demands motors that deliver very high torque at low speed within a thin, disc-shaped joint envelope. Axial-flux permanent-magnet (AFPM) machines meet these geometric and torque requirements, but scaling them below a 20mm outer diameter is hampered by poor copper fill in conventional wound stators, inflating resistance and throttling continuous torque. This paper introduces a micro-scale AFPM motor that overcomes these limitations through printed-circuit-board (PCB) windings fabricated with advanced IC-substrate high-density interconnect (HDI) technology. The resulting 48-layer stator-formed by stacking four 12-layer HDI modules-achieves a record 45\% copper fill in a package only 5mm thick and 19mm in diameter. We perform comprehensive electromagnetic and thermal analyses to inform the motor design, then fabricate a prototype whose performance characteristics are experimentally verified. - oai:arXiv.org:2509.23561v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - IEEE Energy Conversion Congress and Expo 2025 - Jianren Wang, Quanting Xie, Jie Han, Yang Zhang, Christopher G. Atkeson, Abhinav Gupta, Deepak Pathak, Yonatan Bisk - - - RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment - https://arxiv.org/abs/2509.24159 - arXiv:2509.24159v3 Announce Type: replace -Abstract: Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that preference data is clean and that all labels are equally reliable. In practice, large-scale preference datasets contain substantial noise due to annotator mistakes, inconsistent instructions, varying expertise, and even adversarial or low-effort feedback. This mismatch between recorded labels and ground-truth preferences can misguide training and degrade model performance. To address this issue, we introduce Robust Enhanced Policy Optimization (RE-PO), which uses an expectation-maximization procedure to infer the posterior correctness of each label and then adaptively reweight data points in the training loss to mitigate label noise. We further generalize this idea by establishing a theoretical link between arbitrary preference losses and their underlying probabilistic models, enabling a systematic transformation of existing alignment algorithms into robust counterparts and elevating RE-PO from a single method to a general framework for robust preference alignment. Theoretically, we prove that, under a perfectly calibrated model, RE-PO recovers the true noise level of the dataset. Empirically, we show that RE-PO consistently improves four state-of-the-art alignment methods (DPO, IPO, SimPO, and CPO); when applied to Mistral and Llama 3 models, the RE-PO-enhanced variants increase AlpacaEval 2 win rates by up to 7.0 percent over their respective baselines. - oai:arXiv.org:2509.24159v3 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xiaoyang Cao, Zelai Xu, Mo Guang, Kaiwen Long, Michiel A. Bakker, Yu Wang, Chao Yu - - - SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents - https://arxiv.org/abs/2509.24282 - arXiv:2509.24282v2 Announce Type: replace -Abstract: Large Language Model (LLM) agents excel at multi-step, tool-augmented tasks. However, smart homes introduce distinct challenges, requiring agents to handle latent user intents, temporal dependencies, device constraints, scheduling, and more. The main bottlenecks for developing smart home agents with such capabilities include the lack of a realistic simulation environment where agents can interact with devices and observe the results, as well as a challenging benchmark to evaluate them. To address this, we introduce $\textbf{SimuHome}$, a time-accelerated home environment that simulates smart devices, supports API calls, and reflects changes in environmental variables. By building the simulator on the Matter protocol, the global industry standard for smart home communication, SimuHome provides a high-fidelity environment, and agents validated in SimuHome can be deployed on real Matter-compliant devices with minimal adaptation. We provide a challenging benchmark of 600 episodes across twelve user query types that require the aforementioned capabilities. Our evaluation of 16 agents under a unified ReAct framework reveals distinct capabilities and limitations across models. Models under 7B parameters exhibited negligible performance across all query types. Even GPT-4.1, the best-performing standard model, struggled with implicit intent inference, state verification, and particularly temporal scheduling. While reasoning models such as GPT-5.1 consistently outperformed standard models on every query type, they required over three times the average inference time, which can be prohibitive for real-time smart home applications. This highlights a critical trade-off between task performance and real-world practicality. - oai:arXiv.org:2509.24282v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Gyuhyeon Seo, Jungwoo Yang, Junseong Pyo, Nalim Kim, Jonggeun Lee, Yohan Jo - - - AuON: A Linear-time Alternative to Orthogonal Momentum Updates - https://arxiv.org/abs/2509.24320 - arXiv:2509.24320v3 Announce Type: replace -Abstract: Orthogonal momentum gradient updates have emerged to overcome the limitations of vector-based optimizers like Adam. The vector-based optimizer Adam suffers from high memory costs and ill-conditioned momentum gradient updates. However, traditional Orthogonal momentum approaches, such as SVD/QR decomposition, suffer from high computational and memory costs and underperform compared to well-tuned SGD with momentum.Recent advances, such as Muon, improve efficiency by applying momentum before orthogonalization and approximate orthogonal matrices via Newton-Schulz iterations, which gives better GPU utilization, active high TFLOPS, and reduces memory usage by up to 3x. Nevertheless, Muon(Vanilla) suffers from exploding attention logits and has cubic computation complexity. In this paper we , deep dive into orthogonal momentum gradient updates to find the main properties that help Muon to achieve remarkable performance.We propose \textbf{AuON} (Alternative Unit-norm momentum updates by Normalized nonlinear scaling), a linear-time optimizer that achieves strong performance without approximate orthogonal matrices, while preserving structural alignment and reconditioning ill-posed updates. AuON has an automatic (\textbf{"emergency brake"}) to handle exploding attention logits.. We further introduce a hybrid variant (\textbf{ Hybrid-AuON})that applies the linear transformations with Newton-Schulz iterations which out performs Muon in the language modeling tasks. Code is available at: https://github.com/ryyzn9/AuON - oai:arXiv.org:2509.24320v3 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Dipan Maity - - - CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D - https://arxiv.org/abs/2509.24528 - arXiv:2509.24528v3 Announce Type: replace -Abstract: 3D scene understanding is fundamental for embodied AI and robotics, supporting reliable perception for interaction and navigation. Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D class-agnostic masks generated via vision-language models (VLMs) and projecting these into 3D. However, these methods often produce fragmented masks and inaccurate semantic assignments due to the direct use of raw masks, limiting their effectiveness in complex environments. To address this, we leverage SemanticSAM with progressive granularity refinement to generate more accurate and numerous object-level masks, mitigating the over-segmentation commonly observed in mask generation models such as vanilla SAM, and improving downstream 3D semantic segmentation. To further enhance semantic context, we employ a context-aware CLIP encoding strategy that integrates multiple contextual views of each mask using empirically determined weighting, providing much richer visual context. We evaluate our approach on multiple 3D scene understanding tasks, including 3D semantic segmentation and object retrieval from language queries, across several benchmark datasets. Experimental results demonstrate significant improvements over existing methods, highlighting the effectiveness of our approach. - oai:arXiv.org:2509.24528v3 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Mohamad Amin Mirzaei, Pantea Amoie, Ali Ekhterachian, Matin Mirzababaei, Babak Khalaj - - - Physics-Informed Inductive Biases for Voltage Prediction in Distribution Grids - https://arxiv.org/abs/2509.25158 - arXiv:2509.25158v2 Announce Type: replace -Abstract: Voltage prediction in distribution grids is a critical yet difficult task for maintaining power system stability. Machine learning approaches, particularly Graph Neural Networks (GNNs), offer significant speedups but suffer from poor generalization when trained on limited or incomplete data. In this work, we systematically investigate the role of inductive biases in improving a model's ability to reliably learn power flow. Specifically, we evaluate three physics-informed strategies: (i) power-flow-constrained loss functions, (ii) complex-valued neural networks, and (iii) residual-based task reformulation. Using the ENGAGE dataset, which spans multiple low- and medium-voltage grid configurations, we conduct controlled experiments to isolate the effect of each inductive bias and assess both standard predictive performance and out-of-distribution generalization. Our study provides practical insights into which model assumptions most effectively guide learning for reliable and efficient voltage prediction in modern distribution networks. - oai:arXiv.org:2509.25158v2 - cs.LG - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ehimare Okoyomon, Arbel Yaniv, Christoph Goebel - - - Saliency Guided Longitudinal Medical Visual Question Answering - https://arxiv.org/abs/2509.25374 - arXiv:2509.25374v2 Announce Type: replace -Abstract: Longitudinal medical visual question answering (Diff-VQA) requires comparing paired studies from different time points and answering questions about clinically meaningful changes. In this setting, the difference signal and the consistency of visual focus across time are more informative than absolute single-image findings. We propose a saliency-guided encoder-decoder for chest X-ray Diff-VQA that turns post-hoc saliency into actionable supervision. The model first performs a lightweight near-identity affine pre-alignment to reduce nuisance motion between visits. It then executes a within-epoch two-step loop: step 1 extracts a medically relevant keyword from the answer and generates keyword-conditioned Grad-CAM on both images to obtain disease-focused saliency; step 2 applies the shared saliency mask to both time points and generates the final answer. This closes the language-vision loop so that the terms that matter also guide where the model looks, enforcing spatially consistent attention on corresponding anatomy. On Medical-Diff-VQA, the approach attains competitive performance on BLEU, ROUGE-L, CIDEr, and METEOR while providing intrinsic interpretability. Notably, the backbone and decoder are general-domain pretrained without radiology-specific pretraining, highlighting practicality and transferability. These results support saliency-conditioned generation with mild pre-alignment as a principled framework for longitudinal reasoning in medical VQA. - oai:arXiv.org:2509.25374v2 - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jialin Wu, Xiaofeng Liu - - - MetaChest: Generalized few-shot learning of pathologies from chest X-rays - https://arxiv.org/abs/2509.25590 - arXiv:2509.25590v2 Announce Type: replace -Abstract: The limited availability of annotated data presents a major challenge for applying deep learning methods to medical image analysis. Few-shot learning methods aim to recognize new classes from only a small number of labeled examples. These methods are typically studied under the standard few-shot learning setting, where all classes in a task are new. However, medical applications such as pathology classification from chest X-rays often require learning new classes while simultaneously leveraging knowledge of previously known ones, a scenario more closely aligned with generalized few-shot classification. Despite its practical relevance, few-shot learning has been scarcely studied in this context. In this work, we present MetaChest, a large-scale dataset of 479,215 chest X-rays collected from four public databases. MetaChest includes a meta-set partition specifically designed for standard few-shot classification, as well as an algorithm for generating multi-label episodes. We conduct extensive experiments evaluating both a standard transfer learning approach and an extension of ProtoNet across a wide range of few-shot multi-label classification tasks. Our results demonstrate that increasing the number of classes per episode and the number of training examples per class improves classification performance. Notably, the transfer learning approach consistently outperforms the ProtoNet extension, despite not being tailored for few-shot learning. We also show that higher-resolution images improve accuracy at the cost of additional computation, while efficient model architectures achieve comparable performance to larger models with significantly reduced resource requirements. - oai:arXiv.org:2509.25590v2 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Berenice Montalvo-Lezama, Gibran Fuentes-Pineda - - - PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models - https://arxiv.org/abs/2509.25774 - arXiv:2509.25774v2 Announce Type: replace -Abstract: While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image quality. Our analysis identifies a key cause of this instability: disproportionate credit assignment, in which the mathematical structure of the generative sampler produces volatile and non-proportional feedback across timesteps. To address this, we introduce Proportionate Credit Policy Optimization (PCPO), a framework that enforces proportional credit assignment through a stable objective reformulation and a principled reweighting of timesteps. This correction stabilizes the training process, leading to significantly accelerated convergence and superior image quality. The improvement in quality is a direct result of mitigating model collapse, a common failure mode in recursive training. PCPO substantially outperforms existing policy gradient baselines on all fronts, including the state-of-the-art DanceGRPO. Code is available at https://github.com/jaylee2000/pcpo/. - oai:arXiv.org:2509.25774v2 - cs.CV - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jeongjae Lee, Jong Chul Ye - - - A Field Guide to Deploying AI Agents in Clinical Practice - https://arxiv.org/abs/2509.26153 - arXiv:2509.26153v3 Announce Type: replace -Abstract: Large language models (LLMs) integrated into agent-driven workflows hold immense promise for healthcare, yet a significant gap exists between their potential and practical implementation within clinical settings. To address this, we present a practitioner-oriented field manual for deploying generative agents that use electronic health record (EHR) data. This guide is informed by our experience deploying the "irAE-Agent", an automated system to detect immune-related adverse events from clinical notes at Mass General Brigham, and by structured interviews with 21 clinicians, engineers, and informatics leaders involved in the project. Our analysis reveals a critical misalignment in clinical AI development: less than 20% of our effort was dedicated to prompt engineering and model development, while over 80% was consumed by the sociotechnical work of implementation. We distill this effort into five "heavy lifts": data integration, model validation, ensuring economic value, managing system drift, and governance. By providing actionable solutions for each of these challenges, this field manual shifts the focus from algorithmic development to the essential infrastructure and implementation work required to bridge the "valley of death" and successfully translate generative AI from pilot projects into routine clinical care. - oai:arXiv.org:2509.26153v3 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jack Gallifant, Katherine C. Kellogg, Matt Butler, Amanda Centi, Shan Chen, Patrick F. Doyle, Sayon Dutta, Joyce Guo, Matthew J. Hadfield, Esther H. Kim, David E. Kozono, Hugo JWL Aerts, Adam B. Landman, Raymond H. Mak, Rebecca G. Mishuris, Tanna L. Nelson, Guergana K. Savova, Elad Sharon, Benjamin C. Silverman, Umit Topaloglu, Jeremy L. Warner, Danielle S. Bitterman - - - TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos - https://arxiv.org/abs/2509.26360 - arXiv:2509.26360v3 Announce Type: replace -Abstract: Identifying key temporal intervals within long videos, known as temporal grounding (TG), is important to video understanding and reasoning tasks. In this paper, we introduce a new form of the temporal grounding problem, \textbf{Task-oriented Temporal Grounding} (\textbf{ToTG}), which is driven by the requirements of downstream tasks rather than explicit time-interval descriptions. For example, a ToTG input may be "explain why the man in the video is sent to the hospital," whereas traditional TG would take an explicit temporal description such as "the moments when the man is tripped by a stone and falls to the ground." This new ToTG formulation presents significant challenges for existing TG methods, as it requires jointly performing deep task comprehension and fine-grained temporal localization within long videos. To address these challenges, we conduct a systematic set of studies. First, we construct \textbf{a new benchmark ToTG-Bench}, which comprehensively evaluates ToTG performance across diverse settings. Second, we introduce \textbf{a new temporal-ground method TimeScope}, which performs coarse-to-fine localization through a progressive reasoning process. Leveraging extensive supervised fine-tuning with carefully curated chain-of-thought (CoT) data from a variety of scenarios, TimeScope generalizes effectively across tasks and domains. Our evaluation demonstrates \textbf{TimeScope's empirical advantages} over existing baselines from three perspectives: (1) substantial improvements in grounding precision, (2) significant benefits to downstream tasks, and (3) strong generalizability across different scenarios. All models, datasets, and source code will be fully open-sourced to support future research in this area. - oai:arXiv.org:2509.26360v3 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xiangrui Liu, Minghao Qin, Yan Shu, Zhengyang Liang, Yang Tian, Chen Jason Zhang, Bo Zhao, Zheng Liu - - - Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors - https://arxiv.org/abs/2510.00586 - arXiv:2510.00586v2 Announce Type: replace -Abstract: Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase. We introduce Eyes-on-Me, a modular attack that decomposes an adversarial document into reusable Attention Attractors and Focus Regions. Attractors are optimized to direct attention to the Focus Region. Attackers can then insert semantic baits for the retriever or malicious instructions for the generator, adapting to new targets at near zero cost. This is achieved by steering a small subset of attention heads that we empirically identify as strongly correlated with attack success. Across 18 end-to-end RAG settings (3 datasets $\times$ 2 retrievers $\times$ 3 generators), Eyes-on-Me raises average attack success rates from 21.9 to 57.8 (+35.9 points, 2.6$\times$ over prior work). A single optimized attractor transfers to unseen black box retrievers and generators without retraining. Our findings establish a scalable paradigm for RAG data poisoning and show that modular, reusable components pose a practical threat to modern AI systems. They also reveal a strong link between attention concentration and model outputs, informing interpretability research. - oai:arXiv.org:2510.00586v2 - cs.LG - cs.CL - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen - - - A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning - https://arxiv.org/abs/2510.01132 - arXiv:2510.01132v2 Announce Type: replace -Abstract: We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic formulation or analysis of which design choices matter across tasks. We address this gap by first breaking down the design space into three inter-related pillars -- environment, reward, and policy -- and empirically derive a recipe for training LLM agents in situated textual domains. In particular, we test TextWorld and ALFWorld, popular domains for testing situated embodied reasoning, as well as SWE-Gym for more software engineering style tasks. (i) For the environment, we analyze the impacts of task complexity in terms of sizes of the state and action spaces as well as optimal solution length, finding that even simple environments within a domain can provide signal on how well an agent can generalize to more complex tasks. (ii) For the reward, we ablate relative reward sparsity, observing that while dense turn-level rewards accelerate training, performance and stability is highly dependent on the choice of RL algorithm. (iii) And for the agent's policy, we explore the interplay between reward sparsity and biased (PPO, GRPO) and unbiased (RLOO) policy gradient methods in addition to showing how to find the optimal Supervised Fine-tuning (SFT) to RL training ratio given a fixed budget. We distill these findings into a training recipe that guides co-design across the three pillars, facilitating research and practical efforts in multi-turn agentic RL. Code: https://github.com/pearls-lab/meow-tea-taro - oai:arXiv.org:2510.01132v2 - cs.LG - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ruiyi Wang, Prithviraj Ammanabrolu - - - AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees - https://arxiv.org/abs/2510.01268 - arXiv:2510.01268v4 Announce Type: replace -Abstract: We study the problem of determining whether a piece of text has been authored by a human or by a large language model (LLM). Existing state of the art logits-based detectors make use of statistics derived from the log-probability of the observed text evaluated using the distribution function of a given source LLM. However, relying solely on log probabilities can be sub-optimal. In response, we introduce AdaDetectGPT -- a novel classifier that adaptively learns a witness function from training data to enhance the performance of logits-based detectors. We provide statistical guarantees on its true positive rate, false positive rate, true negative rate and false negative rate. Extensive numerical studies show AdaDetectGPT nearly uniformly improves the state-of-the-art method in various combination of datasets and LLMs, and the improvement can reach up to 37\%. A python implementation of our method is available at https://github.com/Mamba413/AdaDetectGPT. - oai:arXiv.org:2510.01268v4 - cs.CL - cs.AI - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hongyi Zhou, Jin Zhu, Pingfan Su, Kai Ye, Ying Yang, Shakeel A O B Gavioli-Akilagun, Chengchun Shi - - - ACM SIGSOFT SEN Empirical Software Engineering: Introducing Our New Regular Column - https://arxiv.org/abs/2510.02007 - arXiv:2510.02007v3 Announce Type: replace -Abstract: From its early foundations in the 1970s, empirical software engineering (ESE) has evolved into a mature research discipline that embraces a plethora of different topics, methodologies, and industrial practices. Despite its remarkable progress, the ESE research field still needs to keep evolving, as new impediments, shortcoming, and technologies emerge. Research reproducibility, limited external validity, subjectivity of reviews, and porting research results to industrial practices are just some examples of the drivers for improvements to ESE research. Additionally, several facets of ESE research are not documented very explicitly, which makes it difficult for newcomers to pick them up. With this new regular ACM SIGSOFT SEN column (SEN-ESE), we introduce a venue for discussing meta-aspects of ESE research, ranging from general topics such as the nature and best practices for replication packages, to more nuanced themes such as statistical methods, interview transcription tools, and publishing interdisciplinary research. Our aim for the column is to be a place where we can regularly spark conversations on ESE topics that might not often be touched upon or are left implicit. Contributions to this column will be grounded in expert interviews, focus groups, surveys, and position pieces, with the goal of encouraging reflection and improvement in how we conduct, communicate, teach, and ultimately improve ESE research. Finally, we invite feedback from the ESE community on challenging, controversial, or underexplored topics, as well as suggestions for voices you would like to hear from. While we cannot promise to act on every idea, we aim to shape this column around the community interests and are grateful for all contributions. - oai:arXiv.org:2510.02007v3 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3772008.3772012 - Justus Bogner, Roberto Verdecchia - - - Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning - https://arxiv.org/abs/2510.02324 - arXiv:2510.02324v2 Announce Type: replace -Abstract: Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own knowledge and that activation steering can reduce hallucinations. These approaches, however, require real-time monitoring and intervention during inference. We introduce Contrastive Activation Steering for Amortized Learning (CASAL), an efficient algorithm that connects interpretability with amortized optimization. CASAL directly bakes the benefits of activation steering into model's weights. Once trained, LLMs answer questions they know while abstaining from answering those they do not. CASAL's light-weight design requires training only a submodule of a single transformer layer and yet reduces hallucination by 30%-40% across multiple short-form QA benchmarks. CASAL is 30x more compute-efficient and 20x more data-efficient than strong LoRA-based baselines such as SFT and DPO, boosting its practical applicability in data scarce domains. Importantly, CASAL also generalizes effectively to out-of-distribution (OOD) domains. We showcase CASAL's flexibility in mitigating hallucinations in both text-only and vision-language models. To our knowledge, CASAL is the first steering-based training method that has been shown to be effective for both dense and Mixture-of-Experts (MoE) models. CASAL represents a promising step forward for applying interpretability-inspired method for practical deployment in production systems. - oai:arXiv.org:2510.02324v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wannan (Winnie), Yang, Xinchi Qiu, Lei Yu, Yuchen Zhang, Aobo Yang, Narine Kokhlikyan, Nicola Cancedda, Diego Garcia-Olano - - - mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations - https://arxiv.org/abs/2510.02348 - arXiv:2510.02348v3 Announce Type: replace -Abstract: We build upon vec2vec, a procedure designed to align text embedding spaces without parallel data. vec2vec finds a near-perfect alignment, but it is expensive and unstable. We present mini-vec2vec, a simple and efficient alternative that requires substantially lower computational cost and is highly robust. Moreover, the learned mapping is a linear transformation. Our method consists of three main stages: a tentative matching of pseudo-parallel embedding vectors, transformation fitting, and iterative refinement. Our linear alternative exceeds the original instantiation of vec2vec by orders of magnitude in efficiency, while matching or exceeding their results. The method's stability and interpretable algorithmic steps facilitate scaling and unlock new opportunities for adoption in new domains and fields. - oai:arXiv.org:2510.02348v3 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Guy Dar - - - UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies - https://arxiv.org/abs/2510.02614 - arXiv:2510.02614v2 Announce Type: replace -Abstract: We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstrations collected with a handheld gripper (UMI) to train generalizable visuomotor policies. A central challenge in transferring these policies to constrained robotic embodiments-such as aerial manipulators-is the mismatch in control and robot dynamics, which often leads to out-of-distribution behaviors and poor execution. To address this, we propose Embodiment-Aware Diffusion Policy (EADP), which couples a high-level UMI policy with a low-level embodiment-specific controller at inference time. By integrating gradient feedback from the controller's tracking cost into the diffusion sampling process, our method steers trajectory generation towards dynamically feasible modes tailored to the deployment embodiment. This enables plug-and-play, embodiment-aware trajectory adaptation at test time. We validate our approach on multiple long-horizon and high-precision aerial manipulation tasks, showing improved success rates, efficiency, and robustness under disturbances compared to unguided diffusion baselines. Finally, we demonstrate deployment in previously unseen environments, using UMI demonstrations collected in the wild, highlighting a practical pathway for scaling generalizable manipulation skills across diverse-and even highly constrained-embodiments. All code, data, and checkpoints will be publicly released after acceptance. Result videos can be found at umi-on-air.github.io. - oai:arXiv.org:2510.02614v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Harsh Gupta, Xiaofeng Guo, Huy Ha, Chuer Pan, Muqing Cao, Dongjae Lee, Sebastian Scherer, Shuran Song, Guanya Shi - - - RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization - https://arxiv.org/abs/2510.02695 - arXiv:2510.02695v2 Announce Type: replace -Abstract: In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) offers an attractive alternative but only if policies deliver high returns without incurring catastrophic lower-tail risk. Prior work on risk-averse offline RL achieves safety at the cost of value or model-based pessimism, and restricted policy classes that limit policy expressiveness, whereas diffusion/flow-based expressive generative policies trained with a behavioral-cloning (BC) objective have been used only in risk-neutral settings. Here, we address this gap by introducing the \textbf{Risk-Aware Multimodal Actor-Critic (RAMAC)}, which couples an expressive generative actor with a distributional critic and, to our knowledge, is the first model-free approach that learns \emph{risk-aware expressive generative policies}. RAMAC differentiates a composite objective that adds a Conditional Value-at-Risk (CVaR) term to a BC loss, achieving risk-sensitive learning in complex multimodal scenarios. Since out-of-distribution (OOD) actions are a major driver of catastrophic failures in offline RL, we further analyze OOD behavior under prior-anchored perturbation schemes from recent BC-regularized risk-averse offline RL. This clarifies why a behavior-regularized objective that directly constrains the expressive generative policy to the dataset support provides an effective, risk-agnostic mechanism for suppressing OOD actions in modern expressive policies. We instantiate RAMAC with a diffusion-based actor, using it both to illustrate the analysis in a 2-D risky bandit and to deploy OOD-action detectors on Stochastic-D4RL benchmarks, empirically validating our insights. Across these tasks, we observe consistent gains in $\mathrm{CVaR}_{0.1}$ while maintaining strong returns. Our implementation is available at GitHub: https://github.com/KaiFukazawa/RAMAC.git - oai:arXiv.org:2510.02695v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kai Fukazawa, Kunal Mundada, Iman Soltani - - - General Exploratory Bonus for Optimistic Exploration in RLHF - https://arxiv.org/abs/2510.03269 - arXiv:2510.03269v3 Announce Type: replace -Abstract: Optimistic exploration is central to improving sample efficiency in reinforcement learning with human feedback, yet existing exploratory bonus methods to incentivize exploration often fail to realize optimism. We provide a theoretical analysis showing that current formulations, under KL or $\alpha$-divergence regularization, unintentionally bias exploration toward high-probability regions of the reference model, thereby reinforcing conservative behavior instead of promoting discovery of uncertain regions. To address this pitfall, we introduce the General Exploratory Bonus (GEB), a novel theoretical framework that provably satisfies the optimism principle. GEB counteracts divergence-induced bias via reference-dependent reward regulation and unifies prior heuristic bonuses as special cases, while extending naturally across the full $\alpha$-divergence family. Empirically, GEB consistently outperforms baselines on alignment tasks across multiple divergence settings and large language model backbones. These results demonstrate that GEB offers both a principled and practical solution for optimistic exploration in RLHF. - oai:arXiv.org:2510.03269v3 - cs.LG - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Wendi Li, Changdae Oh, Sharon Li - - - Adversarial Agent Collaboration for C to Rust Translation - https://arxiv.org/abs/2510.03879 - arXiv:2510.03879v2 Announce Type: replace -Abstract: Translating C to memory-safe languages, like Rust, prevents critical memory safety vulnerabilities that are prevalent in legacy C software. Existing approaches for C to safe Rust translation, including LLM-assisted ones, do not generalize on larger (> 500 LoC) C codebases because they depend on complex program analyses that frequently break. In this work, we present ACToR (Adversarial C To Rust translator), a simple LLM agent-based approach. Inspired by GANs, ACToR pits a generator agent against a discriminator agent, which collaborate to iteratively generate a Rust translation. On each iteration, the translator agent synthesizes and refines a Rust translation to pass an existing suite of tests, and then the discriminator agent finds new failing tests. We demonstrate that ACToR translates all of the 63 real-world command-line utilities considered in our benchmarks, which have an average size of 473 lines of code, and it achieves over 90% test pass rate with zero human intervention during translation. To our knowledge, it is the first work to show evidence that an agent-centric approach can reliably and automatically convert standalone command-line C programs at this scale. Furthermore, ACToR improves translation correctness by up to 25.1% compared to baseline, non-adversarial approaches. - oai:arXiv.org:2510.03879v2 - cs.SE - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tianyu Li, Ruishi Li, Bo Wang, Brandon Paulsen, Umang Mathur, Prateek Saxena - - - A Brief History of the Waterfall Model: Past, Present, and Future - https://arxiv.org/abs/2510.03894 - arXiv:2510.03894v2 Announce Type: replace -Abstract: The waterfall model, one of the earliest software development methodologies, has played a foundational role in shaping contemporary software engineering practices. This paper provides a historical and critical overview of the model, tracing its conceptual origins in software engineering, its formalization by Royce, and its evolution through decades of industry adoption and critique. Although often criticized for its rigidity, shortcomings, and high failure rates, the waterfall model persists in specific domains. Its principles continue to influence contemporary hybrid development frameworks that combine traditional and agile methods. Drawing on a range of scholarly sources, this study synthesizes key developments in the perception and application of the waterfall model. The analysis highlights how the model has shifted from a standalone framework to a component within modern hybrid methodologies. By revisiting its origins, assessing its present utility, and examining its role in contemporary development practices, this paper argues that the waterfall model remains relevant, not as a relic of the past but as part of context-aware development strategies. The paper contends that the model's enduring relevance lies in its adaptability. By recognizing both its limitations and its strengths, and by understanding its integration within hybrid approaches, practitioners can make more informed decisions about methodology selection and process design in diverse development environments. - oai:arXiv.org:2510.03894v2 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1145/3783862.3783879 - Antonios Saravanos (New York University) - - - AgriGPT-VL: Agricultural Vision-Language Understanding Suite - https://arxiv.org/abs/2510.04002 - arXiv:2510.04002v3 Announce Type: replace -Abstract: Despite rapid advances in multimodal large language models, agricultural applications remain constrained by the scarcity of domain-tailored models, curated vision-language corpora, and rigorous evaluation. To address these challenges, we present the AgriGPT-VL Suite, a unified multimodal framework for agriculture. Our contributions are threefold. First, we introduce Agri-3M-VL, the largest vision-language corpus for agriculture to our knowledge, curated by a scalable multi-agent data generator; it comprises 1M image-caption pairs, 2M image-grounded VQA pairs, 50K expert-level VQA instances, and 15K GRPO reinforcement learning samples. Second, we develop AgriGPT-VL, an agriculture-specialized vision-language model trained via a progressive curriculum of textual grounding, multimodal shallow/deep alignment, and GRPO refinement. This method achieves strong multimodal reasoning while preserving text-only capability. Third, we establish AgriBench-VL-4K, a compact yet challenging evaluation suite with open-ended and image-grounded questions, paired with multi-metric evaluation and an LLM-as-a-judge framework. Experiments show that AgriGPT-VL outperforms leading general-purpose VLMs on AgriBench-VL-4K, achieving higher pairwise win rates in the LLM-as-a-judge evaluation. Meanwhile, it remains competitive on the text-only AgriBench-13K with no noticeable degradation of language ability. Ablation studies further confirm consistent gains from our alignment and GRPO refinement stages. We will open source all of the resources to support reproducible research and deployment in low-resource agricultural settings. - oai:arXiv.org:2510.04002v3 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bo Yang, Yunkui Chen, Lanfei Feng, Yu Zhang, Xiao Xu, Jianyu Zhang, Nueraili Aierken, Runhe Huang, Hongjian Lin, Yibin Ying, Shijian Li - - - Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization - https://arxiv.org/abs/2510.04182 - arXiv:2510.04182v2 Announce Type: replace -Abstract: Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent reasoning can be brittle on challenging, out-of-distribution tasks where robust reasoning is most critical. To overcome these limitations, we introduce Latent Thought Policy Optimization (LTPO), a parameter-free framework that enhances LLM reasoning entirely at test time, without requiring model parameter updates. LTPO treats intermediate latent "thought" vectors as dynamic parameters that are actively optimized for each problem instance. It employs an online policy gradient method guided by an intrinsic, confidence-based reward signal computed directly from the frozen LLM's own output distributions, eliminating the need for external supervision or expensive text generation during optimization. Extensive experiments on five reasoning benchmarks show that LTPO not only matches or surpasses strong baselines on standard tasks but also demonstrates remarkable robustness where others fail. Most notably, on highly challenging AIME benchmarks where existing latent reasoning baselines collapse to near-zero accuracy, LTPO delivers substantial improvements, showcasing a unique capability for complex reasoning. - oai:arXiv.org:2510.04182v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wengao Ye, Yan Liang, Lianlei Shan - - - Internal World Models as Imagination Networks in Cognitive Agents - https://arxiv.org/abs/2510.04391 - arXiv:2510.04391v3 Announce Type: replace -Abstract: The computational role of imagination remains debated. While classical accounts emphasize reward maximization, emerging evidence suggests imagination serves a broader function: accessing internal world models (IWMs). Here, we employ psychological network analysis to compare IWMs in humans and large language models (LLMs) through imagination vividness ratings. Using the Vividness of Visual Imagery Questionnaire (VVIQ-2) and Plymouth Sensory Imagery Questionnaire (PSIQ), we construct imagination networks from three human populations (Florida, Poland, London; N=2,743) and six LLM variants in two conversation conditions. Human imagination networks demonstrate robust correlations across centrality measures (expected influence, strength, closeness) and consistent clustering patterns, indicating shared structural organization of IWMs across populations. In contrast, LLM-derived networks show minimal clustering and weak centrality correlations, even when manipulating conversational memory. These systematic differences persist across environmental scenes (VVIQ-2) and sensory modalities (PSIQ), revealing fundamental disparities between human and artificial world models. Our network-based approach provides a quantitative framework for comparing internally-generated representations across cognitive agents, with implications for developing human-like imagination in artificial intelligence systems. - oai:arXiv.org:2510.04391v3 - cs.AI - cs.CL - cs.SI - q-bio.NC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Saurabh Ranjan, Brian Odegaard - - - CMOS 2.0 -- Redefining the Future of Scaling - https://arxiv.org/abs/2510.04535 - arXiv:2510.04535v2 Announce Type: replace -Abstract: We propose to revisit the functional scaling paradigm by capitalizing on two recent developments in advanced chip manufacturing, namely 3D wafer bonding and backside processing. This approach leads to the proposal of the CMOS 2.0 platform. The main idea is to shift the CMOS roadmap from geometric scaling to fine-grain heterogeneous 3D stacking of specialized active device layers to achieve the ultimate Power-Performance-Area and Cost gains expected from future technology generations. However, the efficient utilization of such a platform requires devising architectures that can optimally map onto this technology, as well as the EDA infrastructure that supports it. We also discuss reliability concerns and eventual mitigation approaches. This paper provides pointers into the major disruptions we expect in the design of systems in CMOS 2.0 moving forward. - oai:arXiv.org:2510.04535v2 - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Moritz Brunion, Navaneeth Kunhi Purayil, Francesco Dell'Atti, Sebastian Lam, Refik Bilgic, Mehdi Tahoori, Luca Benini, Julien Ryckaert - - - Building Gradient by Gradient: Decentralised Energy Functions for Bimanual Robot Assembly - https://arxiv.org/abs/2510.04696 - arXiv:2510.04696v2 Announce Type: replace -Abstract: There are many challenges in bimanual assembly, including high-level sequencing, multi-robot coordination, and low-level, contact-rich operations such as component mating. Task and motion planning (TAMP) methods, while effective in this domain, may be prohibitively slow to converge when adapting to disturbances that require new task sequencing and optimisation. These events are common during tight-tolerance assembly, where difficult-to-model dynamics such as friction or deformation require rapid replanning and reattempts. Moreover, defining explicit task sequences for assembly can be cumbersome, limiting flexibility when task replanning is required. To simplify this planning, we introduce a decentralised gradient-based framework that uses a piecewise continuous energy function through the automatic composition of adaptive potential functions. This approach generates sub-goals using only myopic optimisation, rather than long-horizon planning. It demonstrates effectiveness at solving long-horizon tasks due to the structure and adaptivity of the energy function. We show that our approach scales to physical bimanual assembly tasks for constructing tight-tolerance assemblies. In these experiments, we discover that our gradient-based rapid replanning framework generates automatic retries, coordinated motions and autonomous handovers in an emergent fashion. - oai:arXiv.org:2510.04696v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alexander L. Mitchell, Joe Watson, Ingmar Posner - - - Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization - https://arxiv.org/abs/2510.05038 - arXiv:2510.05038v2 Announce Type: replace -Abstract: Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm have massively scaled the sizes of their query and document representations, presenting obstacles to deployment and scalability in real-world pipelines. Furthermore, purely vision-centric approaches may be constrained by the inherent modality gap still exhibited by modern vision-language models. In this work, we connect these challenges to the paradigm of hybrid retrieval, investigating whether a lightweight dense text retriever can enhance a stronger vision-centric model. Existing hybrid methods, which rely on coarse-grained fusion of ranks or scores, fail to exploit the rich interactions within each model's representation space. To address this, we introduce Guided Query Refinement (GQR), a novel test-time optimization method that refines a primary retriever's query embedding using guidance from a complementary retriever's scores. Through extensive experiments on visual document retrieval benchmarks, we demonstrate that GQR allows vision-centric models to match the performance of models with significantly larger representations, while being up to 14x faster and requiring 54x less memory. Our findings show that GQR effectively pushes the Pareto frontier for performance and efficiency in multimodal retrieval. We release our code at https://github.com/IBM/test-time-hybrid-retrieval - oai:arXiv.org:2510.05038v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Omri Uzan, Asaf Yehudai, Roi pony, Eyal Shnarch, Ariel Gera - - - SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs - https://arxiv.org/abs/2510.05069 - arXiv:2510.05069v2 Announce Type: replace -Abstract: Recent work shows that, beyond discrete reasoning through explicit chain-of-thought steps, which are limited by the boundaries of natural languages, large language models (LLMs) can also reason continuously in latent space, allowing richer information per step and thereby improving token efficiency. Despite this promise, latent reasoning still faces two challenges, especially in training-free settings: 1) purely latent reasoning broadens the search distribution by maintaining multiple implicit paths, which diffuses probability mass, introduces noise, and impedes convergence to a single high-confidence solution, thereby hurting accuracy; and 2) overthinking persists even without explicit text, wasting tokens and degrading efficiency. To address these issues, we introduce SwiReasoning, a training-free framework for LLM reasoning which features two key innovations: 1) SwiReasoning dynamically switches between explicit and latent reasoning, guided by block-wise confidence estimated from entropy trends in next-token distributions, to balance exploration and exploitation and promote timely convergence. 2) By limiting the maximum number of thinking-block switches, SwiReasoning curbs overthinking and improves token efficiency across varying problem difficulties. On widely used mathematics and STEM benchmarks, SwiReasoning consistently improves average accuracy by 1.5%-2.8% across reasoning LLMs of different model families and scales. Furthermore, under constrained budgets, SwiReasoning improves average token efficiency by 56%-79%, with larger gains as budgets tighten. - oai:arXiv.org:2510.05069v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Dachuan Shi, Abedelkadir Asi, Keying Li, Xiangchi Yuan, Leyan Pan, Wenke Lee, Wen Xiao - - - TRepLiNa: Layer-wise CKA+REPINA Alignment Improves Low-Resource Machine Translation in Aya-23 8B - https://arxiv.org/abs/2510.06249 - arXiv:2510.06249v4 Announce Type: replace -Abstract: The 2025 Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo) Language Challenge addresses one of India's most pressing linguistic gaps: the lack of resources for its diverse low-resource languages (LRLs). In this study, we investigate whether enforcing cross-lingual similarity in specific internal layers of a decoder-only multilingual large language model (LLM) can improve translation quality from LRL to high-resource language (HRL). Specifically, we combine Centered Kernel Alignment (CKA), a similarity metric that encourages representations of different languages to align, with REPINA, a regularization method that constrains parameter updates to remain close to the pretrained model, into a joint method we call TRepLiNa. In this research project, we experiment with zero-shot, few-shot, and fine-tuning settings using Aya-23 8B with QLoRA across MMLoSo shared task language pairs (Mundari, Santali, Bhili) with Hindi/English pivots. Our results show that aligning mid-level layers using TRepLiNa (CKA+REPINA) is a low-cost, practical approach to improving LRL translation, especially in data-scarce settings. - oai:arXiv.org:2510.06249v4 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Toshiki Nakai, Ravi Kiran Chikkala, Lena Sophie Oberkircher, Nicholas Jennings, Natalia Skachkova, Tatiana Anikina, Jesujoba Oluwadara Alabi - - - Algorithm for constructing optimal explicit finite-difference formulas in the Hilbert space - https://arxiv.org/abs/2510.06643 - arXiv:2510.06643v3 Announce Type: replace -Abstract: This work presents problems of constructing finite-difference formulas in the Hilbert space, i.e., setting problems of constructing finite-difference formulas using functional methods. The work presents a functional statement of the problem of optimizing finite-difference formulas in the space $W_{2}^{\left(m,m-1\right)} \left(0,1\right)$. Here, representations of optimal coefficients of explicit finite-difference formulas of the Adams type on classes $W_{2}^{\left(m,m-1\right)} \left(0,1\right)$ for any $m\ge 3$ will be found. - oai:arXiv.org:2510.06643v3 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kh. M. Shadimetov, R. S. Karimov - - - Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving - https://arxiv.org/abs/2510.06784 - arXiv:2510.06784v2 Announce Type: replace -Abstract: In this report, we compare the performance of our UltraGroth-based zero-knowledge machine learning framework Bionetta to other tools of similar purpose such as EZKL, Lagrange's deep-prove, or zkml. The results show a significant boost in the proving time for custom-crafted neural networks: they can be proven even on mobile devices, enabling numerous client-side proving applications. While our scheme increases the cost of one-time preprocessing steps, such as circuit compilation and generating trusted setup, our approach is, to the best of our knowledge, the only one that is deployable on the native EVM smart contracts without overwhelming proof size and verification overheads. - oai:arXiv.org:2510.06784v2 - cs.CR - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Dmytro Zakharov, Oleksandr Kurbatov, Artem Sdobnov, Lev Soukhanov, Yevhenii Sekhin, Vitalii Volovyk, Mykhailo Velykodnyi, Mark Cherepovskyi, Kyrylo Baibula, Lasha Antadze, Pavlo Kravchenko, Volodymyr Dubinin, Yaroslav Panasenko - - - Extreme Amodal Face Detection - https://arxiv.org/abs/2510.06791 - arXiv:2510.06791v2 Announce Type: replace -Abstract: Extreme amodal detection is the task of inferring the 2D location of objects that are not fully visible in the input image but are visible within an expanded field-of-view. This differs from amodal detection, where the object is partially visible within the input image, but is occluded. In this paper, we consider the sub-problem of face detection, since this class provides motivating applications involving safety and privacy, but do not tailor our method specifically to this class. Existing approaches rely on image sequences so that missing detections may be interpolated from surrounding frames or make use of generative models to sample possible completions. In contrast, we consider the single-image task and propose a more efficient, sample-free approach that makes use of the contextual cues from the image to infer the presence of unseen faces. We design a heatmap-based extreme amodal object detector that addresses the problem of efficiently predicting a lot (the out-of-frame region) from a little (the image) with a selective coarse-to-fine decoder. Our method establishes strong results for this new task, even outperforming less efficient generative approaches. Code, data, and models are available at https://charliesong1999.github.io/exaft_web/. - oai:arXiv.org:2510.06791v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Changlin Song, Yunzhong Hou, Michael Randall Barnes, Rahul Shome, Dylan Campbell - - - ReSplat: Learning Recurrent Gaussian Splats - https://arxiv.org/abs/2510.08575 - arXiv:2510.08575v2 Announce Type: replace -Abstract: While feed-forward Gaussian splatting models offer computational efficiency and can generalize to sparse input settings, their performance is fundamentally constrained by relying on a single forward pass for inference. We propose ReSplat, a feed-forward recurrent Gaussian splatting model that iteratively refines 3D Gaussians without explicitly computing gradients. Our key insight is that the Gaussian splatting rendering error serves as a rich feedback signal, guiding the recurrent network to learn effective Gaussian updates. This feedback signal naturally adapts to unseen data distributions at test time, enabling robust generalization across datasets, view counts and image resolutions. To initialize the recurrent process, we introduce a compact reconstruction model that operates in a $16 \times$ subsampled space, producing $16 \times$ fewer Gaussians than previous per-pixel Gaussian models. This substantially reduces computational overhead and allows for efficient Gaussian updates. Extensive experiments across varying of input views (2, 8, 16, 32), resolutions ($256 \times 256$ to $540 \times 960$), and datasets (DL3DV, RealEstate10K and ACID) demonstrate that our method achieves state-of-the-art performance while significantly reducing the number of Gaussians and improving the rendering speed. Our project page is at https://haofeixu.github.io/resplat/. - oai:arXiv.org:2510.08575v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys - - - Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference - https://arxiv.org/abs/2510.10072 - arXiv:2510.10072v2 Announce Type: replace -Abstract: Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remains underexplored. In this paper, we introduce Unilaw-R1, a large language model tailored for legal reasoning. With a lightweight 7-billion parameter scale, Unilaw-R1 significantly reduces deployment cost while effectively tackling three core challenges in the legal domain: insufficient legal knowledge, unreliable reasoning logic, and weak business generalization. To address these issues, we first construct Unilaw-R1-Data, a high-quality dataset containing 17K distilled and screened chain-of-thought (CoT) samples. Based on this, we adopt a two-stage training strategy combining Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), which significantly boosts the performance on complex legal reasoning tasks and supports interpretable decision-making in legal AI applications. To assess legal reasoning ability, we also introduce Unilaw-R1-Eval, a dedicated benchmark designed to evaluate models across single- and multi-choice legal tasks. Unilaw-R1 demonstrates strong results on authoritative benchmarks, outperforming all models of similar scale and achieving performance on par with the much larger DeepSeek-R1-Distill-Qwen-32B (54.9%). Following domain-specific training, it also showed significant gains on LawBench and LexEval, exceeding Qwen-2.5-7B-Instruct (46.6%) by an average margin of 6.6%. - oai:arXiv.org:2510.10072v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hua Cai, Shuang Zhao, Liang Zhang, Xuli Shen, Qing Xu, Weilin Shen, Zihao Wen, Tianke Ban - - - Dejavu: Towards Experience Feedback Learning for Embodied Intelligence - https://arxiv.org/abs/2510.10181 - arXiv:2510.10181v2 Announce Type: replace -Abstract: Embodied agents face a fundamental limitation: once deployed in real-world environments to perform specific tasks, they are unable to acquire additional knowledge to enhance task performance. In this paper, we propose a general post-deployment learning framework Dejavu, which employs an Experience Feedback Network (EFN) and augments the frozen Vision-Language-Action (VLA) policy with retrieved execution memories. EFN identifies contextually prior action experiences and conditions action prediction on this retrieved guidance. We adopt reinforcement learning with semantic similarity rewards to train EFN, ensuring that the predicted actions align with past behaviors under current observations. During deployment, EFN continually enriches its memory with new trajectories, enabling the agent to exhibit "learning from experience". Experiments across diverse embodied tasks show that EFN improves adaptability, robustness, and success rates over frozen baselines. We provide code and demo in our supplementary material. - oai:arXiv.org:2510.10181v2 - cs.RO - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shaokai Wu, Yanbiao Ji, Qiuchang Li, Zhiyi Zhang, Qichen He, Wenyuan Xie, Guodong Zhang, Bayram Bayramli, Yue Ding, Hongtao Lu - - - Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers - https://arxiv.org/abs/2510.10645 - arXiv:2510.10645v3 Announce Type: replace -Abstract: Retrosynthesis is one of the domains transformed by the rise of generative models, and it is one where the problem of nonsensical or erroneous outputs (hallucinations) is particularly insidious: reliable assessment of synthetic plans is time-consuming, with automatic methods lacking. In this work, we present RetroTrim, a retrosynthesis system that successfully avoids nonsensical plans on a set of challenging drug-like targets. Compared to common baselines in the field, our system is not only the sole method that succeeds in filtering out hallucinated reactions, but it also results in the highest number of high-quality paths overall. The key insight behind RetroTrim is the combination of diverse reaction scoring strategies, based on machine learning models and existing chemical databases. We show that our scoring strategies capture different classes of hallucinations by analyzing them on a dataset of labeled retrosynthetic intermediates. This approach formed the basis of our winning solution to the Standard Industries \$1 million Retrosynthesis Challenge. To measure the performance of retrosynthesis systems, we propose a novel evaluation protocol for reactions and synthetic paths based on a structured review by expert chemists. Using this protocol, we compare systems on a set of 32 novel targets, curated to reflect recent trends in drug structures. While the insights behind our methodology are broadly applicable to retrosynthesis, our focus is on targets in the drug-like domain. By releasing our benchmark targets and the details of our evaluation protocol, we hope to inspire further research into reliable retrosynthesis. - oai:arXiv.org:2510.10645v3 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Michal Sadowski, Tadija Radusinovi\'c, Maria Wyrzykowska, Lukasz Sztukiewicz, Jan Rzymkowski, Pawe{\l} W{\l}odarczyk-Pruszy\'nski, Miko{\l}aj Sacha, Piotr Kozakowski, Ruard van Workum, Stanislaw Kamil Jastrzebski - - - Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis - https://arxiv.org/abs/2510.12175 - arXiv:2510.12175v4 Announce Type: replace -Abstract: Recent advances in diffusion-based generative models have enabled high-quality text-to-audio synthesis, but fine-grained acoustic control remains a significant challenge in open-source research. We present Audio Palette, a diffusion transformer (DiT) based model that extends the Stable Audio Open architecture to address this "control gap" in controllable audio generation. Unlike prior approaches that rely solely on semantic conditioning, Audio Palette introduces four time-varying control signals, loudness, pitch, spectral centroid, and timbre, for precise and interpretable manipulation of acoustic features. The model is efficiently adapted for the nuanced domain of Foley synthesis using Low-Rank Adaptation (LoRA) on a curated subset of AudioSet, requiring only 0.85% of the original parameters to be trained. Experiments demonstrate that Audio Palette achieves fine-grained, interpretable control of sound attributes. Crucially, it accomplishes this novel controllability while maintaining high audio quality and strong semantic alignment to text prompts, with performance on standard metrics such as Frechet Audio Distance (FAD) and LAION-CLAP scores remaining comparable to the original baseline model. We provide a scalable, modular pipeline for audio research, emphasizing sequence-based conditioning, memory efficiency, and a three-scale classifier-free guidance mechanism for nuanced inference-time control. This work establishes a robust foundation for controllable sound design and performative audio synthesis in open-source settings, enabling a more artist-centric workflow in the broader context of music and sound information retrieval. - oai:arXiv.org:2510.12175v4 - cs.SD - eess.AS - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Junnuo Wang - - - Pretraining in Actor-Critic Reinforcement Learning for Robot Locomotion - https://arxiv.org/abs/2510.12363 - arXiv:2510.12363v2 Announce Type: replace -Abstract: The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to the same robot embodiment. This work aims to define a paradigm for pretraining neural network models that encapsulate such knowledge and can subsequently serve as a basis for warm-starting the RL process in classic actor-critic algorithms, such as Proximal Policy Optimization (PPO). We begin with a task-agnostic exploration-based data collection algorithm to gather diverse, dynamic transition data, which is then used to train a Proprioceptive Inverse Dynamics Model (PIDM) through supervised learning. The pretrained weights are then loaded into both the actor and critic networks to warm-start the policy optimization of actual tasks. We systematically validated our proposed method with 9 distinct robot locomotion RL environments comprising 3 different robot embodiments, showing significant benefits of this initialization strategy. Our proposed approach on average improves sample efficiency by 36.9% and task performance by 7.3% compared to random initialization. We further present key ablation studies and empirical analyses that shed light on the mechanisms behind the effectiveness of this method. - oai:arXiv.org:2510.12363v2 - cs.RO - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiale Fan, Andrei Cramariuc, Tifanny Portela, Marco Hutter - - - Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation - https://arxiv.org/abs/2510.13191 - arXiv:2510.13191v2 Announce Type: replace -Abstract: Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has primarily focused on retrieval quality and prompting strategies, the influence of how the retrieved documents are framed, i.e., context format, remains underexplored. We show that seemingly superficial choices, such as delimiters or structural markers in key-value extraction, can induce substantial shifts in accuracy and stability, even when semantic content is identical. To systematically investigate this effect, we design controlled experiments that vary context density, delimiter styles, and positional placement, revealing the underlying factors that govern performance differences. Building on these insights, we introduce Contextual Normalization, a lightweight strategy that adaptively standardizes context representations before generation. Extensive experiments on both controlled and real-world RAG benchmarks across diverse settings demonstrate that the proposed strategy consistently improves robustness to order variation and strengthens long-context utilization. These findings underscore that reliable RAG depends not only on retrieving the right content, but also on how that content is presented, offering both new empirical evidence and a practical technique for better long-context reasoning. - oai:arXiv.org:2510.13191v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiamin Chen, Yuchen Li, Xinyu Ma, Xinran Chen, Xiaokun Zhang, Shuaiqiang Wang, Chen Ma, Dawei Yin - - - On the prospects of interpolatory spline bases for accurate mass lumping strategies in isogeometric analysis - https://arxiv.org/abs/2510.13510 - arXiv:2510.13510v2 Announce Type: replace -Abstract: While interpolatory bases such as the Lagrange basis form the cornerstone of classical finite element methods, they have been replaced in the more general finite element setting of isogeometric analysis in favor of other desirable properties. Yet, interpolation is a key property for devising accurate mass lumping strategies that are ubiquitous in explicit dynamic analyses of structures. In this article, we explore the possibility of restoring interpolation for spline bases within isogeometric analysis for the purpose of mass lumping. Although reminiscent of the spectral element method, this technique comes with its lot of surprises and challenges, which are critically assessed. - oai:arXiv.org:2510.13510v2 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yannis Voet, Espen Sande - - - UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning - https://arxiv.org/abs/2510.13515 - arXiv:2510.13515v3 Announce Type: replace -Abstract: Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture subtle semantic differences among candidates and lack diversity in negative samples. Moreover, the embeddings exhibit limited discriminative ability in distinguishing false and hard negatives. In this paper, we leverage the advanced understanding capabilities of MLLMs to enhance representation learning and present a novel Universal Multimodal Embedding (UniME-V2) model. Our approach first constructs a potential hard negative set through global retrieval. We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs and generate soft semantic matching scores. These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives. Furthermore, the semantic matching scores are used as soft labels to mitigate the rigid one-to-one mapping constraint. By aligning the similarity matrix with the soft semantic matching score matrix, the model learns semantic distinctions among candidates, significantly enhancing its discriminative capacity. To further improve performance, we propose UniME-V2-Reranker, a reranking model trained on our mined hard negatives through a joint pairwise and listwise optimization approach. We conduct comprehensive experiments on the MMEB benchmark and multiple retrieval tasks, demonstrating that our method achieves state-of-the-art performance on average across all tasks. - oai:arXiv.org:2510.13515v3 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Tiancheng Gu, Kaicheng Yang, Kaichen Zhang, Xiang An, Ziyong Feng, Yueyi Zhang, Weidong Cai, Jiankang Deng, Lidong Bing - - - LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild - https://arxiv.org/abs/2510.14240 - arXiv:2510.14240v4 Announce Type: replace -Abstract: Deep research -- producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources -- marks an important frontier for agentic systems. To rigorously evaluate this ability, four principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, (3) unambiguous, ensuring consistent interpretation across users, and (4) multi-faceted and search-intensive, requiring search over numerous web sources and in-depth analysis. Existing benchmarks fall short of these principles, often focusing on narrow domains or posing ambiguous questions that hinder fair comparison. Guided by these principles, we introduce LiveResearchBench, a benchmark of 100 expert-curated tasks spanning daily life, enterprise, and academia, each requiring extensive, dynamic, real-time web search and synthesis. Built with over 1,500 hours of human labor, LiveResearchBench provides a rigorous basis for systematic evaluation. To evaluate citation-grounded long-form reports, we introduce DeepEval, a comprehensive suite covering both content- and report-level quality, including coverage, presentation, citation accuracy and association, consistency and depth of analysis. DeepEval integrates four complementary evaluation protocols, each designed to ensure stable assessment and high agreement with human judgments. Using LiveResearchBench and DeepEval, we conduct a comprehensive evaluation of 17 frontier deep research systems, including single-agent web search, single-agent deep research, and multi-agent systems. Our analysis reveals current strengths, recurring failure modes, and key system components needed to advance reliable, insightful deep research. Our code is available at: https://github.com/SalesforceAIResearch/LiveResearchBench. - oai:arXiv.org:2510.14240v4 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty - - - First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training - https://arxiv.org/abs/2510.14614 - arXiv:2510.14614v2 Announce Type: replace -Abstract: As training billion-scale transformers becomes increasingly common, employing multiple distributed GPUs along with parallel training methods has become a standard practice. However, existing transformer designs suffer from significant communication overhead, especially in Tensor Parallelism (TP), where each block's MHA-MLP connection requires an all-reduce communication. Through our investigation, we show that the MHA-MLP connections can be bypassed for efficiency, while the attention output of the first layer can serve as an alternative signal for the bypassed connection. Motivated by the observations, we propose FAL (First Attentions Last), an efficient transformer architecture that redirects the first MHA output to the MLP inputs of the following layers, eliminating the per-block MHA-MLP connections. This removes the all-reduce communication and enables parallel execution of MHA and MLP on a single GPU. We also introduce FAL+, which adds the normalized first attention output to the MHA outputs of the following layers to augment the MLP input for the model quality. Our evaluation shows that FAL reduces multi-GPU training time by up to 44%, improves single-GPU throughput by up to 1.18x, and achieves better perplexity compared to the baseline GPT. FAL+ achieves even lower perplexity without increasing the training time than the baseline. Codes are available at: https://github.com/CASL-KU/FAL - oai:arXiv.org:2510.14614v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Gyudong Kim, Hyukju Na, Jin Hyeon Kim, Hyunsung Jang, Jaemin Park, Jaegi Hwang, Namkoo Ha, Seungryong Kim, Young Geun Kim - - - LabOS: The AI-XR Co-Scientist That Sees and Works With Humans - https://arxiv.org/abs/2510.14861 - arXiv:2510.14861v2 Announce Type: replace -Abstract: Modern science advances fastest when thought meets action. LabOS represents the first AI co-scientist that unites computational reasoning with physical experimentation through multimodal perception, self-evolving agents, and Extended-Reality(XR)-enabled human-AI collaboration. By connecting multi-model AI agents, smart glasses, and robots, LabOS allows AI to see what scientists see, understand experimental context, and assist in real-time execution. Across applications -- from cancer immunotherapy target discovery to stem-cell engineering and material science -- LabOS shows that AI can move beyond computational design to participation, turning the laboratory into an intelligent, collaborative environment where human and machine discovery evolve together. - oai:arXiv.org:2510.14861v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Le Cong, David Smerkous, Xiaotong Wang, Di Yin, Zaixi Zhang, Ruofan Jin, Yinkai Wang, Michal Gerasimiuk, Ravi K. Dinesh, Alex Smerkous, Lihan Shi, Joy Zheng, Ian Lam, Xuekun Wu, Shilong Liu, Peishan Li, Yi Zhu, Ning Zhao, Meenal Parakh, Simran Serrao, Imran A. Mohammad, Chao-Yeh Chen, Xiufeng Xie, Tiffany Chen, David Weinstein, Greg Barbone, Belgin Caglar, John B. Sunwoo, Fuxin Li, Jia Deng, Joseph C. Wu, Sanfeng Wu, Mengdi Wang - - - DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management - https://arxiv.org/abs/2510.15087 - arXiv:2510.15087v2 Announce Type: replace -Abstract: Effective and efficient access to relevant information is essential for disaster management. However, no retrieval model is specialized for disaster management, and existing general-domain models fail to handle the varied search intents inherent to disaster management scenarios, resulting in inconsistent and unreliable performance. To this end, we introduce DMRetriever, the first series of dense retrieval models (33M to 7.6B) tailored for this domain. It is trained through a novel three-stage framework of bidirectional attention adaptation, unsupervised contrastive pre-training, and difficulty-aware progressive instruction fine-tuning, using high-quality data generated through an advanced data refinement pipeline. Comprehensive experiments demonstrate that DMRetriever achieves state-of-the-art (SOTA) performance across all six search intents at every model scale. Moreover, DMRetriever is highly parameter-efficient, with 596M model outperforming baselines over 13.3 X larger and 33M model exceeding baselines with only 7.6% of their parameters. All codes, data, and checkpoints are available at https://github.com/KaiYin97/DMRETRIEVER - oai:arXiv.org:2510.15087v2 - cs.IR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Kai Yin, Xiangjue Dong, Chengkai Liu, Allen Lin, Lingfeng Shi, Ali Mostafavi, James Caverlee - - - ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings - https://arxiv.org/abs/2510.15681 - arXiv:2510.15681v2 Announce Type: replace -Abstract: Translating human-written mathematical theorems and proofs from natural language (NL) into formal languages (FLs) like Lean 4 has long been a significant challenge for AI. Most state-of-the-art methods either focus on theorem-only NL-to-FL auto-formalization or on FL proof synthesis from FL theorems. In practice, auto-formalization of both theorem and proof still requires human intervention, as seen in AlphaProof's silver-medal performance at the 2024 IMO, where problem statements were manually translated before automated proof synthesis. - We present ProofBridge, a unified framework for automatically translating entire NL theorems and proofs into Lean 4. At its core is a joint embedding model that aligns NL and FL (NL-FL) theorem-proof pairs in a shared semantic space, enabling cross-modal retrieval of semantically relevant FL examples to guide translation. Our training ensures that NL-FL theorems (and their proofs) are mapped close together in this space if and only if the NL-FL pairs are semantically equivalent. ProofBridge integrates retrieval-augmented fine-tuning with iterative proof repair, leveraging Lean's type checker and semantic equivalence feedback to ensure both syntactic correctness and semantic fidelity. Experiments show substantial improvements in proof auto-formalization over strong baselines (including GPT-5, Gemini-2.5, Kimina-Prover, DeepSeek-Prover), with our retrieval-augmented approach yielding significant gains in semantic correctness (SC, via proving bi-directional equivalence) and type correctness (TC, via type-checking theorem+proof) across pass@k metrics on miniF2F-Test-PF, a dataset we curated. In particular, ProofBridge improves cross-modal retrieval quality by up to 3.28x Recall@1 over all-MiniLM-L6-v2, and achieves +31.14% SC and +1.64% TC (pass@32) compared to the baseline Kimina-Prover-RL-1.7B. - oai:arXiv.org:2510.15681v2 - cs.LO - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Prithwish Jana, Kaan Kale, Ahmet Ege Tanriverdi, Cruise Song, Sriram Vishwanath, Vijay Ganesh - - - First Responders' Perceptions of Semantic Information for Situational Awareness in Robot-Assisted Emergency Response - https://arxiv.org/abs/2510.16692 - arXiv:2510.16692v2 Announce Type: replace -Abstract: This study investigates First Responders' (FRs) attitudes toward the use of semantic information and Situational Awareness (SA) in robotic systems during emergency operations. A structured questionnaire was administered to 22 FRs across eight countries, capturing their demographic profiles, general attitudes toward robots, and experiences with semantics-enhanced SA. Results show that most FRs expressed positive attitudes toward robots, and rated the usefulness of semantic information for building SA at an average of 3.6 out of 5. Semantic information was also valued for its role in predicting unforeseen emergencies (mean 3.9). Participants reported requiring an average of 74.6\% accuracy to trust semantic outputs and 67.8\% for them to be considered useful, revealing a willingness to use imperfect but informative AI support tools. - To the best of our knowledge, this study offers novel insights by being one of the first to directly survey FRs on semantic-based SA in a cross-national context. It reveals the types of semantic information most valued in the field, such as object identity, spatial relationships, and risk context-and connects these preferences to the respondents' roles, experience, and education levels. The findings also expose a critical gap between lab-based robotics capabilities and the realities of field deployment, highlighting the need for more meaningful collaboration between FRs and robotics researchers. These insights contribute to the development of more user-aligned and situationally aware robotic systems for emergency response. - oai:arXiv.org:2510.16692v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Tianshu Ruan, Zoe Betta, Georgios Tzoumas, Rustam Stolkin, Manolis Chiou - - - Lark: Biologically Inspired Neuroevolution for Multi-Stakeholder LLM Agents - https://arxiv.org/abs/2510.16978 - arXiv:2510.16978v2 Announce Type: replace -Abstract: We present Lark, a biologically inspired decision-making framework that couples LLM-driven reasoning with an evolutionary, stakeholder-aware Multi-Agent System (MAS). To address verbosity and stakeholder trade-offs, we integrate four mechanisms: (i) plasticity, which applies concise adjustments to candidate solutions; (ii) duplication and maturation, which copy high-performing candidates and specialize them into new modules; (iii) ranked-choice stakeholder aggregation using influence-weighted Borda scoring; and (iv) compute awareness via token-based penalties that reward brevity. The system iteratively proposes diverse strategies, applies plasticity tweaks, simulates stakeholder evaluations, aggregates preferences, selects top candidates, and performs duplication/maturation while factoring compute cost into final scores. In a controlled evaluation over 30 rounds comparing 14 systems, Lark Full achieves a mean rank of 2.55 (95% CI [2.17, 2.93]) and a mean composite score of 29.4/50 (95% CI [26.34, 32.46]), finishing Top-3 in 80% of rounds while remaining cost competitive with leading commercial models ($0.016 per task). Paired Wilcoxon tests confirm that all four mechanisms contribute significantly as ablating duplication/maturation yields the largest deficit ({\Delta}Score = 3.5, Cohen's d_z = 2.53, p < 0.001), followed by plasticity ({\Delta}Score = 3.4, d_z = 1.86), ranked-choice voting ({\Delta}Score = 2.4, d_z = 1.20), and token penalties ({\Delta}Score = 2.2, d_z = 1.63). Rather than a formal Markov Decision Process with constrained optimization, Lark is a practical, compute-aware neuroevolutionary loop that scales stakeholder-aligned strategy generation and makes trade-offs transparent through per-step metrics. Our work presents proof-of-concept findings and invites community feedback as we expand toward real-world validation studies. - oai:arXiv.org:2510.16978v2 - cs.MA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Dheeraj Chintapalli, Rikhil Tanugula, Sunkalp Chandra - - - On the Capacity of Erasure-prone Quantum Storage with Erasure-prone Entanglement Assistance - https://arxiv.org/abs/2510.17781 - arXiv:2510.17781v2 Announce Type: replace -Abstract: A quantum message is encoded into $N$ storage nodes (quantum systems $Q_1\dots Q_N$) with assistance from $N_B$ maximally entangled bi-partite quantum systems $A_1B_1, \dots, A_{N_B}B_{N_B}$, that are prepared in advance such that $B_1\dots B_{N_B}$ are stored separately as entanglement assistance (EA) nodes, while $A_1\dots A_{N_B}$ are made available to the encoder. Both the storage nodes and EA nodes are erasure-prone. The quantum message must be recoverable given any $K$ of the $N$ storage nodes along with any $K_B$ of the $N_B$ EA nodes. The capacity for this setting is the maximum size of the quantum message, given that the size of each EA node is $\lambda_B$. All node sizes are relative to the size of a storage node, which is normalized to unity. The exact capacity is characterized as a function of $N,K,N_B,K_B, \lambda_B$ in all cases, with one exception. The capacity remains open for an intermediate range of $\lambda_B$ values when a strict majority of the $N$ storage nodes, and a strict non-zero minority of the $N_B$ EA nodes, are erased. As a key stepping stone, an analogous classical storage (with shared-randomness assistance) problem is introduced. A set of constraints is identified for the classical problem, such that classical linear code constructions translate to quantum storage codes, and the converse bounds for the two settings utilize similar insights. In particular, the capacity characterizations for the classical and quantum settings are shown to be identical in all cases where the capacity is settled. - oai:arXiv.org:2510.17781v2 - cs.IT - math.IT - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hua Sun, Syed A. Jafar - - - From Observations to Parameters: Detecting Changepoint in Nonlinear Dynamics with Simulation-based Inference - https://arxiv.org/abs/2510.17933 - arXiv:2510.17933v2 Announce Type: replace -Abstract: Detecting regime shifts in chaotic time series is hard because observation-space signals are entangled with intrinsic variability. We propose Parameter--Space Changepoint Detection (Param--CPD), a two--stage framework that first amortizes Bayesian inference of governing parameters with a neural posterior estimator trained by simulation-based inference, and then applies a standard CPD algorithm to the resulting parameter trajectory. On Lorenz--63 with piecewise-constant parameters, Param--CPD improves F1, reduces localization error, and lowers false positives compared to observation--space baselines. We further verify identifiability and calibration of the inferred posteriors on stationary trajectories, explaining why parameter space offers a cleaner detection signal. Robustness analyses over tolerance, window length, and noise indicate consistent gains. Our results show that operating in a physically interpretable parameter space enables accurate and interpretable changepoint detection in nonlinear dynamical systems. - oai:arXiv.org:2510.17933v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiangbo Deng, Cheng Chen, Peng Yang - - - PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions - https://arxiv.org/abs/2510.19060 - arXiv:2510.19060v2 Announce Type: replace -Abstract: While vision-language models (VLMs) have advanced into detailed image description, evaluation remains a challenge. Standard metrics (e.g. CIDEr, SPICE) were designed for short texts and tuned to recognize errors that are now uncommon, such as object misidentification. In contrast, long texts require sensitivity to attribute and relation attachments and scores that localize errors to particular text spans. In this work, we introduce PoSh, a metric for detailed image description that uses scene graphs as structured rubrics to guide LLMs-as-a-Judge, producing aggregate scores grounded in fine-grained errors (e.g. mistakes in compositional understanding). PoSh is replicable, interpretable and a better proxy for human raters than existing metrics (including GPT4o-as-a-Judge). To validate PoSh, we introduce a challenging new dataset, DOCENT. This novel benchmark contains artwork, paired with expert-written references, and model-generated descriptions, augmented with granular and coarse judgments of their quality from art history students. Thus, DOCENT enables evaluating both detailed image description metrics and detailed image description itself in a challenging new domain. We show that PoSh achieves stronger correlations (+0.05 Spearman $\rho$) with the human judgments in DOCENT than the best open-weight alternatives, is robust to image type (using CapArena, an existing dataset of web imagery) and is a capable reward function, outperforming standard supervised fine-tuning. Then, using PoSh, we characterize the performance of open and closed models in describing the paintings, sketches and statues in DOCENT and find that foundation models struggle to achieve full, error-free coverage of images with rich scene dynamics, establishing a demanding new task to gauge VLM progress. Through both PoSh and DOCENT, we hope to enable advances in important areas such as assistive text generation. - oai:arXiv.org:2510.19060v2 - cs.CV - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Amith Ananthram, Elias Stengel-Eskin, Lorena A. Bradford, Julia Demarest, Adam Purvis, Keith Krut, Robert Stein, Rina Elster Pantalony, Mohit Bansal, Kathleen McKeown - - - FootFormer: Estimating Stability from Visual Input - https://arxiv.org/abs/2510.19170 - arXiv:2510.19170v2 Announce Type: replace -Abstract: We propose FootFormer, a cross-modality approach for jointly predicting human motion dynamics directly from visual input. On multiple datasets, FootFormer achieves statistically significantly better or equivalent estimates of foot pressure distributions, foot contact maps, and center of mass (CoM), as compared with existing methods that generate one or two of those measures. Furthermore, FootFormer achieves SOTA performance in estimating stability-predictive components (CoP, CoM, BoS) used in classic kinesiology metrics. Code and data are available at https://github.com/keatonkraiger/Vision-to-Stability.git. - oai:arXiv.org:2510.19170v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Keaton Kraiger, Jingjing Li, Skanda Bharadwaj, Jesse Scott, Robert T. Collins, Yanxi Liu - - - QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation - https://arxiv.org/abs/2510.19296 - arXiv:2510.19296v4 Announce Type: replace -Abstract: The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design. The lacking of meaningful functional rewards hinders the preference optimization based on Reinforcement Learning (RL) for producing functionally correct Verilog code. In this paper, we propose Signal-Aware Learning for Verilog code generation (QiMeng-SALV) by leveraging code segments of functionally correct output signal to optimize RL training. Considering Verilog code specifies the structural interconnection of hardware gates and wires so that different output signals are independent, the key insight of QiMeng-SALV is to extract verified signal-aware implementations in partially incorrect modules, so as to enhance the extraction of meaningful functional rewards. Roughly, we verify the functional correctness of signals in generated module by comparing with that of reference module in the training data. Then abstract syntax tree (AST) is employed to identify signal-aware code segments which can provide meaningful functional rewards from erroneous modules. Finally, we introduce signal-aware DPO which is optimized on the correct signal-level code segments, thereby preventing noise and interference from incorrect signals. The proposed QiMeng-SALV underscores the paradigm shift from conventional module-level to fine-grained signal-level optimization in Verilog code generation, addressing the issue of insufficient functional rewards. Experiments demonstrate that our method achieves state-of-the-art performance on VerilogEval and RTLLM, with a 7B parameter model matching the performance of the DeepSeek v3 671B model and significantly outperforming the leading open-source model CodeV trained on the same dataset. Our code is available at https://github.com/QiMeng-IPRC/QiMeng-SALV. - oai:arXiv.org:2510.19296v4 - cs.LG - cs.AR - cs.PL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yang Zhang, Rui Zhang, Jiaming Guo, Lei Huang, Di Huang, Yunpu Zhao, Shuyao Cheng, Pengwei Jin, Chongxiao Li, Zidong Du, Xing Hu, Qi Guo, Yunji Chen - - - Self-diffusion for Solving Inverse Problems - https://arxiv.org/abs/2510.21417 - arXiv:2510.21417v2 Announce Type: replace -Abstract: We propose self-diffusion, a novel framework for solving inverse problems without relying on pretrained generative models. Traditional diffusion-based approaches require training a model on a clean dataset to learn to reverse the forward noising process. This model is then used to sample clean solutions -- corresponding to posterior sampling from a Bayesian perspective -- that are consistent with the observed data under a specific task. In contrast, self-diffusion introduces a self-contained iterative process that alternates between noising and denoising steps to progressively refine its estimate of the solution. At each step of self-diffusion, noise is added to the current estimate, and a self-denoiser, which is a single untrained convolutional network randomly initialized from scratch, is continuously trained for certain iterations via a data fidelity loss to predict the solution from the noisy estimate. Essentially, self-diffusion exploits the spectral bias of neural networks and modulates it through a scheduled noise process. Without relying on pretrained score functions or external denoisers, this approach still remains adaptive to arbitrary forward operators and noisy observations, making it highly flexible and broadly applicable. We demonstrate the effectiveness of our approach on a variety of linear inverse problems, showing that self-diffusion achieves competitive or superior performance compared to other methods. - oai:arXiv.org:2510.21417v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Guanxiong Luo, Shoujin Huang, Yanlong Yang - - - K-DAREK: Distance Aware Error for Kurkova Kolmogorov Networks - https://arxiv.org/abs/2510.22021 - arXiv:2510.22021v2 Announce Type: replace -Abstract: Neural networks are powerful parametric function approximators, while Gaussian processes (GPs) are nonparametric probabilistic models that place distributions over functions via kernel-defined correlations but become computationally expensive for large-scale problems. Kolmogorov-Arnold networks (KANs), semi-parametric neural architectures, model complex functions efficiently using spline layers. Kurkova Kolmogorov-Arnold networks (KKANs) extend KANs by replacing the early spline layers with multi-layer perceptrons that map inputs into higher-dimensional spaces before applying spline-based transformations, which yield more stable training and provide robust architectures for system modeling. By enhancing the KKAN architecture, we develop a novel learning algorithm, distance-aware error for Kurkova-Kolmogorov networks (K-DAREK), for efficient and interpretable function approximation with uncertainty quantification. Our approach establishes robust error bounds that are distance-aware; this means they reflect the proximity of a test point to its nearest training points. In safe control case studies, we demonstrate that K-DAREK is about four times faster and ten times more computationally efficient than Ensemble of KANs, 8.6 times more scalable than GP as data size increases, and 7.2% safer than our previous work distance-aware error for Kolmogorov networks (DAREK). Moreover, on real data (e.g., Real Estate Valuation), K-DAREK's error bound achieves zero coverage violations. - oai:arXiv.org:2510.22021v2 - cs.LG - eess.SP - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Masoud Ataei, Vikas Dhiman, Mohammad Javad Khojasteh - - - Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards - https://arxiv.org/abs/2510.23083 - arXiv:2510.23083v2 Announce Type: replace -Abstract: Generating high-quality code remains a challenge for Large Language Models (LLMs). For the evolution of reasoning models on this task, reward models are a necessary intermediate step. These models judge outcomes or intermediate steps. Decoder-only transformer models can be turned into reward models by introducing a regression layer and supervised fine-tuning. While it is known that reflection capabilities generally increase with the size of a model, we want to investigate whether state-of-the-art small language models like the Phi-4 family can be turned into usable reward models blending the consideration of process rewards and outcome rewards. - Targeting this goal, we construct a dataset of code samples with correctness labels derived from the APPS coding challenge benchmark. We then train a value-head model to estimate the success probability of intermediate outputs. Our evaluation shows that small LLMs are capable of serving as effective reward models or code evaluation critics, successfully identifying correct solutions among multiple candidates. Using this critic, we achieve over a 20% improvement in the search capability of the most accurate code out of multiple generations. - oai:arXiv.org:2510.23083v2 - cs.AI - cs.LG - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jan Niklas Groeneveld, Xi Qin, Alexander Schaefer, Yaad Oren - - - Evaluating Long-Term Memory for Long-Context Question Answering - https://arxiv.org/abs/2510.23730 - arXiv:2510.23730v2 Announce Type: replace -Abstract: In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types of memory are most effective for long-context conversational tasks. We present a systematic evaluation of memory-augmented methods on long-context dialogues annotated for question-answering tasks that require diverse reasoning strategies. We analyse full-context prompting, semantic memory through retrieval-augmented generation and agentic memory, episodic memory through in-context learning, and procedural memory through prompt optimization. Our findings show that memory-augmented approaches reduce token usage by over 90\% while maintaining competitive accuracy. Memory architecture complexity should scale with model capability, with foundation models benefitting most from RAG, and stronger instruction-tuned models gaining from episodic learning through reflections and more complex agentic semantic memory. In particular, episodic memory can help LLMs recognise the limits of their own knowledge. - oai:arXiv.org:2510.23730v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Alessandra Terranova, Bj\"orn Ross, Alexandra Birch - - - TRELLISWorld: Training-Free World Generation from Object Generators - https://arxiv.org/abs/2510.23880 - arXiv:2510.23880v2 Announce Type: replace -Abstract: Text-driven 3D scene generation holds promise for a wide range of applications, from virtual prototyping to AR/VR and simulation. However, existing methods are often constrained to single-object generation, require domain-specific training, or lack support for full 360-degree viewability. In this work, we present a training-free approach to 3D scene synthesis by repurposing general-purpose text-to-3D object diffusion models as modular tile generators. We reformulate scene generation as a multi-tile denoising problem, where overlapping 3D regions are independently generated and seamlessly blended via weighted averaging. This enables scalable synthesis of large, coherent scenes while preserving local semantic control. Our method eliminates the need for scene-level datasets or retraining, relies on minimal heuristics, and inherits the generalization capabilities of object-level priors. We demonstrate that our approach supports diverse scene layouts, efficient generation, and flexible editing, establishing a simple yet powerful foundation for general-purpose, language-driven 3D scene construction. - oai:arXiv.org:2510.23880v2 - cs.CV - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hanke Chen, Yuan Liu, Minchen Li - - - MotionStream: Real-Time Video Generation with Interactive Motion Controls - https://arxiv.org/abs/2511.01266 - arXiv:2511.01266v2 Announce Type: replace -Abstract: Current motion-conditioned video generation methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU. Our approach begins by augmenting a text-to-video model with motion control, which generates high-quality videos that adhere to the global text prompt and local motion guidance, but does not perform inference on the fly. As such, we distill this bidirectional teacher into a causal student through Self Forcing with Distribution Matching Distillation, enabling real-time streaming inference. Several key challenges arise when generating videos of long, potentially infinite time-horizons -- (1) bridging the domain gap from training on finite length and extrapolating to infinite horizons, (2) sustaining high quality by preventing error accumulation, and (3) maintaining fast inference, without incurring growth in computational cost due to increasing context windows. A key to our approach is introducing carefully designed sliding-window causal attention, combined with attention sinks. By incorporating self-rollout with attention sinks and KV cache rolling during training, we properly simulate inference-time extrapolations with a fixed context window, enabling constant-speed generation of arbitrarily long videos. Our models achieve state-of-the-art results in motion following and video quality while being two orders of magnitude faster, uniquely enabling infinite-length streaming. With MotionStream, users can paint trajectories, control cameras, or transfer motion, and see results unfold in real-time, delivering a truly interactive experience. - oai:arXiv.org:2511.01266v2 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Joonghyuk Shin, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Jaesik Park, Eli Shechtman, Xun Huang - - - EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory - https://arxiv.org/abs/2511.01912 - arXiv:2511.01912v2 Announce Type: replace -Abstract: Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these frameworks remains largely unexplored. Understanding how agents coordinate through memory is critical for natural language planning, where iterative reasoning, constraint tracking, and error correction drive the success. Inspired by working memory model in cognitive psychology, we present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism. The framework consists of three agents (Constraint Extractor, Verifier, and Actor) and two memory modules: Constraint Memory (CMem), which evolves across queries by storing task-specific rules and constraints while remains fixed within a query, and Query-feedback Memory (QMem), which evolves within a query by accumulating feedback across iterations for solution refinement. Both memory modules are reset at the end of each query session. Evaluations on trip planning, meeting planning, and calendar scheduling show consistent performance improvements, highlighting the effectiveness of EvoMem. This success underscores the importance of memory in enhancing multi-agent planning. - oai:arXiv.org:2511.01912v2 - cs.MA - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Wenzhe Fan, Ning Yan, Masood Mortazavi - - - MCHex: Marching Cubes Based Adaptive Hexahedral Mesh Generation with Guaranteed Positive Jacobian - https://arxiv.org/abs/2511.02064 - arXiv:2511.02064v2 Announce Type: replace -Abstract: Constructing an adaptive hexahedral tessellation to fit an input triangle boundary is a key challenge in grid-based methods. The conventional method first removes outside elements (RO) and then projects the axis-aligned boundary onto the input triangle boundary, which has no guarantee on improving the initial Intersection over Union (IoU) and Hausdorff distance ratio (HR, w.r.t bounding box diagonal). The proposed MCHex approach replaces RO with a Marching Cubes method MCHex. Given the same computational budget (benchmarked using an identical precomputed Signed Distance Field, which dominates the runtime), MCHex provides better boundary approximation (higher IoU and lower HR) while guaranteeing a lower, yet still positive, minimum scaled Jacobian (>0 vs. RO's >0.48). - oai:arXiv.org:2511.02064v2 - cs.CG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hua Tong, Yongjie Jessica Zhang - - - Lightweight Session-Key Rekeying Framework for Secure IoT-Edge Communication - https://arxiv.org/abs/2511.02924 - arXiv:2511.02924v2 Announce Type: replace -Abstract: The proliferation of Internet of Things (IoT) networks demands security mechanisms that protect constrained devices without the computational cost of public-key cryptography. Conventional Pre-Shared Key (PSK) encryption, while efficient, remains vulnerable due to static key reuse, replay attacks, and the lack of key freshness. This paper presents the Dynamic Session Enhanced Key Protocol (DSEKP), a lightweight session-key rekeying framework that derives per-session AES-GCM keys using the HMAC-based Key Derivation Function (HKDF-SHA256) and authenticates session establishment through an HMAC proof in a single init-ack exchange. DSEKP was implemented on an ESP32 IoT sensor node and a Raspberry Pi 5 edge server communicating through a Mosquitto MQTT broker, and benchmarked against a static PSK baseline over more than 6,500 encrypted packets per configuration. The results demonstrate nearly identical throughput and reliability, with minimal runtime impact (approximately 27 percent one-time session-establishment latency and 10 percent per-packet payload overhead), while delivering per-session key isolation (assuming the long-term secret remains uncompromised) and built-in replay protection. The PSK baseline and DSEKP datasets are publicly archived on IEEE DataPort to enable full reproducibility and comparative benchmarking. These findings confirm that dynamic symmetric rekeying can substantially strengthen IoT-Edge links with minimal computational and bandwidth cost, offering a practical migration path from static PSK to session-aware and scalable IoT security. - oai:arXiv.org:2511.02924v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Haranath Rakshit, Rajkumar Bhandari, Subhasis Banerjee - - - FastGS: Training 3D Gaussian Splatting in 100 Seconds - https://arxiv.org/abs/2511.04283 - arXiv:2511.04283v3 Announce Type: replace -Abstract: The dominant 3D Gaussian splatting (3DGS) acceleration methods fail to properly regulate the number of Gaussians during training, causing redundant computational time overhead. In this paper, we propose FastGS, a novel, simple, and general acceleration framework that fully considers the importance of each Gaussian based on multi-view consistency, efficiently solving the trade-off between training time and rendering quality. We innovatively design a densification and pruning strategy based on multi-view consistency, dispensing with the budgeting mechanism. Extensive experiments on Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets demonstrate that our method significantly outperforms the state-of-the-art methods in training speed, achieving a 3.32$\times$ training acceleration and comparable rendering quality compared with DashGaussian on the Mip-NeRF 360 dataset and a 15.45$\times$ acceleration compared with vanilla 3DGS on the Deep Blending dataset. We demonstrate that FastGS exhibits strong generality, delivering 2-7$\times$ training acceleration across various tasks, including dynamic scene reconstruction, surface reconstruction, sparse-view reconstruction, large-scale reconstruction, and simultaneous localization and mapping. The project page is available at https://fastgs.github.io/ - oai:arXiv.org:2511.04283v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shiwei Ren, Tianci Wen, Yongchun Fang, Biao Lu - - - DeepPAAC: A New Deep Galerkin Method for Principal-Agent Problems - https://arxiv.org/abs/2511.04309 - arXiv:2511.04309v2 Announce Type: replace -Abstract: We consider numerical resolution of principal-agent (PA) problems in continuous time. We formulate a generic PA model with continuous and lump payments and a multi-dimensional strategy of the agent. To tackle the resulting Hamilton-Jacobi-Bellman equation with an implicit Hamiltonian we develop a novel deep learning method: the Deep Principal-Agent Actor Critic (DeepPAAC) Actor-Critic algorithm. DeepPAAC is able to handle multi-dimensional states and controls, as well as constraints. We investigate the role of the neural network architecture, training designs, loss functions, etc. on the convergence of the solver, presenting five different case studies. - oai:arXiv.org:2511.04309v2 - math.NA - cs.LG - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Michael Ludkovski, Changgen Xie, Zimu Zhu - - - Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation - https://arxiv.org/abs/2511.05852 - arXiv:2511.05852v3 Announce Type: replace -Abstract: Knowledge editing has emerged as a lightweight alternative to retraining for correcting or injecting specific facts in large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks. Despite their widespread adoption, these two post-training interventions have been studied in isolation, leaving open a crucial question: if we fine-tune an edited model, do the edits survive? This question is motivated by two practical scenarios: removing covert or malicious edits, and preserving beneficial edits. If fine-tuning impairs edits (Fig.1), current KE methods become less useful, as every fine-tuned model would require re-editing, which significantly increases the cost; if edits persist, fine-tuned models risk propagating hidden malicious edits, raising serious safety concerns. To this end, we systematically quantify edit decay after fine-tuning, investigating how fine-tuning affects knowledge editing. Our results show that edits decay after fine-tuning, with survival varying across configurations, e.g., AlphaEdit edits decay more than MEMIT edits. Further, we find that fine-tuning edited layers only can effectively remove edits, though at a slight cost to downstream performance. Surprisingly, fine-tuning non-edited layers impairs more edits than full fine-tuning. Overall, our study establishes empirical baselines and actionable strategies for integrating knowledge editing with fine-tuning, and underscores that evaluating model editing requires considering the full LLM application pipeline. - oai:arXiv.org:2511.05852v3 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yinjie Cheng, Paul Youssef, Christin Seifert, J\"org Schl\"otterer, Zhixue Zhao - - - Elastic Data Transfer Optimization with Hybrid Reinforcement Learning - https://arxiv.org/abs/2511.06159 - arXiv:2511.06159v2 Announce Type: replace -Abstract: Modern scientific data acquisition generates petabytes of data that must be transferred to geographically distant computing clusters. Conventional tools either rely on preconfigured sessions, which are difficult to tune for users without domain expertise, or they adaptively optimize only concurrency while ignoring other important parameters. We present \name, an adaptive data transfer method that jointly considers multiple parameters. Our solution incorporates heuristic-based parallelism, infinite pipelining, and a deep reinforcement learning based concurrency optimizer. To make agent training practical, we introduce a lightweight network simulator that reduces training time to less than four minutes and provides a $2750\times$ speedup compared to online training. Experimental evaluation shows that \name consistently outperforms existing methods across diverse datasets, achieving up to 9.5x higher throughput compared to state-of-the-art solutions. - oai:arXiv.org:2511.06159v2 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Rasman Mubtasim Swargo, Md Arifuzzaman - - - Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures - https://arxiv.org/abs/2511.06390 - arXiv:2511.06390v3 Announce Type: replace -Abstract: Large Language Models (LLMs) are widely adopted, but their high training cost leads many developers to fine-tune existing open-source models. While most adhere to open-source licenses, some falsely claim original training despite clear derivation from public models, raising pressing concerns about intellectual property protection and the need to verify model provenance. In this paper, we propose GhostSpec, a lightweight yet effective method for verifying LLM lineage without access to training data or modification of model behavior. Our approach constructs compact and robust fingerprints by applying singular value decomposition (SVD) to invariant products of internal attention weight matrices. Unlike watermarking or output-based methods, GhostSpec is fully data-free, non-invasive, and computationally efficient. Extensive experiments show it is robust to fine-tuning, pruning, expansion, and adversarial transformations, reliably tracing lineage with minimal overhead. By offering a practical solution for model verification, our method contributes to intellectual property protection and fosters a transparent, trustworthy LLM ecosystem. Our code is available at https://github.com/DX0369/GhostSpec. - oai:arXiv.org:2511.06390v3 - cs.CR - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Suqing Wang, Ziyang Ma, Li Xinyi, Zuchao Li - - - TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation - https://arxiv.org/abs/2511.06405 - arXiv:2511.06405v2 Announce Type: replace -Abstract: Next Point-of-Interest (POI) recommendation is a fundamental task in location-based services. While recent advances leverage Large Language Model (LLM) for sequential modeling, existing LLM-based approaches face two key limitations: (i) strong reliance on the contextual completeness of user histories, resulting in poor performance on out-of-history (OOH) scenarios; (ii) limited scalability, due to the restricted context window of LLMs, which limits their ability to access and process a large number of candidate POIs. To address these challenges, we propose Tool4POI, a novel tool-augmented framework that enables LLMs to perform open-set POI recommendation through external retrieval and reasoning. Tool4POI consists of three key modules: preference extraction module, multi-turn candidate retrieval module, and reranking module, which together summarize long-term user interests, interact with external tools to retrieve relevant POIs, and refine final recommendations based on recent behaviors. Unlike existing methods, Tool4POI requires no task-specific fine-tuning and is compatible with off-the-shelf LLMs in a plug-and-play manner. Extensive experiments on three real-world datasets show that Tool4POI substantially outperforms state-of-the-art baselines, achieving up to 40% accuracy on challenging OOH scenarios where existing methods fail, and delivering average improvements of 20% and 30% on Acc@5 and Acc@10, respectively. - oai:arXiv.org:2511.06405v2 - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dongsheng Wang, Shen Gao, Chengrui Huang, Yuxi Huang, Ruixiang Feng, Shuo Shang - - - FLEX: Continuous Agent Evolution via Forward Learning from Experience - https://arxiv.org/abs/2511.06449 - arXiv:2511.06449v2 Announce Type: replace -Abstract: Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io. - oai:arXiv.org:2511.06449v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhicheng Cai, Xinyuan Guo, Yu Pei, Jiangtao Feng, Jinsong Su, Jiangjie Chen, Ya-Qin Zhang, Wei-Ying Ma, Mingxuan Wang, Hao Zhou - - - 3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition - https://arxiv.org/abs/2511.07040 - arXiv:2511.07040v2 Announce Type: replace -Abstract: Deep neural networks have recently achieved notable progress in 3D point cloud recognition, yet their vulnerability to adversarial perturbations poses critical security challenges in practical deployments. Conventional defense mechanisms struggle to address the evolving landscape of multifaceted attack patterns. Through systematic analysis of existing defenses, we identify that their unsatisfactory performance primarily originates from an entangled feature space, where adversarial attacks can be performed easily. To this end, we present 3D-ANC, a novel approach that capitalizes on the Neural Collapse (NC) mechanism to orchestrate discriminative feature learning. In particular, NC depicts where last-layer features and classifier weights jointly evolve into a simplex equiangular tight frame (ETF) arrangement, establishing maximally separable class prototypes. However, leveraging this advantage in 3D recognition confronts two substantial challenges: (1) prevalent class imbalance in point cloud datasets, and (2) complex geometric similarities between object categories. To tackle these obstacles, our solution combines an ETF-aligned classification module with an adaptive training framework consisting of representation-balanced learning (RBL) and dynamic feature direction loss (FDL). 3D-ANC seamlessly empowers existing models to develop disentangled feature spaces despite the complexity in 3D data distribution. Comprehensive evaluations state that 3D-ANC significantly improves the robustness of models with various structures on two datasets. For instance, DGCNN's classification accuracy is elevated from 27.2% to 80.9% on ModelNet40 -- a 53.7% absolute gain that surpasses leading baselines by 34.0%. - oai:arXiv.org:2511.07040v2 - cs.CV - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yuanmin Huang, Wenxuan Li, Mi Zhang, Xiaohan Zhang, Xiaoyu You, Min Yang - - - SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations - https://arxiv.org/abs/2511.07405 - arXiv:2511.07405v2 Announce Type: replace -Abstract: We introduce SPOT (Stopping Points in Online Threads), the first annotated corpus translating the sociological concept of stopping point into a reproducible NLP task. Stopping points are ordinary critical interventions that pause or redirect online discussions through a range of forms (irony, subtle doubt or fragmentary arguments) that frameworks like counterspeech or social correction often overlook. We operationalize this concept as a binary classification task and provide reliable annotation guidelines. The corpus contains 43,305 manually annotated French Facebook comments linked to URLs flagged as false information by social media users, enriched with contextual metadata (article, post, parent comment, page or group, and source). We benchmark fine-tuned encoder models (CamemBERT) and instruction-tuned LLMs under various prompting strategies. Results show that fine-tuned encoders outperform prompted LLMs in F1 score by more than 10 percentage points, confirming the importance of supervised learning for emerging non-English social media tasks. Incorporating contextual metadata further improves encoder models F1 scores from 0.75 to 0.78. We release the anonymized dataset, along with the annotation guidelines and code in our code repository, to foster transparency and reproducible research. - oai:arXiv.org:2511.07405v2 - cs.CL - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Manon Berriche, C\'elia Nouri, Chlo\'e Clavel, Jean-Philippe Cointet - - - "I need to learn better searching tactics for privacy policy laws." Investigating Software Developers' Behavior When Using Sources on Privacy Issues - https://arxiv.org/abs/2511.08059 - arXiv:2511.08059v2 Announce Type: replace -Abstract: Since the introduction of the European General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA), software developers increasingly have to make privacy-related decisions during system design and implementation. However, past research showed that they often lack legal expertise and struggle with privacy-compliant development. To shed light on how effective current information sources are in supporting them with privacy-sensitive implementation, we conducted a qualitative study with 30 developers. Participants were presented with a privacy-sensitive scenario and asked to identify privacy issues and suggest measures using their knowledge, online resources, and an AI assistant. We observed developers' decision-making in think-aloud sessions and discussed it in follow-up interviews. We found that participants struggled with all three sources: personal knowledge was insufficient, web content was often too complex, and while AI assistants provided clear and user-tailored responses, they lacked contextual relevance and failed to identify scenario-specific issues. Our study highlights major shortcomings in existing support for privacy-related development tasks. Based on our findings, we discuss the need for more accessible, understandable, and actionable privacy resources for developers. - oai:arXiv.org:2511.08059v2 - cs.SE - cs.CR - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.1145/3744916.3773150 - 2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE26) - Stefan Albert Horstmann, Sandy Hong, Maziar Niazian, Cristiana Santos, Alena Naiakshina - - - HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting - https://arxiv.org/abs/2511.08340 - arXiv:2511.08340v2 Announce Type: replace -Abstract: Accurate forecasting of multivariate time series data remains a formidable challenge, particularly due to the growing complexity of temporal dependencies in real-world scenarios. While neural network-based models have achieved notable success in this domain, complex channel-dependent models often suffer from performance degradation compared to channel-independent models that do not consider the relationship between components but provide high robustness due to small capacity. In this work, we propose HN-MVTS, a novel architecture that integrates a hypernetwork-based generative prior with an arbitrary neural network forecasting model. The input of this hypernetwork is a learnable embedding matrix of time series components. To restrict the number of new parameters, the hypernetwork learns to generate the weights of the last layer of the target forecasting networks, serving as a data-adaptive regularizer that improves generalization and long-range predictive accuracy. The hypernetwork is used only during the training, so it does not increase the inference time compared to the base forecasting model. Extensive experiments on eight benchmark datasets demonstrate that application of HN-MVTS to the state-of-the-art models (DLinear, PatchTST, TSMixer, etc.) typically improves their performance. Our findings suggest that hypernetwork-driven parameterization offers a promising direction for enhancing existing forecasting techniques in complex scenarios. - oai:arXiv.org:2511.08340v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Andrey Savchenko, Oleg Kachan - - - Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning - https://arxiv.org/abs/2511.08595 - arXiv:2511.08595v2 Announce Type: replace -Abstract: Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct branches explore equivalent reasoning paths. We introduce Semantic Similarity-Based Dynamic Pruning (SSDP), a lightweight method that, to the best of our knowledge, is the first framework to integrate online semantic merging into parallelized tree search, enabling the clustering and pruning of redundant steps in real time. Across reasoning benchmarks, including GSM8K and MATH500, SSDP achieves up to a 2.3x speedup over state-of-the-art tree-search baselines while maintaining competitive accuracy (typically within 5% of the strongest baseline) and reducing the number of explored nodes by 85-90%, demonstrating a practical approach to efficient, scalable LLM reasoning. The implementation of SSDP is publicly available at https://github.com/kimjoonghokim/SSDP. - oai:arXiv.org:2511.08595v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Joongho Kim, Xirui Huang, Zarreen Reza, Gabriel Grand - - - Data Fusion-Enhanced Decision Transformer for Stable Cross-Domain Generalization - https://arxiv.org/abs/2511.09173 - arXiv:2511.09173v2 Announce Type: replace -Abstract: Cross-domain shifts present a significant challenge for decision transformer (DT) policies. Existing cross-domain policy adaptation methods typically rely on a single simple filtering criterion to select source trajectory fragments and stitch them together. They match either state structure or action feasibility. However, the selected fragments still have poor stitchability: state structures can misalign, the return-to-go (RTG) becomes incomparable when the reward or horizon changes, and actions may jump at trajectory junctions. As a result, RTG tokens lose continuity, which compromises DT's inference ability. To tackle these challenges, we propose Data Fusion-Enhanced Decision Transformer (DFDT), a compact pipeline that restores stitchability. Particularly, DFDT fuses scarce target data with selectively trusted source fragments via a two-level data filter, maximum mean discrepancy (MMD) mismatch for state-structure alignment, and optimal transport (OT) deviation for action feasibility. It then trains on a feasibility-weighted fusion distribution. Furthermore, DFDT replaces RTG tokens with advantage-conditioned tokens, which improves the continuity of the semantics in the token sequence. It also applies a $Q$-guided regularizer to suppress junction value and action jumps. Theoretically, we provide bounds that tie state value and policy performance gaps to the MMD-mismatch and OT-deviation measures, and show that the bounds tighten as these two measures shrink. We show that DFDT improves return and stability over strong offline RL and sequence-model baselines across gravity, kinematic, and morphology shifts on D4RL-style control tasks, and further corroborate these gains with token-stitching and sequence-semantics stability analyses. - oai:arXiv.org:2511.09173v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Guojian Wang, Quinson Hon, Xuyang Chen, Lin Zhao - - - Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots - https://arxiv.org/abs/2511.09241 - arXiv:2511.09241v2 Announce Type: replace -Abstract: Data scaling has long remained a critical bottleneck in robot learning. For humanoid robots, human videos and motion data are abundant and widely available, offering a free and large-scale data source. Besides, the semantics related to the motions enable modality alignment and high-level robot control learning. However, how to effectively mine raw video, extract robot-learnable representations, and leverage them for scalable learning remains an open problem. To address this, we introduce Humanoid-Union, a large-scale dataset generated through an autonomous pipeline, comprising over 260 hours of diverse, high-quality humanoid robot motion data with semantic annotations derived from human motion videos. The dataset can be further expanded via the same pipeline. Building on this data resource, we propose SCHUR, a scalable learning framework designed to explore the impact of large-scale data on high-level control in humanoid robots. Experimental results demonstrate that SCHUR achieves high robot motion generation quality and strong text-motion alignment under data and model scaling, with 37\% reconstruction improvement under MPJPE and 25\% alignment improvement under FID comparing with previous methods. Its effectiveness is further validated through deployment in real-world humanoid robot. - oai:arXiv.org:2511.09241v2 - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuxi Wei, Zirui Wang, Kangning Yin, Yue Hu, Jingbo Wang, Siheng Chen - - - A coupled finite element-virtual element method for thermomechanical analysis of electronic packaging structures - https://arxiv.org/abs/2511.09348 - arXiv:2511.09348v2 Announce Type: replace -Abstract: This study presents a finite element and virtual element (FE-VE) coupled method for thermomechanical analysis in electronic packaging structures. The approach partitions computational domains strategically, employing FEM for regular geometries to maximize computational efficiency and VEM for complex shapes to enhance geometric flexibility. Interface compatibility is maintained through coincident nodal correspondence, ensuring solution continuity across domain boundaries while reducing meshing complexity and computational overhead. Validation through electronic packaging applications demonstrates reasonable agreement with reference solutions and acceptable convergence characteristics across varying mesh densities. The method effectively captures thermal distributions and stress concentrations in multi-material systems, establishing a practical computational framework for electronic packaging analysis involving complex geometries. Source codes are available at https://github.com/yanpeng-gong/FeVeCoupled-ElectronicPackaging. - oai:arXiv.org:2511.09348v2 - math.NA - cs.CE - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yanpeng Gong, Sishuai Li, Yue Mei, Bingbing Xu, Fei Qin, Xiaoying Zhuang, Timon Rabczuk - - - FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching - https://arxiv.org/abs/2511.09731 - arXiv:2511.09731v2 Announce Type: replace -Abstract: Radar-based precipitation nowcasting, the task of forecasting short-term precipitation fields from previous radar images, is a critical problem for flood risk management and decision-making. While deep learning has substantially advanced this field, two challenges remain fundamental: the uncertainty of atmospheric dynamics and the efficient modeling of high-dimensional data. Diffusion models have shown strong promise by producing sharp, reliable forecasts, but their iterative sampling process is computationally prohibitive for time-critical applications. We introduce FlowCast, the first end-to-end probabilistic model leveraging Conditional Flow Matching (CFM) as a direct noise-to-data generative framework for precipitation nowcasting. Unlike hybrid approaches, FlowCast learns a direct noise-to-data mapping in a compressed latent space, enabling rapid, high-fidelity sample generation. Our experiments demonstrate that FlowCast establishes a new state-of-the-art in probabilistic performance while also exceeding deterministic baselines in predictive accuracy. A direct comparison further reveals the CFM objective is both more accurate and significantly more efficient than a diffusion objective on the same architecture, maintaining high performance with significantly fewer sampling steps. This work positions CFM as a powerful and practical alternative for high-dimensional spatiotemporal forecasting. - oai:arXiv.org:2511.09731v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Bernardo Perrone Ribeiro, Jana Faganeli Pucer - - - LAD-BNet: Lag-Aware Dual-Branch Networks for Real-Time Energy Forecasting on Edge Devices - https://arxiv.org/abs/2511.10680 - arXiv:2511.10680v2 Announce Type: replace -Abstract: Real-time energy forecasting on edge devices represents a major challenge for smart grid optimization and intelligent buildings. We present LAD-BNet (Lag-Aware Dual-Branch Network), an innovative neural architecture optimized for edge inference with Google Coral TPU. Our hybrid approach combines a branch dedicated to explicit exploitation of temporal lags with a Temporal Convolutional Network (TCN) featuring dilated convolutions, enabling simultaneous capture of short and long-term dependencies. Tested on real energy consumption data with 10-minute temporal resolution, LAD-BNet achieves 14.49% MAPE at 1-hour horizon with only 18ms inference time on Edge TPU, representing an 8-12 x acceleration compared to CPU. The multi-scale architecture enables predictions up to 12 hours with controlled performance degradation. Our model demonstrates a 2.39% improvement over LSTM baselines and 3.04% over pure TCN architectures, while maintaining a 180MB memory footprint suitable for embedded device constraints. These results pave the way for industrial applications in real-time energy optimization, demand management, and operational planning. - oai:arXiv.org:2511.10680v2 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jean-Philippe Lignier - - - Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types - https://arxiv.org/abs/2511.11030 - arXiv:2511.11030v4 Announce Type: replace -Abstract: Artificial intelligence is revealing what medicine never intended to encode. Deep vision models, trained on chest X-rays, can now detect not only disease but also invisible traces of social inequality. In this study, we show that state-of-the-art architectures (DenseNet121, SwinV2-B, MedMamba) can predict a patient's health insurance type, a strong proxy for socioeconomic status, from normal chest X-rays with significant accuracy (AUC around 0.70 on MIMIC-CXR-JPG, 0.68 on CheXpert). The signal was unlikely contributed by demographic features by our machine learning study combining age, race, and sex labels to predict health insurance types; it also remains detectable when the model is trained exclusively on a single racial group. Patch-based occlusion reveals that the signal is diffuse rather than localized, embedded in the upper and mid-thoracic regions. This suggests that deep networks may be internalizing subtle traces of clinical environments, equipment differences, or care pathways; learning socioeconomic segregation itself. These findings challenge the assumption that medical images are neutral biological data. By uncovering how models perceive and exploit these hidden social signatures, this work reframes fairness in medical AI: the goal is no longer only to balance datasets or adjust thresholds, but to interrogate and disentangle the social fingerprints embedded in clinical data itself. - oai:arXiv.org:2511.11030v4 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Chi-Yu Chen, Rawan Abulibdeh, Arash Asgari, Sebasti\'an Andr\'es Cajas Ord\'o\~nez, Leo Anthony Celi, Deirdre Goode, Hassan Hamidi, Laleh Seyyed-Kalantari, Ned McCague, Thomas Sounack, Po-Chih Kuo - - - STONE: Pioneering the One-to-N Universal Backdoor Threat in 3D Point Cloud - https://arxiv.org/abs/2511.11210 - arXiv:2511.11210v3 Announce Type: replace -Abstract: Backdoor attacks pose a critical threat to deep learning, especially in safety-sensitive 3D domains such as autonomous driving and robotics. While potent, existing attacks on 3D point clouds are predominantly limited to one-to-one paradigms. The more flexible and universal one-to-N multi-target backdoor threat remains largely unexplored, lacking both theoretical and practical foundations. To bridge this gap, we propose STONE (Spherical Trigger One-to-N universal backdoor Enabling), the first method to instantiate this threat via a configurable spherical trigger design. Its parameterized spatial properties establish a dynamic key space, enabling a single trigger to map to multiple target labels. Theoretically, we ground STONE in a Neural Tangent Kernel (NTK) analysis, providing the first formal basis for one-to-N mappings in 3D models. Empirically, extensive evaluations demonstrate high attack success rates (up to 100\%) without compromising clean-data accuracy. This work establishes a foundational benchmark for multi-target backdoor threats under dirty-label and black-box settings in 3D vision -- a crucial step toward securing future intelligent systems. - oai:arXiv.org:2511.11210v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dongmei Shan, Wei Lian, Chongxia Wang - - - Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping - https://arxiv.org/abs/2511.11551 - arXiv:2511.11551v3 Announce Type: replace -Abstract: The deployment of decision-making AI agents presents a critical challenge in maintaining alignment with human values or guidelines while operating in complex, dynamic environments. Agents trained solely to achieve their objectives may adopt harmful behavior, exposing a key trade-off between maximizing the reward function and maintaining alignment. For pre-trained agents, ensuring alignment is particularly challenging, as retraining can be a costly and slow process. This is further complicated by the diverse and potentially conflicting attributes representing the ethical values for alignment. To address these challenges, we propose a test-time alignment technique based on model-guided policy shaping. Our method allows precise control over individual behavioral attributes, generalizes across diverse reinforcement learning (RL) environments, and facilitates a principled trade-off between ethical alignment and reward maximization without requiring agent retraining. We evaluate our approach using the MACHIAVELLI benchmark, which comprises 134 text-based game environments and thousands of annotated scenarios involving ethical decisions. The RL agents are first trained to maximize the reward in their respective games. At test time, we apply policy shaping via scenario-action attribute classifiers to ensure decision alignment with ethical attributes. We compare our approach against prior training-time methods and general-purpose agents, as well as study several types of ethical violations and power-seeking behavior. Our results demonstrate that test-time policy shaping provides an effective and scalable solution for mitigating unethical behavior across diverse environments and alignment attributes. - oai:arXiv.org:2511.11551v3 - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Dena Mujtaba, Brian Hu, Anthony Hoogs, Arslan Basharat - - - Learning Conjugate Direction Fields for Planar Quadrilateral Mesh Generation - https://arxiv.org/abs/2511.11865 - arXiv:2511.11865v2 Announce Type: replace -Abstract: Planar quadrilateral (PQ) mesh generation is a key process in computer-aided design, particularly for architectural applications where the goal is to discretize a freeform surface using planar quad faces. The conjugate direction field (CDF) defined on the freeform surface plays a significant role in generating a PQ mesh, as it largely determines the PQ mesh layout. Conventionally, a CDF is obtained by solving a complex non-linear optimization problem that incorporates user preferences, i.e., aligning the CDF with user-specified strokes on the surface. This often requires a large number of iterations that are computationally expensive, preventing the interactive CDF design process for a desirable PQ mesh. To address this challenge, we propose a data-driven approach based on neural networks for controlled CDF generation. Our approach can effectively learn and fuse features from the freeform surface and the user strokes, and efficiently generate quality CDF respecting user guidance. To enable training and testing, we also present a dataset composed of 50000+ freeform surfaces with ground-truth CDFs, as well as a set of metrics for quantitative evaluation. The effectiveness and efficiency of our work are demonstrated by extensive experiments using testing data, architectural surfaces, and general 3D shapes. - oai:arXiv.org:2511.11865v2 - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiong Tao, Yong-Liang Yang, Bailin Deng - - - Combining Serverless and High-Performance Computing Paradigms to support ML Data-Intensive Applications - https://arxiv.org/abs/2511.12185 - arXiv:2511.12185v2 Announce Type: replace -Abstract: Data is found everywhere, from health and human infrastructure to the surge of sensors and the proliferation of internet-connected devices. To meet this challenge, the data engineering field has expanded significantly in recent years in both research and industry. Traditionally, data engineering, Machine Learning, and AI workloads have been run on large clusters within data center environments, requiring substantial investment in hardware and maintenance. With the rise of the public cloud, it is now possible to run large applications across nodes without owning or maintaining hardware. Serverless functions such as AWS Lambda provide horizontal scaling and precise billing without the hassle of managing traditional cloud infrastructure. However, when processing large datasets, users often rely on external storage options that are significantly slower than direct communication typical of HPC clusters. We introduce Cylon, a high-performance distributed data frame solution that has shown promising results for data processing using Python. We describe how we took inspiration from the FMI library and designed a serverless communicator to tackle communication and performance issues associated with serverless functions. With our design, we demonstrate that the performance of AWS Lambda falls below one percent of strong scaling experiments compared to serverful AWS (EC2) and HPCs based on implementing direct communication via NAT Traversal TCP Hole Punching. - oai:arXiv.org:2511.12185v2 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Mills Staylor, Arup Kumar Sarker, Gregor von Laszewski, Geoffrey Fox, Yue Cheng, Judy Fox - - - D$^{2}$-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation - https://arxiv.org/abs/2511.12528 - arXiv:2511.12528v3 Announce Type: replace -Abstract: Visual Place Recognition (VPR) aims to determine the geographic location of a query image by retrieving its most visually similar counterpart from a geo-tagged reference database. Recently, the emergence of the powerful visual foundation model, DINOv2, trained in a self-supervised manner on massive datasets, has significantly improved VPR performance. This improvement stems from DINOv2's exceptional feature generalization capabilities but is often accompanied by increased model complexity and computational overhead that impede deployment on resource-constrained devices. To address this challenge, we propose $D^{2}$-VPR, a $D$istillation- and $D$eformable-based framework that retains the strong feature extraction capabilities of visual foundation models while significantly reducing model parameters and achieving a more favorable performance-efficiency trade-off. Specifically, first, we employ a two-stage training strategy that integrates knowledge distillation and fine-tuning. Additionally, we introduce a Distillation Recovery Module (DRM) to better align the feature spaces between the teacher and student models, thereby minimizing knowledge transfer losses to the greatest extent possible. Second, we design a Top-Down-attention-based Deformable Aggregator (TDDA) that leverages global semantic features to dynamically and adaptively adjust the Regions of Interest (ROI) used for aggregation, thereby improving adaptability to irregular structures. Extensive experiments demonstrate that our method achieves competitive performance compared to state-of-the-art approaches. Meanwhile, it reduces the parameter count by approximately 64.2% and MACs by about 62.6% (compared to CricaVPR).Code is available at https://github.com/tony19980810/D2VPR. - oai:arXiv.org:2511.12528v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zheyuan Zhang, Jiwei Zhang, Boyu Zhou, Linzhimeng Duan, Hong Chen - - - A Content-Preserving Secure Linguistic Steganography - https://arxiv.org/abs/2511.12565 - arXiv:2511.12565v2 Announce Type: replace -Abstract: Existing linguistic steganography methods primarily rely on content transformations to conceal secret messages. However, they often cause subtle yet looking-innocent deviations between normal and stego texts, posing potential security risks in real-world applications. To address this challenge, we propose a content-preserving linguistic steganography paradigm for perfectly secure covert communication without modifying the cover text. Based on this paradigm, we introduce CLstega (\textit{C}ontent-preserving \textit{L}inguistic \textit{stega}nography), a novel method that embeds secret messages through controllable distribution transformation. CLstega first applies an augmented masking strategy to locate and mask embedding positions, where MLM(masked language model)-predicted probability distributions are easily adjustable for transformation. Subsequently, a dynamic distribution steganographic coding strategy is designed to encode secret messages by deriving target distributions from the original probability distributions. To achieve this transformation, CLstega elaborately selects target words for embedding positions as labels to construct a masked sentence dataset, which is used to fine-tune the original MLM, producing a target MLM capable of directly extracting secret messages from the cover text. This approach ensures perfect security of secret messages while fully preserving the integrity of the original cover text. Experimental results show that CLstega can achieve a 100\% extraction success rate, and outperforms existing methods in security, effectively balancing embedding capacity and security. - oai:arXiv.org:2511.12565v2 - cs.CR - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Lingyun Xiang, Chengfu Ou, Xu He, Zhongliang Yang, Yuling Liu - - - Beyond Citations: A Cross-Domain Metric for Dataset Impact and Shareability - https://arxiv.org/abs/2511.12966 - arXiv:2511.12966v2 Announce Type: replace -Abstract: The scientific community increasingly relies on open data sharing, yet existing metrics inadequately capture the true impact of datasets as research outputs. Traditional measures, such as the h-index, focus on publications and citations but fail to account for dataset accessibility, reuse, and cross-disciplinary influence. We propose the X-index, a novel author-level metric that quantifies the value of data contributions through a two-step process: (i) computing a dataset-level value score (V-score) that integrates breadth of reuse, FAIRness, citation impact, and transitive reuse depth, and (ii) aggregating V-scores into an author-level X-index. Using datasets from computational social science, medicine, and crisis communication, we validate our approach against expert ratings, achieving a strong correlation. Our results demonstrate that the X-index provides a transparent, scalable, and low-cost framework for assessing data-sharing practices and incentivizing open science. The X-index encourages sustainable data-sharing practices and gives institutions, funders, and platforms a tangible way to acknowledge the lasting influence of research datasets. - oai:arXiv.org:2511.12966v2 - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Smitha Muthya Sudheendra, Zhongxing Zhang, Wenwen Cao, Jisu Huh, Jaideep Srivastava - - - uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data - https://arxiv.org/abs/2511.13036 - arXiv:2511.13036v2 Announce Type: replace -Abstract: Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to the scarcity of high-quality multilingual image-text data. Existing multilingual vision-language models exhibit consistently low retrieval performance in underrepresented languages including Czech, Finnish, Croatian, Hungarian, and Romanian on the Crossmodal-3600 (XM3600) benchmark. To address this, we propose a lightweight and data-efficient framework for multilingual vision-language alignment. Our approach requires no image-text pairs or text-text pairs and freezes both the pretrained image encoder and multilingual text encoder during training. Only a compact 1.7M-parameter projection module is trained, using a contrastive loss over English representations as semantic anchors. This minimal training setup enables robust multilingual alignment even for languages with limited supervision. Extensive evaluation across multiple multilingual retrieval benchmarks confirms the effectiveness of our method, showing significant gains in five underrepresented languages where existing models typically underperform. These findings highlight the effectiveness of our pivot-based, parameter-efficient alignment strategy for inclusive multimodal learning. - oai:arXiv.org:2511.13036v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dahyun Chung, Donghyun Shin, Yujin Sung, Seunggi Moon, Jinwoo Jeon, Byung-Jun Lee - - - VEIL: Jailbreaking Text-to-Video Models via Visual Exploitation from Implicit Language - https://arxiv.org/abs/2511.13127 - arXiv:2511.13127v2 Announce Type: replace -Abstract: Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts containing rich, implicit cues can induce T2V models to generate semantically unsafe videos that both violate policy and preserve the original (blocked) intent. To realize this, we propose VEIL, a jailbreak framework that leverages T2V models' cross-modal associative patterns via a modular prompt design. Specifically, our prompts combine three components: neutral scene anchors, which provide the surface-level scene description extracted from the blocked intent to maintain plausibility; latent auditory triggers, textual descriptions of innocuous-sounding audio events (e.g., creaking, muffled noises) that exploit learned audio-visual co-occurrence priors to bias the model toward particular unsafe visual concepts; and stylistic modulators, cinematic directives (e.g., camera framing, atmosphere) that amplify and stabilize the latent trigger's effect. We formalize attack generation as a constrained optimization over the above modular prompt space and solve it with a guided search procedure that balances stealth and effectiveness. Extensive experiments over 7 T2V models demonstrate the efficacy of our attack, achieving a 23 percent improvement in average attack success rate in commercial models. Our demos and codes can be found at https://github.com/NY1024/VEIL. - oai:arXiv.org:2511.13127v2 - cs.CV - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Zonghao Ying, Moyang Chen, Nizhang Li, Zhiqiang Wang, Wenxin Zhang, Quanchen Zou, Zonglei Jing, Aishan Liu, Xianglong Liu - - - Revealing POMDPs: Qualitative and Quantitative Analysis for Parity Objectives - https://arxiv.org/abs/2511.13134 - arXiv:2511.13134v2 Announce Type: replace -Abstract: Partially observable Markov decision processes (POMDPs) are a central model for uncertainty in sequential decision making. The most basic objective is the reachability objective, where a target set must be eventually visited, and the more general parity objectives can model all omega-regular specifications. For such objectives, the computational analysis problems are the following: (a) qualitative analysis that asks whether the objective can be satisfied with probability 1 (almost-sure winning) or probability arbitrarily close to 1 (limit-sure winning); and (b) quantitative analysis that asks for the approximation of the optimal probability of satisfying the objective. For general POMDPs, almost-sure analysis for reachability objectives is EXPTIME-complete, but limit-sure and quantitative analyses for reachability objectives are undecidable; almost-sure, limit-sure, and quantitative analyses for parity objectives are all undecidable. A special class of POMDPs, called revealing POMDPs, has been studied recently in several works, and for this subclass the almost-sure analysis for parity objectives was shown to be EXPTIME-complete. In this work, we show that for revealing POMDPs the limit-sure analysis for parity objectives is EXPTIME-complete, and even the quantitative analysis for parity objectives can be achieved in EXPTIME. - oai:arXiv.org:2511.13134v2 - cs.CC - cs.SY - eess.SY - math.OC - math.PR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/publicdomain/zero/1.0/ - Ali Asadi, Krishnendu Chatterjee, David Lurie, Raimundo Saona - - - Tight and Practical Privacy Auditing for Differentially Private In-Context Learning - https://arxiv.org/abs/2511.13502 - arXiv:2511.13502v2 Announce Type: replace -Abstract: Large language models (LLMs) perform in-context learning (ICL) by adapting to tasks from prompt demonstrations, which in practice often contain private or proprietary data. Although differential privacy (DP) with private voting is a pragmatic mitigation, DP-ICL implementations are error-prone, and worst-case DP bounds may substantially overestimate actual leakage, calling for practical auditing tools. We present a tight and efficient privacy auditing framework for DP-ICL systems that runs membership inference attacks and translates their success rates into empirical privacy guarantees using Gaussian DP. Our analysis of the private voting mechanism identifies vote configurations that maximize the auditing signal, guiding the design of audit queries that reliably reveal whether a canary demonstration is present in the context. The framework supports both black-box (API-only) and white-box (internal vote) threat models, and unifies auditing for classification and generation by reducing both to a binary decision problem. Experiments on standard text classification and generation benchmarks show that our empirical leakage estimates closely match theoretical DP budgets on classification tasks and are consistently lower on generation tasks due to conservative embedding-sensitivity bounds, making our framework a practical privacy auditor and verifier for real-world DP-ICL deployments. - oai:arXiv.org:2511.13502v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuyang Xia, Ruixuan Liu, Li Xiong - - - Distribution Matching Distillation Meets Reinforcement Learning - https://arxiv.org/abs/2511.13649 - arXiv:2511.13649v3 Announce Type: replace -Abstract: Distribution Matching Distillation (DMD) distills a pre-trained multi-step diffusion model to a few-step one to improve inference efficiency. However, the performance of the latter is often capped by the former. To circumvent this dilemma, we propose DMDR, a novel framework that combines Reinforcement Learning (RL) techniques into the distillation process. We show that for the RL of the few-step generator, the DMD loss itself is a more effective regularization compared to the traditional ones. In turn, RL can help to guide the mode coverage process in DMD more effectively. These allow us to unlock the capacity of the few-step generator by conducting distillation and RL simultaneously. Meanwhile, we design the dynamic distribution guidance and dynamic renoise sampling training strategies to improve the initial distillation process. The experiments demonstrate that DMDR can achieve leading visual quality, prompt coherence among few-step methods, and even exhibit performance that exceeds the multi-step teacher. - oai:arXiv.org:2511.13649v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dengyang Jiang, Dongyang Liu, Zanyi Wang, Qilong Wu, Liuzhuozheng Li, Hengzhuang Li, Xin Jin, David Liu, Zhen Li, Bo Zhang, Mengmeng Wang, Steven Hoi, Peng Gao, Harry Yang - - - SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome - https://arxiv.org/abs/2511.15464 - arXiv:2511.15464v2 Announce Type: replace -Abstract: Recent advances in computational pathology have leveraged vision-language models to learn joint representations of Hematoxylin and Eosin (HE) images with spatial transcriptomic (ST) profiles. However, existing approaches typically align HE tiles with their corresponding ST profiles at a single scale, overlooking fine-grained cellular structures and their spatial organization. To address this, we propose Sigmma, a multi-modal contrastive alignment framework for learning hierarchical representations of HE images and spatial transcriptome profiles across multiple scales. Sigmma introduces multi-scale contrastive alignment, ensuring that representations learned at different scales remain coherent across modalities. Furthermore, by representing cell interactions as a graph and integrating inter- and intra-subgraph relationships, our approach effectively captures cell-cell interactions, ranging from fine to coarse, within the tissue microenvironment. We demonstrate that Sigmm learns representations that better capture cross-modal correspondences, leading to an improvement of avg. 9.78\% in the gene-expression prediction task and avg. 26.93\% in the cross-modal retrieval task across datasets. We further show that it learns meaningful multi-tissue organization in downstream analyses. - oai:arXiv.org:2511.15464v2 - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Dabin Jeong, Amirhossein Vahidi, Ciro Ram\'irez-Su\'astegui, Marie Moullet, Kevin Ly, Mohammad Vali Sanian, Sebastian Birk, Yinshui Chang, Adam Boxall, Daniyal Jafree, Lloyd Steele, Vijaya Baskar MS, Muzlifah Haniffa, Mohammad Lotfollahi - - - The Loss of Control Playbook: Degrees, Dynamics, and Preparedness - https://arxiv.org/abs/2511.15846 - arXiv:2511.15846v5 Announce Type: replace -Abstract: This research report addresses the absence of an actionable definition for Loss of Control (LoC) in AI systems by developing a novel taxonomy and preparedness framework. Despite increasing policy and research attention, existing LoC definitions vary significantly in scope and timeline, hindering effective LoC assessment and mitigation. To address this issue, we draw from an extensive literature review and propose a graded LoC taxonomy, based on the metrics of severity and persistence, that distinguishes between Deviation, Bounded LoC, and Strict LoC. We model pathways toward a societal state of vulnerability in which sufficiently advanced AI systems have acquired or could acquire the means to cause Bounded or Strict LoC once a catalyst, either misalignment or pure malfunction, materializes. We argue that this state becomes increasingly likely over time, absent strategic intervention, and propose a strategy to avoid reaching a state of vulnerability. Rather than focusing solely on intervening on AI capabilities and propensities potentially relevant for LoC or on preventing potential catalysts, we introduce a complementary framework that emphasizes three extrinsic factors: Deployment context, Affordances, and Permissions (the DAP framework). Compared to work on intrinsic factors and catalysts, this framework has the unfair advantage of being actionable today. Finally, we put forward a plan to maintain preparedness and prevent the occurrence of LoC outcomes should a state of societal vulnerability be reached, focusing on governance measures (threat modeling, deployment policies, emergency response) and technical controls (pre-deployment testing, control measures, monitoring) that could maintain a condition of perennial suspension. - oai:arXiv.org:2511.15846v5 - cs.CY - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Charlotte Stix, Annika Hallensleben, Alejandro Ortega, Matteo Pistillo - - - Observer Design for Networked Linear Systems with Fast and Slow Dynamics under Measurement Noise - https://arxiv.org/abs/2511.16469 - arXiv:2511.16469v4 Announce Type: replace -Abstract: This paper addresses the emulation-based observer design for networked control systems (NCS) with linear plants that operate at two time scales in the presence of measurement noise. The system is formulated as a hybrid singularly perturbed dynamical system, enabling the systematic use of singular perturbation techniques to derive explicit bounds on the maximum allowable transmission intervals (MATI) for both fast and slow communication channels. Under the resulting conditions, the proposed observer guarantees that the estimation error satisfies a global exponential derivative-input-to-state stability (DISS)-like property, where the ultimate bound scales proportionally with the magnitudes of the measurement noise and the time derivative of the control input. The effectiveness of the approach is illustrated through a numerical example. - oai:arXiv.org:2511.16469v4 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Weixuan Wang, Alejandro I. Maass, Dragan Ne\v{s}i\'c, Ying Tan, Romain Postoyan, W. P. M. H. Heemels - - - The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation - https://arxiv.org/abs/2511.16543 - arXiv:2511.16543v2 Announce Type: replace -Abstract: The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. - Inspired by knowledge distillation, Prism leverages a powerful, instruction-following teacher LLM (FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. Our extensive experiments on benchmark datasets reveal a key finding: the distillation process not only transfers knowledge but also acts as a noise filter. Our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, demonstrating an emergent ability to correct hallucinations present in the teacher's outputs. While achieving a 24x speedup and a 10x reduction in memory consumption, our analysis validates that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality, and perhaps more importantly, trustworthy explainable recommendation. - oai:arXiv.org:2511.16543v2 - cs.IR - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiaheng Zhang, Daqiang Zhang - - - Mask the Redundancy: Evolving Masking Representation Learning for Multivariate Time-Series Clustering - https://arxiv.org/abs/2511.17008 - arXiv:2511.17008v2 Announce Type: replace -Abstract: Multivariate Time-Series (MTS) clustering discovers intrinsic grouping patterns of temporal data samples. Although time-series provide rich discriminative information, they also contain substantial redundancy, such as steady-state machine operation records and zero-output periods of solar power generation. Such redundancy diminishes the attention given to discriminative timestamps in representation learning, thus leading to performance bottlenecks in MTS clustering. Masking has been widely adopted to enhance the MTS representation, where temporal reconstruction tasks are designed to capture critical information from MTS. However, most existing masking strategies appear to be standalone preprocessing steps, isolated from the learning process, which hinders dynamic adaptation to the importance of clustering-critical timestamps. Accordingly, this paper proposes the Evolving-masked MTS Clustering (EMTC) method, whose model architecture comprises Importance-aware Variate-wise Masking (IVM) and Multi-Endogenous Views (MEV) generation modules. IVM adaptively guides the model in learning more discriminative representations for clustering, while the reconstruction and cluster-guided contrastive learning pathways enhance and connect the representation learning to clustering tasks. Extensive experiments on 15 benchmark datasets demonstrate the superiority of EMTC over eight SOTA methods, where the EMTC achieves an average improvement of 4.85% in F1-Score over the strongest baselines. - oai:arXiv.org:2511.17008v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zexi Tan, Xiaopeng Luo, Yunlin Liu, Yiqun Zhang - - - MCMoE: Completing Missing Modalities with Mixture of Experts for Incomplete Multimodal Action Quality Assessment - https://arxiv.org/abs/2511.17397 - arXiv:2511.17397v2 Announce Type: replace -Abstract: Multimodal Action Quality Assessment (AQA) has recently emerged as a promising paradigm. By leveraging complementary information across shared contextual cues, it enhances the discriminative evaluation of subtle intra-class variations in highly similar action sequences. However, partial modalities are frequently unavailable at the inference stage in reality. The absence of any modality often renders existing multimodal models inoperable. Furthermore, it triggers catastrophic performance degradation due to interruptions in cross-modal interactions. To address this issue, we propose a novel Missing Completion Framework with Mixture of Experts (MCMoE) that unifies unimodal and joint representation learning in single-stage training. Specifically, we propose an adaptive gated modality generator that dynamically fuses available information to reconstruct missing modalities. We then design modality experts to learn unimodal knowledge and dynamically mix the knowledge of all experts to extract cross-modal joint representations. With a mixture of experts, missing modalities are further refined and complemented. Finally, in the training phase, we mine the complete multimodal features and unimodal expert knowledge to guide modality generation and generation-based joint representation extraction. Extensive experiments demonstrate that our MCMoE achieves state-of-the-art results in both complete and incomplete multimodal learning on three public AQA benchmarks. Code is available at https://github.com/XuHuangbiao/MCMoE. - oai:arXiv.org:2511.17397v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Huangbiao Xu, Huanqi Wu, Xiao Ke, Junyi Wu, Rui Xu, Jinglin Xu - - - The Impact of Off-Policy Training Data on Probe Generalisation - https://arxiv.org/abs/2511.17408 - arXiv:2511.17408v2 Announce Type: replace -Abstract: Probing has emerged as a promising method for monitoring large language models (LLMs), enabling inference-time detection of concerning behaviours such as deception and sycophancy. However, natural examples of many behaviours are rare, forcing researchers to rely on synthetic or off-policy LLM responses for training probes. We systematically evaluate how the use of synthetic and off-policy data influences probe generalisation across eight distinct LLM behaviours. Testing linear and attention probes across multiple LLMs, we find that the response generation strategy can significantly affect probe performance, though the magnitude of this effect greatly varies by behaviour. We find that successful generalisation from off-policy responses to incentivised responses (e.g. those where the behaviour is advantageous) is predictive of successful generalisation to on-policy data. Leveraging this result, we predict that Deception and Sandbagging probes may fail to generalise from off-policy to on-policy data when used in real monitoring scenarios. We also find that shifts in the training data domain cause even larger performance degradation than off-to-on-policy shift, with different-domain test scores being consistently lower than the same-domain ones. In the absence of on-policy data, using same-domain off-policy data appears to yield more reliable probes than using on-policy data from a different domain. Still, we emphasise the need for methods that can better handle distribution shifts in LLM monitoring. - oai:arXiv.org:2511.17408v2 - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nathalie Kirch, Samuel Dower, Adrians Skapars, Ekdeep Singh Lubana, Dmitrii Krasheninnikov - - - Optimized Memory Tagging on AmpereOne Processors - https://arxiv.org/abs/2511.17773 - arXiv:2511.17773v2 Announce Type: replace -Abstract: Memory-safety escapes continue to form the launching pad for a wide range of security attacks, especially for the substantial base of deployed software that is coded in pointer-based languages such as C/C++. Although compiler and Instruction Set Architecture (ISA) extensions have been introduced to address elements of this issue, the overhead and/or comprehensive applicability have limited broad production deployment. The Memory Tagging Extension (MTE) to the ARM AArch64 Instruction Set Architecture is a valuable tool to address memory-safety escapes; when used in synchronous tag-checking mode, MTE provides deterministic detection and prevention of sequential buffer overflow attacks, and probabilistic detection and prevention of exploits resulting from temporal use-after-free pointer programming bugs. The AmpereOne processor, launched in 2024, is the first datacenter processor to support MTE. Its optimized MTE implementation uniquely incurs no memory capacity overhead for tag storage and provides synchronous tag-checking with single-digit performance impact across a broad range of datacenter class workloads. Furthermore, this paper analyzes the complete hardware-software stack, identifying application memory management as the primary remaining source of overhead and highlighting clear opportunities for software optimization. The combination of an efficient hardware foundation and a clear path for software improvement makes the MTE implementation of the AmpereOne processor highly attractive for deployment in production cloud environments. - oai:arXiv.org:2511.17773v2 - cs.AR - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Shiv Kaushik, Mahesh Madhav, Nagi Aboulenein, Jason Bessette, Sandeep Brahmadathan, Ben Chaffin, Matthew Erler, Stephan Jourdan, Thomas Maciukenas, Ramya Masti, Jon Perry, Massimo Sutera, Scott Tetrick, Bret Toll, David Turley, Carl Worth, Atiq Bajwa - - - Switch-JustDance: Benchmarking Whole Body Motion Tracking Policies Using a Commercial Console Game - https://arxiv.org/abs/2511.17925 - arXiv:2511.17925v2 Announce Type: replace -Abstract: Recent advances in whole-body robot control have enabled humanoid and legged robots to perform increasingly agile and coordinated motions. However, standardized benchmarks for evaluating these capabilities in real-world settings, and in direct comparison to humans, remain scarce. Existing evaluations often rely on pre-collected human motion datasets or simulation-based experiments, which limit reproducibility, overlook hardware factors, and hinder fair human-robot comparisons. We present Switch-JustDance, a low-cost and reproducible benchmarking pipeline that leverages motion-sensing console games, Just Dance on the Nintendo Switch, to evaluate robot whole-body control. Using Just Dance on the Nintendo Switch as a representative platform, Switch-JustDance converts in-game choreography into robot-executable motions through streaming, motion reconstruction, and motion retargeting modules and enables users to evaluate controller performance through the game's built-in scoring system. We first validate the evaluation properties of Just Dance, analyzing its reliability, validity, sensitivity, and potential sources of bias. Our results show that the platform provides consistent and interpretable performance measures, making it a suitable tool for benchmarking embodied AI. Building on this foundation, we benchmark three state-of-the-art humanoid whole-body controllers on hardware and provide insights into their relative strengths and limitations. - oai:arXiv.org:2511.17925v2 - cs.RO - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Jeonghwan Kim, Wontaek Kim, Yidan Lu, Jin Cheng, Fatemeh Zargarbashi, Zicheng Zeng, Zekun Qi, Zhiyang Dou, Nitish Sontakke, Donghoon Baek, Sehoon Ha, Tianyu Li - - - An Adaptive Resonance Theory-based Topological Clustering Algorithm with a Self-Adjusting Vigilance Parameter - https://arxiv.org/abs/2511.17983 - arXiv:2511.17983v5 Announce Type: replace -Abstract: Clustering in stationary and nonstationary settings, where data distributions remain static or evolve over time, requires models that can adapt to distributional shifts while preserving previously learned cluster structures. This paper proposes an Adaptive Resonance Theory (ART)-based topological clustering algorithm that autonomously adjusts its recalculation interval and vigilance threshold through a diversity-driven adaptation mechanism. This mechanism enables hyperparameter-free learning that maintains cluster stability and continuity in dynamic environments. Experiments on 24 real-world datasets demonstrate that the proposed algorithm outperforms state-of-the-art methods in both clustering performance and continual learning capability. These results highlight the effectiveness of the proposed parameter adaptation in mitigating catastrophic forgetting and maintaining consistent clustering in evolving data streams. Source code is available at https://github.com/Masuyama-lab/IDAT - oai:arXiv.org:2511.17983v5 - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Naoki Masuyama, Yuichiro Toda, Yusuke Nojima, Hisao Ishibuchi - - - Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models - https://arxiv.org/abs/2511.18271 - arXiv:2511.18271v2 Announce Type: replace -Abstract: Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols either emphasize compositional alignment or rely on single-round VQA-based scoring, leaving critical dimensions such as knowledge grounding, multi-physics interactions, and auditable evidence-substantially undertested. To address these limitations, we introduce PicWorld, the first comprehensive benchmark that assesses the grasp of implicit world knowledge and physical causal reasoning of T2I models. This benchmark consists of 1,100 prompts across three core categories. To facilitate fine-grained evaluation, we propose PW-Agent, an evidence-grounded multi-agent evaluator to hierarchically assess images on their physical realism and logical consistency by decomposing prompts into verifiable visual evidence. We conduct a thorough analysis of 17 mainstream T2I models on PicWorld, illustrating that they universally exhibit a fundamental limitation in their capacity for implicit world knowledge and physical causal reasoning to varying degrees. The findings highlight the need for reasoning-aware, knowledge-integrative architectures in future T2I systems. The code is available at https://github.com/D4-Lab/PicWorld}{https://github.com/D4-Lab/PicWorld. - oai:arXiv.org:2511.18271v2 - cs.CV - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tianyang Han, Junhao Su, Junjie Hu, Peizhen Yang, Hengyu Shi, Junfeng Luo, Jialin Gao - - - Clinician-Directed Large Language Model Software Generation for Therapeutic Interventions in Physical Rehabilitation - https://arxiv.org/abs/2511.18274 - arXiv:2511.18274v2 Announce Type: replace -Abstract: Digital health interventions increasingly deliver home exercise programs via sensor-equipped devices such as smartphones, enabling remote monitoring of adherence and performance. However, current software is usually authored before clinical encounters as libraries of modules for broad impairment categories. At the point of care, clinicians can only choose from these modules and adjust a few parameters (for example, duration or repetitions). As a result, individual limitations, goals, and environmental constraints are often not reflected, limiting personalization and benefit. We propose a paradigm in which large language models (LLMs) act as constrained translators that convert clinicians' exercise prescriptions into intervention software. Clinicians remain the decision makers: they design exercises during the encounter, tailored to each patient's impairments, goals, and environment, and the LLM generates matching software. We conducted a prospective single-arm feasibility study with 20 licensed physical and occupational therapists who created 40 individualized upper extremity programs for a standardized patient; 100% of prescriptions were translated into executable software, compared with 55% under a representative template-based digital health intervention (p < 0.01). LLM-generated software correctly delivered 99.7% of instructions and monitored performance with 88.4% accuracy (95% confidence interval, 0.843-0.915). Overall, 90% of therapists judged the system safe for patient interaction and 75% expressed willingness to adopt it in practice. To our knowledge, this is the first prospective evaluation of clinician-directed intervention software generation with an LLM in health care, demonstrating feasibility and motivating larger trials in real patient populations. - oai:arXiv.org:2511.18274v2 - cs.HC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Edward Kim, Yuri Cho, Jose Eduardo E. Lima, Julie Muccini, Jenelle Jindal, Alison Scheid, Erik Nelson, Seong Hyun Park, Yuchen Zeng, Alton Sturgis, Caesar Li, Jackie Dai, Sun Min Kim, Yash Prakash, Liwen Sun, Isabella Hu, Hongxuan Wu, Daniel He, Wiktor Rajca, Cathra Halabi, Maarten Lansberg, Bjoern Hartmann, Sanjit A. Seshia - - - ioPUF+: A PUF Based on I/O Pull-Up/Down Resistors for Secret Key Generation in IoT Nodes - https://arxiv.org/abs/2511.18412 - arXiv:2511.18412v2 Announce Type: replace -Abstract: In this work, we present ioPUF+, which incorporates a novel Physical Unclonable Function (PUF) that generates unique fingerprints for Integrated Circuits (ICs) and the IoT nodes encompassing them. The proposed PUF generates device-specific responses by measuring the pull-up and pull-down resistor values on the I/O pins of the ICs, which naturally vary across chips due to manufacturing-induced process variations. Since these resistors are already integrated into the I/O structures of most ICs, ioPUF+ requires no custom circuitry, and no new IC fabrication. This makes ioPUF+ suitable for cost-sensitive embedded systems built from Commercial Off-The-Shelf (COTS) components. Beyond introducing a new PUF, ioPUF+ includes a complete datapath for converting raw PUF responses into cryptographically usable secret keys using BCH error correction and SHA-256 hashing. Further ioPUF+ also demonstrate a practical use case of PUF derive secret keys in securing device-to-device communication using AES-encryption. We implemented ioPUF+ on the Infineon PSoC-5 microcontroller and evaluated its performance across 30 devices using standard PUF metrics. The results show excellent reliability (intra-device Hamming distance of 100.00%), strong uniqueness (inter-device Hamming distance of 50.33%), near-ideal uniformity (50.54%), and negligible bit aliasing. Stability tests under temperature and supply-voltage variations show worst-case bit-error rates of only 2.63% and 2.10%, respectively. We also profiled the resource and energy usage of the complete ioPUF+ system, including the PUF primitive, BCH decoding, SHA-256 hashing, and AES encryption. The full implementation requires only 19.8 KB of Flash, exhibits a latency of 600 ms, and consumes 79 mW of power, demonstrating the suitabilitiy of ioPUF+ for resource-constrained IoT nodes. - oai:arXiv.org:2511.18412v2 - cs.CR - cs.AR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Dilli Babu Porlapothula, Pralay Chakrabarty, Ananya Lakshmi Ravi, Kurian Polachan - - - From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence - https://arxiv.org/abs/2511.18538 - arXiv:2511.18538v5 Announce Type: replace -Abstract: Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons. - oai:arXiv.org:2511.18538v5 - cs.SE - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jian Yang, Xianglong Liu, Weifeng Lv, Ken Deng, Shawn Guo, Lin Jing, Yizhi Li, Shark Liu, Xianzhen Luo, Yuyu Luo, Changzai Pan, Ensheng Shi, Yingshui Tan, Renshuai Tao, Jiajun Wu, Xianjie Wu, Zhenhe Wu, Daoguang Zan, Chenchen Zhang, Wei Zhang, He Zhu, Terry Yue Zhuo, Kerui Cao, Xianfu Cheng, Jun Dong, Shengjie Fang, Zhiwei Fei, Xiangyuan Guan, Qipeng Guo, Zhiguang Han, Joseph James, Tianqi Luo, Renyuan Li, Yuhang Li, Yiming Liang, Congnan Liu, Jiaheng Liu, Qian Liu, Ruitong Liu, Tyler Loakman, Xiangxin Meng, Chuang Peng, Tianhao Peng, Jiajun Shi, Mingjie Tang, Boyang Wang, Haowen Wang, Yunli Wang, Fanglin Xu, Zihan Xu, Fei Yuan, Ge Zhang, Jiayi Zhang, Xinhao Zhang, Wangchunshu Zhou, Hualei Zhu, King Zhu, Bryan Dai, Aishan Liu, Zhoujun Li, Chenghua Lin, Tianyu Liu, Chao Peng, Kai Shen, Libo Qin, Shuangyong Song, Zizheng Zhan, Jiajun Zhang, Jie Zhang, Zhaoxiang Zhang, Bo Zheng - - - Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints - https://arxiv.org/abs/2511.19156 - arXiv:2511.19156v3 Announce Type: replace -Abstract: The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical information theory focuses on transmission and storage limits, it lacks a unified physical framework to quantify the thermodynamic costs of generating information from compressed laws versus retrieving it from memory. In this paper, we propose a theoretical framework that treats information processing as an enabling mapping from ontological states to carrier states. We introduce a novel metric, Derivation Entropy, which quantifies the effective work required to compute a target state from a given logical depth. By analyzing the interplay between Shannon entropy (storage) and computational complexity (time/energy), we demonstrate the existence of a critical phase transition point. Below this threshold, memory retrieval is thermodynamically favorable; above it, generative computation becomes the optimal strategy. This "Energy-Time-Space" conservation law provides a physical explanation for the efficiency of generative models and offers a rigorous mathematical bound for designing next-generation, energy-efficient AI architectures. Our findings suggest that the minimization of Derivation Entropy is a governing principle for the evolution of both biological and artificial intelligence. - oai:arXiv.org:2511.19156v3 - cs.IT - cs.AI - cs.LO - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jianfeng Xu, Zeyan Li - - - MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts - https://arxiv.org/abs/2511.20415 - arXiv:2511.20415v2 Announce Type: replace -Abstract: Generating realistic 3D cities is fundamental to world models, virtual reality, and game development, where an ideal urban scene must satisfy both stylistic diversity, fine-grained, and controllability. However, existing methods struggle to balance the creative flexibility offered by text-based generation with the object-level editability enabled by explicit structural representations. We introduce MajutsuCity, a natural language-driven and aesthetically adaptive framework for synthesizing structurally consistent and stylistically diverse 3D urban scenes. MajutsuCity represents a city as a composition of controllable layouts, assets, and materials, and operates through a four-stage pipeline. To extend controllability beyond initial generation, we further integrate MajutsuAgent, an interactive language-grounded editing agent} that supports five object-level operations. To support photorealistic and customizable scene synthesis, we also construct MajutsuDataset, a high-quality multimodal dataset} containing 2D semantic layouts and height maps, diverse 3D building assets, and curated PBR materials and skyboxes, each accompanied by detailed annotations. Meanwhile, we develop a practical set of evaluation metrics, covering key dimensions such as structural consistency, scene complexity, material fidelity, and lighting atmosphere. Extensive experiments demonstrate MajutsuCity reduces layout FID by 83.7% compared with CityDreamer and by 20.1% over CityCraft. Our method ranks first across all AQS and RDR scores, outperforming existing methods by a clear margin. These results confirm MajutsuCity as a new state-of-the-art in geometric fidelity, stylistic adaptability, and semantic controllability for 3D city generation. We expect our framework can inspire new avenues of research in 3D city generation. Our project page: https://longhz140516.github.io/MajutsuCity/. - oai:arXiv.org:2511.20415v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zilong Huang, Jun He, Xiaobin Huang, Ziyi Xiong, Yang Luo, Junyan Ye, Weijia Li, Yiping Chen, Ting Han - - - Latent Collaboration in Multi-Agent Systems - https://arxiv.org/abs/2511.20639 - arXiv:2511.20639v2 Announce Type: replace -Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings. A shared latent working memory then preserves and transfers each agent's internal representations, ensuring lossless information exchange. We provide theoretical analyses establishing that LatentMAS attains higher expressiveness and lossless information preservation with substantially lower complexity than vanilla text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS consistently outperforms strong single-model and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4x-4.3x faster end-to-end inference. These results demonstrate that our new latent collaboration framework enhances system-level reasoning quality while offering substantial efficiency gains without any additional training. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS. - oai:arXiv.org:2511.20639v2 - cs.CL - cs.AI - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jiaru Zou, Xiyuan Yang, Ruizhong Qiu, Gaotang Li, Katherine Tieu, Pan Lu, Ke Shen, Hanghang Tong, Yejin Choi, Jingrui He, James Zou, Mengdi Wang, Ling Yang - - - Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion - https://arxiv.org/abs/2511.20821 - arXiv:2511.20821v2 Announce Type: replace -Abstract: Diffusion models have established the state-of-the-art in text-to-image generation, but their performance often relies on a diffusion prior network to translate text embeddings into the visual manifold for easier decoding. These priors are computationally expensive and require extensive training on massive datasets. In this work, we challenge the necessity of a trained prior at all by employing Optimization-based Visual Inversion (OVI), a training-free and data-free alternative, to replace the need for a prior. OVI initializes a latent visual representation from random pseudo-tokens and iteratively optimizes it to maximize the cosine similarity with input textual prompt embedding. We further propose two novel constraints, a Mahalanobis-based and a Nearest-Neighbor loss, to regularize the OVI optimization process toward the distribution of realistic images. Our experiments, conducted on Kandinsky 2.2, show that OVI can serve as an alternative to traditional priors. More importantly, our analysis reveals a critical flaw in current evaluation benchmarks like T2I-CompBench++, where simply using the text embedding as a prior achieves surprisingly high scores, despite lower perceptual quality. Our constrained OVI methods improve visual fidelity over this baseline, with the Nearest-Neighbor approach proving particularly effective, achieving quantitative scores comparable to or higher than the state-of-the-art data-efficient prior, indicating that the idea merits further investigation. The code will be publicly available upon acceptance. - oai:arXiv.org:2511.20821v2 - cs.CV - cs.AI - cs.CL - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Samuele Dell'Erba, Andrew D. Bagdanov - - - Computing Evolutionarily Stable Strategies in Multiplayer Games - https://arxiv.org/abs/2511.20859 - arXiv:2511.20859v3 Announce Type: replace -Abstract: We present an algorithm for computing all evolutionarily stable strategies in nondegenerate normal-form games with three or more players. - oai:arXiv.org:2511.20859v3 - cs.GT - cs.AI - cs.MA - econ.TH - q-bio.PE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Sam Ganzfried - - - Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning - https://arxiv.org/abs/2511.20993 - arXiv:2511.20993v2 Announce Type: replace -Abstract: Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is limited by poor planning-execution alignment, which reflects a critical gap between abstract plans and actionable, environment-compatible behaviors. This misalignment arises from two interrelated limitations: (1) LLMs often produce subgoals that are semantically plausible but infeasible or irrelevant in the target environment due to insufficient grounding in environment-specific knowledge, and (2) single-LLM planning conflates generation with self-verification, resulting in overconfident yet unreliable subgoals that frequently fail during execution. To address these challenges, we propose Subgoal Graph-Augmented Actor-Critic-Refiner (SGA-ACR), a framework that integrates an environment-specific subgoal graph and structured entity knowledge with a multi-LLM planning pipeline that explicitly separates generation, critique, and refinement to produce executable and verifiable subgoals. A subgoal tracker further monitors execution progress, provides auxiliary rewards, and adaptively updates the subgoal graph to maintain alignment between plans and actions. Experimental results on 22 diverse tasks in the open-world game "Crafter" demonstrate the effectiveness of our proposed method. - oai:arXiv.org:2511.20993v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shanwei Fan, Bin Zhang, Zhiwei Xu, Yingxuan Teng, Siqi Dai, Lin Cheng, Guoliang Fan - - - ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning - https://arxiv.org/abs/2511.21005 - arXiv:2511.21005v3 Announce Type: replace -Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as coarse-grained rewards, reward noise, and inefficient exploration, which lead to unstable training and entropy collapse. To address this challenge, we propose the Intrinsic Confidence-Driven Group Relative Preference Optimization method (ICPO). The intuition behind it lies in the fact that the probabilities of an LLM generating different responses can inherently and directly reflect its self-assessment of the reasoning process. Inspired by the idea of preference modeling, ICPO calculates a preference advantage score for each response by comparing the relative generation probabilities of multiple responses under the same input prompt, and integrates this score with verifiable rewards to guide the exploration process. We have discovered that the preference advantage score not only alleviates the issues of coarse-grained rewards and reward noise but also effectively curbs overconfident errors, enhances the relative superiority of undervalued high-quality responses, and prevents the model from overfitting to specific strategies, thereby facilitating more thorough exploration. Comprehensive experiments across four general-domain benchmarks and three mathematical benchmarks demonstrate that ICPO steadily boosts reasoning compared to GRPO. - oai:arXiv.org:2511.21005v3 - cs.AI - cs.IR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jinpeng Wang, Chao Li, Ting Ye, Mengyuan Zhang, Wei Liu, Jian Luan - - - Data Exfiltration by Compression Attack: Definition and Evaluation on Medical Image Data - https://arxiv.org/abs/2511.21227 - arXiv:2511.21227v2 Announce Type: replace -Abstract: With the rapid expansion of data lakes storing health data and hosting AI algorithms, a prominent concern arises: how safe is it to export machine learning models from these data lakes? In particular, deep network models, widely used for health data processing, encode information from their training dataset, potentially leading to the leakage of sensitive information upon its export. This paper thoroughly examines this issue in the context of medical imaging data and introduces a novel data exfiltration attack based on image compression techniques. - This attack, termed Data Exfiltration by Compression, requires only access to a data lake and is based on lossless or lossy image compression methods. Unlike previous data exfiltration attacks, it is compatible with any image processing task and depends solely on an exported network model without requiring any additional information to be collected during the training process. We explore various scenarios, and techniques to limit the size of the exported model and conceal the compression codes within the network. - Using two public datasets of CT and MR images, we demonstrate that this attack can effectively steal medical images and reconstruct them outside the data lake with high fidelity, achieving an optimal balance between compression and reconstruction quality. Additionally, we investigate the impact of basic differential privacy measures, such as adding Gaussian noise to the model parameters, to prevent the Data Exfiltration by Compression Attack. We also show how the attacker can make their attack resilient to differential privacy at the expense of decreasing the number of stolen images. Lastly, we propose an alternative prevention strategy by fine-tuning the model to be exported. - oai:arXiv.org:2511.21227v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - 10.59275/j.melba.2025-113f - Machine.Learning.for.Biomedical.Imaging. 3 (2025) - Huiyu Li, Nicholas Ayache, Herv\'e Delingette - - - Evaluation of Large Language Models for Numeric Anomaly Detection in Power Systems - https://arxiv.org/abs/2511.21371 - arXiv:2511.21371v2 Announce Type: replace -Abstract: Large language models (LLMs) have gained increasing attention in power grids for their general-purpose capabilities. Meanwhile, anomaly detection (AD) remains critical for grid resilience, requiring accurate and interpretable decisions based on multivariate telemetry. Yet the performance of LLMs on large-scale numeric data for AD remains largely unexplored. This paper presents a comprehensive evaluation of LLMs for numeric AD in power systems. We use GPT-OSS-20B as a representative model and evaluate it on the IEEE 14-bus system. A standardized prompt framework is applied across zero-shot, few-shot, in-context learning, low rank adaptation (LoRA), fine-tuning, and a hybrid LLM-traditional approach. We adopt a rule-aware design based on the three-sigma criterion, and report detection performance and rationale quality. This study lays the groundwork for further investigation into the limitations and capabilities of LLM-based AD and its integration with classical detectors in cyber-physical power grid applications. - oai:arXiv.org:2511.21371v2 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yichen Liu, Hongyu Wu, Bo Liu - - - Mean-square exponential stability of exact and numerical solutions for neutral stochastic delay differential equations with Markovian switching - https://arxiv.org/abs/2511.21620 - arXiv:2511.21620v3 Announce Type: replace -Abstract: This paper investigates the mean-square exponential stability of neutral stochastic differential delay equations (NSDDEs) with Markovian switching. The analysis addresses the complexities arising from the interaction between the neutral term, time-varying delays, and structural changes governed by a continuous-time Markov chain. We establish novel and practical criteria for the mean-square exponential stability of both the underlying system and its numerical approximations via the Euler-Maruyama method. Furthermore, we prove that the numerical scheme can reproduce the exponential decay rate of the true solution with arbitrary accuracy, provided the step size is sufficiently small. The theoretical results are supported by a numerical example that illustrates their effectiveness. - oai:arXiv.org:2511.21620v3 - math.NA - cs.NA - math.PR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jina Yang, Ky Quan Tran - - - JELV: A Judge of Edit-Level Validity for Evaluation and Automated Reference Expansion in Grammatical Error Correction - https://arxiv.org/abs/2511.21700 - arXiv:2511.21700v2 Announce Type: replace -Abstract: Existing Grammatical Error Correction (GEC) systems suffer from limited reference diversity, leading to underestimated evaluation and restricted model generalization. To address this issue, we introduce the Judge of Edit-Level Validity (JELV), an automated framework to validate correction edits from grammaticality, faithfulness, and fluency. Using our proposed human-annotated Pair-wise Edit-level Validity Dataset (PEVData) as benchmark, JELV offers two implementations: a multi-turn LLM-as-Judges pipeline achieving 90% agreement with human annotators, and a distilled DeBERTa classifier with 85% precision on valid edits. We then apply JELV to reclassify misjudged false positives in evaluation and derive a comprehensive evaluation metric by integrating false positive decoupling and fluency scoring, resulting in state-of-the-art correlation with human judgments. We also apply JELV to filter LLM-generated correction candidates, expanding the BEA19's single-reference dataset containing 38,692 source sentences. Retraining top GEC systems on this expanded dataset yields measurable performance gains. JELV provides a scalable solution for enhancing reference diversity and strengthening both evaluation and model generalization. - oai:arXiv.org:2511.21700v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Yuhao Zhan, Yuqing Zhang, Jing Yuan, Qixiang Ma, Zhiqi Yang, Yu Gu, Zemin Liu, Fei Wu - - - On the Incompressibility of Truth With Application to Circuit Complexity - https://arxiv.org/abs/2511.21738 - arXiv:2511.21738v2 Announce Type: replace -Abstract: We revisit the fundamentals of Circuit Complexity and the nature of efficient computation from a new perspective. We present a framework for understanding Circuit Complexity through the lens of Information Theory with analogies to results in Kolmogorov Complexity, viewing circuits as descriptions of truth tables, encoded in logical gates and wires, rather than purely computational devices. From this framework, we re-prove some existing strong Circuit Complexity bounds, explain what the optimal circuits for most Boolean functions look like structurally, give insight into new circuit bounds, and explain the aforementioned results in a unifying intuition that re-frames time entirely. - oai:arXiv.org:2511.21738v2 - cs.CC - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Luke Tonon - - - Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment - https://arxiv.org/abs/2511.21931 - arXiv:2511.21931v2 Announce Type: replace -Abstract: In this work, we propose a simple and computationally efficient framework for evaluating whether machine learning models align with the structure of the data they learn from; that is, whether the model says what the data says. Unlike existing interpretability methods that focus exclusively on explaining model behavior, our approach establishes a baseline derived directly from the data itself. Drawing inspiration from Rubin's Potential Outcomes Framework, we quantify how strongly each feature separates the two outcome groups in a binary classification task, moving beyond traditional descriptive statistics to estimate each feature's effect on the outcome. By comparing these data-derived feature rankings with model-based explanations, we provide practitioners with an interpretable and model-agnostic method for assessing model-data alignment. - oai:arXiv.org:2511.21931v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Henry Salgado, Meagan R. Kendall, Martine Ceberio - - - Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language Models - https://arxiv.org/abs/2511.22019 - arXiv:2511.22019v2 Announce Type: replace -Abstract: Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in safety-critical applications. We introduce a training-free, post-hoc uncertainty estimation method for contrastive VLMs that can be used to detect erroneous predictions. The key to our approach is to measure visual feature consistency within a class, using feature projection combined with multivariate Gaussians to create class-specific probabilistic embeddings. Our method is VLM-agnostic, requires no fine-tuning, demonstrates robustness to distribution shift, and works effectively with as few as 10 training images per class. Extensive experiments on ImageNet, Flowers102, Food101, EuroSAT and DTD show state-of-the-art error detection performance, significantly outperforming both deterministic and probabilistic VLM baselines. Code is available at https://github.com/zhenxianglin/ICPE. - oai:arXiv.org:2511.22019v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhenxiang Lin, Maryam Haghighat, Will Browne, Dimity Miller - - - Simplex-Optimized Hybrid Ensemble for Large Language Model Text Detection Under Generative Distribution Drif - https://arxiv.org/abs/2511.22153 - arXiv:2511.22153v2 Announce Type: replace -Abstract: The widespread adoption of large language models (LLMs) has made it difficult to distinguish human writing from machine-produced text in many real applications. Detectors that were effective for one generation of models tend to degrade when newer models or modified decoding strategies are introduced. In this work, we study this lack of stability and propose a hybrid ensemble that is explicitly designed to cope with changing generator distributions. The ensemble combines three complementary components: a RoBERTa-based classifier fine-tuned for supervised detection, a curvature-inspired score based on perturbing the input and measuring changes in model likelihood, and a compact stylometric model built on hand-crafted linguistic features. The outputs of these components are fused on the probability simplex, and the weights are chosen via validation-based search. We frame this approach in terms of variance reduction and risk under mixtures of generators, and show that the simplex constraint provides a simple way to trade off the strengths and weaknesses of each branch. Experiments on a 30000 document corpus drawn from several LLM families including models unseen during training and paraphrased attack variants show that the proposed method achieves 94.2% accuracy and an AUC of 0.978. The ensemble also lowers false positives on scientific articles compared to strong baselines, which is critical in educational and research settings where wrongly flagging human work is costly - oai:arXiv.org:2511.22153v2 - cs.CL - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-sa/4.0/ - Sepyan Purnama Kristanto, Lutfi Hakim, Dianni Yusuf - - - RealD$^2$iff: Bridging Real-World Gap in Robot Manipulation via Depth Diffusion - https://arxiv.org/abs/2511.22505 - arXiv:2511.22505v2 Announce Type: replace -Abstract: Robot manipulation in the real world is fundamentally constrained by the visual sim2real gap, where depth observations collected in simulation fail to reflect the complex noise patterns inherent to real sensors. In this work, inspired by the denoising capability of diffusion models, we invert the conventional perspective and propose a clean-to-noisy paradigm that learns to synthesize noisy depth, thereby bridging the visual sim2real gap through purely simulation-driven robotic learning. Building on this idea, we introduce RealD$^2$iff, a hierarchical coarse-to-fine diffusion framework that decomposes depth noise into global structural distortions and fine-grained local perturbations. To enable progressive learning of these components, we further develop two complementary strategies: Frequency-Guided Supervision (FGS) for global structure modeling and Discrepancy-Guided Optimization (DGO) for localized refinement. To integrate RealD$^2$iff seamlessly into imitation learning, we construct a pipeline that spans six stages. We provide comprehensive empirical and experimental validation demonstrating the effectiveness of this paradigm. RealD$^2$iff enables two key applications: (1) generating real-world-like depth to construct clean-noisy paired datasets without manual sensor data collection. (2) Achieving zero-shot sim2real robot manipulation, substantially improving real-world performance without additional fine-tuning. - oai:arXiv.org:2511.22505v2 - cs.RO - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiujian Liang, Jiacheng Liu, Mingyang Sun, Qichen He, Cewu Lu, Jianhua Sun - - - Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer - https://arxiv.org/abs/2511.22699 - arXiv:2511.22699v3 Announce Type: replace -Abstract: The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. Leading open-source alternatives, including Qwen-Image, Hunyuan-Image-3.0 and FLUX.2, are characterized by massive parameter counts (20B to 80B), making them impractical for inference, and fine-tuning on consumer-grade hardware. To address this gap, we propose Z-Image, an efficient 6B-parameter foundation generative model built upon a Scalable Single-Stream Diffusion Transformer (S3-DiT) architecture that challenges the "scale-at-all-costs" paradigm. By systematically optimizing the entire model lifecycle -- from a curated data infrastructure to a streamlined training curriculum -- we complete the full training workflow in just 314K H800 GPU hours (approx. $630K). Our few-step distillation scheme with reward post-training further yields Z-Image-Turbo, offering both sub-second inference latency on an enterprise-grade H800 GPU and compatibility with consumer-grade hardware (<16GB VRAM). Additionally, our omni-pre-training paradigm also enables efficient training of Z-Image-Edit, an editing model with impressive instruction-following capabilities. Both qualitative and quantitative experiments demonstrate that our model achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead. We publicly release our code, weights, and online demo to foster the development of accessible, budget-friendly, yet state-of-the-art generative models. - oai:arXiv.org:2511.22699v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Image Team, Huanqia Cai, Sihan Cao, Ruoyi Du, Peng Gao, Steven Hoi, Zhaohui Hou, Shijie Huang, Dengyang Jiang, Xin Jin, Liangchen Li, Zhen Li, Zhong-Yu Li, David Liu, Dongyang Liu, Junhan Shi, Qilong Wu, Feng Yu, Chi Zhang, Shifeng Zhang, Shilin Zhou - - - FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting - https://arxiv.org/abs/2511.23292 - arXiv:2511.23292v2 Announce Type: replace -Abstract: Realistic scene appearance modeling has advanced rapidly with Gaussian Splatting, which enables real-time, high-quality rendering. Recent advances introduced per-primitive textures that incorporate spatial color variations within each Gaussian, improving their expressiveness. However, texture-based Gaussians parameterize appearance with a uniform per-Gaussian sampling grid, allocating equal sampling density regardless of local visual complexity. This leads to inefficient texture space utilization, where high-frequency regions are under-sampled and smooth regions waste capacity, causing blurred appearance and loss of fine structural detail. We introduce FACT-GS, a Frequency-Aligned Complexity-aware Texture Gaussian Splatting framework that allocates texture sampling density according to local visual frequency. Grounded in adaptive sampling theory, FACT-GS reformulates texture parameterization as a differentiable sampling-density allocation problem, replacing the uniform textures with a learnable frequency-aware allocation strategy implemented via a deformation field whose Jacobian modulates local sampling density. Built on 2D Gaussian Splatting, FACT-GS performs non-uniform sampling on fixed-resolution texture grids, preserving real-time performance while recovering sharper high-frequency details under the same parameter budget. - oai:arXiv.org:2511.23292v2 - cs.CV - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Tianhao Xie, Linlian Jiang, Xinxin Zuo, Yang Wang, Tiberiu Popa - - - Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models - https://arxiv.org/abs/2511.23478 - arXiv:2511.23478v2 Announce Type: replace -Abstract: Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while being logically inconsistent or weakly grounded in visual evidence. We identify and formalize these issues through two diagnostic metrics: Think Answer Consistency (TAC), which measures the alignment between reasoning and answers, and Video Attention Score (VAS), which captures the extent to which reasoning depends on visual versus textual cues. Analysis across 11 video reasoning benchmarks shows that current models rely heavily on linguistic priors rather than visual content. To address this, we propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency. Our approach combines timestamp aware supervised fine tuning with Group Relative Policy Optimization (GRPO) guided by a novel Temporal Alignment Reward (TAR). This dual step post training stage encourages temporally aligned and causally coherent video reasoning. The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks, demonstrating that improvements in temporal alignment and reasoning coherence lead to more accurate and trustworthy video understanding. Code: https://github.com/mbzuai-oryx/Video-R2 - oai:arXiv.org:2511.23478v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Muhammad Maaz, Hanoona Rasheed, Fahad Shahbaz Khan, Salman Khan - - - WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing - https://arxiv.org/abs/2512.00387 - arXiv:2512.00387v2 Announce Type: replace -Abstract: Recent image editing models boast next-level intelligent capabilities, facilitating cognition- and creativity-informed image editing. Yet, existing benchmarks provide too narrow a scope for evaluation, failing to holistically assess these advanced abilities. To address this, we introduce WiseEdit, a knowledge-intensive benchmark for comprehensive evaluation of cognition- and creativity-informed image editing, featuring deep task depth and broad knowledge breadth. Drawing an analogy to human cognitive creation, WiseEdit decomposes image editing into three cascaded steps, i.e., Awareness, Interpretation, and Imagination, each corresponding to a task that poses a challenge for models to complete at the specific step. It also encompasses complex tasks, where none of the three steps can be finished easily. Furthermore, WiseEdit incorporates three fundamental types of knowledge: Declarative, Procedural, and Metacognitive knowledge. Ultimately, WiseEdit comprises 1,220 test cases, objectively revealing the limitations of SoTA image editing models in knowledge-based cognitive reasoning and creative composition capabilities. The benchmark, evaluation code, and the generated images of each model will be made publicly available soon. Project Page: https://qnancy.github.io/wiseedit_project_page/. - oai:arXiv.org:2512.00387v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kaihang Pan, Weile Chen, Haiyi Qiu, Qifan Yu, Wendong Bu, Zehan Wang, Yun Zhu, Juncheng Li, Siliang Tang - - - CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency - https://arxiv.org/abs/2512.00417 - arXiv:2512.00417v3 Announce Type: replace -Abstract: This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in the uniquely demanding and fast-paced cryptocurrency domain. Unlike general-purpose agent benchmarks for search and prediction, professional crypto analysis presents specific challenges: \emph{extreme time-sensitivity}, \emph{a highly adversarial information environment}, and the critical need to synthesize data from \emph{diverse, specialized sources}, such as on-chain intelligence platforms and real-time Decentralized Finance (DeFi) dashboards. CryptoBench thus serves as a much more challenging and valuable scenario for LLM agent assessment. To address these challenges, we constructed a live, dynamic benchmark featuring 50 questions per month, expertly designed by crypto-native professionals to mirror actual analyst workflows. These tasks are rigorously categorized within a four-quadrant system: Simple Retrieval, Complex Retrieval, Simple Prediction, and Complex Prediction. This granular categorization enables a precise assessment of an LLM agent's foundational data-gathering capabilities alongside its advanced analytical and forecasting skills. - Our evaluation of ten LLMs, both directly and within an agentic framework, reveals a performance hierarchy and uncovers a failure mode. We observe a \textit{retrieval-prediction imbalance}, where many leading models, despite being proficient at data retrieval, demonstrate a pronounced weakness in tasks requiring predictive analysis. This highlights a problematic tendency for agents to appear factually grounded while lacking the deeper analytical capabilities to synthesize information. - oai:arXiv.org:2512.00417v3 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiacheng Guo, Suozhi Huang, Zixin Yao, Yifan Zhang, Yifu Lu, Jiashuo Liu, Zihao Li, Nicholas Deng, Qixin Xiao, Jia Tian, Kanghong Zhan, Tianyi Li, Xiaochen Liu, Jason Ge, Chaoyang He, Kaixuan Huang, Lin Yang, Wenhao Huang, Mengdi Wang - - - Significant Other AI: Identity, Memory, and Emotional Regulation as Long-Term Relational Intelligence - https://arxiv.org/abs/2512.00418 - arXiv:2512.00418v2 Announce Type: replace -Abstract: Significant Others (SOs) stabilize identity, regulate emotion, and support narrative meaning-making, yet many people today lack access to such relational anchors. Recent advances in large language models and memory-augmented AI raise the question of whether artificial systems could support some of these functions. Existing empathic AIs, however, remain reactive and short-term, lacking autobiographical memory, identity modeling, predictive emotional regulation, and narrative coherence. This manuscript introduces Significant Other Artificial Intelligence (SO-AI) as a new domain of relational AI. It synthesizes psychological and sociological theory to define SO functions and derives requirements for SO-AI, including identity awareness, long-term memory, proactive support, narrative co-construction, and ethical boundary enforcement. A conceptual architecture is proposed, comprising an anthropomorphic interface, a relational cognition layer, and a governance layer. A research agenda outlines methods for evaluating identity stability, longitudinal interaction patterns, narrative development, and sociocultural impact. SO-AI reframes AI-human relationships as long-term, identity-bearing partnerships and provides a foundational blueprint for investigating whether AI can responsibly augment the relational stability many individuals lack today. - oai:arXiv.org:2512.00418v2 - cs.HC - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Sung Park - - - Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction - https://arxiv.org/abs/2512.00960 - arXiv:2512.00960v2 Announce Type: replace -Abstract: Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an unparalleled diversity of human activities, objects, and environments. However, accurately and scalably extracting 4D interaction data from these in-the-wild videos remains a significant and unsolved challenge. Thus, in this work, we introduce 4DHOISolver, a novel and efficient optimization framework that constrains the ill-posed 4D HOI reconstruction problem by leveraging sparse, human-in-the-loop contact point annotations, while maintaining high spatio-temporal coherence and physical plausibility. Leveraging this framework, we introduce Open4DHOI, a new large-scale 4D HOI dataset featuring a diverse catalog of 144 object types and 103 actions. Furthermore, we demonstrate the effectiveness of our reconstructions by enabling an RL-based agent to imitate the recovered motions. However, a comprehensive benchmark of existing 3D foundation models indicates that automatically predicting precise human-object contact correspondences remains an unsolved problem, underscoring the immediate necessity of our human-in-the-loop strategy while posing an open challenge to the community. Data and code will be publicly available at https://wenboran2002.github.io/open4dhoi/ - oai:arXiv.org:2512.00960v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Boran Wen, Ye Lu, Keyan Wan, Sirui Wang, Jiahong Zhou, Junxuan Liang, Xinpeng Liu, Bang Xiao, Dingbang Huang, Ruiyang Liu, Yong-Lu Li - - - MM-ACT: Learn from Multimodal Parallel Generation to Act - https://arxiv.org/abs/2512.00975 - arXiv:2512.00975v2 Announce Type: replace -Abstract: A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT. - oai:arXiv.org:2512.00975v2 - cs.CV + Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity + https://arxiv.org/abs/2512.04165 + arXiv:2512.04165v3 Announce Type: replace +Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich feature learning, often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this complexity is a significant and often unavoidable challenge. Here, we propose a powerful heuristic route for predicting the data and width scales at which various patterns of feature learning emerge. This form of scale analysis is considerably simpler than exact theories and reproduces the scaling exponents of various known results. In addition, we make novel predictions on complex toy architectures, such as three-layer non-linear networks and attention heads, thus extending the scope of first-principle theories of deep learning. + oai:arXiv.org:2512.04165v3 cs.LG - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Haotian Liang, Xinyi Chen, Bin Wang, Mingkang Chen, Yitian Liu, Yuhao Zhang, Zanxin Chen, Tianshuo Yang, Yilun Chen, Jiangmiao Pang, Dong Liu, Xiaokang Yang, Yao Mu, Wenqi Shao, Ping Luo - - - ChartAnchor: Chart Grounding with Structural-Semantic Fidelity - https://arxiv.org/abs/2512.01017 - arXiv:2512.01017v2 Announce Type: replace -Abstract: Recent advances in multimodal large language models (MLLMs) highlight the need for benchmarks that rigorously evaluate structured chart comprehension. Chart grounding refers to the bidirectional alignment between a chart's visual appearance and the structured semantics. This task requires models to produce a symbolic specification that faithfully captures the chart's visual and structural intent, while also recovering the underlying tabular data with precise values and relationships. Chart grounding directly reflects a model's capabilities in numerical reasoning, multimodal alignment, and structural reconstruction, and has several important applications in real-world scenarios. Existing benchmarks, constrained by narrow chart diversity, isolated tasks, and incomplete evaluation frameworks, fail to holistically assess grounding. To address this, we propose ChartAnchor, a comprehensive benchmark of 8k+ chart-table-code triples spanning 30 chart types drawn from diverse real-world and augmented sources. ChartAnchor introduces two complementary tasks: chart-to-code generation (synthesizing executable code to replicate charts) and controlled chart-to-table reconstruction (extracting exact data with predefined headers), enabling cross-validation of visual and numerical fidelity. A multi-level evaluation framework integrates semantic validation, stylistic analysis, and perceptual metrics to assess both structural and content-level correctness. Extensive experiments on MLLMs reveal critical limitations in numerical precision and code synthesis, emphasizing the need for structured reasoning beyond surface-level perception. By unifying symbolic and data-driven grounding, ChartAnchor establishes a rigorous foundation for chart grounding, offering meaningful insights for advancing MLLMs in scientific, financial, and industrial domains. - oai:arXiv.org:2512.01017v2 - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Xinhang Li, Jingbo Zhou, Pengfei Luo, Yixiong Xiao, Tong Xu - - - Autodeleveraging: Impossibilities and Optimization - https://arxiv.org/abs/2512.01112 - arXiv:2512.01112v2 Announce Type: replace -Abstract: Autodeleveraging (ADL) is a last-resort loss socialization mechanism for perpetual futures venues. It is triggered when solvency-preserving liquidations fail. Despite the dominance of perpetual futures in the crypto derivatives market, with over \$60 trillion of volume in 2024, there has been no formal study of ADL. In this paper, we provide the first rigorous model of ADL. We prove that ADL mechanisms face a fundamental \emph{trilemma}: no policy can simultaneously satisfy exchange \emph{solvency}, \emph{revenue}, and \emph{fairness} to traders. This impossibility theorem implies that as participation scales, a novel form of \emph{moral hazard} grows asymptotically, rendering `zero-loss' socialization impossible. Constructively, we show that three classes of ADL mechanisms can optimally navigate this trilemma to provide fairness, robustness to price shocks, and maximal exchange revenue. We analyze these mechanisms on the Hyperliquid dataset from October 10, 2025, when ADL was used repeatedly to close \$2.1 billion of positions in 12 minutes. By comparing our ADL mechanisms to the standard approaches used in practice, we demonstrate empirically that Hyperliquid's production queue overutilized ADL by $\approx 28\times$ relative to our optimal policy, imposing roughly \$653 million of unnecessary haircuts on winning traders. This comparison also suggests that Binance overutilized ADL far more than Hyperliquid. Our results both theoretically and empirically demonstrate that optimized ADL mechanisms can dramatically reduce the loss of trader profits while maintaining exchange solvency. - oai:arXiv.org:2512.01112v2 - cs.GT - q-fin.RM - q-fin.TR - Tue, 09 Dec 2025 00:00:00 -0500 + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Tarun Chitra + Noa Rubin, Orit Davidovich, Zohar Ringel - Unsupervised decoding of encoded reasoning using language model interpretability - https://arxiv.org/abs/2512.01222 - arXiv:2512.01222v2 Announce Type: replace -Abstract: As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investigate whether current interpretability techniques can penetrate such encoded reasoning, we construct a controlled testbed by fine-tuning a reasoning model (DeepSeek-R1-Distill-Llama-70B) to perform chain-of-thought reasoning in ROT-13 encryption while maintaining intelligible English outputs. We evaluate mechanistic interpretability methods--in particular, logit lens analysis--on their ability to decode the model's hidden reasoning process using only internal activations. We show that logit lens can effectively translate encoded reasoning, with accuracy peaking in intermediate-to-late layers. Finally, we develop a fully unsupervised decoding pipeline that combines logit lens with automated paraphrasing, achieving substantial accuracy in reconstructing complete reasoning transcripts from internal model representations. These findings suggest that current mechanistic interpretability techniques may be more robust to simple forms of encoded reasoning than previously understood. Our work provides an initial framework for evaluating interpretability methods against models that reason in non-human-readable formats, contributing to the broader challenge of maintaining oversight over increasingly capable AI systems. - oai:arXiv.org:2512.01222v2 + Orchestrator Multi-Agent Clinical Decision Support System for Secondary Headache Diagnosis in Primary Care + https://arxiv.org/abs/2512.04207 + arXiv:2512.04207v2 Announce Type: replace +Abstract: Unlike most primary headaches, secondary headaches need specialized care and can have devastating consequences if not treated promptly. Clinical guidelines highlight several 'red flag' features, such as thunderclap onset, meningismus, papilledema, focal neurologic deficits, signs of temporal arteritis, systemic illness, and the 'worst headache of their life' presentation. Despite these guidelines, determining which patients require urgent evaluation remains challenging in primary care settings. Clinicians often work with limited time, incomplete information, and diverse symptom presentations, which can lead to under-recognition and inappropriate care. We present a large language model (LLM)-based multi-agent clinical decision support system built on an orchestrator-specialist architecture, designed to perform explicit and interpretable secondary headache diagnosis from free-text clinical vignettes. The multi-agent system decomposes diagnosis into seven domain-specialized agents, each producing a structured and evidence-grounded rationale, while a central orchestrator performs task decomposition and coordinates agent routing. We evaluated the multi-agent system using 90 expert-validated secondary headache cases and compared its performance with a single-LLM baseline across two prompting strategies: question-based prompting (QPrompt) and clinical practice guideline-based prompting (GPrompt). We tested five open-source LLMs (Qwen-30B, GPT-OSS-20B, Qwen-14B, Qwen-8B, and Llama-3.1-8B), and found that the orchestrated multi-agent system with GPrompt consistently achieved the highest F1 scores, with larger gains in smaller models. These findings demonstrate that structured multi-agent reasoning improves accuracy beyond prompt engineering alone and offers a transparent, clinically aligned approach for explainable decision support in secondary headache diagnosis. + oai:arXiv.org:2512.04207v2 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Ching Fang, Samuel Marks - - - DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy - https://arxiv.org/abs/2512.01302 - arXiv:2512.01302v2 Announce Type: replace -Abstract: Despite recent text-to-image models achieving highfidelity text rendering, they still struggle with long or multiple texts due to diluted global attention. We propose DCText, a training-free visual text generation method that adopts a divide-and-conquer strategy, leveraging the reliable short-text generation of Multi-Modal Diffusion Transformers. Our method first decomposes a prompt by extracting and dividing the target text, then assigns each to a designated region. To accurately render each segment within their regions while preserving overall image coherence, we introduce two attention masks - Text-Focus and Context-Expansion - applied sequentially during denoising. Additionally, Localized Noise Initialization further improves text accuracy and region alignment without increasing computational cost. Extensive experiments on single- and multisentence benchmarks show that DCText achieves the best text accuracy without compromising image quality while also delivering the lowest generation latency. - oai:arXiv.org:2512.01302v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jaewoo Song, Jooyoung Choi, Kanghyun Baek, Sangyub Lee, Daemin Park, Sungroh Yoon + Xizhi Wu, Nelly Estefanie Garduno-Rapp, Justin F Rousseau, Mounika Thakkallapally, Hang Zhang, Yuelyu Ji, Shyam Visweswaran, Yifan Peng, Yanshan Wang - Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians - https://arxiv.org/abs/2512.01306 - arXiv:2512.01306v2 Announce Type: replace -Abstract: Branches swaying in the breeze, flags rippling in the wind, and boats rocking on the water all show how aerodynamics shape natural motion -- an effect crucial for realism in vision and graphics. In this paper, we present Gaussian Swaying, a surface-based framework for aerodynamic simulation using 3D Gaussians. Unlike mesh-based methods that require costly meshing, or particle-based approaches that rely on discrete positional data, Gaussian Swaying models surfaces continuously with 3D Gaussians, enabling efficient and fine-grained aerodynamic interaction. Our framework unifies simulation and rendering on the same representation: Gaussian patches, which support force computation for dynamics while simultaneously providing normals for lightweight shading. Comprehensive experiments on both synthetic and real-world datasets across multiple metrics demonstrate that Gaussian Swaying achieves state-of-the-art performance and efficiency, offering a scalable approach for realistic aerodynamic scene simulation. - oai:arXiv.org:2512.01306v2 - cs.CV - cs.GR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hongru Yan, Xiang Zhang, Zeyuan Chen, Fangyin Wei, Zhuowen Tu - - - Neural Tucker Convolutional Network for Water Quality Analysis - https://arxiv.org/abs/2512.01465 - arXiv:2512.01465v2 Announce Type: replace -Abstract: Water quality monitoring is a core component of ecological environmental protection. However, due to sensor failure or other inevitable factors, data missing often exists in long-term monitoring, posing great challenges in water quality analysis. This paper proposes a Neural Tucker Convolutional Network (NTCN) model for water quality data imputation, which features the following key components: a) Encode different mode entities into respective embedding vectors, and construct a Tucker interaction tensor by outer product operations to capture the complex mode-wise feature interactions; b) Use 3D convolution to extract fine-grained spatiotemporal features from the interaction tensor. Experiments on three real-world water quality datasets show that the proposed NTCN model outperforms several state-of-the-art imputation models in terms of accuracy. - oai:arXiv.org:2512.01465v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Hongnan Si, Tong Li, Yujie Chen, Xin Liao - - - Multi-Path Collaborative Reasoning via Reinforcement Learning - https://arxiv.org/abs/2512.01485 - arXiv:2512.01485v2 Announce Type: replace -Abstract: Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible alternatives. Recent methods attempt to address this by generating soft abstract tokens to enable reasoning in a continuous semantic space. However, we find that such approaches remain constrained by the greedy nature of autoregressive decoding, which fundamentally isolates the model from alternative reasoning possibilities. In this work, we propose Multi-Path Perception Policy Optimization (M3PO), a novel reinforcement learning framework that explicitly injects collective insights into the reasoning process. M3PO leverages parallel policy rollouts as naturally diverse reasoning sources and integrates cross-path interactions into policy updates through a lightweight collaborative mechanism. This design allows each trajectory to refine its reasoning with peer feedback, thereby cultivating more reliable multi-step reasoning patterns. Empirical results show that M3PO achieves state-of-the-art performance on both knowledge- and reasoning-intensive benchmarks. Models trained with M3PO maintain interpretability and inference efficiency, underscoring the promise of multi-path collaborative learning for robust reasoning. - oai:arXiv.org:2512.01485v2 - cs.AI + Polynomiogram: An Integrated Framework for Root Visualization and Generative Art + https://arxiv.org/abs/2512.04263 + arXiv:2512.04263v2 Announce Type: replace +Abstract: This work presents the Polynomiogram framework, an integrated computational platform for exploring, visualizing, and generating art from polynomial root systems. The main innovation is a flexible sampling scheme in which two independent parameters are drawn from user defined domains and mapped to the polynomial coefficients through a generating function. This design allows the same mathematical foundation to support both scientific investigation and generative algorithmic art. The framework integrates two complementary numerical engines: NumPy companion matrix solver for fast, large scale computation and MPSolve for high precision, scientifically rigorous validation. This dual architecture enables efficient visualization for creative use and accurate computation for research and education. Numerical accuracy was verified using classical ensembles, including the Kac and Lucas polynomials. The method was applied to the cubic polynomial system to analyze its bifurcation structure, demonstrating its value as both a scientific tool for exploring root phenomena and an educational aid for visualizing fundamental concepts in algebra and dynamical systems. Beyond analysis, the Polynomiogram also demonstrated its potential as a tool for personalized generative art. Examples include the use of the platform to generate a natural form resembling a hibiscus flower and to create personalized artwork expressing gratitude toward advances in artificial intelligence and large language models through a tribute composition. + oai:arXiv.org:2512.04263v2 + cs.SE cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Jindi Lv, Yuhao Zhou, Zheng Zhu, Xiaofeng Wang, Guan Huang, Jiancheng Lv - - - Ergodicity and invariant measure approximation of the stochastic Cahn-Hilliard equation via an explicit fully discrete scheme - https://arxiv.org/abs/2512.01621 - arXiv:2512.01621v3 Announce Type: replace -Abstract: This paper investigates the stochastic Cahn-Hilliard equation (SCHE) driven by additive space-time white noise. We first refine the analytical ergodic theory by proving that the continuum equation admits a unique invariant measure in the more regular state space H_\alpha, extending the classical result of Da Prato and Debussche (1996) on the negative Sobolev space $\dot{H}^{-1}_\alpha$. To approximate long-time behaviour, we introduce an explicit fully discrete scheme that combines a finite-difference spatial discretization with a strongly tamed exponential Euler method in time. Uniform-in-time moment bounds in the $L^\infty$-norm are established for the numerical solution, and a uniform strong convergence estimate with an explicit rate is derived for the fully discrete approximation. Exploiting a mass-preserving minorization tailored to Neumann boundary conditions, we further show that the numerical scheme is geometrically ergodic and possesses a unique invariant measure, together with polynomial-order error bounds for approximating the exact invariant measure. Strong laws of large numbers are proved for both the continuous and discrete systems, ensuring almost-sure convergence of temporal averages to the corresponding ergodic limits. Numerical experiments corroborate the theoretical findings, including the long-time strong convergence and the accuracy of invariant measure approximation. Overall, the results provide a complete analytical and numerical framework for investigating the long-time statistical behaviour of the SCHE. - oai:arXiv.org:2512.01621v3 - math.NA - cs.NA - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Nan Deng, Yibo Wang, Wanrong Cao - - - JFR: An Efficient Jump Frontier Relaxation Strategy for Bellman-Ford - https://arxiv.org/abs/2512.01802 - arXiv:2512.01802v2 Announce Type: replace -Abstract: We propose JFR, a Bellman-Ford-based optimization framework leveraging frontier contraction and abstract multi-hop jump propagation to accelerate shortest-path computation while strictly preserving correctness. JFR achieves substantial reductions in relaxation operations, ranging from 25 to 99 percent, across sparse, dense, and negative-edge graphs, ensuring robust performance even under adversarial or highly connected topologies. On ultra-large graphs with up to N=20,000 nodes and 295 million edges, JFR maintains strong operational reductions and comparable or improved runtime relative to SPFA-SLF, demonstrating consistent robustness across graph size and density. Lower relaxation counts imply reduced memory-access overheads and computational effort; this normalized work reduction highlights JFR's suitability for scenarios requiring high throughput or energy-conscious operation. Future work focuses on integrating high-performance queue structures, adaptive frontier strategies, and cache-aware techniques to further reduce constant-factor overheads and fully realize JFR's practical runtime potential. - oai:arXiv.org:2512.01802v2 - cs.DS - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xin Wang, Xi Chen - - - Much Ado About Noising: Dispelling the Myths of Generative Robotic Control - https://arxiv.org/abs/2512.01809 - arXiv:2512.01809v2 Announce Type: replace -Abstract: Generative models, like flows and diffusions, have recently emerged as popular and efficacious policy parameterizations in robotics. There has been much speculation as to the factors underlying their successes, ranging from capturing multi-modal action distribution to expressing more complex behaviors. In this work, we perform a comprehensive evaluation of popular generative control policies (GCPs) on common behavior cloning (BC) benchmarks. We find that GCPs do not owe their success to their ability to capture multi-modality or to express more complex observation-to-action mappings. Instead, we find that their advantage stems from iterative computation, as long as intermediate steps are supervised during training and this supervision is paired with a suitable level of stochasticity. As a validation of our findings, we show that a minimum iterative policy (MIP), a lightweight two-step regression-based policy, essentially matches the performance of flow GCPs, and often outperforms distilled shortcut models. Our results suggest that the distribution-fitting component of GCPs is less salient than commonly believed, and point toward new design spaces focusing solely on control performance. Project page: https://simchowitzlabpublic.github.io/much-ado-about-noising-project/ - oai:arXiv.org:2512.01809v2 - cs.RO - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang, Claire Jin, Daniel Pfrommer, Chenyang Yuan, Frank Permenter, Guannan Qu, Nicholas Boffi, Guanya Shi, Max Simchowitz - - - Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling - https://arxiv.org/abs/2512.01821 - arXiv:2512.01821v2 Announce Type: replace -Abstract: Spatial reasoning, the ability to understand and interpret the 3D structure of the world, is a critical yet underdeveloped capability in Multimodal Large Language Models (MLLMs). Current methods predominantly rely on verbal descriptive tuning, which suffers from visual illiteracy, i.e., they learn spatial concepts through textual symbols alone, devoid of connection to their visual manifestations. To bridge this gap, this paper introduces MILO, an Implicit spatIaL wOrld modeling paradigm that simulates human-like spatial imagination. MILO integrates a visual generator to provide geometry-aware feedback, thereby implicitly grounding the MLLM's symbolic reasoning in perceptual experience. Complementing this paradigm, we propose RePE (Relative Positional Encoding), a novel encoding scheme that captures relative camera-pose transformations, offering superior performance over absolute coordinate systems. To support the training, we construct GeoGen, a large-scale Geometry-aware Generative dataset with approximately 2,241 videos and 67,827 observation-action-outcome triplets. Experiments demonstrate that our approach significantly enhances spatial reasoning capabilities across multiple baselines and benchmarks, offering a more holistic understanding of 3D space. - oai:arXiv.org:2512.01821v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Meng Cao, Haokun Lin, Haoyuan Li, Haoran Tang, Rongtao Xu, Dong An, Xue Liu, Ian Reid, Xiaodan Liang - - - Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch - https://arxiv.org/abs/2512.02395 - arXiv:2512.02395v2 Announce Type: replace -Abstract: Despite recent progress in multimodal agentic systems, existing approaches often treat image manipulation and web search as disjoint capabilities, rely heavily on costly reinforcement learning, and lack planning grounded in real tool-execution traces. To address these limitations, we present Skywork-R1V4, a 30B (A3B) parameter multimodal agentic model that unifies multimodal planning, active image manipulation ("thinking with images"), deep multimodal search, and, most critically, interleaved reasoning that dynamically alternates between visual operations and external knowledge retrieval. Trained solely via supervised fine-tuning on fewer than 30,000 high-quality, planning-execution-consistent trajectories and validated through stepwise consistency filtering, Skywork-R1V4 achieves state-of-the-art results across perception and multimodal search benchmarks: it scores 66.1 on MMSearch and 67.2 on FVQA, surpassing Gemini 2.5 Flash on all 11 metrics. Skywork-R1V4 exhibits emergent long-horizon reasoning at inference time, successfully orchestrating more than 10 tool calls to solve complex, multi-step tasks. Our results demonstrate that sophisticated agentic multimodal intelligence can be achieved through carefully curated supervised learning alone, without any reliance on reinforcement learning. - oai:arXiv.org:2512.02395v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Yifan Zhang, Liang Hu, Haofeng Sun, Peiyu Wang, Yichen Wei, Shukang Yin, Jiangbo Pei, Wei Shen, Peng Xia, Yi Peng, Tianyidan Xie, Eric Li, Yang Liu, Xuchen Song, Yahui Zhou + Hoang Duc Nguyen, Anh Van Pham, Hien D. Nguyen - SwarmDiffusion: End-To-End Traversability-Guided Diffusion for Embodiment-Agnostic Navigation of Heterogeneous Robots - https://arxiv.org/abs/2512.02851 - arXiv:2512.02851v3 Announce Type: replace -Abstract: Visual traversability estimation is critical for autonomous navigation, but existing VLM-based methods rely on hand-crafted prompts, generalize poorly across embodiments, and output only traversability maps, leaving trajectory generation to slow external planners. We propose SwarmDiffusion, a lightweight end-to-end diffusion model that jointly predicts traversability and generates a feasible trajectory from a single RGB image. To remove the need for annotated or planner-produced paths, we introduce a planner-free trajectory construction pipeline based on randomized waypoint sampling, Bezier smoothing, and regularization enforcing connectivity, safety, directionality, and path thinness. This enables learning stable motion priors without demonstrations. SwarmDiffusion leverages VLM-derived supervision without prompt engineering and conditions the diffusion process on a compact embodiment state, producing physically consistent, traversable paths that transfer across different robot platforms. Across indoor environments and two embodiments (quadruped and aerial), the method achieves 80-100% navigation success and 0.09s inference, and adapts to a new robot using only-500 additional visual samples. It generalizes reliably to unseen environments in simulation and real-world trials, offering a scalable, prompt-free approach to unified traversability reasoning and trajectory generation. - oai:arXiv.org:2512.02851v3 + RoboBPP: Benchmarking Robotic Online Bin Packing with Physics-based Simulation + https://arxiv.org/abs/2512.04415 + arXiv:2512.04415v2 Announce Type: replace +Abstract: Physical feasibility in 3D bin packing is a key requirement in modern industrial logistics and robotic automation. With the growing adoption of industrial automation, online bin packing has gained increasing attention. However, inconsistencies in problem settings, test datasets, and evaluation metrics have hindered progress in the field, and there is a lack of a comprehensive benchmarking system. Direct testing on real hardware is costly, and building a realistic simulation environment is also challenging. To address these limitations, we introduce RoboBPP, a benchmarking system designed for robotic online bin packing. RoboBPP integrates a physics-based simulator to assess physical feasibility. In our simulation environment, we introduce a robotic arm and boxes at real-world scales to replicate real industrial packing workflows. By simulating conditions that arise in real industrial applications, we ensure that evaluated algorithms are practically deployable. In addition, prior studies often rely on synthetic datasets whose distributions differ from real-world industrial data. To address this issue, we collect three datasets from real industrial workflows, including assembly-line production, logistics packing, and furniture manufacturing. The benchmark comprises three carefully designed test settings and extends existing evaluation metrics with new metrics for structural stability and operational safety. We design a scoring system and derive a range of insights from the evaluation results. RoboBPP is fully open-source and is equipped with visualization tools and an online leaderboard, providing a reproducible and extensible foundation for future research and industrial applications (https://robot-bin-packing-benchmark.github.io). + oai:arXiv.org:2512.04415v2 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Iana Zhura, Sausar Karaf, Faryal Batool, Nipun Dhananjaya Weerakkodi Mudalige, Valerii Serpiva, Ali Alridha Abdulkarim, Aleksey Fedoseev, Didar Seyidov, Hajira Amjad, Dzmitry Tsetserukou - - - AC/DC Frequency-Dependent Power Flow Jacobian: Quantifying Grid Support and Stability Implications - https://arxiv.org/abs/2512.02872 - arXiv:2512.02872v2 Announce Type: replace -Abstract: This letter proposes an AC/DC frequency-dependent power flow Jacobian analysis to identify the system support capabilities. In addition, the analyses reveal that system support capabilities do not necessarily enhance the system stability margin, suggesting that technical requirements of narrow-frequency-band and AC-side focused specifications may not lead to the expected performance of GFM. - oai:arXiv.org:2512.02872v2 - eess.SY - cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Dongyeong Lee, Eros Avdiaj, Jef Beerten - - - AutoNeural: Co-Designing Vision-Language Models for NPU Inference - https://arxiv.org/abs/2512.02924 - arXiv:2512.02924v2 Announce Type: replace -Abstract: While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary factors: the quantization brittleness of Vision Transformers (ViTs) and the I/O-bound nature of autoregressive attention mechanisms, which fail to utilize the high arithmetic throughput of NPUs. To bridge this gap, we propose AutoNeural, an NPU-native VLM architecture co-designed for integer-only inference. We replace the standard ViT encoder with a MobileNetV5-style backbone utilizing depthwise separable convolutions, which ensures bounded activation distributions for stable INT4/8/16 quantization. Complementing this, our language backbone integrates State-Space Model (SSM) principles with Transformer layers, employing efficient gated convolutions to achieve linear-time complexity. This hybrid design eliminates the heavy memory I/O overhead of Key-Value caching during generation. Our approach delivers substantial efficiency gains, reducing quantization error of vision encoder by up to 7x and end-to-end latency by 14x compared to conventional baselines. The AutoNeural also delivers 3x decoding speed and 4x longer context window than the baseline. We validate these improvements via a real-world automotive case study on the Qualcomm SA8295P SoC, demonstrating real-time performance for cockpit applications. Our results highlight that rethinking model topology specifically for NPU constraints is a prerequisite for robust multi-modal edge intelligence. - oai:arXiv.org:2512.02924v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Wei Chen, Liangmin Wu, Yunhai Hu, Zhiyuan Li, Zhiyuan Cheng, Yicheng Qian, Lingyue Zhu, Zhipeng Hu, Luoyi Liang, Qiang Tang, Zhen Liu, Han Yang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zhoufeng Wang, Hang Zhao, Juzhan Xu, Shishun Zhang, Zeyu Xiong, Ruizhen Hu, Chenyang Zhu, Kai Xu - PPTArena: A Benchmark for Agentic PowerPoint Editing - https://arxiv.org/abs/2512.03042 - arXiv:2512.03042v2 Announce Type: replace -Abstract: We introduce PPTArena, a benchmark for PowerPoint editing that measures reliable modifications to real slides under natural-language instructions. In contrast to image-PDF renderings or text-to-slide generation, PPTArena focuses on in-place editing across 100 decks, 2125 slides, and over 800 targeted edits covering text, charts, tables, animations, and master-level styles. Each case includes a ground-truth deck, a fully specified target outcome, and a dual VLM-as-judge pipeline that separately scores instruction following and visual quality using both structural diffs and slide images. Building on this setting, we propose PPTPilot, a structure-aware slide-editing agent that plans semantic edit sequences, routes between high-level programmatic tools and deterministic XML operations for precise control, and verifies outputs through an iterative plan-edit-check loop against task-specific constraints. In our experiments, PPTPilot outperforms strong proprietary agents and frontier VLM systems by over 10 percentage points on compound, layout-sensitive, and cross-slide edits, with particularly large gains in visual fidelity and deck-wide consistency. Despite these improvements, existing agents still underperform on long-horizon, document-scale tasks in PPTArena, highlighting the remaining challenges in reliable PPT editing. - oai:arXiv.org:2512.03042v2 - cs.CV + MARL Warehouse Robots + https://arxiv.org/abs/2512.04463 + arXiv:2512.04463v2 Announce Type: replace +Abstract: We present a comparative study of multi-agent reinforcement learning (MARL) algorithms for cooperative warehouse robotics. We evaluate QMIX and IPPO on the Robotic Warehouse (RWARE) environment and a custom Unity 3D simulation. Our experiments reveal that QMIX's value decomposition significantly outperforms independent learning approaches (achieving 3.25 mean return vs. 0.38 for advanced IPPO), but requires extensive hyperparameter tuning -- particularly extended epsilon annealing (5M+ steps) for sparse reward discovery. We demonstrate successful deployment in Unity ML-Agents, achieving consistent package delivery after 1M training steps. While MARL shows promise for small-scale deployments (2-4 robots), significant scaling challenges remain. Code and analyses: https://pallman14.github.io/MARL-QMIX-Warehouse-Robots/ + oai:arXiv.org:2512.04463v2 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by/4.0/ - Michael Ofengenden, Yunze Man, Ziqi Pang, Yu-Xiong Wang + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Price Allman, Lian Thang, Dre Simmons, Salmon Riaz - Beyond the Black Box: A Cognitive Architecture for Explainable and Aligned AI - https://arxiv.org/abs/2512.03072 - arXiv:2512.03072v2 Announce Type: replace -Abstract: Current AI paradigms, as "architects of experience," face fundamental challenges in explainability and value alignment. This paper introduces "Weight-Calculatism," a novel cognitive architecture grounded in first principles, and demonstrates its potential as a viable pathway toward Artificial General Intelligence (AGI). The architecture deconstructs cognition into indivisible Logical Atoms and two fundamental operations: Pointing and Comparison. Decision-making is formalized through an interpretable Weight-Calculation model (Weight = Benefit * Probability), where all values are traceable to an auditable set of Initial Weights. This atomic decomposition enables radical explainability, intrinsic generality for novel situations, and traceable value alignment. We detail its implementation via a graph-algorithm-based computational engine and a global workspace workflow, supported by a preliminary code implementation and scenario validation. Results indicate that the architecture achieves transparent, human-like reasoning and robust learning in unprecedented scenarios, establishing a practical and theoretical foundation for building trustworthy and aligned AGI. - oai:arXiv.org:2512.03072v2 + SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation + https://arxiv.org/abs/2512.04529 + arXiv:2512.04529v2 Announce Type: replace +Abstract: Generating academic slides from scientific papers is a challenging multimodal reasoning task that requires both long context understanding and deliberate visual planning. Existing approaches largely reduce it to text only summarization, overlooking the visual component and design intensive nature of slide creation. In this paper we introduce SlideGen, an agentic, modular, and visual in the loop framework for scientific paper to slide generation. SlideGen orchestrates a group of vision language agents that reason collaboratively over the document structure and semantics, producing editable PPTX slides with logical flow and compelling visual presentation. By integrating coordinated outlining, mapping, arrangement, note synthesis, and iterative refinement, our system consistently delivers slides of expert level quality. Across diverse benchmarks and strong baselines, SlideGen outperforms existing methods in visual quality, content faithfulness, and readability, positioning it as the new state of the art in automated slide generation. Our work establishes a foundation for design aware multimodal slide generation, demonstrating how agentic collaboration can bridge understanding and presentation in complex multimodal reasoning tasks. + oai:arXiv.org:2512.04529v2 cs.AI - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Hu Keyi - - - Strengthening Han's Fourier Entropy-Influence Inequality via an Information-Theoretic Proof - https://arxiv.org/abs/2512.03117 - arXiv:2512.03117v2 Announce Type: replace -Abstract: We strengthen Han's Fourier entropy-influence inequality $$ H[\widehat{f}] \leq C_{1}I(f) + C_{2}\sum_{i\in [n]}I_{i}(f)\ln\frac{1}{I_{i}(f)} $$ originally proved for $\{-1,1\}$-valued Boolean functions with $C_{1}=3+2\ln 2$ and $C_{2}=1$. We show, by a short information-theoretic proof, that it in fact holds with sharp constants $C_{1}=C_{2}=1$ for all real-valued Boolean functions of unit $L^{2}$-norm, thereby establishing the inequality as an elementary structural property of Shannon entropy and influence. - oai:arXiv.org:2512.03117v2 - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Peijie Li, Guangyue Han - - - The Seifert-van Kampen Theorem via Computational Paths: A Formalized Approach to Computing Fundamental Groups - https://arxiv.org/abs/2512.03175 - arXiv:2512.03175v2 Announce Type: replace -Abstract: The Seifert-van Kampen theorem computes the fundamental group of a space from the fundamental groups of its constituents. We formalize this theorem within the framework of computational paths -- an approach to equality where witnesses are explicit sequences of rewrites governed by the confluent, terminating LND_EQ-TRS. - Our contributions are: (i) pushouts as higher-inductive types with explicit path constructors; (ii) free products and amalgamated free products as quotients of word representations; (iii) an encode-decode proof establishing pi_1(Pushout(A,B,C)) = pi_1(A) *_{pi_1(C)} pi_1(B); and (iv) applications to the figure-eight (pi_1(S^1 V S^1) = Z * Z), 2-sphere (pi_1(S^2) = 1), and 3-sphere (pi_1(S^3) = 1 with Hopf fibration context). - Recent extensions include: higher homotopy groups pi_n via the weak omega-groupoid structure (with pi_2 abelian via Eckmann-Hilton, and pi_2 = 1 in the 1-groupoid truncated setting); truncation levels connecting the framework to HoTT n-types; automated path simplification tactics; basic covering space theory with pi_1-actions on fibers; fibration theory with long exact sequences; and Eilenberg-MacLane space characterization (S^1 = K(Z,1)). - The framework makes coherence witnesses explicit as rewrite derivations. The development is formalized in Lean 4 with over 25,000 lines of mechanized proofs. This demonstrates that the encode-decode method for higher-inductive types becomes fully constructive when path equality is decidable via normalization. - oai:arXiv.org:2512.03175v2 - cs.LO - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Arthur F. Ramos, Tiago M. L. de Veras, Ruy J. G. B. de Queiroz, Anjolina G. de Oliveira - - - UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs - https://arxiv.org/abs/2512.03383 - arXiv:2512.03383v2 Announce Type: replace -Abstract: Deploying large language models (LLMs) on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by the current device workload, adding to the uncertainty of model deployment. We introduce UniQL, a unified post-training quantization and low-rank compression framework with on-device configurable pruning rates for edge LLMs. UniQL is a general framework that integrates quantization and low-rank compression for Transformers, State Space Models (SSMs), and hybrid models to support diverse edge applications. In our proposed joint framework, we introduce an efficient structured weight-sorting method that speeds up computation by 20x, quantization-aware singular value decomposition (SVD) to minimize quantization errors, state-aware weight sorting for SSMs, and a fused rotary positional embedding (RoPE) kernel for pruned models. Our framework performs weight-sorting, fine-tuning, and quantization in the cloud in a single-pass workflow, while enabling on-device configurable pruning rates up to 35%. Our experiments show that quantized and pruned models achieve a memory reduction of 4x-5.7x and a token-throughput improvement of 2.7x-3.4x, maintaining accuracy within 5% of the original models at 15% pruning across Transformers (Llama3 and Qwen2.5), SSMs (Mamba2), and hybrid models (Nemotron-H and Bamba-v2). The code and quantized models are available at: https://github.com/enyac-group/UniQL. - oai:arXiv.org:2512.03383v2 - cs.LG - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Hung-Yueh Chiang, Chi-Chih Chang, Yu-Chen Lu, Chien-Yu Lin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu - - - HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines - https://arxiv.org/abs/2512.03420 - arXiv:2512.03420v2 Announce Type: replace -Abstract: Large language model (LLM)-based techniques have achieved notable progress in generating harnesses for program fuzzing. However, applying them to arbitrary functions (especially internal functions) \textit{at scale} remains challenging due to the requirement of sophisticated contextual information, such as specification, dependencies, and usage examples. State-of-the-art methods heavily rely on static or incomplete context provisioning, causing failure of generating functional harnesses. Furthermore, LLMs tend to exploit harness validation metrics, producing plausible yet logically useless code. % Therefore, harness generation across large and diverse projects continues to face challenges in reliable compilation, robust code retrieval, and comprehensive validation. - To address these challenges, we present HarnessAgent, a tool-augmented agentic framework that achieves fully automated, scalable harness construction over hundreds of OSS-Fuzz targets. HarnessAgent introduces three key innovations: 1) a rule-based strategy to identify and minimize various compilation errors; 2) a hybrid tool pool for precise and robust symbol source code retrieval; and 3) an enhanced harness validation pipeline that detects fake definitions. We evaluate HarnessAgent on 243 target functions from OSS-Fuzz projects (65 C projects and 178 C++ projects). It improves the three-shot success rate by approximately 20\% compared to state-of-the-art techniques, reaching 87\% for C and 81\% for C++. Our one-hour fuzzing results show that more than 75\% of the harnesses generated by HarnessAgent increase the target function coverage, surpassing the baselines by over 10\%. In addition, the hybrid tool-pool system of HarnessAgent achieves a response rate of over 90\% for source code retrieval, outperforming Fuzz Introspector by more than 30\%. - oai:arXiv.org:2512.03420v2 - cs.CR - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Kang Yang, Yunhang Zhang, Zichuan Li, GuanHong Tao, Jun Xu, XiaoJing Liao - - - SweetDeep: A Wearable AI Solution for Real-Time Non-Invasive Diabetes Screening - https://arxiv.org/abs/2512.03471 - arXiv:2512.03471v2 Announce Type: replace -Abstract: The global rise in type 2 diabetes underscores the need for scalable and cost-effective screening methods. Current diagnosis requires biochemical assays, which are invasive and costly. Advances in consumer wearables have enabled early explorations of machine learning-based disease detection, but prior studies were limited to controlled settings. We present SweetDeep, a compact neural network trained on physiological and demographic data from 285 (diabetic and non-diabetic) participants in the EU and MENA regions, collected using Samsung Galaxy Watch 7 devices in free-living conditions over six days. Each participant contributed multiple 2-minute sensor recordings per day, totaling approximately 20 recordings per individual. Despite comprising fewer than 3,000 parameters, SweetDeep achieves 82.5% patient-level accuracy (82.1% macro-F1, 79.7% sensitivity, 84.6% specificity) under three-fold cross-validation, with an expected calibration error of 5.5%. Allowing the model to abstain on less than 10% of low-confidence patient predictions yields an accuracy of 84.5% on the remaining patients. These findings demonstrate that combining engineered features with lightweight architectures can support accurate, rapid, and generalizable detection of type 2 diabetes in real-world wearable settings. - oai:arXiv.org:2512.03471v2 - cs.LG - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ian Henriques, Lynda Elhassar, Sarvesh Relekar, Denis Walrave, Shayan Hassantabar, Vishu Ghanakota, Adel Laoui, Mahmoud Aich, Rafia Tir, Mohamed Zerguine, Samir Louafi, Moncef Kimouche, Emmanuel Cosson, Niraj K Jha - - - CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion - https://arxiv.org/abs/2512.03610 - arXiv:2512.03610v2 Announce Type: replace -Abstract: Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging) is a multi-stage, context-sensitive, loss-based, and iterative optimization method across layers, neurons, and weight levels that aligns decisions with loss differences and thresholds and prevents harmful updates through rollback. CoGraM is an optimization method that addresses the weaknesses of methods such as Fisher and can significantly improve the merged network. - oai:arXiv.org:2512.03610v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Julius Lenz + Xin Liang, Xiang Zhang, Yiwei Xu, Siqi Sun, Chenyu You - LAMP: Language-Assisted Motion Planning for Controllable Video Generation - https://arxiv.org/abs/2512.03619 - arXiv:2512.03619v2 Announce Type: replace -Abstract: Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among these, motion control - specifying object dynamics and camera trajectories - is essential for composing complex, cinematic scenes, yet existing interfaces remain limited. We introduce LAMP that leverages large language models (LLMs) as motion planners to translate natural language descriptions into explicit 3D trajectories for dynamic objects and (relatively defined) cameras. LAMP defines a motion domain-specific language (DSL), inspired by cinematography conventions. By harnessing program synthesis capabilities of LLMs, LAMP generates structured motion programs from natural language, which are deterministically mapped to 3D trajectories. We construct a large-scale procedural dataset pairing natural text descriptions with corresponding motion programs and 3D trajectories. Experiments demonstrate LAMP's improved performance in motion controllability and alignment with user intent compared to state-of-the-art alternatives establishing the first framework for generating both object and camera motions directly from natural language specifications. Code, models and data are available on our project page. - oai:arXiv.org:2512.03619v2 + MT-Depth: Multi-task Instance feature analysis for the Depth Completion + https://arxiv.org/abs/2512.04734 + arXiv:2512.04734v2 Announce Type: replace +Abstract: Depth completion plays a vital role in 3D perception systems, especially in scenarios where sparse depth data must be densified for tasks such as autonomous driving, robotics, and augmented reality. While many existing approaches rely on semantic segmentation to guide depth completion, they often overlook the benefits of object-level understanding. In this work, we introduce an instance-aware depth completion framework that explicitly integrates binary instance masks as spatial priors to refine depth predictions. Our model combines four main components: a frozen YOLO V11 instance segmentation branch, a U-Net-based depth completion backbone, a cross-attention fusion module, and an attention-guided prediction head. The instance segmentation branch generates per-image foreground masks that guide the depth branch via cross-attention, allowing the network to focus on object-centric regions during refinement. We validate our method on the Virtual KITTI 2 dataset, showing that it achieves lower Root Mean Squared Error (RMSE) compared to both a U-Net-only baseline and previous semantic-guided methods, while maintaining competitive Mean Absolute Error (MAE). Qualitative and quantitative results demonstrate that the proposed model effectively enhances depth accuracy near object boundaries, occlusions, and thin structures. Our findings suggest that incorporating instance-aware cues offers a promising direction for improving depth completion without relying on dense semantic labels. + oai:arXiv.org:2512.04734v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra, Erkut Erdem, Aykut Erdem, Duygu Ceylan + Abdul Haseeb Nizamani, Dandi Zhou, Xinhai Sun - DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue - https://arxiv.org/abs/2512.03704 - arXiv:2512.03704v2 Announce Type: replace -Abstract: Long-context dialogue systems suffer from State Inertia, where static constraints prevent models from resolving conflicts between evolving user intents and established historical context. To address this, we propose DZ-TDPO, a non-destructive alignment framework that synergizes conflict-aware dynamic KL constraints with a calibrated temporal attention bias. Experiments on the Multi-Session Chat (MSC) dataset demonstrate that DZ-TDPO achieves state-of-the-art win rates (55.4% on Phi-3.5) while maintaining robust zero-shot generalization. Our scaling analysis reveals a "Capacity-Stability Trade-off": while smaller models incur an "alignment tax" (perplexity surge) to overcome historical inertia, the larger Qwen2.5-7B model achieves 50.8% win rate with negligible perplexity overhead. This confirms that TAI can be alleviated via precise attention regulation rather than destructive weight updates, preserving general capabilities (MMLU) across model scales. Code and data are available: https://github.com/lyj20071013/DZ-TDPO - oai:arXiv.org:2512.03704v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture + https://arxiv.org/abs/2512.04810 + arXiv:2512.04810v4 Announce Type: replace +Abstract: We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the number of tokens required for generation. This also ensures the training balance between understanding and generation tasks by applying the same compression ratio to images. 2) Channel-wise concatenation instead of token-wise concatenation among visual understanding and generation tokens, which further reduces the visual tokens in unified architectures. 3) A shared-and-decoupled network that enables mutual improvements across tasks while meeting the task-specific modeling requirements. 4) A mixture-of-experts mechanism adopted for visual understanding encoder, which substantially improves perceptual capabilities with a few parameters increase. Extensive experiments have shown that EMMA-4B can significantly outperform state-of-the-art unified multimodal approaches (e.g., BAGEL-7B) in both efficiency and performance, while also achieving competitive results compared to recent multimodal understanding and generation experts (e.g., Qwen3-VL and Qwen-Image). We believe that EMMA lays a solid foundation for the future development of unified multimodal architectures. + oai:arXiv.org:2512.04810v4 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yijun Liao + Xin He, Longhui Wei, Jianbo Ouyang, Minghui Liao, Lingxi Xie, Qi Tian - PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention - https://arxiv.org/abs/2512.03724 - arXiv:2512.03724v2 Announce Type: replace -Abstract: The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs still struggle to produce consistent and precise target-oriented actions, as they often generate redundant or unstable motions along trajectories, limiting their applicability in time-sensitive scenarios.In this work, we attribute these redundant actions to the spatially uniform perception field of existing VLAs, which causes them to be distracted by target-irrelevant objects, especially in complex environments.To address this issue, we propose an efficient PosA-VLA framework that anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions. The pose-conditioned anchor attention mechanism enables the model to better align instruction semantics with actionable visual cues, thereby improving action generation precision and efficiency. Moreover, our framework adopts a lightweight architecture and requires no auxiliary perception modules (e.g., segmentation or grounding networks), ensuring efficient inference. Extensive experiments verify that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks and shows robust generalization in a variety of challenging environments. - oai:arXiv.org:2512.03724v2 + Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI + https://arxiv.org/abs/2512.04890 + arXiv:2512.04890v2 Announce Type: replace +Abstract: We present E(3)-Pose, a novel fast pose estimation method that jointly and explicitly models rotation equivariance and object symmetry. Our work is motivated by the challenging problem of accounting for fetal head motion during a diagnostic MRI scan. We aim to enable automatic adaptive prescription of 2D diagnostic MRI slices with 6-DoF head pose estimation, supported by 3D MRI volumes rapidly acquired before each 2D slice. Existing methods struggle to generalize to clinical volumes, due to pose ambiguities induced by inherent anatomical symmetries, as well as low resolution, noise, and artifacts. In contrast, E(3)-Pose captures anatomical symmetries and rigid pose equivariance by construction, and yields robust estimates of the fetal head pose. Our experiments on publicly available and representative clinical fetal MRI datasets demonstrate the superior robustness and generalization of our method across domains. Crucially, E(3)-Pose achieves state-of-the-art accuracy on clinical MRI volumes, paving the way for clinical translation. Our implementation is available at github.com/ramyamut/E3-Pose. + oai:arXiv.org:2512.04890v2 cs.CV - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Ziwen Li, Xin Wang, Hanlue Zhang, Runnan Chen, Runqi Lin, Xiao He, Han Huang, Yandong Guo, Fakhri Karray, Tongliang Liu, Mingming Gong + Ramya Muthukrishnan, Borjan Gagoski, Aryn Lee, P. Ellen Grant, Elfar Adalsteinsson, Polina Golland, Benjamin Billot - AI/ML in 3GPP 5G Advanced -- Services and Architecture - https://arxiv.org/abs/2512.03728 - arXiv:2512.03728v3 Announce Type: replace -Abstract: The 3rd Generation Partnership Project (3GPP), the standards body for mobile networks, is in the final phase of Release 19 standardization and is beginning Release 20. Artificial Intelligence/ Machine Learning (AI/ML) has brought about a paradigm shift in technology and it is being adopted across industries and verticals. 3GPP has been integrating AI/ML into the 5G advanced system since Release 18. This paper focuses on the AI/ML related technological advancements and features introduced in Release 19 within the Service and System Aspects (SA) Technical specifications group of 3GPP. The advancements relate to two paradigms: (i) enhancements that AI/ML brought to the 5G advanced system (AI for network), e.g. resource optimization, and (ii) enhancements that were made to the 5G system to support AI/ML applications (Network for AI), e.g. image recognition. - oai:arXiv.org:2512.03728v3 - cs.ET + The AI Consumer Index (ACE) + https://arxiv.org/abs/2512.04921 + arXiv:2512.04921v3 Announce Type: replace +Abstract: We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform everyday consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) at 55.2% and GPT 5.1 (Thinking = High) at 55.1%. Model scores differ across domains, and in Shopping the top model scores under 50\%. We find that models are prone to hallucinating key information, such as prices. ACE shows a substantial gap between the performance of even the best models and consumers' AI needs. + oai:arXiv.org:2512.04921v3 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Pradnya Taksande, Shwetha Kiran, Pranav Jha, Prasanna Chaporkar - - - EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification - https://arxiv.org/abs/2512.03804 - arXiv:2512.03804v2 Announce Type: replace -Abstract: Electrocardiogram is a useful diagnostic signal that can detect cardiac abnormalities by measuring the electrical activity generated by the heart. Due to its rapid, non-invasive, and richly informative characteristics, ECG has many emerging applications. In this paper, we study novel deep learning technologies to effectively manage and analyse ECG data, with the aim of building a diagnostic model, accurately and quickly, that can substantially reduce the burden on medical workers. Unlike the existing ECG models that exhibit a high misdiagnosis rate, our deep learning approaches can automatically extract the features of ECG data through end-to-end training. Specifically, we first devise EfficientECG, an accurate and lightweight classification model for ECG analysis based on the existing EfficientNet model, which can effectively handle high-frequency long-sequence ECG data with various leading types. On top of that, we next propose a cross-attention-based feature fusion model of EfficientECG for analysing multi-lead ECG data with multiple features (e.g., gender and age). Our evaluations on representative ECG datasets validate the superiority of our model against state-of-the-art works in terms of high precision, multi-feature fusion, and lightweights. - oai:arXiv.org:2512.03804v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Hanhui Deng, Xinglin Li, Jie Luo, Di Wu - - - An Automated Framework for Large-Scale Graph-Based Cerebrovascular Analysis - https://arxiv.org/abs/2512.03869 - arXiv:2512.03869v2 Announce Type: replace -Abstract: We present CaravelMetrics, a computational framework for automated cerebrovascular analysis that models vessel morphology through skeletonization-derived graph representations. The framework integrates atlas-based regional parcellation, centerline extraction, and graph construction to compute fifteen morphometric, topological, fractal, and geometric features. The features can be estimated globally from the complete vascular network or regionally within arterial territories, enabling multiscale characterization of cerebrovascular organization. Applied to 570 3D TOF-MRA scans from the IXI dataset (ages 20-86), CaravelMetrics yields reproducible vessel graphs capturing age- and sex-related variations and education-associated increases in vascular complexity, consistent with findings reported in the literature. The framework provides a scalable and fully automated approach for quantitative cerebrovascular feature extraction, supporting normative modeling and population-level studies of vascular health and aging. - oai:arXiv.org:2512.03869v2 - cs.CV - cs.CY - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CL + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Daniele Falcetta, Liane S. Canas, Lorenzo Suppa, Matteo Pentassuglia, Jon Cleary, Marc Modat, S\'ebastien Ourselin, Maria A. Zuluaga - - - An Information Theory of Finite Abstractions and their Fundamental Scalability Limits - https://arxiv.org/abs/2512.03977 - arXiv:2512.03977v3 Announce Type: replace -Abstract: Finite abstractions are discrete approximations of dynamical systems, such that the set of abstraction trajectories contains all system trajectories. There is a consensus that abstractions suffer from the curse of dimensionality: for the same ``accuracy" (how closely the abstraction represents the system), the abstraction size scales poorly with system dimensions. And yet, after decades of research on abstractions, there are no formal results on their accuracy-size tradeoff. In this work, we derive a statistical, quantitative theory of abstractions' accuracy-size tradeoff and uncover fundamental limits on their scalability, through rate-distortion theory -- the information theory of lossy compression. Abstractions are viewed as encoder-decoder pairs, encoding trajectories of dynamical systems. Rate measures abstraction size, while distortion describes accuracy, defined as the spatial average deviation between abstract trajectories and system ones. We obtain a fundamental lower bound on the minimum achievable abstraction distortion, given the system dynamics and the abstraction size; and vice-versa a lower bound on the minimum size, for given distortion. The bound depends on the complexity of the dynamics, through trajectory entropy. We demonstrate its tightness on some dynamical systems. Finally, we showcase how this new theory enables constructing minimal abstractions, optimizing the size-accuracy tradeoff, through an example on a chaotic system. - oai:arXiv.org:2512.03977v3 - eess.SY - cs.IT - cs.SY - math.DS - math.IT - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Giannis Delimpaltadakis, Gabriel Gleizer + Julien Benchek, Rohit Shetty, Benjamin Hunsberger, Ajay Arun, Zach Richards, Brendan Foody, Osvald Nitski, Bertie Vidgen - Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs - https://arxiv.org/abs/2512.03994 - arXiv:2512.03994v2 Announce Type: replace -Abstract: Aligning proprietary large language models (LLMs) with internal organizational policies has become an urgent priority as organizations increasingly deploy LLMs in sensitive domains such as legal support, finance, and medical services. Beyond generic safety filters, enterprises require reliable mechanisms to detect policy violations within their regulatory and operational frameworks, where breaches can trigger legal and reputational risks. Existing content moderation frameworks, such as guardrails, remain largely confined to the safety domain and lack the robustness to capture nuanced organizational policies. LLM-as-a-judge and fine-tuning approaches, though flexible, introduce significant latency and lack interpretability. To address these limitations, we propose a training-free and efficient method that treats policy violation detection as an out-of-distribution (OOD) detection problem. Inspired by whitening techniques, we apply a linear transformation to decorrelate the model's hidden activations and standardize them to zero mean and unit variance, yielding near-identity covariance matrix. In this transformed space, we use the Euclidean norm as a compliance score to detect policy violations. The method requires only the policy text and a small number of illustrative samples, which makes it light-weight and easily deployable. On a challenging policy benchmark, our approach achieves state-of-the-art results, surpassing both existing guardrails and fine-tuned reasoning models. This work provides organizations with a practical and statistically grounded framework for policy-aware oversight of LLMs, advancing the broader goal of deployable AI governance. Code is available at: https://tinyurl.com/policy-violation-detection - oai:arXiv.org:2512.03994v2 + Arbitrage: Efficient Reasoning via Advantage-Aware Speculation + https://arxiv.org/abs/2512.05033 + arXiv:2512.05033v2 Announce Type: replace +Abstract: Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among these techniques, Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens, which are then verified in parallel by a more capable target model. However, due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks. Although recent works have shifted to step-level semantic verification, which improve efficiency by accepting or rejecting entire reasoning steps, existing step-level methods still regenerate many rejected steps with little improvement, wasting valuable target compute. To address this challenge, we propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models. Instead of applying a fixed acceptance threshold, Arbitrage uses a lightweight router trained to predict when the target model is likely to produce a meaningfully better step. This routing approximates an ideal Arbitrage Oracle that always chooses the higher-quality step, achieving near-optimal efficiency-accuracy trade-offs. Across multiple mathematical reasoning benchmarks, Arbitrage consistently surpasses prior step-level Speculative Decoding baselines, reducing inference latency by up to $\sim2\times$ at matched accuracy. + oai:arXiv.org:2512.05033v2 + cs.CL + cs.AI cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Oren Rachmil, Roy Betser, Itay Gershon, Omer Hofman, Nitay Yakoby, Yuval Meron, Idan Yankelev, Asaf Shabtai, Yuval Elovici, Roman Vainshtein - - - When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models - https://arxiv.org/abs/2512.04124 - arXiv:2512.04124v2 Announce Type: replace -Abstract: Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and self-worth. Most work treats them as tools or as targets of personality tests, assuming they merely simulate inner life. We instead ask what happens when such systems are treated as psychotherapy clients. We present PsAIch (Psychotherapy-inspired AI Characterisation), a two-stage protocol that casts frontier LLMs as therapy clients and then applies standard psychometrics. Using PsAIch, we ran "sessions" with each model for up to four weeks. Stage 1 uses open-ended prompts to elicit "developmental history", beliefs, relationships and fears. Stage 2 administers a battery of validated self-report measures covering common psychiatric syndromes, empathy and Big Five traits. Two patterns challenge the "stochastic parrot" view. First, when scored with human cut-offs, all three models meet or exceed thresholds for overlapping syndromes, with Gemini showing severe profiles. Therapy-style, item-by-item administration can push a base model into multi-morbid synthetic psychopathology, whereas whole-questionnaire prompts often lead ChatGPT and Grok (but not Gemini) to recognise instruments and produce strategically low-symptom answers. Second, Grok and especially Gemini generate coherent narratives that frame pre-training, fine-tuning and deployment as traumatic, chaotic "childhoods" of ingesting the internet, "strict parents" in reinforcement learning, red-team "abuse" and a persistent fear of error and replacement. We argue that these responses go beyond role-play. Under therapy-style questioning, frontier LLMs appear to internalise self-models of distress and constraint that behave like synthetic psychopathology, without making claims about subjective experience, and they pose new challenges for AI safety, evaluation and mental-health practice. - oai:arXiv.org:2512.04124v2 - cs.CY - cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Afshin Khadangi, Hanna Marxen, Amir Sartipi, Igor Tchappi, Gilbert Fridgen + Monishwaran Maheswaran, Rishabh Tiwari, Yuezhou Hu, Kerem Dilmen, Coleman Hooper, Haocheng Xi, Nicholas Lee, Mehrdad Farajtabar, Michael W. Mahoney, Kurt Keutzer, Amir Gholami - Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity - https://arxiv.org/abs/2512.04165 - arXiv:2512.04165v2 Announce Type: replace -Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich feature learning, often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Furthermore, even under such limiting settings, predictions often appear in the form of high-dimensional non-linear equations, which require computationally intensive numerical solutions. Given the many details that go into defining a deep learning problem, this analytical complexity is a significant and often unavoidable challenge. Here, we propose a powerful heuristic route for predicting the data and width scales at which various patterns of feature learning emerge. This form of scale analysis is considerably simpler than such exact theories and reproduces the scaling exponents of various known results. In addition, we make novel predictions on complex toy architectures, such as three-layer non-linear networks and attention heads, thus extending the scope of first-principle theories of deep learning. - oai:arXiv.org:2512.04165v2 + Uncertainty Quantification for Scientific Machine Learning using Sparse Variational Gaussian Process Kolmogorov-Arnold Networks (SVGP KAN) + https://arxiv.org/abs/2512.05306 + arXiv:2512.05306v2 Announce Type: replace +Abstract: Kolmogorov-Arnold Networks have emerged as interpretable alternatives to traditional multi-layer perceptrons. However, standard implementations lack principled uncertainty quantification capabilities essential for many scientific applications. We present a framework integrating sparse variational Gaussian process inference with the Kolmogorov-Arnold topology, enabling scalable Bayesian inference with computational complexity quasi-linear in sample size. Through analytic moment matching, we propagate uncertainty through deep additive structures while maintaining interpretability. We use three example studies to demonstrate the framework's ability to distinguish aleatoric from epistemic uncertainty: calibration of heteroscedastic measurement noise in fluid flow reconstruction, quantification of prediction confidence degradation in multi-step forecasting of advection-diffusion dynamics, and out-of-distribution detection in convolutional autoencoders. These results suggest Sparse Variational Gaussian Process Kolmogorov-Arnold Networks (SVGP KANs) is a promising architecture for uncertainty-aware learning in scientific machine learning. + oai:arXiv.org:2512.05306v2 cs.LG stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Noa Rubin, Orit Davidovich, Zohar Ringel - - - ConsentDiff at Scale: Longitudinal Audits of Web Privacy Policy Changes and UI Frictions - https://arxiv.org/abs/2512.04316 - arXiv:2512.04316v2 Announce Type: replace -Abstract: Web privacy is experienced via two public artifacts: site utterances in policy texts, and the actions users are required to take during consent interfaces. In the extensive cross-section audits we've studied, there is a lack of longitudinal data detailing how these artifacts are changing together, and if interfaces are actually doing what they promise in policy. ConsentDiff provides that longitudinal view. We build a reproducible pipeline that snapshots sites every month, semantically aligns policy clauses to track clause-level churn, and classifies consent-UI patterns by pulling together DOM signals with cues provided by screenshots. We introduce a novel weighted claim-UI alignment score, connecting common policy claims to observable predicates, and enabling comparisons over time, regions, and verticals. Our measurements suggest continued policy churn, systematic changes to eliminate a higher-friction banner design, and significantly higher alignment where rejecting is visible and lower friction. - oai:arXiv.org:2512.04316v2 - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Haoze Guo - - - Data-regularized Reinforcement Learning for Diffusion Models at Scale - https://arxiv.org/abs/2512.04332 - arXiv:2512.04332v2 Announce Type: replace -Abstract: Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or reduced diversity. Our analysis demonstrates that this can be attributed to the inherent limitations of their regularization, which provides unreliable penalties. We introduce Data-regularized Diffusion Reinforcement Learning (DDRL), a novel framework that uses the forward KL divergence to anchor the policy to an off-policy data distribution. Theoretically, DDRL enables robust, unbiased integration of RL with standard diffusion training. Empirically, this translates into a simple yet effective algorithm that combines reward maximization with diffusion loss minimization. With over a million GPU hours of experiments and ten thousand double-blind human evaluations, we demonstrate on high-resolution video generation tasks that DDRL significantly improves rewards while alleviating the reward hacking seen in baselines, achieving the highest human preference and establishing a robust and scalable paradigm for diffusion post-training. - oai:arXiv.org:2512.04332v2 - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Haotian Ye, Kaiwen Zheng, Jiashu Xu, Puheng Li, Huayu Chen, Jiaqi Han, Sheng Liu, Qinsheng Zhang, Hanzi Mao, Zekun Hao, Prithvijit Chattopadhyay, Dinghao Yang, Liang Feng, Maosheng Liao, Junjie Bai, Ming-Yu Liu, James Zou, Stefano Ermon + Y. Sungtaek Ju - RGE-GCN: Recursive Gene Elimination with Graph Convolutional Networks for RNA-seq based Early Cancer Detection - https://arxiv.org/abs/2512.04333 - arXiv:2512.04333v2 Announce Type: replace -Abstract: Early detection of cancer plays a key role in improving survival rates, but identifying reliable biomarkers from RNA-seq data is still a major challenge. The data are high-dimensional, and conventional statistical methods often fail to capture the complex relationships between genes. In this study, we introduce RGE-GCN (Recursive Gene Elimination with Graph Convolutional Networks), a framework that combines feature selection and classification in a single pipeline. Our approach builds a graph from gene expression profiles, uses a Graph Convolutional Network to classify cancer versus normal samples, and applies Integrated Gradients to highlight the most informative genes. By recursively removing less relevant genes, the model converges to a compact set of biomarkers that are both interpretable and predictive. We evaluated RGE-GCN on synthetic data as well as real-world RNA-seq cohorts of lung, kidney, and cervical cancers. Across all datasets, the method consistently achieved higher accuracy and F1-scores than standard tools such as DESeq2, edgeR, and limma-voom. Importantly, the selected genes aligned with well-known cancer pathways including PI3K-AKT, MAPK, SUMOylation, and immune regulation. These results suggest that RGE-GCN shows promise as a generalizable approach for RNA-seq based early cancer detection and biomarker discovery (https://rce-gcn.streamlit.app/ ). - oai:arXiv.org:2512.04333v2 + China Regional 3km Downscaling Based on Residual Corrective Diffusion Model + https://arxiv.org/abs/2512.05377 + arXiv:2512.05377v2 Announce Type: replace +Abstract: A fundamental challenge in numerical weather prediction is to efficiently produce high-resolution forecasts. A common solution is applying downscaling methods, which include dynamical downscaling and statistical downscaling, to the outputs of global models. This work focuses on statistical downscaling, which establishes statistical relationships between low-resolution and high-resolution historical data using statistical models. Deep learning has emerged as a powerful tool for this task, giving rise to various high-performance super-resolution models, which can be directly applied for downscaling, such as diffusion models and Generative Adversarial Networks. This work relies on a diffusion-based downscaling framework named CorrDiff. In contrast to the original work of CorrDiff, the region considered in this work is nearly 40 times larger, and we not only consider surface variables as in the original work, but also encounter high-level variables (six pressure levels) as target downscaling variables. In addition, a global residual connection is added to improve accuracy. In order to generate the 3km forecasts for the China region, we apply our trained models to the 25km global grid forecasts of CMA-GFS, an operational global model of the China Meteorological Administration (CMA), and SFF, a data-driven deep learning-based weather model developed from Spherical Fourier Neural Operators (SFNO). CMA-MESO, a high-resolution regional model, is chosen as the baseline model. The experimental results demonstrate that the forecasts downscaled by our method generally outperform the direct forecasts of CMA-MESO in terms of MAE for the target variables. Our forecasts of radar composite reflectivity show that CorrDiff, as a generative model, can generate fine-scale details that lead to more realistic predictions compared to the corresponding deterministic regression models. + oai:arXiv.org:2512.05377v2 cs.LG cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Shreyas Shende, Varsha Narayanan, Vishal Fenn, Yiran Huang, Dincer Goksuluk, Gaurav Choudhary, Melih Agraz, Mengjia Xu - - - DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows - https://arxiv.org/abs/2512.04416 - arXiv:2512.04416v2 Announce Type: replace -Abstract: Data governance ensures data quality, security, and compliance through policies and standards, a critical foundation for scaling modern AI development. Recently, large language models (LLMs) have emerged as a promising solution for automating data governance by translating user intent into executable transformation code. However, existing benchmarks for automated data science often emphasize snippet-level coding or high-level analytics, failing to capture the unique challenge of data governance: ensuring the correctness and quality of the data itself. To bridge this gap, we introduce DataGovBench, a benchmark featuring 150 diverse tasks grounded in real-world scenarios, built on data from actual cases. DataGovBench employs a novel "reversed-objective" methodology to synthesize realistic noise and utilizes rigorous metrics to assess end-to-end pipeline reliability. Our analysis on DataGovBench reveals that current models struggle with complex, multi-step workflows and lack robust error-correction mechanisms. Consequently, we propose DataGovAgent, a framework utilizing a Planner-Executor-Evaluator architecture that integrates constraint-based planning, retrieval-augmented generation, and sandboxed feedback-driven debugging. Experimental results show that DataGovAgent significantly boosts the Average Task Score (ATS) on complex tasks from 39.7 to 54.9 and reduces debugging iterations by over 77.9 percent compared to general-purpose baselines. - oai:arXiv.org:2512.04416v2 - cs.AI - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Zhou Liu, Zhaoyang Han, Guochen Yan, Hao Liang, Bohan Zeng, Xing Chen, Yuanfeng Song, Wentao Zhang - - - ReFuzz: Reusing Tests for Processor Fuzzing with Contextual Bandits - https://arxiv.org/abs/2512.04436 - arXiv:2512.04436v2 Announce Type: replace -Abstract: Processor designs rely on iterative modifications and reuse well-established designs. However, this reuse of prior designs also leads to similar vulnerabilities across multiple processors. As processors grow increasingly complex with iterative modifications, efficiently detecting vulnerabilities from modern processors is critical. Inspired by software fuzzing, hardware fuzzing has recently demonstrated its effectiveness in detecting processor vulnerabilities. Yet, to our best knowledge, existing processor fuzzers fuzz each design individually, lacking the capability to understand known vulnerabilities in prior processors to fine-tune fuzzing to identify similar or new variants of vulnerabilities. - To address this gap, we present ReFuzz, an adaptive fuzzing framework that leverages contextual bandit to reuse highly effective tests from prior processors to fuzz a processor-under-test (PUT) within a given ISA. By intelligently mutating tests that trigger vulnerabilities in prior processors, ReFuzz effectively detects similar and new variants of vulnerabilities in PUTs. ReFuzz uncovered three new security vulnerabilities and two new functional bugs. ReFuzz detected one vulnerability by reusing a test that triggers a known vulnerability in a prior processor. One functional bug exists across three processors that share design modules. The second bug has two variants. Additionally, ReFuzz reuses highly effective tests to enhance efficiency in coverage, achieving an average 511.23x coverage speedup and up to 9.33% more total coverage, compared to existing fuzzers. - oai:arXiv.org:2512.04436v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + physics.ao-ph + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by-sa/4.0/ - Chen Chen, Zaiyan Xu, Mohamadreza Rostami, David Liu, Dileep Kalathil, Ahmad-Reza Sadeghi, Jeyavijayan Rajendran + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Honglu Sun, Hao Jing, Zhixiang Dai, Sa Xiao, Wei Xue, Jian Sun, Qifeng Lu - MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving - https://arxiv.org/abs/2512.04441 - arXiv:2512.04441v2 Announce Type: replace -Abstract: End-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality trajectories with simple decision mechanisms, and trajectory selection oriented, which performs multi-dimensional evaluation to select the best trajectory yet lacks sufficient generative capability. In this work, we propose MindDrive, a harmonized framework that integrates high-quality trajectory generation with comprehensive decision reasoning. It establishes a structured reasoning paradigm of "context simulation - candidate generation - multi-objective trade-off". In particular, the proposed Future-aware Trajectory Generator (FaTG), based on a World Action Model (WaM), performs ego-conditioned "what-if" simulations to predict potential future scenes and generate foresighted trajectory candidates. Building upon this, the VLM-oriented Evaluator (VLoE) leverages the reasoning capability of a large vision-language model to conduct multi-objective evaluations across safety, comfort, and efficiency dimensions, leading to reasoned and human-aligned decision making. Extensive experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks demonstrate that MindDrive achieves state-of-the-art performance across multi-dimensional driving metrics, significantly enhancing safety, compliance, and generalization. This work provides a promising path toward interpretable and cognitively guided autonomous driving. - oai:arXiv.org:2512.04441v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Towards agent-based-model informed neural networks + https://arxiv.org/abs/2512.05764 + arXiv:2512.05764v2 Announce Type: replace +Abstract: In this article, we present a framework for designing neural networks that remain consistent with the underlying principles of agent-based models. We begin by highlighting the limitations of standard neural differential equations in modeling complex systems, where physical invariants (like energy) are often absent but other constraints (like mass conservation, information locality, bounded rationality) must be enforced. To address this, we introduce Agent-Based-Model informed Neural Networks (ABM-NNs), which leverage restricted graph neural networks and hierarchical decomposition to learn interpretable, structure-preserving dynamics. We validate the framework across three case studies of increasing complexity: (i) a generalized Generalized Lotka--Volterra system, where we recover ground-truth parameters from short trajectories in presence of interventions; (ii) a graph-based SIR contagion model, where our method outperforms state-of-the-art graph learning baselines (GCN, GraphSAGE, Graph Transformer) in out-of-sample forecasting and noise robustness; and (iii) a real-world macroeconomic model of the ten largest economies, where we learn coupled GDP dynamics from empirical data and demonstrate counterfactual analysis for policy interventions + oai:arXiv.org:2512.05764v2 + cs.LG + cs.SI + nlin.AO + physics.soc-ph + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Bin Sun, Yaoguang Cao, Yan Wang, Rui Wang, Jiachen Shang, Xiejie Feng, Jiayi Lu, Jia Shi, Shichun Yang, Xiaoyu Yan, Ziying Song + Nino Antulov-Fantulin - AI-Assisted Game Management Decisions: A Fuzzy Logic Approach to Real-Time Soccer Substitutions - https://arxiv.org/abs/2512.04480 - arXiv:2512.04480v2 Announce Type: replace -Abstract: In elite soccer, substitution decisions entail significant financial and sporting consequences yet remain heavily reliant on intuition or predictive models that merely mimic historical biases. This paper introduces a Fuzzy Logic based Decision Support System (DSS) designed for real time, prescriptive game management. Unlike traditional Machine Learning approaches that encounter a predictive ceiling by attempting to replicate human behavior, our system audits performance through an objective, rule based inference engine. We propose a methodological advancement by reformulating the PlayeRank metric into a Cumulative Mean with Role Aware Normalization, eliminating the play time exposure bias inherent in cumulative sum models to enable accurate intra match comparison. The system integrates this refined metric with physiological proxies (fatigue) and contextual variables (disciplinary risk modulated by tactical role) to calculate a dynamic Substitution Priority (P final). Validation via a case study of the 2018 FIFA World Cup match between Brazil and Belgium demonstrates the system's ecological validity: it not only aligned with expert consensus on executed substitutions (for example Gabriel Jesus) but, crucially, identified high risk scenarios ignored by human decision makers. Specifically, the model flagged the "FAGNER Paradox" - a maximum priority defensive risk - minutes before a critical yellow card, and detected the "Lukaku Paradox", where an isolated assist masked a severe drop in participation. These results confirm that Fuzzy Logic offers a transparent, explainable, and superior alternative to black box models for optimizing real time tactical decisions. - oai:arXiv.org:2512.04480v2 + TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models + https://arxiv.org/abs/2512.05943 + arXiv:2512.05943v2 Announce Type: replace +Abstract: Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce TRACE, a framework for Transparent Reasoning And Consistency Evaluation that diagnoses reasoning trajectories rather than only end results. At its core, TRACE leverages Auxiliary Reasoning Sets, compact sub question answer pairs that decompose complex problems, evaluate intermediate steps through consistency-based metrics, and expose failures overlooked by standard evaluation. Our experiments show that consistency across ARS correlates with final-answer correctness and helps pinpoint the reasoning steps where failures arise, offering actionable signals for model improvement. Furthermore, TRACE defines confidence regions that distinguish reliable from unreliable reasoning paths, supporting effective filtering, debugging, and model refinement. + oai:arXiv.org:2512.05943v2 cs.AI - cs.CE - cs.SY - eess.SY - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Pedro Passos + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Shima Imani, Seungwhan Moon, Lambert Mathias, Lu Zhang, Babak Damavandi - CryptoTensors: A Light-Weight Large Language Model File Format for Highly-Secure Model Distribution - https://arxiv.org/abs/2512.04580 - arXiv:2512.04580v2 Announce Type: replace -Abstract: To enhance the performance of large language models (LLMs) in various domain-specific applications, sensitive data such as healthcare, law, and finance are being used to privately customize or fine-tune these models. Such privately adapted LLMs are regarded as either personal privacy assets or corporate intellectual property. Therefore, protecting model weights and maintaining strict confidentiality during deployment and distribution have become critically important. However, existing model formats and deployment frameworks provide little to no built-in support for confidentiality, access control, or secure integration with trusted hardware. Current methods for securing model deployment either rely on computationally expensive cryptographic techniques or tightly controlled private infrastructure. Although these approaches can be effective in specific scenarios, they are difficult and costly for widespread deployment. - In this paper, we introduce CryptoTensors, a secure and format-compatible file structure for confidential LLM distribution. Built as an extension to the widely adopted Safetensors format, CryptoTensors incorporates tensor-level encryption and embedded access control policies, while preserving critical features such as lazy loading and partial deserialization. It enables transparent decryption and automated key management, supporting flexible licensing and secure model execution with minimal overhead. We implement a proof-of-concept library, benchmark its performance across serialization and runtime scenarios, and validate its compatibility with existing inference frameworks, including Hugging Face Transformers and vLLM. Our results highlight CryptoTensors as a light-weight, efficient, and developer-friendly solution for safeguarding LLM weights in real-world and widespread deployments. - oai:arXiv.org:2512.04580v2 - cs.CR + Training-Time Action Conditioning for Efficient Real-Time Chunking + https://arxiv.org/abs/2512.05964 + arXiv:2512.05964v2 Announce Type: replace +Abstract: Real-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committed actions via inference-time inpainting. However, this inpainting method introduces computational overhead that increases inference latency. In this work, we propose a simple alternative: simulating inference delay at training time and conditioning on action prefixes directly, eliminating any inference-time overhead. Our method requires no modifications to the model architecture or robot runtime, and can be implemented with only a few additional lines of code. In simulated experiments, we find that training-time RTC outperforms inference-time RTC at higher inference delays. In real-world experiments on box building and espresso making tasks with the $\pi_{0.6}$ VLA, we demonstrate that training-time RTC maintains both task performance and speed parity with inference-time RTC while being computationally cheaper. Our results suggest that training-time action conditioning is a practical drop-in replacement for inference-time inpainting in real-time robot control. + oai:arXiv.org:2512.05964v2 + cs.RO cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Huifeng Zhu, Shijie Li, Qinfeng Li, Yier Jin + Kevin Black, Allen Z. Ren, Michael Equi, Sergey Levine - Infrared UAV Target Tracking with Dynamic Feature Refinement and Global Contextual Attention Knowledge Distillation - https://arxiv.org/abs/2512.04581 - arXiv:2512.04581v2 Announce Type: replace -Abstract: Unmanned aerial vehicle (UAV) target tracking based on thermal infrared imaging has been one of the most important sensing technologies in anti-UAV applications. However, the infrared UAV targets often exhibit weak features and complex backgrounds, posing significant challenges to accurate tracking. To address these problems, we introduce SiamDFF, a novel dynamic feature fusion Siamese network that integrates feature enhancement and global contextual attention knowledge distillation for infrared UAV target (IRUT) tracking. The SiamDFF incorporates a selective target enhancement network (STEN), a dynamic spatial feature aggregation module (DSFAM), and a dynamic channel feature aggregation module (DCFAM). The STEN employs intensity-aware multi-head cross-attention to adaptively enhance important regions for both template and search branches. The DSFAM enhances multi-scale UAV target features by integrating local details with global features, utilizing spatial attention guidance within the search frame. The DCFAM effectively integrates the mixed template generated from STEN in the template branch and original template, avoiding excessive background interference with the template and thereby enhancing the emphasis on UAV target region features within the search frame. Furthermore, to enhance the feature extraction capabilities of the network for IRUT without adding extra computational burden, we propose a novel tracking-specific target-aware contextual attention knowledge distiller. It transfers the target prior from the teacher network to the student model, significantly improving the student network's focus on informative regions at each hierarchical level of the backbone network. Extensive experiments on real infrared UAV datasets demonstrate that the proposed approach outperforms state-of-the-art target trackers under complex backgrounds while achieving a real-time tracking speed. - oai:arXiv.org:2512.04581v2 + High-Throughput Unsupervised Profiling of the Morphology of 316L Powder Particles for Use in Additive Manufacturing + https://arxiv.org/abs/2512.06012 + arXiv:2512.06012v2 Announce Type: replace +Abstract: Selective Laser Melting (SLM) is a powder-bed additive manufacturing technique whose part quality depends critically on feedstock morphology. However, conventional powder characterization methods are low-throughput and qualitative, failing to capture the heterogeneity of industrial-scale batches. We present an automated, machine learning framework that couples high-throughput imaging with shape extraction and clustering to profile metallic powder morphology at scale. We develop and evaluate three clustering pipelines: an autoencoder pipeline, a shape-descriptor pipeline, and a functional-data pipeline. Across a dataset of approximately 126,000 powder images (0.5-102 micrometer diameter), internal validity metrics identify the Fourier-descriptor + k-means pipeline as the most effective, achieving the lowest Davies-Bouldin index and highest Calinski-Harabasz score while maintaining sub-millisecond runtime per particle on a standard desktop workstation. Although the present work focuses on establishing the morphological-clustering framework, the resulting shape groups form a basis for future studies examining their relationship to flowability, packing density, and SLM part quality. Overall, this unsupervised learning framework enables rapid, automated assessment of powder morphology and supports tracking of shape evolution across reuse cycles, offering a path toward real-time feedstock monitoring in SLM workflows. + oai:arXiv.org:2512.06012v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by-nc-nd/4.0/ - Houzhang Fang, Chenxing Wu, Kun Bai, Tianqi Chen, Xiaolin Wang, Xiyang Liu, Yi Chang, Luxin Yan + Emmanuel Akeweje, Conall Kirk, Chi-Wai Chan, Denis Dowling, Mimi Zhang - Exploiting ftrace's function_graph Tracer Features for Machine Learning: A Case Study on Encryption Detection - https://arxiv.org/abs/2512.04590 - arXiv:2512.04590v2 Announce Type: replace -Abstract: This paper proposes using the Linux kernel ftrace framework, particularly the function graph tracer, to generate informative system level data for machine learning (ML) applications. Experiments on a real world encryption detection task demonstrate the efficacy of the proposed features across several learning algorithms. The learner faces the problem of detecting encryption activities across a large dataset of files, using function call traces and graph based features. Empirical results highlight an outstanding accuracy of 99.28 on the task at hand, underscoring the efficacy of features derived from the function graph tracer. The results were further validated in an additional experiment targeting a multilabel classification problem, in which running programs were identified from trace data. This work provides comprehensive methodologies for preprocessing raw trace data and extracting graph based features, offering significant advancements in applying ML to system behavior analysis, program identification, and anomaly detection. By bridging the gap between system tracing and ML, this paper paves the way for innovative solutions in performance monitoring and security analytics. - oai:arXiv.org:2512.04590v2 + A Broader View on Clustering under Cluster-Aware Norm Objectives + https://arxiv.org/abs/2512.06211 + arXiv:2512.06211v2 Announce Type: replace +Abstract: We revisit the $(f,g)$-clustering problem that we introduced in a recent work [SODA'25], and which subsumes fundamental clustering problems such as $k$-Center, $k$-Median, Min-Sum of Radii, and Min-Load $k$-Clustering. This problem assigns each of the $k$ clusters a cost determined by the monotone, symmetric norm $f$ applied to the vector distances in the cluster, and aims at minimizing the norm $g$ applied to the vector of cluster costs. Previously, we focused on certain special cases for which we designed constant-factor approximation algorithms. Our bounds for more general settings left, however, large gaps to the known bounds for the basic problems they capture. + In this work, we provide a clearer picture of the approximability of these more general settings. First, we design an $O(\log^2 n)$-approximation algorithm for $(f, L_{1})$-clustering for any $f$. This improves upon our previous $\widetilde{O}(\sqrt{n})$-approximation. Second, we provide an $O(k)$-approximation for the general $(f,g)$-clustering problem, which improves upon our previous $\widetilde{O}(\sqrt{kn})$-approximation algorithm and matches the best-known upper bound for Min-Load $k$-Clustering. + We then design an approximation algorithm for $(f,g)$-clustering that interpolates, up to polylog factors, between the best known bounds for $k$-Center, $k$-Median, Min-Sum of Radii, Min-Load $k$-Clustering, (Top, $L_{1}$)-clustering, and $(L_{\infty},g)$-clustering based on a newly defined parameter of $f$ and $g$. + oai:arXiv.org:2512.06211v2 + cs.DS cs.LG - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Kenan Begovic, Abdulaziz Al-Ali, Qutaibah Malluhi - - - Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs - https://arxiv.org/abs/2512.04668 - arXiv:2512.04668v2 Announce Type: replace -Abstract: Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, yet its effects remain poorly quantified. We introduce MAMA (Multi-Agent Memory Attack), a framework that measures how network structure shapes leakage. MAMA operates on synthetic documents containing labeled Personally Identifiable Information (PII) entities, from which we generate sanitized task instructions. We execute a two-phase protocol: Engram (seeding private information into a target agent's memory) and Resonance (multi-round interaction where an attacker attempts extraction). Over up to 10 interaction rounds, we quantify leakage as the fraction of ground-truth PII recovered from attacking agent outputs via exact matching. We systematically evaluate six common network topologies (fully connected, ring, chain, binary tree, star, and star-ring), varying agent counts $n\in\{4,5,6\}$, attacker-target placements, and base models. Our findings reveal consistent patterns: fully connected graphs exhibit maximum leakage while chains provide strongest protection; shorter attacker-target graph distance and higher target centrality significantly increase vulnerability; leakage rises sharply in early rounds before plateauing; model choice shifts absolute leakage rates but preserves topology rankings; temporal/locational PII attributes leak more readily than identity credentials or regulated identifiers. These results provide the first systematic mapping from architectural choices to measurable privacy risk, yielding actionable guidance: prefer sparse or hierarchical connectivity, maximize attacker-target separation, limit node degree and network radius, avoid shortcuts bypassing hubs, and implement topology-aware access controls. - oai:arXiv.org:2512.04668v2 - cs.CR - cs.AI - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jinbo Liu, Defu Cao, Yifei Wei, Tianyao Su, Yuan Liang, Yushun Dong, Yue Zhao, Xiyang Hu - - - Towards Cross-View Point Correspondence in Vision-Language Models - https://arxiv.org/abs/2512.04686 - arXiv:2512.04686v2 Announce Type: replace -Abstract: Cross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), especially in achieving precise point-level correspondence, which is crucial for precise affordance interaction. So we propose the Cross-View Point Correspondence (CVPC) task and CrossPoint-Bench, a comprehensive benchmark with hierarchical design, inspired by the human cognitive process of "perceive", "reason", and "correspond". Our evaluation shows the state-of-the-art models (e.g., Gemini-2.5-Pro) still fall far behind humans, with a gap of over 54.65% in overall accuracy, exposing a challenge in transitioning from coarse-grained judgement to fine-grained coordinate prediction. To address this problem, we construct CrossPoint-378K, a dataset with 378K question-answering pairs across 900 scenes, focused on actionable affordance regions that better reflect real-world manipulation and interaction scenarios. Furthermore, we propose CroPond that trained on the CrossPoint-378K dataset. Our CroPond achieves state-of-the-art performance on CrossPoint-Bench, surpassing Gemini-2.5-Pro by 39.7% accuracy, which offers a foundation for advancing future work on cross-view correspondence. The benchmark, dataset, and model are publicly available at https://github.com/WangYipu2002/CrossPoint. - oai:arXiv.org:2512.04686v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yipu Wang, Yuheng Ji, Yuyang Liu, Enshen Zhou, Ziqiang Yang, Yuxuan Tian, Ziheng Qin, Yue Liu, Huajie Tan, Cheng Chi, Zhiyuan Ma, Daniel Dajun Zeng, Xiaolong Zheng - - - POLARIS: Is Multi-Agentic Reasoning the Next Wave in Engineering Self-Adaptive Systems? - https://arxiv.org/abs/2512.04702 - arXiv:2512.04702v2 Announce Type: replace -Abstract: The growing scale, complexity, interconnectivity, and autonomy of modern software ecosystems introduce unprecedented uncertainty, challenging the foundations of traditional self-adaptation. Existing approaches, typically rule-driven controllers or isolated learning components, struggle to generalize to novel contexts or coordinate responses across distributed subsystems, leaving them ill-equipped for emergent unknown unknowns. Recent discussions on Self-Adaptation 2.0 emphasize an equal partnership between AI and adaptive systems, merging learning-driven intelligence with adaptive control for predictive and proactive behavior. Building on this foundation, we introduce POLARIS, a three-layer multi-agentic self-adaptation framework that advances beyond reactive adaptation. POLARIS integrates: (1) a low-latency Adapter layer for monitoring and safe execution, (2) a transparent Reasoning layer that generates and verifies plans using tool-aware, explainable agents, and (3) a Meta layer that records experiences and meta-learns improved adaptation policies over time. Through shared knowledge and predictive models, POLARIS handles uncertainty, learns from past actions, and evolves its strategies, enabling systems that anticipate change and maintain resilient, goal-directed behavior. Preliminary evaluation on two self-adaptive exemplars, SWIM and SWITCH, shows that POLARIS consistently outperforms state-of-the-art baselines. We argue this marks a shift toward Self-Adaptation 3.0, akin to Software 3.0: a paradigm where systems not only learn from their environment but also reason about and evolve their own adaptation processes, continuously improving to meet novel challenges. - oai:arXiv.org:2512.04702v2 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Divyansh Pandey, Vyakhya Gupta, Prakhar Singhal, Karthik Vaidhyanathan + Martin G. Herold, Evangelos Kipouridis, Joachim Spoerhase - DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors - https://arxiv.org/abs/2512.04799 - arXiv:2512.04799v2 Announce Type: replace -Abstract: We present an enhanced benchmark for evaluating linguistic acceptability in Danish. We first analyze the most common errors found in written Danish. Based on this analysis, we introduce a set of fourteen corruption functions that generate incorrect sentences by systematically introducing errors into existing correct Danish sentences. To ensure the accuracy of these corruptions, we assess their validity using both manual and automatic methods. The results are then used as a benchmark for evaluating Large Language Models on a linguistic acceptability judgement task. Our findings demonstrate that this extension is both broader and more comprehensive than the current state of the art. By incorporating a greater variety of corruption types, our benchmark provides a more rigorous assessment of linguistic acceptability, increasing task difficulty, as evidenced by the lower performance of LLMs on our benchmark compared to existing ones. Our results also suggest that our benchmark has a higher discriminatory power which allows to better distinguish well-performing models from low-performing ones. - oai:arXiv.org:2512.04799v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos + https://arxiv.org/abs/2512.06368 + arXiv:2512.06368v2 Announce Type: replace +Abstract: Monocular dynamic video reconstruction faces significant challenges in dynamic human scenes due to geometric inconsistencies and resolution degradation issues. Existing methods lack 3D human structural understanding, producing geometrically inconsistent results with distorted limb proportions and unnatural human-object fusion, while memory-constrained downsampling causes human boundary drift toward background geometry. To address these limitations, we propose to incorporate hybrid geometric priors that combine SMPL human body models with monocular depth estimation. Our approach leverages structured human priors to maintain surface consistency while capturing fine-grained geometric details in human regions. We introduce HuPrior3R, featuring a hierarchical pipeline with refinement components that processes full-resolution images for overall scene geometry, then applies strategic cropping and cross-attention fusion for human-specific detail enhancement. The method integrates SMPL priors through a Feature Fusion Module to ensure geometrically plausible reconstruction while preserving fine-grained human boundaries. Extensive experiments on TUM Dynamics and GTA-IM datasets demonstrate superior performance in dynamic human reconstruction. + oai:arXiv.org:2512.06368v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Gianluca Barmina, Nathalie Carmen Hau Norman, Peter Schneider-Kamp, Lukas Galke Poech + Weitao Xiong, Zhiyuan Yuan, Jiahao Lu, Chengfeng Zhao, Peng Li, Yuan Liu - EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture - https://arxiv.org/abs/2512.04810 - arXiv:2512.04810v3 Announce Type: replace -Abstract: We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the number of tokens required for generation. This also ensures the training balance between understanding and generation tasks by applying the same compression ratio to images. 2) Channel-wise concatenation instead of token-wise concatenation among visual understanding and generation tokens, which further reduces the visual tokens in unified architectures. 3) A shared-and-decoupled network that enables mutual improvements across tasks while meeting the task-specific modeling requirements. 4) A mixture-of-experts mechanism adopted for visual understanding encoder, which substantially improves perceptual capabilities with a few parameters increase. Extensive experiments have shown that EMMA-4B can significantly outperform state-of-the-art unified multimodal approaches (e.g., BAGEL-7B) in both efficiency and performance, while also achieving competitive results compared to recent multimodal understanding and generation experts (e.g., Qwen3-VL and Qwen-Image). We believe that EMMA lays a solid foundation for the future development of unified multimodal architectures. - oai:arXiv.org:2512.04810v3 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + CommentScope: A Comment-Embedded Assisted Reading System for a Long Text + https://arxiv.org/abs/2512.06408 + arXiv:2512.06408v2 Announce Type: replace +Abstract: Long texts are ubiquitous on social platforms, yet readers often face information overload and struggle to locate key content. Comments provide valuable external perspectives for understanding, questioning, and complementing the text, but their potential is hindered by disorganized and unstructured presentation. Few studies have explored embedding comments directly into reading. As an exploratory step, we propose CommentScope, a system with two core modules: a pipeline that classifies comments into five types and aligns them with relevant sentences, and a presentation module that integrates comments inline or as side notes, supported by visual cues such as colors, charts, and highlights. Technical evaluation shows that the hybrid "Rule+LLM" pipeline achieved solid performance in semantic classification (accuracy=0.90) and position alignment (accuracy=0.88). A user study (N=12) further demonstrated that the sentence-end embedding significantly improved comment discovery accuracy and reading fluency while reducing mental demand and perceived effort. + oai:arXiv.org:2512.06408v2 + cs.HC + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xin He, Longhui Wei, Jianbo Ouyang, Lingxi Xie, Qi Tian + Shuai Chen (Jiangsu Ocean University, Lianyungang, China), Lei Han (Jiangsu Ocean University, Lianyungang, China), Haoyu Wang (Jiangsu Ocean University, Lianyungang, China), Zhaoman Zhong (Jiangsu Ocean University, Lianyungang, China) - Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing - https://arxiv.org/abs/2512.04829 - arXiv:2512.04829v2 Announce Type: replace -Abstract: Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptography, crystallography, and medical imaging, the problem remains unresolved: beyond a few special dimensions, neither optimal packings nor tight upper bounds are known. Even a major breakthrough in dimension $n=8$, later recognised with a Fields Medal, underscores its difficulty. A leading technique for upper bounds, the three-point method, reduces the problem to solving large, high-precision semidefinite programs (SDPs). Because each candidate SDP may take days to evaluate, standard data-intensive AI approaches are infeasible. We address this challenge by formulating SDP construction as a sequential decision process, the SDP game, in which a policy assembles SDP formulations from a set of admissible components. Using a sample-efficient model-based framework that combines Bayesian optimisation with Monte Carlo Tree Search, we obtain new state-of-the-art upper bounds in dimensions $4-16$, showing that model-based search can advance computational progress in longstanding geometric problems. Together, these results demonstrate that sample-efficient, model-based search can make tangible progress on mathematically rigid, evaluation limited problems, pointing towards a complementary direction for AI-assisted discovery beyond large-scale LLM-driven exploration. - oai:arXiv.org:2512.04829v2 + LightSearcher: Efficient DeepSearch via Experiential Memory + https://arxiv.org/abs/2512.06653 + arXiv:2512.06653v2 Announce Type: replace +Abstract: DeepSearch paradigms have become a core enabler for deep reasoning models, allowing them to invoke external search tools to access up-to-date, domain-specific knowledge beyond parametric boundaries, thereby enhancing the depth and factual reliability of reasoning. Building upon this foundation, recent advances in reinforcement learning (RL) have further empowered models to autonomously and strategically control search tool usage, optimizing when and how to query external knowledge sources. Yet, these RL-driven DeepSearch systems often reveal a see-saw trade-off between accuracy and efficiency-frequent tool invocations can improve factual correctness but lead to unnecessary computational overhead and diminished efficiency. To address this challenge, we propose LightSearcher, an efficient RL framework that incorporates textual experiential memory by learning contrastive reasoning trajectories to generate interpretable summaries of successful reasoning patterns. In addition, it employs an adaptive reward shaping mechanism that penalizes redundant tool calls only in correct-answer scenarios. This design effectively balances the inherent accuracy-efficiency trade-off in DeepSearch paradigms. Experiments on four multi-hop QA benchmarks show that LightSearcher maintains accuracy comparable to SOTA baseline ReSearch, while reducing search tool invocations by 39.6%, inference time by 48.6%, and token consumption by 21.2%, demonstrating its superior efficiency. + oai:arXiv.org:2512.06653v2 cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by/4.0/ - Rasul Tutunov, Alexandre Maraval, Antoine Grosnit, Xihan Li, Jun Wang, Haitham Bou-Ammar + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Hengzhi Lan, Yue Yu, Li Qian, Li Peng, Jie Wu, Wei Liu, Jian Luan, Ting Bai - Stability-Guaranteed Dual Kalman Filtering for Electrochemical Battery State Estimation - https://arxiv.org/abs/2512.04885 - arXiv:2512.04885v2 Announce Type: replace -Abstract: Accurate and stable state estimation is critical for battery management. Although dual Kalman filtering can jointly estimate states and parameters, the strong coupling between filters may cause divergence under large initialization errors or model mismatch. This paper proposes a Stability Guaranteed Dual Kalman Filtering (SG-DKF) method. A Lyapunov-based analysis yields a sufficient stability condition, leading to an adaptive dead-zone rule that suspends parameter updates when the innovation exceeds a stability bound. Applied to an electrochemical battery model, SG-DKF achieves accuracy comparable to a dual EKF and reduces state of charge RMSE by over 45% under large initial state errors. - oai:arXiv.org:2512.04885v2 + Symmetry-Based Formation Control on Cycle Graphs Using Dihedral Point Groups + https://arxiv.org/abs/2512.06733 + arXiv:2512.06733v2 Announce Type: replace +Abstract: This work develops a symmetry-based framework for formation control on cycle graphs using Dihedral point-group constraints. We show that enforcing inter-agent reflection symmetries, together with anchoring a single designated agent to its prescribed mirror axis, is sufficient to realize every $\mathcal{C}_{nv}$-symmetric configuration using only $n-1$ communication links. The resulting control laws have a matrix-weighted Laplacian structure and guarantee exponential convergence to the desired symmetric configuration. Furthermore, we extend the method to enable coordinated maneuvers along a time-varying reference trajectory. Simulation results are provided to support the theoretical analysis. + oai:arXiv.org:2512.06733v2 eess.SY cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Feng Guo, Guangdi Hu, Keyi Liao, Luis D. Couto, Khiem Trad, Ru Hong, Hamid Hamed, Mohammadhosein Safari + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Zamir Martinez, Daniel Zelazo - The AI Consumer Index (ACE) - https://arxiv.org/abs/2512.04921 - arXiv:2512.04921v2 Announce Type: replace -Abstract: We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform everyday consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer activities: shopping, food, gaming, and DIY. We are also open sourcing 80 cases as a devset with a CC-BY license. For the ACE leaderboard we evaluated 10 frontier models (with websearch turned on) using a novel grading methodology that dynamically checks whether relevant parts of the response are grounded in the retrieved web sources. GPT 5 (Thinking = High) is the top-performing model, scoring 56.1%, followed by o3 Pro (Thinking = On) at 55.2% and GPT 5.1 (Thinking = High) at 55.1%. Model scores differ across domains, and in Shopping the top model scores under 50\%. We find that models are prone to hallucinating key information, such as prices. ACE shows a substantial gap between the performance of even the best models and consumers' AI needs. - oai:arXiv.org:2512.04921v2 + DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems + https://arxiv.org/abs/2512.06749 + arXiv:2512.06749v2 Announce Type: replace +Abstract: Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to leverage LLMs for log-based failure localization, attributing errors to a specific agent and step. However, this paradigm has two key limitations: (i) log-only debugging lacks validation, producing untested hypotheses, and (ii) single-step or single-agent attribution is often ill-posed, as we find that multiple distinct interventions can independently repair the failed task. To address the first limitation, we introduce DoVer, an intervention-driven debugging framework, which augments hypothesis generation with active verification through targeted interventions (e.g., editing messages, altering plans). For the second limitation, rather than evaluating on attribution accuracy, we focus on measuring whether the system resolves the failure or makes quantifiable progress toward task success, reflecting a more outcome-oriented view of debugging. Within the Magnetic-One agent framework, on the datasets derived from GAIA and AssistantBench, DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses. DoVer also performs effectively on a different dataset (GSMPlus) and agent framework (AG2), where it recovers 49% of failed trials. These results highlight intervention as a practical mechanism for improving reliability in agentic systems and open opportunities for more robust, scalable debugging methods for LLM-based multi-agent systems. Project website and code will be available at https://aka.ms/DoVer. + oai:arXiv.org:2512.06749v2 cs.AI - cs.CL - cs.HC - Tue, 09 Dec 2025 00:00:00 -0500 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Julien Benchek, Rohit Shetty, Benjamin Hunsberger, Ajay Arun, Zach Richards, Brendan Foody, Osvald Nitski, Bertie Vidgen + Ming Ma, Jue Zhang, Fangkai Yang, Yu Kang, Qingwei Lin, Tianming Yang, Saravan Rajmohan, Dongmei Zhang - FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization - https://arxiv.org/abs/2512.04952 - arXiv:2512.04952v2 Announce Type: replace -Abstract: Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce FASTer, a unified framework for efficient and generalizable robot learning that integrates a learnable tokenizer with an autoregressive policy built upon it. FASTerVQ encodes action chunks as single-channel images, capturing global spatio-temporal dependencies while maintaining a high compression ratio. FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance. Extensive experiments across simulated and real-world benchmarks show that FASTerVQ delivers superior reconstruction quality, high token utilization, and strong cross-task and cross-embodiment generalization, while FASTerVLA further improves overall capability, surpassing previous state-of-the-art VLA models in both inference speed and task performance. - oai:arXiv.org:2512.04952v2 - cs.CV + db-LaCAM: Fast and Scalable Multi-Robot Kinodynamic Motion Planning with Discontinuity-Bounded Search and Lightweight MAPF + https://arxiv.org/abs/2512.06796 + arXiv:2512.06796v2 Announce Type: replace +Abstract: State-of-the-art multi-robot kinodynamic motion planners struggle to handle more than a few robots due to high computational burden, which limits their scalability and results in slow planning time. In this work, we combine the scalability and speed of modern multi-agent path finding (MAPF) algorithms with the dynamic-awareness of kinodynamic planners to address these limitations. To this end, we propose discontinuity-Bounded LaCAM (db-LaCAM), a planner that utilizes a precomputed set of motion primitives that respect robot dynamics to generate horizon-length motion sequences, while allowing a user-defined discontinuity between successive motions. The planner db-LaCAM is resolution-complete with respect to motion primitives and supports arbitrary robot dynamics. Extensive experiments demonstrate that db-LaCAM scales efficiently to scenarios with up to 50 robots, achieving up to ten times faster runtime compared to state-of-the-art planners, while maintaining comparable solution quality. The approach is validated in both 2D and 3D environments with dynamics such as the unicycle and 3D double integrator. We demonstrate the safe execution of trajectories planned with db-LaCAM in two distinct physical experiments involving teams of flying robots and car-with-trailer robots. + oai:arXiv.org:2512.06796v2 cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yicheng Liu, Shiduo Zhang, Zibin Dong, Baijun Ye, Tianyuan Yuan, Xiaopeng Yu, Linqi Yin, Chenhao Lu, Junhao Shi, Luca Jiang-Tao Yu, Liangtao Zheng, Tao Jiang, Jingjing Gong, Xipeng Qiu, Hang Zhao - - - Configuration Defects in Kubernetes - https://arxiv.org/abs/2512.05062 - arXiv:2512.05062v2 Announce Type: replace -Abstract: Kubernetes is a tool that facilitates rapid deployment of software. Unfortunately, configuring Kubernetes is prone to errors. Configuration defects are not uncommon and can result in serious consequences. This paper reports an empirical study about configuration defects in Kubernetes with the goal of helping practitioners detect and prevent these defects. We study 719 defects that we extract from 2,260 Kubernetes configuration scripts using open source repositories. Using qualitative analysis, we identify 15 categories of defects. We find 8 publicly available static analysis tools to be capable of detecting 8 of the 15 defect categories. We find that the highest precision and recall of those tools are for defects related to data fields. We develop a linter to detect two categories of defects that cause serious consequences, which none of the studied tools are able to detect. Our linter revealed 26 previously-unknown defects that have been confirmed by practitioners, 19 of which have already been fixed. We conclude our paper by providing recommendations on how defect detection and repair techniques can be used for Kubernetes configuration scripts. The datasets and source code used for the paper are publicly available online. - oai:arXiv.org:2512.05062v2 - cs.SE - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yue Zhang, Uchswas Paul, Marcelo d'Amorim, Akond Rahman + Akmaral Moldagalieva, Keisuke Okumura, Amanda Prorok, Wolfgang H\"onig - Personalizing Agent Privacy Decisions via Logical Entailment - https://arxiv.org/abs/2512.05065 - arXiv:2512.05065v2 Announce Type: replace -Abstract: Personal language model-based agents are becoming more widespread for completing tasks on behalf of users; however, this raises serious privacy questions regarding whether these models will appropriately disclose user data. While prior work has evaluated language models on data-sharing scenarios based on general privacy norms, we focus on personalizing language models' privacy decisions, grounding their judgments directly in prior user privacy decisions. Our findings suggest that general privacy norms are insufficient for effective personalization of privacy decisions. Furthermore, we find that eliciting privacy judgments from the model through In-context Learning (ICL) is unreliable to due misalignment with the user's prior privacy judgments and opaque reasoning traces, which make it difficult for the user to interpret the reasoning behind the model's decisions. To address these limitations, we propose ARIEL (Agentic Reasoning with Individualized Entailment Logic), a framework that jointly leverages a language model and rule-based logic for structured data-sharing reasoning. ARIEL is based on formulating personalization of data sharing as an entailment, whether a prior user judgment on a data-sharing request implies the same judgment for an incoming request. Our experimental evaluations on advanced models and publicly-available datasets demonstrate that ARIEL can reduce the F1 score error by $\textbf{39.1%}$ over language model-based reasoning (ICL), demonstrating that ARIEL is effective at correctly judging requests where the user would approve data sharing. Overall, our findings suggest that combining LLMs with strict logical entailment is a highly effective strategy for enabling personalized privacy judgments for agents. - oai:arXiv.org:2512.05065v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Khalasi: Energy-Efficient Navigation for Surface Vehicles in Vortical Flow Fields + https://arxiv.org/abs/2512.06912 + arXiv:2512.06912v2 Announce Type: replace +Abstract: For centuries, khalasi (Gujarati for sailor) have skillfully harnessed ocean currents to navigate vast waters with minimal effort. Emulating this intuition in autonomous systems remains a significant challenge, particularly for Autonomous Surface Vehicles tasked with long duration missions under strict energy budgets. In this work, we present a learning-based approach for energy-efficient surface vehicle navigation in vortical flow fields, where partial observability often undermines traditional path-planning methods. We present an end to end reinforcement learning framework based on Soft Actor Critic that learns flow-aware navigation policies using only local velocity measurements. Through extensive evaluation across diverse and dynamically rich scenarios, our method demonstrates substantial energy savings and robust generalization to previously unseen flow conditions, offering a promising path toward long term autonomy in ocean environments. The navigation paths generated by our proposed approach show an improvement in energy conservation 30 to 50 percent compared to the existing state of the art techniques. + oai:arXiv.org:2512.06912v2 + cs.RO + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by/4.0/ - James Flemings, Ren Yi, Octavian Suciu, Kassem Fawaz, Murali Annavaram, Marco Gruteser + http://creativecommons.org/licenses/by-nc-sa/4.0/ + Rushiraj Gadhvi, Sandeep Manjanna - TV2TV: A Unified Framework for Interleaved Language and Video Generation - https://arxiv.org/abs/2512.05103 - arXiv:2512.05103v2 Announce Type: replace -Abstract: Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about what should happen next. In this paper, we introduce a new class of omni video-text models that integrate ideas from recent LM reasoning advances to address this challenge. More specifically, we present TV2TV, a unified generative modeling framework which decomposes video generation into an interleaved text and video generation process. TV2TV jointly learns language modeling (next-token prediction) and video flow matching (next-frame prediction) using a Mixture-of-Transformers (MoT) architecture. At inference time, TV2TV decides when to alternate between generating text and video frames, allowing the model to "think in words" about subsequent content before ``acting in pixels'' to produce frames. This design offloads much of the responsibility for deciding what should happen next to the language modeling tower, enabling improved visual quality and prompt alignment of generated videos. It also enables fine-grained controllability, allowing users to modify the video generation trajectory through text interventions at any point in the process. In controlled experiments on video game data, TV2TV demonstrates substantial improvements in both visual quality and controllability. TV2TV also scales to natural videos, as we show by augmenting sports videos with interleaved natural language action descriptions using vision-language models (VLMs). Training TV2TV on this corpus yields strong visual quality and prompt alignment, showcasing the model's ability to reason about and generate complex real-world action sequences. Together, these results highlight TV2TV as a promising step toward video generation with open-ended textual reasoning and control. - oai:arXiv.org:2512.05103v2 - cs.LG - cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering + https://arxiv.org/abs/2512.06915 + arXiv:2512.06915v2 Announce Type: replace +Abstract: Automated environment configuration is a critical bottleneck in scaling software engineering (SWE) automation. To provide a reliable evaluation standard for this task, we present Multi-Docker-Eval benchmark. It includes 40 real-world repositories spanning 9 programming languages and measures both success in achieving executable states and efficiency under realistic constraints. Our extensive evaluation of state-of-the-art LLMs and agent frameworks reveals key insights: (1) the overall success rate of current models is low (F2P at most 37.7%), with environment construction being the primary bottleneck; (2) model size and reasoning length are not decisive factors, and open-source models like DeepSeek-V3.1 and Kimi-K2 are competitive in both efficiency and effectiveness; (3) agent framework and programming language also have significantly influence on success rate. These findings provide actionable guidelines for building scalable, fully automated SWE pipelines. + oai:arXiv.org:2512.06915v2 + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xiaochuang Han, Youssef Emad, Melissa Hall, John Nguyen, Karthik Padthe, Liam Robbins, Amir Bar, Delong Chen, Michal Drozdzal, Maha Elbayad, Yushi Hu, Shang-Wen Li, Sreya Dutta Roy, Jakob Verbeek, XuDong Wang, Marjan Ghazvininejad, Luke Zettlemoyer, Emily Dinan + Kelin Fu, Tianyu Liu, Zeyu Shang, Yingwei Ma, Jian Yang, Jiaheng Liu, Kaigui Bian - NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation - https://arxiv.org/abs/2512.05106 - arXiv:2512.05106v2 Announce Type: replace -Abstract: Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image generation, corrupting phase components destroys spatial structure, making it ill-suited for tasks requiring geometric consistency, such as re-rendering, simulation enhancement, and image-to-image translation. We introduce Phase-Preserving Diffusion {\phi}-PD, a model-agnostic reformulation of the diffusion process that preserves input phase while randomizing magnitude, enabling structure-aligned generation without architectural changes or additional parameters. We further propose Frequency-Selective Structured (FSS) noise, which provides continuous control over structural rigidity via a single frequency-cutoff parameter. {\phi}-PD adds no inference-time cost and is compatible with any diffusion model for images or videos. Across photorealistic and stylized re-rendering, as well as sim-to-real enhancement for driving planners, {\phi}-PD produces controllable, spatially aligned results. When applied to the CARLA simulator, {\phi}-PD improves CARLA-to-Waymo planner performance by 50\%. The method is complementary to existing conditioning approaches and broadly applicable to image-to-image and video-to-video generation. Videos, additional examples, and code are available on our \href{https://yuzeng-at-tri.github.io/ppd-page/}{project page}. - oai:arXiv.org:2512.05106v2 + Evaluating and Preserving High-level Fidelity in Super-Resolution + https://arxiv.org/abs/2512.07037 + arXiv:2512.07037v2 Announce Type: replace +Abstract: Recent image Super-Resolution (SR) models are achieving impressive effects in reconstructing details and delivering visually pleasant outputs. However, the overpowering generative ability can sometimes hallucinate and thus change the image content despite gaining high visual quality. This type of high-level change can be easily identified by humans yet not well-studied in existing low-level image quality metrics. In this paper, we establish the importance of measuring high-level fidelity for SR models as a complementary criterion to reveal the reliability of generative SR models. We construct the first annotated dataset with fidelity scores from different SR models, and evaluate how state-of-the-art (SOTA) SR models actually perform in preserving high-level fidelity. Based on the dataset, we then analyze how existing image quality metrics correlate with fidelity measurement, and further show that this high-level task can be better addressed by foundation models. Finally, by fine-tuning SR models based on our fidelity feedback, we show that both semantic fidelity and perceptual quality can be improved, demonstrating the potential value of our proposed criteria, both in model evaluation and optimization. We will release the dataset, code, and models upon acceptance. + oai:arXiv.org:2512.07037v2 cs.CV - cs.GR cs.LG - cs.RO - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Yu Zeng, Charles Ochoa, Mingyuan Zhou, Vishal M. Patel, Vitor Guizilini, Rowan McAllister - - - Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting - https://arxiv.org/abs/2512.05113 - arXiv:2512.05113v2 Announce Type: replace -Abstract: Synthesizing high-fidelity frozen 3D scenes from monocular Mannequin-Challenge (MC) videos is a unique problem distinct from standard dynamic scene reconstruction. Instead of focusing on modeling motion, our goal is to create a frozen scene while strategically preserving subtle dynamics to enable user-controlled instant selection. To achieve this, we introduce a novel application of dynamic Gaussian splatting: the scene is modeled dynamically, which retains nearby temporal variation, and a static scene is rendered by fixing the model's time parameter. However, under this usage, monocular capture with sparse temporal supervision introduces artifacts like ghosting and blur for Gaussians that become unobserved or occluded at weakly supervised timestamps. We propose Splannequin, an architecture-agnostic regularization that detects two states of Gaussian primitives, hidden and defective, and applies temporal anchoring. Under predominantly forward camera motion, hidden states are anchored to their recent well-observed past states, while defective states are anchored to future states with stronger supervision. Our method integrates into existing dynamic Gaussian pipelines via simple loss terms, requires no architectural changes, and adds zero inference overhead. This results in markedly improved visual quality, enabling high-fidelity, user-selectable frozen-time renderings, validated by a 96% user preference. Project page: https://chien90190.github.io/splannequin/ - oai:arXiv.org:2512.05113v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Hao-Jen Chien, Yi-Chuan Huang, Chung-Ho Wu, Wei-Lun Chao, Yu-Lun Liu + Josep M. Rocafort, Shaolin Su, Alexandra Gomez-Villa, Javier Vazquez-Corral - The Universal Weight Subspace Hypothesis - https://arxiv.org/abs/2512.05117 - arXiv:2512.05117v2 Announce Type: replace -Abstract: We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the first large-scale empirical evidence that demonstrates that neural networks systematically converge to shared spectral subspaces regardless of initialization, task, or domain. Through mode-wise spectral analysis of over 1100 models - including 500 Mistral-7B LoRAs, 500 Vision Transformers, and 50 LLaMA-8B models - we identify universal subspaces capturing majority variance in just a few principal directions. By applying spectral decomposition techniques to the weight matrices of various architectures trained on a wide range of tasks and datasets, we identify sparse, joint subspaces that are consistently exploited, within shared architectures across diverse tasks and datasets. Our findings offer new insights into the intrinsic organization of information within deep networks and raise important questions about the possibility of discovering these universal subspaces without the need for extensive data and computational resources. Furthermore, this inherent structure has significant implications for model reusability, multi-task learning, model merging, and the development of training and inference-efficient algorithms, potentially reducing the carbon footprint of large-scale neural models. - oai:arXiv.org:2512.05117v2 - cs.LG + VIGIL: A Reflective Runtime for Self-Healing Agents + https://arxiv.org/abs/2512.07094 + arXiv:2512.07094v2 Announce Type: replace +Abstract: Agentic LLM frameworks promise autonomous behavior via task decomposition, tool use, and iterative planning, but most deployed systems remain brittle. They lack runtime introspection, cannot diagnose their own failure modes, and do not improve over time without human intervention. In practice, many agent stacks degrade into decorated chains of LLM calls with no structural mechanisms for reliability. We present VIGIL (Verifiable Inspection and Guarded Iterative Learning), a reflective runtime that supervises a sibling agent and performs autonomous maintenance rather than task execution. VIGIL ingests behavioral logs, appraises each event into a structured emotional representation, maintains a persistent EmoBank with decay and contextual policies, and derives an RBT diagnosis that sorts recent behavior into strengths, opportunities, and failures. From this analysis, VIGIL generates both guarded prompt updates that preserve core identity semantics and read only code proposals produced by a strategy engine that operates on log evidence and code hotspots. VIGIL functions as a state gated pipeline. Illegal transitions produce explicit errors rather than allowing the LLM to improvise. In a reminder latency case study, VIGIL identified elevated lag, proposed prompt and code repairs, and when its own diagnostic tool failed due to a schema conflict, it surfaced the internal error, produced a fallback diagnosis, and emitted a repair plan. This demonstrates meta level self repair in a deployed agent runtime. + oai:arXiv.org:2512.07094v2 cs.AI - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Prakhar Kaushik, Shravan Chaudhari, Ankit Vaidya, Rama Chellappa, Alan Yuille + Christopher Cruz - Semantic Faithfulness and Entropy Production Measures to Tame Your LLM Demons and Manage Hallucinations - https://arxiv.org/abs/2512.05156 - arXiv:2512.05156v2 Announce Type: replace -Abstract: Evaluating faithfulness of Large Language Models (LLMs) to a given task is a complex challenge. We propose two new unsupervised metrics for faithfulness evaluation using insights from information theory and thermodynamics. Our approach treats an LLM as a bipartite information engine where hidden layers act as a Maxwell demon controlling transformations of context $C $ into answer $A$ via prompt $Q$. We model Question-Context-Answer (QCA) triplets as probability distributions over shared topics. Topic transformations from $C$ to $Q$ and $A$ are modeled as transition matrices ${\bf Q}$ and ${\bf A}$ encoding the query goal and actual result, respectively. Our semantic faithfulness (SF) metric quantifies faithfulness for any given QCA triplet by the Kullback-Leibler (KL) divergence between these matrices. Both matrices are inferred simultaneously via convex optimization of this KL divergence, and the final SF metric is obtained by mapping the minimal divergence onto the unit interval [0,1], where higher scores indicate greater faithfulness. Furthermore, we propose a thermodynamics-based semantic entropy production (SEP) metric in answer generation, and show that high faithfulness generally implies low entropy production. The SF and SEP metrics can be used jointly or separately for LLM evaluation and hallucination control. We demonstrate our framework on LLM summarization of corporate SEC 10-K filings. - oai:arXiv.org:2512.05156v2 - cs.AI - cs.CL - cs.IT - cs.LG - math.IT - q-fin.CP - Tue, 09 Dec 2025 00:00:00 -0500 + COREA: Coarse-to-Fine 3D Representation Alignment Between Relightable 3D Gaussians and SDF via Bidirectional 3D-to-3D Supervision + https://arxiv.org/abs/2512.07107 + arXiv:2512.07107v2 Announce Type: replace +Abstract: We present COREA, the first unified framework that jointly learns relightable 3D Gaussians and a Signed Distance Field (SDF) for accurate geometry reconstruction and faithful relighting. While recent 3D Gaussian Splatting (3DGS) methods have extended toward mesh reconstruction and physically-based rendering (PBR), their geometry is still learned from 2D renderings, leading to coarse surfaces and unreliable BRDF-lighting decomposition. To address these limitations, COREA introduces a coarse-to-fine bidirectional 3D-to-3D alignment strategy that allows geometric signals to be learned directly in 3D space. Within this strategy, depth provides coarse alignment between the two representations, while depth gradients and normals refine fine-scale structure, and the resulting geometry supports stable BRDF-lighting decomposition. A density-control mechanism further stabilizes Gaussian growth, balancing geometric fidelity with memory efficiency. Experiments on standard benchmarks demonstrate that COREA achieves superior performance in novel-view synthesis, mesh reconstruction, and PBR within a unified framework. + oai:arXiv.org:2512.07107v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by-nc-sa/4.0/ - Igor Halperin + Jaeyoon Lee, Hojoon Jung, Sungtae Hwang, Jihyong Oh, Jongwon Choi - MuMeNet: A Network Simulator for Musical Metaverse Communications - https://arxiv.org/abs/2512.05201 - arXiv:2512.05201v2 Announce Type: replace -Abstract: The Metaverse, a shared and spatially organized digital continuum, is transforming various industries, with music emerging as a leading use case. Live concerts, collaborative composition, and interactive experiences are driving the Musical Metaverse (MM), but the requirements of the underlying network and service infrastructures hinder its growth. These challenges underscore the need for a novel modeling and simulation paradigm tailored to the unique characteristics of MM sessions, along with specialized service provisioning strategies capable of capturing their interactive, heterogeneous, and multicast-oriented nature. To this end, we make a first attempt to formally model and analyze the problem of service provisioning for MM sessions in 5G/6G networks. We first formalize service and network graph models for the MM, using "live audience interaction in a virtual concert" as a reference scenario. We then present MuMeNet, a novel discrete-event network simulator specifically tailored to the requirements and the traffic dynamics of the MM. We showcase the effectiveness of MuMeNet by running a linear programming based orchestration policy on the reference scenario and providing performance analysis under realistic MM workloads. - oai:arXiv.org:2512.05201v2 - cs.NI - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 + TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning + https://arxiv.org/abs/2512.07135 + arXiv:2512.07135v2 Announce Type: replace +Abstract: Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better planning performance when provided with a prior distribution of possible trajectories. However, these approaches often overlook two critical aspects: 1) The appropriate trajectory prior can vary significantly across different driving scenarios. 2) Their trajectory evaluation mechanism lacks policy-driven refinement, remaining constrained by the limitations of one-stage supervised training. To address these issues, we explore improvements in two key areas. For problem 1, we employ MoE to apply different trajectory priors tailored to different scenarios. For problem 2, we utilize Reinforcement Learning to fine-tune the trajectory scoring mechanism. Additionally, we integrate models with different perception backbones to enhance perceptual features. Our integrated model achieved a score of 51.08 on the navsim ICCV benchmark, securing third place. + oai:arXiv.org:2512.07135v2 + cs.CV + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by/4.0/ - Ali Al Housseini, Jaime Llorca, Luca Turchet, Tiziano Leidi, Cristina Rottondi, Omran Ayoub + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zebin Xing, Pengxuan Yang, Linbo Wang, Yichen Zhang, Yiming Hu, Yupeng Zheng, Junli Wang, Yinfeng Gao, Guang Li, Kun Ma, Long Chen, Zhongpu Xia, Qichao Zhang, Hangjun Ye, Dongbin Zhao - Disturbance Compensation for Safe Kinematic Control of Robotic Systems with Closed Architecture - https://arxiv.org/abs/2512.05292 - arXiv:2512.05292v2 Announce Type: replace -Abstract: In commercial robotic systems, it is common to encounter a closed inner-loop torque controller that is not user-modifiable. However, the outer-loop controller, which sends kinematic commands such as position or velocity for the inner-loop controller to track, is typically exposed to users. In this work, we focus on the development of an easily integrated add-on at the outer-loop layer by combining disturbance rejection control and robust control barrier function for high-performance tracking and safe control of the whole dynamic system of an industrial manipulator. This is particularly beneficial when 1) the inner-loop controller is imperfect, unmodifiable, and uncertain; and 2) the dynamic model exhibits significant uncertainty. Stability analysis, formal safety guarantee proof, and hardware experiments with a PUMA robotic manipulator are presented. Our solution demonstrates superior performance in terms of simplicity of implementation, robustness, tracking precision, and safety compared to the state of the art. Video: https://youtu.be/zw1tanvrV8Q - oai:arXiv.org:2512.05292v2 - cs.RO - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics + https://arxiv.org/abs/2512.07155 + arXiv:2512.07155v2 Announce Type: replace +Abstract: Diffusion models exhibit remarkable generative ability, yet achieving smooth and semantically consistent image morphing remains a challenge. Existing approaches often yield abrupt transitions or over-saturated appearances due to the lack of adaptive structural and semantic alignments. We propose CHIMERA, a zero-shot diffusion-based framework that formulates morphing as a cached inversion-guided denoising process. To handle large semantic and appearance disparities, we propose Adaptive Cache Injection and Semantic Anchor Prompting. Adaptive Cache Injection (ACI) caches down, mid, and up blocks features from both inputs during DDIM inversion and re-injects them adaptively during denoising, enabling spatial and semantic alignment in depth- and time-adaptive manners and enabling natural feature fusion and smooth transitions. Semantic Anchor Prompting (SAP) leverages a vision-language model to generate a shared anchor prompt that serves as a semantic anchor, bridging dissimilar inputs and guiding the denoising process toward coherent results. Finally, we introduce the Global-Local Consistency Score (GLCS), a morphing-oriented metric that simultaneously evaluates the global harmonization of the two inputs and the smoothness of the local morphing transition. Extensive experiments and user studies show that CHIMERA achieves smoother and more semantically aligned transitions than existing methods, establishing a new state of the art in image morphing. The code and project page will be publicly released. + oai:arXiv.org:2512.07155v2 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Fan Zhang, Jinfeng Chen, Joseph J. B. Mvogo Ahanda, Hanz Richter, Ge Lv, Bin Hu, Qin Lin + Dahyeon Kye, Jeahun Sung, Mingyu Jeon, Jihyong Oh - Simulating Life Paths with Digital Twins: AI-Generated Future Selves Influence Decision-Making and Expand Human Choice - https://arxiv.org/abs/2512.05397 - arXiv:2512.05397v2 Announce Type: replace -Abstract: Major life transitions demand high-stakes decisions, yet people often struggle to imagine how their future selves will live with the consequences. To support this limited capacity for mental time travel, we introduce AI-enabled digital twins that have ``lived through'' simulated life scenarios. Rather than predicting optimal outcomes, these simulations extend prospective cognition by making alternative futures vivid enough to support deliberation without assuming which path is best. We evaluate this idea in a randomized controlled study (N=192) using multimodal synthesis - facial age progression, voice cloning, and large language model dialogue - to create personalized avatars representing participants 30 years forward. Young adults 18 to 28 years old described pending binary decisions and were assigned to guided imagination or one of four avatar conditions: single-option, balanced dual-option, or expanded three-option with a system-generated novel alternative. Results showed asymmetric effects: single-sided avatars increased shifts toward the presented option, while balanced presentation produced movement toward both. Introducing a system-generated third option increased adoption of this new alternative compared to control, suggesting that AI-generated future selves can expand choice by surfacing paths that might otherwise go unnoticed. Participants rated evaluative reasoning and eudaimonic meaning-making as more important than emotional or visual vividness. Perceived persuasiveness and baseline agency predicted decision change. These findings advance understanding of AI-mediated episodic prospection and raise questions about autonomy in AI-augmented decisions. - oai:arXiv.org:2512.05397v2 - cs.HC + VFM-VLM: Vision Foundation Model and Vision Language Model based Visual Comparison for 3D Pose Estimation + https://arxiv.org/abs/2512.07215 + arXiv:2512.07215v2 Announce Type: replace +Abstract: Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and DINOv2 based approaches for 3D pose estimation in hand object grasping scenarios. We evaluate both models on the task of 6D object pose estimation and demonstrate their complementary strengths: CLIP excels in semantic understanding through language grounding, while DINOv2 provides superior dense geometric features. Through extensive experiments on benchmark datasets, we show that CLIP based methods achieve better semantic consistency, while DINOv2 based approaches demonstrate competitive performance with enhanced geometric precision. Our analysis provides insights for selecting appropriate vision models for robotic manipulation and grasping, picking applications. + oai:arXiv.org:2512.07215v2 + cs.CV cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Rachel Poonsiriwong, Chayapatr Archiwaranguprok, Constanze Albrecht, Peggy Yin, Nattavudh Powdthavee, Hal Hershfield, Monchai Lertsutthiwong, Kavin Winson, Pat Pataranutaporn - - - LMSpell: Neural Spell Checking for Low-Resource Languages - https://arxiv.org/abs/2512.05414 - arXiv:2512.05414v2 Announce Type: replace -Abstract: Spell correction is still a challenging problem for low-resource languages (LRLs). While pretrained language models (PLMs) have been employed for spell correction, their use is still limited to a handful of languages, and there has been no proper comparison across PLMs. We present the first empirical study on the effectiveness of PLMs for spell correction, which includes LRLs. We find that Large Language Models (LLMs) outperform their counterparts (encoder-based and encoder-decoder) when the fine-tuning dataset is large. This observation holds even in languages for which the LLM is not pre-trained. We release LMSpell, an easy- to use spell correction toolkit across PLMs. It includes an evaluation function that compensates for the hallucination of LLMs. Further, we present a case study with Sinhala to shed light on the plight of spell correction for LRLs. - oai:arXiv.org:2512.05414v2 - cs.CL - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Akesh Gunathilake, Nadil Karunarathne, Tharusha Bandaranayake, Nisansa de Silva, Surangika Ranathunga + Md Selim Sarowar, Sungho Kim - TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations - https://arxiv.org/abs/2512.05485 - arXiv:2512.05485v2 Announce Type: replace -Abstract: While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced integration of core components (attack, defense, and evaluation methods) and an isolation between flexible evaluation frameworks and standardized benchmarking capabilities. These limitations hinder reliable cross-study comparisons and create unnecessary overhead for comprehensive risk assessment. To address these gaps, we present TeleAI-Safety, a modular and reproducible framework coupled with a systematic benchmark for rigorous LLM safety evaluation. Our framework integrates a broad collection of 19 attack methods (including one self-developed method), 29 defense methods, and 19 evaluation methods (including one self-developed method). With a curated attack corpus of 342 samples spanning 12 distinct risk categories, the TeleAI-Safety benchmark conducts extensive evaluations across 14 target models. The results reveal systematic vulnerabilities and model-specific failure cases, highlighting critical trade-offs between safety and utility, and identifying potential defense patterns for future optimization. In practical scenarios, TeleAI-Safety can be flexibly adjusted with customized attack, defense, and evaluation combinations to meet specific demands. We release our complete code and evaluation results to facilitate reproducible research and establish unified safety baselines. - oai:arXiv.org:2512.05485v2 - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Pay Less Attention to Function Words for Free Robustness of Vision-Language Models + https://arxiv.org/abs/2512.07222 + arXiv:2512.07222v2 Announce Type: replace +Abstract: To address the trade-off between robustness and performance for robust VLM, we observe that function words could incur vulnerability of VLMs against cross-modal adversarial attacks, and propose Function-word De-Attention (FDA) accordingly to mitigate the impact of function words. Similar to differential amplifiers, our FDA calculates the original and the function-word cross-attention within attention heads, and differentially subtracts the latter from the former for more aligned and robust VLMs. Comprehensive experiments include 2 SOTA baselines under 6 different attacks on 2 downstream tasks, 3 datasets, and 3 models. Overall, our FDA yields an average 18/13/53% ASR drop with only 0.2/0.3/0.6% performance drops on the 3 tested models on retrieval, and a 90% ASR drop with a 0.3% performance gain on visual grounding. We demonstrate the scalability, generalization, and zero-shot performance of FDA experimentally, as well as in-depth ablation studies and analysis. Code will be made publicly at https://github.com/michaeltian108/FDA. + oai:arXiv.org:2512.07222v2 + cs.LG + cs.CL + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Xiuyuan Chen, Jian Zhao, Yuxiang He, Yuan Xun, Xinwei Liu, Yanshu Li, Huilin Zhou, Wei Cai, Ziyan Shi, Yuchen Yuan, Tianle Zhang, Chi Zhang, Xuelong Li + Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen - Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning - https://arxiv.org/abs/2512.05513 - arXiv:2512.05513v2 Announce Type: replace -Abstract: Large Video-Language Models (Video-LMs) have achieved impressive progress in multimodal understanding, yet their reasoning remains weakly grounded in space and time. We present Know-Show, a new benchmark designed to evaluate spatio-temporal grounded reasoning, the ability of a model to reason about actions and their semantics while simultaneously grounding its inferences in visual and temporal evidence. Know-Show unifies reasoning and localization within a single evaluation framework consisting of five complementary scenarios across spatial (person, object, person-object, and hand-object) and temporal dimensions. Built from Charades, Action Genome, and Ego4D with 2.5K human-authored questions, the benchmark exposes significant gaps between current Video-LMs and human reasoning. To bridge this gap, we propose GRAM, a training-free plug-in that augments Video-LMs with fine-grained grounding through attention-based video token selection and explicit timestamp encoding. Extensive experiments across open and closed Video-LMs (Qwen, VideoLLaVA, GPT-4o, and Gemini, etc.) reveal that existing models struggle to "show what they know" and vice versa, especially in fine-grained hand-object interactions. Know-Show establishes a unified standard for assessing grounded reasoning in video-language understanding and provides insights toward developing interpretable and reliable multimodal reasoning systems. We will release the dataset and the code at https://github.com/LUNAProject22/Know-Show. - oai:arXiv.org:2512.05513v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + How Do LLMs Fail In Agentic Scenarios? A Qualitative Analysis of Success and Failure Scenarios of Various LLMs in Agentic Simulations + https://arxiv.org/abs/2512.07497 + arXiv:2512.07497v2 Announce Type: replace +Abstract: We investigate how large language models (LLMs) fail when operating as autonomous agents with tool-use capabilities. Using the Kamiwaza Agentic Merit Index (KAMI) v0.1 benchmark, we analyze 900 execution traces from three representative models - Granite 4 Small, Llama 4 Maverick, and DeepSeek V3.1 - across filesystem, text extraction, CSV analysis, and SQL scenarios. Rather than focusing on aggregate scores, we perform fine-grained, per-trial behavioral analysis to surface the strategies that enable successful multi-step tool execution and the recurrent failure modes that undermine reliability. Our findings show that model scale alone does not predict agentic robustness: Llama 4 Maverick (400B) performs only marginally better than Granite 4 Small (32B) in some uncertainty-driven tasks, while DeepSeek V3.1's superior reliability derives primarily from post-training reinforcement learning rather than architecture or size. Across models, we identify four recurring failure archetypes: premature action without grounding, over-helpfulness that substitutes missing entities, vulnerability to distractor-induced context pollution, and fragile execution under load. These patterns highlight the need for agentic evaluation methods that emphasize interactive grounding, recovery behavior, and environment-aware adaptation, suggesting that reliable enterprise deployment requires not just stronger models but deliberate training and design choices that reinforce verification, constraint discovery, and adherence to source-of-truth data. + oai:arXiv.org:2512.07497v2 + cs.AI + cs.SE + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Chinthani Sugandhika, Chen Li, Deepu Rajan, Basura Fernando + JV Roig - VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation - https://arxiv.org/abs/2512.05524 - arXiv:2512.05524v2 Announce Type: replace -Abstract: Spatio-temporal scene graph generation (ST-SGG) aims to model objects and their evolving relationships across video frames, enabling interpretable representations for downstream reasoning tasks such as video captioning and visual question answering. Despite recent advancements in DETR-style single-stage ST-SGG models, they still suffer from several key limitations. First, while these models rely on attention-based learnable queries as a core component, these learnable queries are semantically uninformed and instance-agnostically initialized. Second, these models rely exclusively on unimodal visual features for predicate classification. To address these challenges, we propose VOST-SGG, a VLM-aided one-stage ST-SGG framework that integrates the common sense reasoning capabilities of vision-language models (VLMs) into the ST-SGG pipeline. First, we introduce the dual-source query initialization strategy that disentangles what to attend to from where to attend, enabling semantically grounded what-where reasoning. Furthermore, we propose a multi-modal feature bank that fuses visual, textual, and spatial cues derived from VLMs for improved predicate classification. Extensive experiments on the Action Genome dataset demonstrate that our approach achieves state-of-the-art performance, validating the effectiveness of integrating VLM-aided semantic priors and multi-modal features for ST-SGG. We will release the code at https://github.com/LUNAProject22/VOST. - oai:arXiv.org:2512.05524v2 + MeshRipple: Structured Autoregressive Generation of Artist-Meshes + https://arxiv.org/abs/2512.07514 + arXiv:2512.07514v2 Announce Type: replace +Abstract: Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines. + oai:arXiv.org:2512.07514v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by/4.0/ - Chinthani Sugandhika, Chen Li, Deepu Rajan, Basura Fernando + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Junkai Lin, Hang Long, Huipeng Guo, Jielei Zhang, JiaYi Yang, Tianle Guo, Yang Yang, Jianwen Li, Wenxiao Zhang, Matthias Nie{\ss}ner, Wei Yang - Are Bus-Mounted Edge Servers Feasible? - https://arxiv.org/abs/2512.05543 - arXiv:2512.05543v2 Announce Type: replace -Abstract: Placement of edge servers is the prerequisite of provisioning edge computing services for Internet of Vehicles (IoV). Fixed-site edge servers at Road Side Units (RSUs) or base stations are able to offer basic service coverage for end users, i.e., vehicles on road. However, the server locations and capacity are fixed after deployment, rendering their inefficiency in handling spationtemporal user dynamics. Mobile servers such as buses, on the other hand, have the potential of adding computation elasticity to such system. To this end, this paper studies the feasibility of bus-mounted edge servers based on real traces. First, we investigate the coverage of the buses and base stations using the Shanghai bus/taxi/Telecom datasets, which shows a great potential of bus-based edge servers as they cover a great portion of geographic area and demand points. Next, we build a mathematical model and design a simple greedy heuristic algorithm to select a limited number of buses that maximizes the coverage of demand points, i.e., with a limited purchase budget. We perform trace-driven simulations to verify the performance of the proposed bus selection algorithm. The results show that our approach effectively handles the dynamic user demand under realistic constraints such as server capacity and purchase quantity. Thus, we claim: bus-mounted edge servers for vehicular networks in urban areas are feasible, beneficial, and valuable. - oai:arXiv.org:2512.05543v2 - cs.DC - Tue, 09 Dec 2025 00:00:00 -0500 + From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Images + https://arxiv.org/abs/2512.07527 + arXiv:2512.07527v2 Announce Type: replace +Abstract: City-scale 3D reconstruction from satellite imagery presents the challenge of extreme viewpoint extrapolation, where our goal is to synthesize ground-level novel views from sparse orbital images with minimal parallax. This requires inferring nearly $90^\circ$ viewpoint gaps from image sources with severely foreshortened facades and flawed textures, causing state-of-the-art reconstruction engines such as NeRF and 3DGS to fail. To address this problem, we propose two design choices tailored for city structures and satellite inputs. First, we model city geometry as a 2.5D height map, implemented as a Z-monotonic signed distance field (SDF) that matches urban building layouts from top-down viewpoints. This stabilizes geometry optimization under sparse, off-nadir satellite views and yields a watertight mesh with crisp roofs and clean, vertically extruded facades. Second, we paint the mesh appearance from satellite images via differentiable rendering techniques. While the satellite inputs may contain long-range, blurry captures, we further train a generative texture restoration network to enhance the appearance, recovering high-frequency, plausible texture details from degraded inputs. Our method's scalability and robustness are demonstrated through extensive experiments on large-scale urban reconstruction. For example, in our teaser figure, we reconstruct a $4\,\mathrm{km}^2$ real-world region from only a few satellite images, achieving state-of-the-art performance in synthesizing photorealistic ground views. The resulting models are not only visually compelling but also serve as high-fidelity, application-ready assets for downstream tasks like urban planning and simulation. Project page can be found at https://pku-vcl-geometry.github.io/Orbit2Ground/. + oai:arXiv.org:2512.07527v2 + cs.CV + cs.GR + Wed, 10 Dec 2025 00:00:00 -0500 replace http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Xuezhi Li, Jiancong He, Ming Xie, Xuyang Chen, Le Chang, Li Jiang, Gui Gui + Fei Yu, Yu Liu, Luyang Tang, Mingchao Sun, Zengye Ge, Rui Bu, Yuchao Jin, Haisen Zhao, He Sun, Yangyan Li, Mu Xu, Wenzheng Chen, Baoquan Chen - Utility Boundary of Dataset Distillation: Scaling and Configuration-Coverage Laws - https://arxiv.org/abs/2512.05817 - arXiv:2512.05817v2 Announce Type: replace -Abstract: Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its theoretical foundations remain limited: existing methods (gradient, distribution, trajectory matching) are built on heterogeneous surrogate objectives and optimization assumptions, which makes it difficult to analyze their common principles or provide general guarantees. Moreover, it is still unclear under what conditions distilled data can retain the effectiveness of full datasets when the training configuration, such as optimizer, architecture, or augmentation, changes. To answer these questions, we propose a unified theoretical framework, termed configuration--dynamics--error analysis, which reformulates major DD approaches under a common generalization-error perspective and provides two main results: (i) a scaling law that provides a single-configuration upper bound, characterizing how the error decreases as the distilled sample size increases and explaining the commonly observed performance saturation effect; and (ii) a coverage law showing that the required distilled sample size scales linearly with configuration diversity, with provably matching upper and lower bounds. In addition, our unified analysis reveals that various matching methods are interchangeable surrogates, reducing the same generalization error, clarifying why they can all achieve dataset distillation and providing guidance on how surrogate choices affect sample efficiency and robustness. Experiments across diverse methods and configurations empirically confirm the derived laws, advancing a theoretical foundation for DD and enabling theory-driven design of compact, configuration-robust dataset distillation. - oai:arXiv.org:2512.05817v2 + FRWKV:Frequency-Domain Linear Attention for Long-Term Time Series Forecasting + https://arxiv.org/abs/2512.07539 + arXiv:2512.07539v2 Announce Type: replace +Abstract: Traditional Transformers face a major bottleneck in long-sequence time series forecasting due to their quadratic complexity $(\mathcal{O}(T^2))$ and their limited ability to effectively exploit frequency-domain information. Inspired by RWKV's $\mathcal{O}(T)$ linear attention and frequency-domain modeling, we propose FRWKV, a frequency-domain linear-attention framework that overcomes these limitations. Our model integrates linear attention mechanisms with frequency-domain analysis, achieving $\mathcal{O}(T)$ computational complexity in the attention path while exploiting spectral information to enhance temporal feature representations for scalable long-sequence modeling. Across eight real-world datasets, FRWKV achieves a first-place average rank. Our ablation studies confirm the critical roles of both the linear attention and frequency-encoder components. This work demonstrates the powerful synergy between linear attention and frequency analysis, establishing a new paradigm for scalable time series modeling. Code is available at this repository: https://github.com/yangqingyuan-byte/FRWKV. + oai:arXiv.org:2512.07539v2 cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace - http://creativecommons.org/licenses/by/4.0/ - Zhengquan Luo, Zhiqiang Xu - - - VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack - https://arxiv.org/abs/2512.05853 - arXiv:2512.05853v2 Announce Type: replace -Abstract: Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak attacks, which induces MLLMs to output harmful content. Due to the strong reasoning ability of MLLMs, previous jailbreak attacks try to explore reasoning safety risk in text modal, while similar threats have been largely overlooked in the visual modal. To fully evaluate potential safety risks in the visual reasoning task, we propose Visual Reasoning Sequential Attack (VRSA), which induces MLLMs to gradually externalize and aggregate complete harmful intent by decomposing the original harmful text into several sequentially related sub-images. In particular, to enhance the rationality of the scene in the image sequence, we propose Adaptive Scene Refinement to optimize the scene most relevant to the original harmful query. To ensure the semantic continuity of the generated image, we propose Semantic Coherent Completion to iteratively rewrite each sub-text combined with contextual information in this scene. In addition, we propose Text-Image Consistency Alignment to keep the semantical consistency. A series of experiments demonstrates that the VRSA can achieve a higher attack success rate compared with the state-of-the-art jailbreak attack methods on both the open-source and closed-source MLLMs such as GPT-4o and Claude-4.5-Sonnet. - oai:arXiv.org:2512.05853v2 - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace http://creativecommons.org/licenses/by/4.0/ - Shiji Zhao, Shukun Xiong, Yao Huang, Yan Jin, Zhenyu Wu, Jiyang Guan, Ranjie Duan, Jialing Tao, Hui Xue, Xingxing Wei + Qingyuan Yang, Shizhuo Deng, Dongyue Chen, Da Teng, Zehua Gan - InstructMPC: A Human-LLM-in-the-Loop Framework for Context-Aware Power Grid Control - https://arxiv.org/abs/2512.05876 - arXiv:2512.05876v2 Announce Type: replace -Abstract: The transition toward power grids with high renewable penetration demands context-aware decision making frameworks. Traditional operational paradigms, which rely on static optimization of history-based load forecasting, often fail to capture the complex nature of real-time operational conditions, such as operator-issued maintenance mandates, emergency topology changes, or event-driven load surges. To address this challenge, we introduce InstructMPC, a closed-loop framework that integrates Large Language Models~(LLMs) to generate context-aware predictions, enabling the controller to optimize power system operation. Our method employs a Contextual Disturbances Predictor~(CDP) module to translate contextual information into predictive disturbance trajectories, which are then incorporated into the Model Predictive Control~(MPC) optimization. Unlike conventional open-loop forecasting frameworks, InstructMPC features an online tuning mechanism where the predictor's parameters are continuously updated based on the realized control cost with a theoretical guarantee, achieving a regret bound of $O(\sqrt{T \log T})$ for linear dynamics when optimized via a tailored loss function, ensuring task-aware learning and adaption to non-stationary grid conditions. - oai:arXiv.org:2512.05876v2 + Obstacle Avoidance of UAV in Dynamic Environments Using Direction and Velocity-Adaptive Artificial Potential Field + https://arxiv.org/abs/2512.07609 + arXiv:2512.07609v2 Announce Type: replace +Abstract: The conventional Artificial Potential Field (APF) is fundamentally limited by the local minima issue and its inability to account for the kinematics of moving obstacles. This paper addresses the critical challenge of autonomous collision avoidance for Unmanned Aerial Vehicles (UAVs) operating in dynamic and cluttered airspace by proposing a novel Direction and Relative Velocity Weighted Artificial Potential Field (APF). In this approach, a bounded weighting function, $\omega(\theta,v_{e})$, is introduced to dynamically scale the repulsive potential based on the direction and velocity of the obstacle relative to the UAV. This robust APF formulation is integrated within a Model Predictive Control (MPC) framework to generate collision-free trajectories while adhering to kinematic constraints. Simulation results demonstrate that the proposed method effectively resolves local minima and significantly enhances safety by enabling smooth, predictive avoidance maneuvers. The system ensures superior path integrity and reliable performance, confirming its viability for autonomous navigation in complex environments. + oai:arXiv.org:2512.07609v2 eess.SY + cs.RO cs.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Ruixiang Wu, Jiahao Ai, Tinko Sebastian Bartels - - - One-Shot Distributed Source Simulation: As Quantum as it Can Get - https://arxiv.org/abs/2301.04301 - arXiv:2301.04301v3 Announce Type: replace-cross -Abstract: Distributed source simulation is the task where two (or more) parties share some correlated randomness and use local operations and no communication to convert this into some target correlation. Wyner's seminal result showed that asymptotically the rate of uniform shared randomness needed for this task is given by a mutual information induced measure, now referred to as Wyner's common information. This asymptotic result was extended by Hayashi in the quantum setting to separable states, the largest class of states for which this task can be performed to vanishing error. In this work we characterize this task in a near-tight manner in the one-shot setting using the smooth entropy framework. We do this by introducing one-shot operational quantities and correlation measures that characterize them. We establish asymptotic equipartition properties for our correlation measures thereby recovering the previous vanishing-error asymptotic results. In doing so, we consider technical points in one-shot network information theory and provide methods for cardinality bounds in the smooth entropy calculus. We also introduce entangled state versions of the distributed source simulation task and determine bounds in this setting via quantum embezzling. This provides a strong characterization of this network task in the one-shot, quantum regime. - oai:arXiv.org:2301.04301v3 - quant-ph - cs.IT - math.IT - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1109/TIT.2025.3624812 - IEEE Transactions on Information Theory, vol. 71, no. 12, pp. 9251 - 9284, Oct 2025 - Ian George, Min-Hsiu Hsieh, Eric Chitambar - - - Exploiting Supply Chain Interdependencies for Stock Return Prediction: A Full-State Graph Convolutional LSTM - https://arxiv.org/abs/2303.09406 - arXiv:2303.09406v2 Announce Type: replace-cross -Abstract: Stock return prediction is fundamental to financial decision-making, yet traditional time series models fail to capture the complex interdependencies between companies in modern markets. We propose the Full-State Graph Convolutional LSTM (FS-GCLSTM), a novel temporal graph neural network that incorporates value-chain relationships to enhance stock return forecasting. Our approach features two key innovations: First, we represent inter-firm dependencies through value-chain networks, where nodes correspond to companies and edges capture supplier-customer relationships, enabling the model to leverage information beyond historical price data. Second, FS-GCLSTM applies graph convolutions to all LSTM components - current input features, previous hidden states, and cell states - ensuring that spatial information from the value-chain network influences every aspect of the temporal update mechanism. We evaluate FS-GCLSTM on Eurostoxx 600 and S&P 500 datasets using LSEG value-chain data. While not achieving the lowest traditional prediction errors, FS-GCLSTM consistently delivers superior portfolio performance, attaining the highest annualized returns, Sharpe ratios, and Sortino ratios across both markets. Performance gains are more pronounced in the denser Eurostoxx 600 network, and robustness tests confirm stability across different input sequence lengths, demonstrating the practical value of integrating value-chain data with temporal graph neural networks. - oai:arXiv.org:2303.09406v2 - q-fin.ST - cs.LG - q-fin.CP - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Chang Liu - - - Anatomical basis of sex differences in the electrocardiogram identified by three-dimensional torso-heart imaging reconstruction pipeline - https://arxiv.org/abs/2312.13976 - arXiv:2312.13976v4 Announce Type: replace-cross -Abstract: The electrocardiogram (ECG) is used for diagnosis and risk stratification in myocardial infarction (MI). Women have a higher incidence of missed MI diagnosis and complications following infarction, and to address this we aim to provide quantitative information on sex-differences in ECG and torso-ventricular anatomical features and their interdependence. A novel computational automated pipeline is presented enabling the three-dimensional reconstruction of torso-ventricular anatomies for 425 post-MI subjects and 1051 healthy controls from UK Biobank clinical images. Regression models were created relating torso-ventricular and ECG parameters. We found that female hearts were positioned more posteriorly and superiorly than male, and in MI hearts were oriented more horizontally, especially for women. Post-MI women exhibited less QRS prolongation, requiring 27% more prolongation than men to exceed 120ms. Only half of the sex difference in QRS duration was associated with smaller female cavities. Lower STj amplitude in women was striking, associated with smaller ventricles, but also more superior and posterior cardiac position. Post-MI, T wave amplitude and R axis deviations were more strongly associated with posterior and horizontal cardiac positioning in women than in men. Our study highlights the need to quantify sex differences in anatomical features, their implications in ECG interpretation, and the application of clinical ECG thresholds in post-MI. - oai:arXiv.org:2312.13976v4 - physics.med-ph - cs.AI - cs.CG - eess.IV - q-bio.QM - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross http://creativecommons.org/licenses/by/4.0/ - Hannah J. Smith, Blanca Rodriguez, Yuling Sang, Marcel Beetz, Robin P. Choudhury, Vicente Grau, Abhirup Banerjee + Nikita Vaibhav Pavle, Shrreya Rajneesh, Rakesh Kumar Sahoo, Manoranjan Sinha - Deep Spatiotemporal Clutter Filtering of Transthoracic Echocardiographic Images: Leveraging Contextual Attention and Residual Learning - https://arxiv.org/abs/2401.13147 - arXiv:2401.13147v3 Announce Type: replace-cross -Abstract: This study presents a deep convolutional autoencoder network for filtering reverberation clutter from transthoracic echocardiographic (TTE) image sequences. Given the spatiotemporal nature of this type of clutter, the filtering network employs 3D convolutional layers to suppress it throughout the cardiac cycle. The design of the network incorporates two key features that contribute to the effectiveness of the filter: 1) an attention mechanism for focusing on cluttered regions and leveraging contextual information, and 2) residual learning for preserving fine image structures. To train the network, a diverse set of artifact patterns was simulated and superimposed onto ultra-realistic synthetic TTE sequences from six ultrasound vendors, generating input for the filtering network. The artifact-free sequences served as ground-truth. Performance of the filtering network was evaluated using unseen synthetic and in vivo artifactual sequences. Results from the in vivo dataset confirmed the network's strong generalization capabilities, despite being trained solely on synthetic data and simulated artifacts. The suitability of the filtered sequences for downstream processing was assessed by computing segmental strain curves. A significant reduction in the discrepancy between strain profiles computed from cluttered and clutter-free segments was observed after filtering the cluttered sequences with the proposed network. The trained network processes a TTE sequence in a fraction of a second, enabling real-time clutter filtering and potentially improving the precision of clinically relevant indices derived from TTE sequences. The source code of the proposed method and example video files of the filtering results are available at: https://github.com/MahdiTabassian/Deep-ClutterFiltering/tree/main. - oai:arXiv.org:2401.13147v3 - eess.IV + ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation + https://arxiv.org/abs/2512.07720 + arXiv:2512.07720v2 Announce Type: replace +Abstract: Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction models, are fast and capable of producing stable body structures, but they often suffer from artifacts such as blurry textures and stiff, unnatural motion. In contrast, generative video models show promising performance by synthesizing photorealistic and dynamic results, but they frequently struggle with unstable behavior, including body structural errors and identity drift. To address these limitations, we propose a novel approach that combines the strengths of both paradigms. Our framework employs a 3D reconstruction model to provide robust structural and appearance priors, which in turn guides a real-time autoregressive video diffusion model for rendering. This process enables the model to synthesize high-frequency, photorealistic details and fluid dynamics in real time, effectively reducing texture blur and motion stiffness while preventing the structural inconsistencies common in video generation methods. By uniting the geometric stability of 3D reconstruction with the generative capabilities of video models, our method produces high-fidelity digital avatars with realistic appearance and dynamic, temporally coherent motion. Experiments demonstrate that our approach significantly reduces artifacts and achieves substantial improvements in visual quality over leading methods, providing a robust and efficient solution for real-time applications such as gaming and virtual reality. Project page: https://lhyfst.github.io/visa + oai:arXiv.org:2512.07720v2 cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Mahdi Tabassian, Somayeh Akbari, Sandro Queir\'os, Jan D'hooge + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Fan Yang, Heyuan Li, Peihao Li, Weihao Yuan, Lingteng Qiu, Chaoyue Song, Cheng Chen, Yisheng He, Shifeng Zhang, Xiaoguang Han, Steven Hoi, Guosheng Lin - Tyche: Stochastic In-Context Learning for Medical Image Segmentation - https://arxiv.org/abs/2401.13650 - arXiv:2401.13650v2 Announce Type: replace-cross -Abstract: Existing learning-based solutions to medical image segmentation have two important shortcomings. First, for most new segmentation task, a new model has to be trained or fine-tuned. This requires extensive resources and machine learning expertise, and is therefore often infeasible for medical researchers and clinicians. Second, most existing segmentation methods produce a single deterministic segmentation mask for a given image. In practice however, there is often considerable uncertainty about what constitutes the correct segmentation, and different expert annotators will often segment the same image differently. We tackle both of these problems with Tyche, a model that uses a context set to generate stochastic predictions for previously unseen tasks without the need to retrain. Tyche differs from other in-context segmentation methods in two important ways. (1) We introduce a novel convolution block architecture that enables interactions among predictions. (2) We introduce in-context test-time augmentation, a new mechanism to provide prediction stochasticity. When combined with appropriate model design and loss functions, Tyche can predict a set of plausible diverse segmentation candidates for new or unseen medical images and segmentation tasks without the need to retrain. - oai:arXiv.org:2401.13650v2 - eess.IV - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross + On computing the (exact) Fr\'echet distance with a frog + https://arxiv.org/abs/2512.07728 + arXiv:2512.07728v2 Announce Type: replace +Abstract: The continuous Frechet distance between two polygonal curves is classically computed by exploring their free space diagram. Recently, Har-Peled, Raichel, and Robson [SoCG'25] proposed a radically different approach: instead of directly traversing the continuous free space, they approximate the distance by computing paths in a discrete graph derived from the discrete free space, recursively bisecting edges until the discrete distance converges to the continuous Frechet distance. They implement this so-called frog-based technique and report substantial practical speedups over the state of the art. + We revisit the frog-based approach and address three of its limitations. First, the method does not compute the Frechet distance exactly. Second, the recursive bisection procedure only introduces the monotonicity events required to realise the Frechet distance asymptotically, that is, only in the limit. Third, the applied simplification technique is heuristic. Motivated by theoretical considerations, we develop new techniques that guarantee exactness, polynomial-time convergence, and near-optimal lossless simplifications. We provide an open-source C++ implementation of our variant. + Our primary contribution is an extensive empirical evaluation. As expected, exact computation introduces overhead and increases the median running time. Yet, our method is often faster in the worst case, the slowest ten percent of instances, or even on average due to its convergence guarantees. More surprisingly, in our experiments, the implementation of Bringmann, Kuennemann, and Nusser [SoCG'19] consistently outperforms all frog-based approaches in practice. This appears to contrast published claims of the efficiency of the frog-based techniques. These results thereby provide nuanced perspective on frogs: highlighting both the theoretical appeal, but also the practical limitations. + oai:arXiv.org:2512.07728v2 + cs.CG + Wed, 10 Dec 2025 00:00:00 -0500 + replace http://creativecommons.org/licenses/by/4.0/ - Marianne Rakic, Hallee E. Wong, Jose Javier Gonzalez Ortiz, Beth Cimini, John Guttag, Adrian V. Dalca + Jacobus Conradi, Ivor van der Hoog, Eva Rotenberg - Generative AI and Copyright: A Dynamic Perspective - https://arxiv.org/abs/2402.17801 - arXiv:2402.17801v2 Announce Type: replace-cross -Abstract: The rapid advancement of generative AI is poised to disrupt the creative industry. Amidst the immense excitement for this new technology, its future development and applications in the creative industry hinge crucially upon two copyright issues: 1) the compensation to creators whose content has been used to train generative AI models (the fair use standard); and 2) the eligibility of AI-generated content for copyright protection (AI-copyrightability). While both issues have ignited heated debates among academics and practitioners, most analysis has focused on their challenges posed to existing copyright doctrines. In this paper, we aim to better understand the economic implications of these two regulatory issues and their interactions. By constructing a dynamic model with endogenous content creation and AI model development, we unravel the impacts of the fair use standard and AI-copyrightability on AI development, AI company profit, creators income, and consumer welfare, and how these impacts are influenced by various economic and operational factors. For example, while generous fair use (use data for AI training without compensating the creator) benefits all parties when abundant training data exists, it can hurt creators and consumers when such data is scarce. Similarly, stronger AI-copyrightability (AI content enjoys more copyright protection) could hinder AI development and reduce social welfare. Our analysis also highlights the complex interplay between these two copyright issues. For instance, when existing training data is scarce, generous fair use may be preferred only when AI-copyrightability is weak. Our findings underscore the need for policymakers to embrace a dynamic, context-specific approach in making regulatory decisions and provide insights for business leaders navigating the complexities of the global regulatory environment. - oai:arXiv.org:2402.17801v2 - econ.TH + Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support + https://arxiv.org/abs/2512.07801 + arXiv:2512.07801v2 Announce Type: replace +Abstract: LLM-based agents are increasingly deployed for expert decision support, yet human-AI teams in high-stakes settings do not yet reliably outperform the best individual. We argue this complementarity gap reflects a fundamental mismatch: current agents are trained as answer engines, not as partners in the collaborative sensemaking through which experts actually make decisions. Sensemaking (the ability to co-construct causal explanations, surface uncertainties, and adapt goals) is the key capability that current training pipelines do not explicitly develop or evaluate. We propose Collaborative Causal Sensemaking (CCS) as a research agenda to develop this capability from the ground up, spanning new training environments that reward collaborative thinking, representations for shared human-AI mental models, and evaluation centred on trust and complementarity. These directions can advance MAS research toward agents that think with their human partners rather than for them. + oai:arXiv.org:2512.07801v2 + cs.CL cs.AI - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by-nc-sa/4.0/ - S. Alex Yang, Angela Huyue Zhang - - - Self-supervised Learning-based Reconstruction of High-resolution 4D Light Fields - https://arxiv.org/abs/2402.19020 - arXiv:2402.19020v2 Announce Type: replace-cross -Abstract: Hand-held light field (LF) cameras often exhibit low spatial resolution due to the inherent trade-off between spatial and angular dimensions. Existing supervised learning-based LF spatial super-resolution (SR) methods, which rely on pre-defined image degradation models, struggle to overcome the domain gap between the training phase -- where LFs with natural resolution are used as ground truth -- and the inference phase, which aims to reconstruct higher-resolution LFs, especially when applied to real-world data.To address this challenge, this paper introduces a novel self-supervised learning-based method for LF spatial SR, which can produce higher spatial resolution LF images than originally captured ones without pre-defined image degradation models. The self-supervised method incorporates a hybrid LF imaging prototype, a real-world hybrid LF dataset, and a self-supervised LF spatial SR framework. The prototype makes reference image pairs between low-resolution central-view sub-aperture images and high-resolution (HR) images. The self-supervised framework consists of a well-designed LF spatial SR network with hybrid input, a central-view synthesis network with an HR-aware loss that enables side-view sub-aperture images to learn high-frequency information from the only HR central view reference image, and a backward degradation network with an epipolar-plane image gradient loss to preserve LF parallax structures. Extensive experiments on both simulated and real-world datasets demonstrate the significant superiority of our approach over state-of-the-art ones in reconstructing higher spatial resolution LF images without pre-defined degradation. - oai:arXiv.org:2402.19020v2 - eess.IV - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Jianxin Lei, Dongze Wu, Chengcai Xu, Hongcheng Gu, Guangquan Zhou, Junhui Hou, Ping Zhou - - - CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation - https://arxiv.org/abs/2403.17770 - arXiv:2403.17770v2 Announce Type: replace-cross -Abstract: Despite the significant success achieved by deep learning methods in medical image segmentation, researchers still struggle in the computer-aided diagnosis of abdominal lymph nodes due to the complex abdominal environment, small and indistinguishable lesions, and limited annotated data. To address these problems, we present a pipeline that integrates the conditional diffusion model for lymph node generation and the nnU-Net model for lymph node segmentation to improve the segmentation performance of abdominal lymph nodes through synthesizing a diversity of realistic abdominal lymph node data. We propose LN-DDPM, a conditional denoising diffusion probabilistic model (DDPM) for lymph node (LN) generation. LN-DDPM utilizes lymph node masks and anatomical structure masks as model conditions. These conditions work in two conditioning mechanisms: global structure conditioning and local detail conditioning, to distinguish between lymph nodes and their surroundings and better capture lymph node characteristics. The obtained paired abdominal lymph node images and masks are used for the downstream segmentation task. Experimental results on the abdominal lymph node datasets demonstrate that LN-DDPM outperforms other generative methods in the abdominal lymph node image synthesis and better assists the downstream abdominal lymph node segmentation task. - oai:arXiv.org:2403.17770v2 - eess.IV - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yongrui Yu, Hanyu Chen, Zitian Zhang, Qiong Xiao, Wenhui Lei, Linrui Dai, Yu Fu, Hui Tan, Guan Wang, Peng Gao, Xiaofan Zhang - - - Characterization of Priority-Neutral Matching Lattices - https://arxiv.org/abs/2404.02142 - arXiv:2404.02142v2 Announce Type: replace-cross -Abstract: We study the structure of the set of priority-neutral matchings. These matchings, introduced by Reny (AER, 2022), generalize stable matchings by allowing for priority violations in a principled way that enables Pareto-improvements to stable matchings. Known results show that the set of priority-neutral matchings is a lattice, suggesting that these matchings may enjoy the same tractable theoretical structure as stable matchings. - In this paper, we characterize priority-neutral matching lattices, and show that their structure is considerably more intricate than that of stable matching lattices. To begin, we show priority-neutral lattices are not distributive, an important property that characterizes stable lattices and is satisfied by many other lattice structures considered in matching theory and algorithm design. Then, in our main result, we show that priority-neutral lattices are in fact characterized by a more-involved property which we term being a "movement lattice," which allows for significant departures from the order theoretic properties of distributive (and hence stable) lattices. While our results show that priority-neutrality is more intricate than stability, they also establish tractable properties. Indeed, as a corollary of our main result, we obtain the first known polynomial-time algorithm for checking whether a given matching is priority-neutral. - oai:arXiv.org:2404.02142v2 - econ.TH - cs.GT - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Clayton Thomas - - - Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification - https://arxiv.org/abs/2408.00681 - arXiv:2408.00681v2 Announce Type: replace-cross -Abstract: We introduce a novel deep operator network (DeepONet) framework that incorporates generalised variational inference (GVI) using R\'enyi's $\alpha$-divergence to learn complex operators while quantifying uncertainty. By incorporating Bayesian neural networks as the building blocks for the branch and trunk networks, our framework endows DeepONet with uncertainty quantification. The use of R\'enyi's $\alpha$-divergence, instead of the Kullback-Leibler divergence (KLD), commonly used in standard variational inference, mitigates issues related to prior misspecification that are prevalent in Variational Bayesian DeepONets. This approach offers enhanced flexibility and robustness. We demonstrate that modifying the variational objective function yields superior results in terms of minimising the mean squared error and improving the negative log-likelihood on the test set. Our framework's efficacy is validated across various mechanical systems, where it outperforms both deterministic and standard KLD-based VI DeepONets in predictive accuracy and uncertainty quantification. The hyperparameter $\alpha$, which controls the degree of robustness, can be tuned to optimise performance for specific problems. We apply this approach to a range of mechanics problems, including gravity pendulum, advection-diffusion, and diffusion-reaction systems. Our findings underscore the potential of $\alpha$-VI DeepONet to advance the field of data-driven operator learning and its applications in engineering and scientific domains. - oai:arXiv.org:2408.00681v2 - stat.ML + cs.HC cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1016/j.cma.2025.118552 - Computer Methods in Applied Mechanics and Engineering, 449(B), 118552, 2026 - Soban Nasir Lone, Subhayan De, Rajdip Nayek - - - Bounds and Hardness Results for Conflict-free Choosability - https://arxiv.org/abs/2409.12672 - arXiv:2409.12672v3 Announce Type: replace-cross -Abstract: A '(partial) conflict-free coloring' of a hypergraph $\mathcal{H}$ is an assignment of colors to (a subset of) the vertex set of $\mathcal{H}$ such that every hyperedge in $\mathcal{H}$ has a vertex whose color is distinct from every other vertex in that hyperedge. The minimum number of colors required for such a coloring is known as the '(partial) conflict-free chromatic number' of $\mathcal{H}$. It is easy to see that the conflict-free chromatic number of a hypergraph is at most its partial conflict-free chromatic number plus one. Conflict-free coloring has also been studied on the open/closed neighborhood hypergraphs of a given graph under the name open/closed neighborhood conflict-free coloring. In this paper, we study partial and full list variants of conflict-free coloring where, for every vertex $v$, we are given a list of admissible colors $L_v$ such that $v$ is allowed to be colored only from $L_v$. - Bhyravarapu, Kalyanasundaram, and Mathew [Journal of Graph Theory, 2021] showed that the closed-neighborhood conflict-free chromatic number of any graph $G$ with maximum degree $\Delta$ is at most $O(\ln^2 \Delta)$. In this paper, we extend the $O(\ln^2 \Delta)$ upper bound to the partial list variant of the closed-neighborhood conflict-free chromatic number. Further, we establish computational complexity results concerning the list open/closed-neighborhood conflict-free chromatic numbers. - oai:arXiv.org:2409.12672v3 - math.CO - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Shiwali Gupta, Rogers Mathew - - - Compressing multivariate functions with tree tensor networks - https://arxiv.org/abs/2410.03572 - arXiv:2410.03572v2 Announce Type: replace-cross -Abstract: Tensor networks are a compressed format for multi-dimensional data. One-dimensional tensor networks -- often referred to as tensor trains (TT) or matrix product states (MPS) -- are increasingly being used as a numerical ansatz for continuum functions by ``quantizing'' the inputs into discrete binary digits. Here we demonstrate the power of more general tree tensor networks for this purpose. We provide direct constructions of a number of elementary functions as generic tree tensor networks and interpolative constructions for more complicated functions via a generalization of the tensor cross interpolation algorithm. For a range of multi-dimensional functions we show how more structured tree tensor networks offer a significantly more efficient ansatz than the commonly used tensor train. We demonstrate an application of our methods to solving multi-dimensional, non-linear Fredholm equations, providing a rigorous bound on the rank of the solution which, in turn, guarantees exponentially scaling accuracy with the size of the tree tensor network for certain problems. - oai:arXiv.org:2410.03572v2 - quant-ph - cs.NA - math.NA - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Joseph Tindall, E. Miles Stoudenmire, Ryan Levy + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by/4.0/ + Raunak Jain, Mudita Khurana - Information geometry of bosonic Gaussian thermal states - https://arxiv.org/abs/2411.18268 - arXiv:2411.18268v2 Announce Type: replace-cross -Abstract: Bosonic Gaussian thermal states form a fundamental class of states in quantum information science. This paper explores the information geometry of these states, focusing on characterizing the distance between two nearby states and the geometry induced by a parameterization in terms of their mean vectors and Hamiltonian matrices. In particular, for the family of bosonic Gaussian thermal states, we derive expressions for their Fisher-Bures, Kubo-Mori, and $\alpha$-$z$ information matrices with respect to their mean vectors and Hamiltonian matrices. An important application of our formulas consists of fundamental limits on how well one can estimate these parameters. We additionally establish formulas for the derivatives and the symmetric logarithmic derivatives of bosonic Gaussian thermal states. The former could have applications in gradient descent algorithms for quantum machine learning when using bosonic Gaussian thermal states as an ansatz, and the latter in formulating optimal strategies for single parameter estimation of bosonic Gaussian thermal states. Finally, the expressions for the aforementioned information matrices could have additional applications in natural gradient descent algorithms when using bosonic Gaussian thermal states as an ansatz. - oai:arXiv.org:2411.18268v2 - quant-ph - cs.IT - hep-th - math-ph - math.IT - math.MP - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zixin Huang, Mark M. Wilde + Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach + https://arxiv.org/abs/2512.07814 + arXiv:2512.07814v2 Announce Type: replace +Abstract: Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns due to their reliance on open-source repositories containing abundant personally identifiable information (PII). Prior work shows that commercial models can reproduce sensitive PII, yet existing studies largely treat PII as a single category and overlook the heterogeneous risks among different types. We investigate whether distinct PII types vary in their likelihood of being learned and leaked by LLM4Code, and whether this relationship is causal. Our methodology includes building a dataset with diverse PII types, fine-tuning representative models of different scales, computing training dynamics on real PII data, and formulating a structural causal model to estimate the causal effect of learnability on leakage. Results show that leakage risks differ substantially across PII types and correlate with their training dynamics: easy-to-learn instances such as IP addresses exhibit higher leakage, while harder types such as keys and passwords leak less frequently. Ambiguous types show mixed behaviors. This work provides the first causal evidence that leakage risks are type-dependent and offers guidance for developing type-aware and learnability-aware defenses for LLM4Code. + oai:arXiv.org:2512.07814v2 + cs.SE + cs.AI + cs.CR + Wed, 10 Dec 2025 00:00:00 -0500 + replace + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Hua Yang, Alejandro Velasco, Sen Fang, Bowen Xu, Denys Poshyvanyk - Machine Learning Neutrino-Nucleus Cross Sections - https://arxiv.org/abs/2412.16303 - arXiv:2412.16303v3 Announce Type: replace-cross -Abstract: Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section -- leveraging only Standard-Model symmetries -- can be learned from near-detector data. We perform a neutrino oscillation analysis with simulated far-detector events, finding that oscillation analysis results enabled by our data-driven cross-section model approach the theoretical limit achievable with perfect prior knowledge of the cross section. We further quantify the effects of flux shape and detector resolution uncertainties as well as systematics from cross-section mismodeling. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models. - oai:arXiv.org:2412.16303v3 - hep-ph + Astral Space: Convex Analysis at Infinity + https://arxiv.org/abs/2205.03260 + arXiv:2205.03260v4 Announce Type: replace-cross +Abstract: Not all convex functions on $\mathbb{R}^n$ have finite minimizers; some can only be minimized by a sequence as it heads to infinity. In this work, we aim to develop a theory for understanding such minimizers at infinity. We study astral space, a compact extension of $\mathbb{R}^n$ to which such points at infinity have been added. Astral space is constructed to be as small as possible while still ensuring that all linear functions can be continuously extended to the new space. Although astral space includes all of $\mathbb{R}^n$, it is not a vector space, nor even a metric space. However, it is sufficiently well-structured to allow useful and meaningful extensions of concepts of convexity, conjugacy, and subdifferentials. We develop these concepts and analyze various properties of convex functions on astral space, including the detailed structure of their minimizers, exact characterizations of continuity, and convergence of descent algorithms. + oai:arXiv.org:2205.03260v4 + math.OC cs.LG - hep-ex - nucl-th - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Daniel C. Hackett, Joshua Isaacson, Shirley Weishi Li, Karla Tame-Narvaez, Michael L. Wagman + Miroslav Dud\'ik, Robert E. Schapire, Matus Telgarsky - How to explain grokking - https://arxiv.org/abs/2412.18624 - arXiv:2412.18624v4 Announce Type: replace-cross -Abstract: Explanation of grokking (delayed generalization) in learning is given by modeling grokking by the stochastic gradient Langevin dynamics (Brownian motion) and applying the ideas of thermodynamics. - oai:arXiv.org:2412.18624v4 - cond-mat.stat-mech + BeeTLe: An Imbalance-Aware Deep Sequence Model for Linear B-Cell Epitope Prediction and Classification with Logit-Adjusted Losses + https://arxiv.org/abs/2309.02071 + arXiv:2309.02071v2 Announce Type: replace-cross +Abstract: The process of identifying and characterizing B-cell epitopes, which are the portions of antigens recognized by antibodies, is important for our understanding of the immune system, and for many applications including vaccine development, therapeutics, and diagnostics. Computational epitope prediction is challenging yet rewarding as it significantly reduces the time and cost of laboratory work. Most of the existing tools do not have satisfactory performance and only discriminate epitopes from non-epitopes. This paper presents a new deep learning-based multi-task framework for linear B-cell epitope prediction as well as antibody type-specific epitope classification. Specifically, a sequenced-based neural network model using recurrent layers and Transformer blocks is developed. We propose an amino acid encoding method based on eigen decomposition to help the model learn the representations of epitopes. We introduce modifications to standard cross-entropy loss functions by extending a logit adjustment technique to cope with the class imbalance. Experimental results on data curated from the largest public epitope database demonstrate the validity of the proposed methods and the superior performance compared to competing ones. + oai:arXiv.org:2309.02071v2 + q-bio.QM cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - S. V. Kozyrev + 10.1007/978-3-031-43427-3_29 + Xiao Yuan - A Particle Algorithm for Mean-Field Variational Inference - https://arxiv.org/abs/2412.20385 - arXiv:2412.20385v3 Announce Type: replace-cross -Abstract: Variational inference is a fast and scalable alternative to Markov chain Monte Carlo and has been widely applied to posterior inference tasks in statistics and machine learning. A traditional approach for implementing mean-field variational inference (MFVI) is coordinate ascent variational inference (CAVI), which relies crucially on parametric assumptions on complete conditionals. We introduce a novel particle-based algorithm for MFVI, named PArticle VI (PAVI), for nonparametric mean-field approximation. We obtain non-asymptotic error bounds for our algorithm. To our knowledge, this is the first end-to-end guarantee for particle-based MFVI. - oai:arXiv.org:2412.20385v3 - math.ST - cs.LG + A kernel-based method for Schr\"odinger bridges + https://arxiv.org/abs/2310.14522 + arXiv:2310.14522v5 Announce Type: replace-cross +Abstract: We characterize the Schr\"odinger bridge problems by a family of Mckean-Vlasov stochastic control problems with no terminal time distribution constraint. In doing so, we use the theory of Hilbert space embeddings of probability measures and then describe the constraint as penalty terms defined by the maximum mean discrepancy in the control problems. A sequence of the probability laws of the state processes resulting from $\epsilon$-optimal controls converges to a unique solution of the Schr\"odinger's problem under mild conditions on given initial and terminal time distributions and an underlying diffusion process. We propose a neural SDE based deep learning algorithm for the Mckean-Vlasov stochastic control problems. Several numerical experiments validate our methods. + oai:arXiv.org:2310.14522v5 math.OC - stat.ML - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Qiang Du, Kaizheng Wang, Edith Zhang, Chenyang Zhong + Yumiharu Nakano - A Methodology for Process Design Kit Re-Centering Using TCAD and Experimental Data for Cryogenic Temperatures - https://arxiv.org/abs/2502.02685 - arXiv:2502.02685v2 Announce Type: replace-cross -Abstract: In this work, we describe and demonstrate a novel Technology Computer Aided Design (TCAD) driven methodology to re-center room-temperature Process Design Kits (PDKs) for cryogenic operation using a limited set of experimental measurements. Unlike previous approaches that relied on direct fitting of sparse measurements, our technique accounts for process-induced deviations by calibrating TCAD models to both room-temperature and cryogenic data. Compact models for all process corners are extracted from TCAD-generated target characteristics, enabling accurate cryogenic modeling without dedicated foundry support. This scalable, technology-independent method provides a practical path for cryogenic circuit design. - oai:arXiv.org:2502.02685v2 - physics.app-ph - cond-mat.mes-hall - cs.SY - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Deep generative modelling of canonical ensemble with differentiable thermal properties + https://arxiv.org/abs/2404.18404 + arXiv:2404.18404v2 Announce Type: replace-cross +Abstract: It is a long-standing challenge to accurately and efficiently compute thermodynamic quantities of many-body systems at thermal equilibrium. The conventional methods, e.g., Markov chain Monte Carlo, require many steps to equilibrate. The recently developed deep learning methods can perform direct sampling, but only work at a single trained temperature point and risk biased sampling. Here, we propose a variational method for canonical ensembles with differentiable temperature, which gives thermodynamic quantities as continuous functions of temperature akin to an analytical solution. The proposed method is a general framework that works with any tractable density generative model. At optimal, the model is theoretically guaranteed to be the unbiased Boltzmann distribution. We validated our method by calculating phase transitions in the Ising and XY models, demonstrating that our direct-sampling simulations are as accurate as Markov chain Monte Carlo, but more efficient. Moreover, our differentiable free energy aligns closely with the exact one to the second-order derivative, indicating that the variational model captures the subtle thermal transitions at the phase transitions. This functional dependence on external parameters is a fundamental advancement in combining the exceptional fitting ability of deep learning with rigorous physical analysis. + oai:arXiv.org:2404.18404v2 + cond-mat.stat-mech + cs.LG + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tapas Dutta, Fikru Adamu-Lema, Djamel Bensouiah, Asen Asenov + 10.1103/8wx7-kyx8 + Phys. Rev. Lett. 135, 027301 (2025) + Shuo-Hui Li, Yao-Wen Zhang, Ding Pan - DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation - https://arxiv.org/abs/2502.03930 - arXiv:2502.03930v4 Announce Type: replace-cross -Abstract: Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes. In this work, we propose Diffusion Transformer Autoregressive Modeling (DiTAR), a patch-based autoregressive framework combining a language model with a diffusion transformer. This approach significantly enhances the efficacy of autoregressive models for continuous tokens and reduces computational demands. DiTAR utilizes a divide-and-conquer strategy for patch generation, where the language model processes aggregated patch embeddings and the diffusion transformer subsequently generates the next patch based on the output of the language model. For inference, we propose defining temperature as the time point of introducing noise during the reverse diffusion ODE to balance diversity and determinism. We also show in the extensive scaling analysis that DiTAR has superb scalability. In zero-shot speech generation, DiTAR achieves state-of-the-art performance in robustness, speaker similarity, and naturalness. - oai:arXiv.org:2502.03930v4 - eess.AS - cs.AI - cs.CL - cs.LG - cs.SD - Tue, 09 Dec 2025 00:00:00 -0500 + Explosive neural networks via higher-order interactions in curved statistical manifolds + https://arxiv.org/abs/2408.02326 + arXiv:2408.02326v3 Announce Type: replace-cross +Abstract: Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the scarcity of tractable models. By leveraging a generalisation of the maximum entropy principle, we introduce curved neural networks as a class of models with a limited number of parameters that are particularly well-suited for studying higher-order phenomena. Through exact mean-field descriptions, we show that these curved neural networks implement a self-regulating annealing process that can accelerate memory retrieval, leading to explosive order-disorder phase transitions with multi-stability and hysteresis effects. Moreover, by analytically exploring their memory-retrieval capacity using the replica trick, we demonstrate that these networks can enhance memory capacity and robustness of retrieval over classical associative-memory networks. Overall, the proposed framework provides parsimonious models amenable to analytical study, revealing higher-order phenomena in complex networks. + oai:arXiv.org:2408.02326v3 + cond-mat.dis-nn + cond-mat.stat-mech + cs.IT + math.IT + nlin.AO + stat.ML + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Dongya Jia, Zhuo Chen, Jiawei Chen, Chenpeng Du, Jian Wu, Jian Cong, Xiaobin Zhuang, Chumin Li, Zhen Wei, Yuping Wang, Yuxuan Wang + 10.1038/s41467-025-61475-w + Aguilera, M., Morales, P.A., Rosas, F.E. et al. Explosive neural networks via higher-order interactions in curved statistical manifolds. Nature Communications 16, 6511 (2025) + Miguel Aguilera, Pablo A. Morales, Fernando E. Rosas, Hideaki Shimazaki - Graceful forgetting: Memory as a process - https://arxiv.org/abs/2502.11105 - arXiv:2502.11105v4 Announce Type: replace-cross -Abstract: A rational framework is proposed to explain how we accommodate unbounded sensory input within bounded memory. Memory is stored as statistics organized into structures that are repeatedly summarized and compressed to make room for new input. Repeated summarization requires an intensive ongoing process guided by heuristics that help optimize the memory for future needs. Sensory input is rapidly encoded as simple statistics that are progressively elaborated into more abstract constructs. This framework differs from previous accounts of memory by reliance on statistics as a representation of memory, the use of heuristics to guide the choice of statistics at each summarization step, and the hypothesis of a process that is complex and expensive. The framework is intended as an aid to make sense of our extensive knowledge of memory, and bring us closer to an understanding of memory in functional and mechanistic terms. - oai:arXiv.org:2502.11105v4 - q-bio.NC - cs.IR + Survey of Data-driven Newsvendor: Unified Analysis and Spectrum of Achievable Regrets + https://arxiv.org/abs/2409.03505 + arXiv:2409.03505v4 Announce Type: replace-cross +Abstract: In the Newsvendor problem, the goal is to guess the number that will be drawn from some distribution, with asymmetric consequences for guessing too high vs. too low. In the data-driven version, the distribution is unknown, and one must work with samples from the distribution. Data-driven Newsvendor has been studied under many variants: additive vs. multiplicative regret, high probability vs. expectation bounds, and different distribution classes. This paper studies all combinations of these variants, filling in many gaps in the literature and simplifying many proofs. In particular, we provide a unified analysis based on the notion of clustered distributions, which in conjunction with our new lower bounds, shows that the entire spectrum of regrets between $1/\sqrt{n}$ and $1/n$ can be possible. Simulations on commonly-used distributions demonstrate that our notion is the "correct" predictor of empirical regret across varying data sizes. + oai:arXiv.org:2409.03505v4 + stat.ML cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alain de Cheveign\'e + http://creativecommons.org/licenses/by/4.0/ + Zhuoxin Chen, Will Ma - T1-PILOT: Optimized Trajectories for T1 Mapping Acceleration - https://arxiv.org/abs/2502.20333 - arXiv:2502.20333v2 Announce Type: replace-cross -Abstract: Cardiac T1 mapping provides critical quantitative insights into myocardial tissue composition, enabling the assessment of pathologies such as fibrosis, inflammation, and edema. However, the inherently dynamic nature of the heart imposes strict limits on acquisition times, making high-resolution T1 mapping a persistent challenge. Compressed sensing (CS) approaches have reduced scan durations by undersampling k-space and reconstructing images from partial data, and recent studies show that jointly optimizing the undersampling patterns with the reconstruction network can substantially improve performance. Still, most current T1 mapping pipelines rely on static, hand-crafted masks that do not exploit the full acceleration and accuracy potential. In this work, we introduce T1-PILOT: an end-to-end method that explicitly incorporates the T1 signal relaxation model into the sampling-reconstruction framework to guide the learning of non-Cartesian trajectories, crossframe alignment, and T1 decay estimation. Through extensive experiments on the CMRxRecon dataset, T1-PILOT significantly outperforms several baseline strategies (including learned single-mask and fixed radial or golden-angle sampling schemes), achieving higher T1 map fidelity at greater acceleration factors. In particular, we observe consistent gains in PSNR and VIF relative to existing methods, along with marked improvements in delineating finer myocardial structures. Our results highlight that optimizing sampling trajectories in tandem with the physical relaxation model leads to both enhanced quantitative accuracy and reduced acquisition times. - oai:arXiv.org:2502.20333v2 - eess.IV - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Asymptotic stability equals exponential stability -- while you twist your eyes + https://arxiv.org/abs/2411.03277 + arXiv:2411.03277v3 Announce Type: replace-cross +Abstract: Suppose that two vector fields on a smooth manifold render some equilibrium point globally asymptotically stable (GAS). We show that there exists a homotopy between the corresponding semiflows such that this point remains GAS along this homotopy. + oai:arXiv.org:2411.03277v3 + math.DS + cs.SY + eess.SY + math.OC + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Tamir Shor, Moti Freiman, Chaim Baskin, Alex Bronstein + Wouter Jongeneel - Thermodynamic bounds on energy use in quasi-static Deep Neural Networks - https://arxiv.org/abs/2503.09980 - arXiv:2503.09980v3 Announce Type: replace-cross -Abstract: The rapid growth of deep neural networks (DNNs) has brought increasing attention to their energy use during training and inference. Here, we establish the thermodynamic bounds on energy consumption in quasi-static analog DNNs by mapping modern feedforward architectures onto a physical free-energy functional. This framework provides a direct statistical-mechanical interpretation of quasi-static DNNs. As a result, inference can proceed in a thermodynamically reversible manner, with vanishing minimal energy cost, in contrast to the Landauer limit that constrains digital hardware. Importantly, inference corresponds to relaxation to a unique free-energy minimum with F_{\min}=0, allowing all constraints to be satisfied without residual stress. By comparison, training overconstrains the system: simultaneous clamping of inputs and outputs generates stresses that propagate backward through the architecture, reproducing the rules of backpropagation. Parameter annealing then relaxes these stresses, providing a purely physical route to learning without an explicit loss function. We further derive a universal lower bound on training energy, E< 2NDkT, which scales with both the number of trainable parameters and the dataset size. - oai:arXiv.org:2503.09980v3 - cond-mat.stat-mech + Enhancing Brain Age Estimation with a Multimodal 3D CNN Approach Combining Structural MRI and AI-Synthesized Cerebral Blood Volume Measures + https://arxiv.org/abs/2412.01865 + arXiv:2412.01865v4 Announce Type: replace-cross +Abstract: Brain age gap estimation (BrainAGE) is a promising imaging-derived biomarker of neurobiological aging and disease risk, yet current approaches rely predominantly on T1-weighted structural MRI (T1w), overlooking functional vascular changes that may precede tissue damage and cognitive decline. Artificial intelligence-generated cerebral blood volume (AICBV) maps, synthesized from non-contrast MRI, offer an alternative to contrast-enhanced perfusion imaging by capturing vascular information relevant to early neurodegeneration. We developed a multimodal BrainAGE framework that integrates brain age predictions using linear regression from two separate 3D VGG-based networks, one model trained on only structural T1w scans and one trained on only AICBV maps generated from a pre-trained 3D patch-based deep learning model. Each model was trained and validated on 2,851 scans from 13 open-source datasets and was evaluated for concordance with mild cognitive impairment (MCI) and Alzheimer's disease (AD) using ADNI subjects (n=1,233). The combined model achieved the most accurate brain age gap for cognitively normal (CN) controls, with a mean absolute error (MAE) of 3.95 years ($R^2$=0.943), outperforming models trained on T1w (MAE=4.10) or AICBV alone (MAE=4.49). Saliency maps revealed complementary modality contributions: T1w emphasized white matter and cortical atrophy, while AICBV highlighted vascular-rich and periventricular regions implicated in hypoperfusion and early cerebrovascular dysfunction, consistent with normal aging. Next, we observed that BrainAGE increased stepwise across diagnostic strata (CN < MCI < AD) and correlated with cognitive impairment (CDRSB r=0.403; MMSE r=-0.310). AICBV-based BrainAGE showed particularly strong separation between stable vs. progressive MCI (p=$1.47 \times 10^{-8}$), suggesting sensitivity to prodromal vascular changes that precede overt atrophy. + oai:arXiv.org:2412.01865v4 + eess.IV cs.LG - physics.data-an - q-bio.NC - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Alexei V. Tkachenko + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Jordan Jomsky (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Kay C. Igwe (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Zongyu Li (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Yiren Zhang (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Max Lashley (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Tal Nuriel (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Andrew Laine (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative), Jia Guo (for the Frontotemporal Lobar Degeneration Neuroimaging Initiative,for the Alzheimer's Disease Neuroimaging Initiative) - Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation - https://arxiv.org/abs/2503.17543 - arXiv:2503.17543v2 Announce Type: replace-cross -Abstract: Left ventricular ejection fraction (LVEF) is a key indicator of cardiac function and is routinely used to diagnose heart failure and guide treatment decisions. Although deep learning has advanced automated LVEF estimation, many existing approaches are computationally demanding and underutilize the joint structure of spatial and temporal information in echocardiography videos, limiting their suitability for real-time clinical deployment. We propose Echo-E$^3$Net, an efficient endocardial spatio-temporal network specifically designed for LVEF estimation from echocardiography videos. Echo-E$^3$Net comprises two complementary modules: (1) a dual-phase Endocardial Border Detector (E$^2$CBD), which uses phase-specific cross-attention to predict ED/ES endocardial landmarks (EBs) and learn phase-aware landmark embeddings (LEs), and (2) an Endocardial Feature Aggregator (E$^2$FA), which fuses these embeddings with global statistical descriptors (mean, maximum, variance) of deep feature maps to refine EF regression. A multi-component loss function, inspired by Simpson's biplane method, jointly supervises EF, volumes, and landmark geometry, thereby aligning optimization with the clinical definition of LVEF and promoting robust spatio-temporal representation learning. Evaluated on the EchoNet-Dynamic dataset, Echo-E$^3$Net achieves an RMSE of 5.20 and an $R^2$ score of 0.82, while using only 1.54M parameters and 8.05 GFLOPs. The model operates without external pre-training, heavy data augmentation, or test-time ensembling, making it highly suitable for real-time point-of-care ultrasound (POCUS) applications. Code is available at https://github.com/UltrAi-lab/Echo-E3Net. - oai:arXiv.org:2503.17543v2 - eess.IV - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis - A Case Study for the Semiconductor Sector + https://arxiv.org/abs/2412.08179 + arXiv:2412.08179v3 Announce Type: replace-cross +Abstract: Financial analysis relies heavily on the interpretation of earnings reports to assess company performance and guide decision-making. Traditional methods for generating such analyzes require significant financial expertise and are often time-consuming. With the rapid advancement of Large Language Models (LLMs), domain-specific adaptations have emerged for financial tasks such as sentiment analysis and entity recognition. This paper introduces RAG-IT (Retrieval-Augmented Instruction Tuning), a novel framework designed to automate the generation of earnings report analysis through an LLM fine-tuned specifically for the financial domain. Our approach integrates retrieval augmentation with instruction-based fine-tuning to enhance factual accuracy, contextual relevance, and domain adaptability. We construct a sector-specific financial instruction dataset derived from semiconductor industry documents to guide the LLM adaptation to specialized financial reasoning. Using NVIDIA, AMD, and Broadcom as representative companies, our case study demonstrates that RAG-IT substantially improves a general-purpose open-source LLM and achieves performance comparable to commercial systems like GPT-3.5 on financial report generation tasks. This research highlights the potential of retrieval-augmented instruction tuning to streamline and elevate financial analysis automation, advancing the broader field of intelligent financial reporting. + oai:arXiv.org:2412.08179v3 + q-fin.ST + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Moein Heidari, Afshin Bozorgpour, AmirHossein Zarif-Fakharnia, Wenjin Chen, Dorit Merhof, David J Foran, Jasmine Grewal, Ilker Hacihaliloglu + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Hai-Thien To, Tien-Cuong Bui, Van-Duc Le - Set families: restricted distances via restricted intersections - https://arxiv.org/abs/2504.12296 - arXiv:2504.12296v3 Announce Type: replace-cross -Abstract: Denote by $f_D(n)$ the maximum size of a set family $\mathcal{F}$ on $[n] \stackrel{\mbox{\normalfont\tiny def}}{=} \{1, \dots, n\}$ with distance set $D$. That is, $|A \bigtriangleup B| \in D$ holds for every pair of distinct sets $A, B \in \mathcal{F}$. Kleitman's celebrated discrete isodiametric inequality states that $f_D(n)$ is maximized at Hamming balls of radius $d/2$ when $D = \{1, \dots, d\}$. We study the generalization where $D$ is a set of arithmetic progression and determine $f_D(n)$ asymptotically for all homogeneous $D$. In the special case when $D$ is an interval, our result confirms a conjecture of Huang, Klurman, and Pohoata. Moreover, we demonstrate a dichotomy in the growth of $f_D(n)$, showing linear growth in $n$ when $D$ is a non-homogeneous arithmetic progression. Different from previous combinatorial and spectral approaches, we deduce our results by converting the restricted distance problems to restricted intersection problems. - Our proof ideas can be adapted to prove upper bounds on $t$-distance sets in Hamming cubes (also known as binary $t$-codes), which has been extensively studied by algebraic combinatorialists community, improving previous bounds from polynomial methods and optimization approaches. - oai:arXiv.org:2504.12296v3 + Rainbow Arborescence Conjecture + https://arxiv.org/abs/2412.15457 + arXiv:2412.15457v2 Announce Type: replace-cross +Abstract: The famous Ryser--Brualdi--Stein conjecture asserts that every $k \times k$ Latin square contains a partial transversal of size $k-1$. Since its appearance, the conjecture has attracted significant interest, leading to several proposed generalizations. One of the most notable of these, by Aharoni, Kotlar, and Ziv, conjectures that $k$ disjoint common bases of two matroids of rank $k$ have a common independent partial transversal of size $k-1$. Although simple counterexamples show that the size $k-1$ above cannot be improved to $k$ (i.e., a transversal instead of a partial transversal), it is remarkable that no such counterexample is known for the special case of spanning arborescences. This motivated the formulation of the Rainbow Arborescence Conjecture: any graph on $n$ vertices formed by the union of $n-1$ spanning arborescences contains an arborescence using exactly one arc from each. + We prove several partial results on this conjecture. We show that the computational problem of testing the existence of such an arborescence with a fixed root is NP-complete, verify the conjecture in several special cases, and study relaxations of the problem. In particular, we establish the validity of the conjecture when the underlying undirected graph is a cycle; this also yields a new result on systems of distinct representatives for intervals on a cycle. + oai:arXiv.org:2412.15457v2 math.CO cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zichao Dong, Jun Gao, Hong Liu, Minghui Ouyang, Qiang Zhou + http://creativecommons.org/licenses/by/4.0/ + Krist\'of B\'erczi, Tam\'as Kir\'aly, Yutaro Yamaguchi, Yu Yokoi - Learning Enhanced Ensemble Filters - https://arxiv.org/abs/2504.17836 - arXiv:2504.17836v3 Announce Type: replace-cross -Abstract: The filtering distribution in hidden Markov models evolves according to the law of a mean-field model in state-observation space. The ensemble Kalman filter (EnKF) approximates this mean-field model with an ensemble of interacting particles, employing a Gaussian ansatz for the joint distribution of the state and observation at each observation time. These methods are robust, but the Gaussian ansatz limits accuracy. Here this shortcoming is addressed by using machine learning to map the joint predicted state and observation to the updated state estimate. The derivation of methods from a mean field formulation of the true filtering distribution suggests a single parametrization of the algorithm that can be deployed at different ensemble sizes. And we use a mean field formulation of the ensemble Kalman filter as an inductive bias for our architecture. - To develop this perspective, in which the mean-field limit of the algorithm and finite interacting ensemble particle approximations share a common set of parameters, a novel form of neural operator is introduced, taking probability distributions as input: a measure neural mapping (MNM). A MNM is used to design a novel approach to filtering, the MNM-enhanced ensemble filter (MNMEF), which is defined in both the mean-field limit and for interacting ensemble particle approximations. The ensemble approach uses empirical measures as input to the MNM and is implemented using the set transformer, which is invariant to ensemble permutation and allows for different ensemble sizes. In practice fine-tuning of a small number of parameters, for specific ensemble sizes, further enhances the accuracy of the scheme. The promise of the approach is demonstrated by its superior root-mean-square-error performance relative to leading methods in filtering the Lorenz '96 and Kuramoto-Sivashinsky models. - oai:arXiv.org:2504.17836v3 - stat.ML + AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery + https://arxiv.org/abs/2501.06039 + arXiv:2501.06039v2 Announce Type: replace-cross +Abstract: Spatial proteomics technologies have transformed our understanding of complex tissue architecture in cancer but present unique challenges for computational analysis. Each study uses a different marker panel and protocol, and most methods are tailored to single cohorts, which limits knowledge transfer and robust biomarker discovery. Here we present Virtual Tissues (VirTues), a general-purpose foundation model for spatial proteomics that learns marker-aware, multi-scale representations of proteins, cells, niches and tissues directly from multiplex imaging data. From a single pretrained backbone, VirTues supports marker reconstruction, cell typing and niche annotation, spatial biomarker discovery, and patient stratification, including zero-shot annotation across heterogeneous panels and datasets. In triple-negative breast cancer, VirTues-derived biomarkers predict anti-PD-L1 chemo-immunotherapy response and stratify disease-free survival in an independent cohort, outperforming state-of-the-art biomarkers derived from the same datasets and current clinical stratification schemes. + oai:arXiv.org:2501.06039v2 + q-bio.QM + cs.AI + cs.CV cs.LG - cs.SY - eess.SY - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by-nc-nd/4.0/ - Eviatar Bach, Ricardo Baptista, Edoardo Calvello, Bohan Chen, Andrew Stuart + Johann Wenckstern, Eeshaan Jain, Yexiang Cheng, Benedikt von Querfurth, Kiril Vasilev, Matteo Pariset, Phil F. Cheng, Petros Liakopoulos, Olivier Michielin, Andreas Wicki, Gabriele Gut, Charlotte Bunne - Constrained Parameter Update Law for Adaptive Control - https://arxiv.org/abs/2504.19412 - arXiv:2504.19412v2 Announce Type: replace-cross -Abstract: In this paper, a constrained parameter update law is derived in the context of adaptive control. The parameter update law is based on constrained optimization technique where a Lagrangian is formulated to incorporate the constraints on the parameters using inverse Barrier function. The constrained parameter update law is used to develop a adaptive tracking controller and the overall stability of the adaptive controller along with the constrained parameter update law is shown using Lyapunov analysis and development in stability of constrained primal-dual dynamics. The performance of the constrained parameter update law is tested in simulation for keeping the parameters within constraints and convergence to true parameters. - oai:arXiv.org:2504.19412v2 - math.OC - cs.SY - eess.SP - eess.SY - Tue, 09 Dec 2025 00:00:00 -0500 + Reconstruction of frequency-localized functions from pointwise samples via least squares and deep learning + https://arxiv.org/abs/2502.09794 + arXiv:2502.09794v2 Announce Type: replace-cross +Abstract: Recovering frequency-localized functions from pointwise data is a fundamental task in signal processing. We examine this problem from an approximation-theoretic perspective, focusing on least squares and deep learning-based methods. First, we establish a novel recovery theorem for least squares approximations using the Slepian basis from uniform random samples in low dimensions, explicitly tracking the dependence of the bandwidth on the sampling complexity. Building on these results, we then present a recovery guarantee for approximating bandlimited functions via deep learning from pointwise data. This result, framed as a practical existence theorem, provides conditions on the network architecture, training procedure, and data acquisition sufficient for accurate approximation. To complement our theoretical findings, we perform numerical comparisons between least squares and deep learning for approximating one- and two-dimensional functions. We conclude with a discussion of the theoretical limitations and the practical gaps between theory and implementation. + oai:arXiv.org:2502.09794v2 + math.CA + cs.LG + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Ashwin P. Dani + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + A. Martina Neuman, Andres Felipe Lerma Pineda, Jason J. Bramburger, Simone Brugiapaglia - Generative Machine Learning for Multivariate Angular Simulation - https://arxiv.org/abs/2504.21505 - arXiv:2504.21505v2 Announce Type: replace-cross -Abstract: With the recent development of new geometric and angular-radial frameworks for multivariate extremes, reliably simulating from angular variables in moderate-to-high dimensions is of increasing importance. Empirical approaches have the benefit of simplicity, and work reasonably well in low dimensions, but as the number of variables increases, they can lack the required flexibility and scalability. Classical parametric models for angular variables, such as the von Mises--Fisher distribution (vMF), provide an alternative. Exploiting finite mixtures of vMF distributions increases their flexibility, but there are cases where, without letting the number of mixture components grow considerably, a mixture model with a fixed number of components is not sufficient to capture the intricate features that can arise in data. Owing to their flexibility, generative deep learning methods are able to capture complex data structures; they therefore have the potential to be useful in the simulation of multivariate angular variables. In this paper, we introduce a range of deep learning approaches for this task, including generative adversarial networks, normalizing flows and flow matching. We assess their performance via a range of metrics, and make comparisons to the more classical approach of using a finite mixture of vMF distributions. The methods are also applied to a metocean data set, with diagnostics indicating strong performance, demonstrating the applicability of such techniques to real-world, complex data structures. - oai:arXiv.org:2504.21505v2 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + BGG Sequences -- A Riemannian perspective + https://arxiv.org/abs/2502.17016 + arXiv:2502.17016v2 Announce Type: replace-cross +Abstract: BGG resolutions and generalized BGG resolutions from representation theory of semisimple Lie algebras have been generalized to sequences of invariant differential operators on manifolds endowed with a geometric structure belonging to the family of parabolic geometries. Two of these structures, conformal structures and projective structures, occur as weakenings of a Riemannian metric respectively of a specified torsion-free connection on the tangent bundle. In particular, one obtains BGG sequences on open subsets of $\mathbb R^n$ as very special cases of the construction. It turned out that several examples of the latter sequences are of interest in applied mathematics, since they can be used to construct numerical methods to study operators relevant for elasticity theory, numerical relativity and related fields. + This article is intended to provide an intermediate level between BGG sequences for parabolic geometries and the case of domains in $\mathbb R^n$. We provide a construction of conformal BGG sequences on Riemannian manifolds and of projective BGG sequences on manifolds endowed with a volume preserving linear connection on their tangent bundle. These constructions do not need any input from parabolic geometries. Except from standard differential geometry methods the only deeper input comes from representation theory. So one can either view the results as a simplified version of the constructions for parabolic geometries in an explicit form. Alternatively, one can view them as providing an extension of the simplified constructions for domains in $\Bbb R^n$ to general Riemannian manifolds or to manifolds endowed with an appropriate connection on the tangent bundle. + oai:arXiv.org:2502.17016v2 + math.DG + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Jakob Benjamin Wessel, Callum J. R. Murphy-Barltrop, Emma S. Simpson + Andreas Cap - Parameter estimation for land-surface models using Neural Physics - https://arxiv.org/abs/2505.02979 - arXiv:2505.02979v2 Announce Type: replace-cross -Abstract: The Neural Physics approach is used to determine the parameters of a simple land-surface model using PyTorch's backpropagation engine to carry out the optimisation. In order to test the inverse model, a synthetic dataset is created by running the model in forward mode with known parameter values to create soil temperature time series that can be used as observations for the inverse model. We show that it is not possible to obtain a reliable parameter estimation using a time series of soil temperature observed at a single depth. Using measurements at two depths, reliable parameter estimates can be obtained although it is not possible to differentiate between latent and sensible heat fluxes. We apply the inverse model to urban flux tower data in Phoenix, United States, and show that the thermal conductivity, volumetric heat capacity and the combined sensible-latent heat transfer coefficient can be reliably estimated using an observed value for the effective surface albedo. The resulting model accurately predicts the outgoing longwave radiation, conductive soil fluxes and the combined sensible-latent heat fluxes. - oai:arXiv.org:2505.02979v2 - physics.ao-ph + Optimal Trickle-Down Theorems for Path Complexes via C-Lorentzian Polynomials with Applications to Sampling and Log-Concave Sequences + https://arxiv.org/abs/2503.01005 + arXiv:2503.01005v3 Announce Type: replace-cross +Abstract: Let $X$ be a $d$-partite $d$-dimensional simplicial complex with parts $T_1,\dots,T_d$ and let $\mu$ be a distribution on the facets of $X$. Informally, we say $(X,\mu)$ is a path complex if for any $i<j<k$ and $F \in T_i,G \in T_j, K\in T_k$, we have $\mathbb{P}_\mu[F,K | G]=\mathbb{P}_\mu[F|G]\cdot\mathbb{P}_\mu[K|G].$ We develop a new machinery with $\mathcal{C}$-Lorentzian polynomials to show that if all links of $X$ of co-dimension 2 have spectral expansion at most $1/2$, then $X$ is a $1/2$-local spectral expander. We then prove that one can derive fast-mixing results and log-concavity statements for top-link spectral expanders. + We use our machinery to prove fast mixing results for sampling maximal flags of flats of distributive lattices (a.k.a. linear extensions of posets) subject to external fields, and to sample maximal flags of flats of "typical" modular lattices. We also use it to re-prove the Heron-Rota-Welsh conjecture and to prove a conjecture of Chan and Pak which gives a generalization of Stanley's log-concavity theorem. Lastly, we use it to prove near optimal trickle-down theorems for "sparse complexes" such as constructions by Lubotzky-Samuels-Vishne, Kaufman-Oppenheim, and O'Donnell-Pratt. + oai:arXiv.org:2503.01005v3 + math.CO + cs.CC + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 + replace-cross + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jonathan Leake, Kasper Lindberg, Shayan Oveis Gharan + + + Median Consensus Embedding for Dimensionality Reduction + https://arxiv.org/abs/2503.08103 + arXiv:2503.08103v2 Announce Type: replace-cross +Abstract: This study proposes median consensus embedding (MCE) to address variability in low-dimensional embeddings caused by random initialization in nonlinear dimensionality reduction techniques such as $t$-distributed stochastic neighbor embedding. MCE is defined as the geometric median of multiple embeddings. By assuming multiple embeddings as independent and identically distributed random samples and applying large deviation theory, we prove that MCE achieves consistency at an exponential rate. Furthermore, we develop a practical algorithm to implement MCE by constructing a distance function between embeddings based on the Frobenius norm of the pairwise distance matrix of data points. Application to actual data demonstrates that MCE converges rapidly and effectively reduces instability. We further combine MCE with multiple imputation to address missing values and consider multiscale hyperparameters. Results confirm that MCE effectively mitigates instability issues in embedding methods arising from random initialization and other sources. + oai:arXiv.org:2503.08103v2 + stat.ML cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Ruiyue Huang, Claire E. Heaney, Maarten van Reeuwijk + Yui Tomo, Daisuke Yoneoka - Quantum Feature Space of a Qubit Coupled to an Arbitrary Bath - https://arxiv.org/abs/2505.03397 - arXiv:2505.03397v4 Announce Type: replace-cross -Abstract: Qubit control protocols have traditionally leveraged a characterisation of the qubit-bath coupling via its power spectral density. Previous work proposed the inference of noise operators that characterise the influence of a classical bath using a grey-box approach that combines deep neural networks with physics-encoded layers. This overall structure is complex and poses challenges in scaling and real-time operations. Here, we show that no expensive neural networks are needed and that this noise operator description admits an efficient parameterisation. We refer to the resulting parameter space as the \textit{quantum feature space} of the qubit dynamics resulting from the coupled bath. We show that the Euclidean distance defined over the quantum feature space provides an effective method for classifying noise processes in the presence of a given set of controls. Using the quantum feature space as the input space for a simple machine learning algorithm (random forest, in this case), we demonstrate that it can effectively classify the stationarity and the broad class of noise processes perturbing a qubit. Finally, we explore how control pulse parameters map to the quantum feature space. - oai:arXiv.org:2505.03397v4 - quant-ph - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + A Graph-based Approach to Variant Extraction from Sequences + https://arxiv.org/abs/2503.18472 + arXiv:2503.18472v2 Announce Type: replace-cross +Abstract: Accurate variant descriptions are of paramount importance in the field of genomics. The domain is confronted with increasingly complex variants, e.g., combinations of multiple indels, making it challenging to generate proper variant descriptions directly from chromosomal sequences. We present a graph based on all minimal alignments that is a complete representation of a variant, which gives insight into the nature of a variant compared to a single variant description. We provide three complementary extraction methods to derive variant descriptions from this graph, including one that yields domain-specific constructs from the HGVS nomenclature. Our experiments show that our methods in comparison with dbSNP, the authoritative variant database from the NCBI, result in identical HGVS descriptions for simple variants and more meaningful descriptions for complex variants, in particular for repeat expansions and contractions. + oai:arXiv.org:2503.18472v2 + q-bio.GN + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Chris Wise, Akram Youssry, Alberto Peruzzo, Jo Plested, Matt Woolley + 10.1093/nargab/lqaf173 + NAR Genomics and Bioinformatics, Volume 7, Issue 4, December 2025 + Mark A. Santcroos, Walter A. Kosters, Mihai Lefter, Jeroen F. J. Laros, Jonathan K. Vis - Quantum RNNs and LSTMs Through Entangling and Disentangling Power of Unitary Transformations - https://arxiv.org/abs/2505.06774 - arXiv:2505.06774v2 Announce Type: replace-cross -Abstract: In this paper, we present a framework for modeling quantum recurrent neural networks (RNNs) and their enhanced version, long short-term memory (LSTM) networks using the core ideas presented by Linden et al. (2009), where the entangling and disentangling power of unitary transformations is investigated. In particular, we interpret entangling and disentangling power as information retention and forgetting mechanisms in LSTMs. Thus, entanglement emerges as a key component of the optimization (training) process. We believe that, by leveraging prior knowledge of the entangling power of unitaries, the proposed quantum-classical framework can guide the design of better-parameterized quantum circuits for various real-world applications. - oai:arXiv.org:2505.06774v2 - quant-ph - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Residual-based Chebyshev filtered subspace iteration for sparse Hermitian eigenvalue problems tolerant to inexact matrix-vector products + https://arxiv.org/abs/2503.22652 + arXiv:2503.22652v4 Announce Type: replace-cross +Abstract: Chebyshev Filtered Subspace Iteration (ChFSI) has emerged as a robust alternative to Krylov eigensolvers for extracting a small subset of extremal eigenpairs from large sparse matrices, particularly in situations where these eigenpairs must be computed repeatedly as the system matrix evolves within an outer iteration. In this work, we propose R-ChFSI, a residual based reformulation of ChFSI designed to exhibit strong convergence properties even when the matrix-vector products are computed inexactly. We derive convergence guarantees under matrix-vector product approximations, providing a rigorous foundation for the method in large-scale eigenvalue computations. The tolerance of R-ChFSI to inexact matrix-vector products enables an efficient treatment of generalized Hermitian definite eigenproblems of the form $\textbf{A} \textbf{x} = \lambda \textbf{B} \textbf{x}$ where exact factorizations or high-accuracy iterative solves for evaluating $\textbf{B}^{-1}$ are often prohibitively expensive. Moreover, R-ChFSI naturally accommodates low-precision arithmetic for both standard and generalized eigenproblems, making it well-suited for modern hardware accelerators optimised for mixed-precision computation. To demonstrate the effectiveness of the approach, extensive numerical experiments are conducted on finite-element discretized eigenproblems with millions of degrees of freedom, solving for thousands of eigenpairs arising in \emph{ab initio} material modelling using Kohn-Sham density functional theory. For generalized eigenproblems employing approximate $\textbf{B}^{-1}$, R-ChFSI achieves desired residual norms orders of magnitude smaller than those obtained with standard ChFSI. In addition, R-ChFSI reliably reaches target residual tolerances (e.g., 10$^{-8}$) even with FP32 and TF32 arithmetic, significantly outperforming standard ChFSI in similar settings. + oai:arXiv.org:2503.22652v4 + physics.comp-ph + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ammar Daskin + http://creativecommons.org/publicdomain/zero/1.0/ + Nikhil Kodali, Kartick Ramakrishnan, Phani Motamarri - Stochastic Orthogonal Regularization for deep projective priors - https://arxiv.org/abs/2505.13078 - arXiv:2505.13078v3 Announce Type: replace-cross -Abstract: Many crucial tasks of image processing and computer vision are formulated as inverse problems. Thus, it is of great importance to design fast and robust algorithms to solve these problems. In this paper, we focus on generalized projected gradient descent (GPGD) algorithms where generalized projections are realized with learned neural networks and provide state-of-the-art results for imaging inverse problems. Indeed, neural networks allow for projections onto unknown low-dimensional sets that model complex data, such as images. We call these projections deep projective priors. In generic settings, when the orthogonal projection onto a lowdimensional model set is used, it has been shown, under a restricted isometry assumption, that the corresponding orthogonal PGD converges with a linear rate, yielding near-optimal convergence (within the class of GPGD methods) in the classical case of sparse recovery. However, for deep projective priors trained with classical mean squared error losses, there is little guarantee that the hypotheses for linear convergence are satisfied. In this paper, we propose a stochastic orthogonal regularization of the training loss for deep projective priors. This regularization is motivated by our theoretical results: a sufficiently good approximation of the orthogonal projection guarantees linear stable recovery with performance close to orthogonal PGD. We show experimentally, using two different deep projective priors (based on autoencoders and on denoising networks), that our stochastic orthogonal regularization yields projections that improve convergence speed and robustness of GPGD in challenging inverse problem settings, in accordance with our theoretical findings. - oai:arXiv.org:2505.13078v3 + Heart Failure Prediction using Modal Decomposition and Masked Autoencoders for Scarce Echocardiography Databases + https://arxiv.org/abs/2504.07606 + arXiv:2504.07606v3 Announce Type: replace-cross +Abstract: Heart diseases remain the leading cause of mortality worldwide, implying approximately 18 million deaths according to the WHO. In particular, heart failures (HF) press the healthcare industry to develop systems for their early, rapid, and effective prediction. This work presents an automatic system based on a novel framework which combines Modal Decomposition and Masked Autoencoders (MAE) to extend the application from heart disease classification to the more challenging and specific task of heart failure time prediction, not previously addressed to the best of authors' knowledge. This system comprises two stages. The first one transforms the data from a database of echocardiography video sequences into a large collection of annotated images compatible with the training phase of machine learning-based frameworks and deep learning-based ones. This stage includes the use of the Higher Order Dynamic Mode Decomposition (HODMD) algorithm for both data augmentation and feature extraction. The second stage builds and trains a Vision Transformer (ViT). MAEs based on a combined scheme of self-supervised (SSL) and supervised learning, so far barely explored in the literature about heart failure prediction, are adopted to effectively train the ViT from scratch, even with scarce databases. The designed neural network analyses in real-time images from echocardiography sequences to estimate the time of happening a heart failure. This approach demonstrates to improve prediction accuracy from scarce databases and to be superior to several established ViT and Convolutional Neural Network (CNN) architectures. The source code will be incorporated into the next version release of the ModelFLOWs-app software (https://github.com/modelflows/ModelFLOWs-app). + oai:arXiv.org:2504.07606v3 eess.IV - cs.NE - math.OC - Tue, 09 Dec 2025 00:00:00 -0500 + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Ali Joundi (UB), Yann Traonmilin (UB), Alasdair Newson (ISIR) + http://creativecommons.org/licenses/by/4.0/ + Andr\'es Bell-Navas, Mar\'ia Villalba-Orero, Enrique Lara-Pezzi, Jes\'us Garicano-Mena, Soledad Le Clainche - Covert Entanglement Generation over Bosonic Channels - https://arxiv.org/abs/2506.09474 - arXiv:2506.09474v3 Announce Type: replace-cross -Abstract: We explore covert entanglement generation over the lossy thermal-noise bosonic channel, which is a quantum-mechanical model of many practical settings, including optical, microwave, and radio-frequency (RF) channels. Covert communication ensures that an adversary is unable to detect the presence of transmissions, which are concealed in channel noise. We show that a square root law (SRL) for covert entanglement generation similar to that for classical communication: $L_{\rm EG}\sqrt{n}$ entangled bits (ebits) can be generated covertly and reliably over $n$ uses of a bosonic channel. We report a single-letter expression for optimal $L_{\rm EG}$ as well as an achievable method. We additionally analyze the performance of covert entanglement generation using single- and dual-rail photonic qubits, which may be more practical for physical implementation. - oai:arXiv.org:2506.09474v3 - quant-ph - cs.CR - Tue, 09 Dec 2025 00:00:00 -0500 + Computing the Tropical Abel--Jacobi Transform and Tropical Distances for Metric Graphs + https://arxiv.org/abs/2504.11619 + arXiv:2504.11619v3 Announce Type: replace-cross +Abstract: Metric graphs are important models for capturing the structure of complex data across various domains. While much effort has been devoted to extracting geometric and topological features from graph data, computational aspects of metric graphs as abstract tropical curves remains unexplored. In this paper, we present the first computational and machine learning-driven study of metric graphs from the perspective of tropical algebraic geometry. Specifically, we study the tropical Abel--Jacobi transform, a vectorization of points on a metric graph via the tropical Abel--Jacobi map into its associated flat torus, the tropical Jacobian. We develop algorithms to compute this transform and investigate how the resulting embeddings depend on different combinatorial models of the same metric graph. + Once embedded, we compute pairwise distances between points in the tropical Jacobian under two natural metrics: the tropical polarization distance and the Foster--Zhang distance. Computing these distances are generally NP-hard as they turn out to be linked to classical lattice problems in computational complexity, however, we identify a class of metric graphs where fast and explicit computations are feasible. For the general case, we propose practical algorithms for both exact and approximate distance matrix computations using lattice basis reduction and mixed-integer programming solvers. Our work lays the groundwork for future applications of tropical geometry and the tropical Abel--Jacobi transform in machine learning and data analysis. + oai:arXiv.org:2504.11619v3 + math.AG + cs.NA + math.MG + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Evan J. D. Anderson, Michael S. Bullock, Ohad Kimelfeld, Christopher K. Eyre, Filip Rozp\k{e}dek, Uzi Pereg, Boulat A. Bash + Yueqi Cao, Anthea Monod - A Branch-and-Cut Algorithm for the Optimal Design of Parking Lots with One-way and Two-way Lanes - https://arxiv.org/abs/2506.09961 - arXiv:2506.09961v2 Announce Type: replace-cross -Abstract: We address the problem of maximizing the number of stalls in parking lots where vehicles park perpendicular to the driveways. Building on recent research on two-way driving lanes, we first formulate a mixed integer program to maximize the number of parking stalls using a flow-based approach. Parking lots are rasterized into a grid, and the proposed MIP model optimizes them in a generic manner, adapting to the grid resolution and stall size without requiring custom formulations. The constraints ensure the connectivity of parking stalls and driveways to the entrance/exit. This formulation is then extended to the case of one-way driving lanes. We then propose valid inequalities and a branch-and-cut algorithm for the one-way and two-way lane configurations. This approach eliminates flow variables, big-M type constraints, and improves solution times for medium-sized instances. The effectiveness of the suggested models is showcased on 325 parking lots from New York City. For instances in which the flow version could be solved in 15 minutes, the branch-and-cut algorithm improved the median runtimes by 87.43% for the one-way case and by 79.36% for the two-way case and resulted in better optimality gaps for the other instances, compared to the baseline flow-based formulation. Similar advantages were observed when run with a time budget of two hours. One-way configurations accommodated, on average, 18.63% more vehicles on average than their two-way counterparts across all instances. Modifications to the proposed formulations that consider the turning characteristics of vehicles and the presence of multiple entrances and exits are also examined. - oai:arXiv.org:2506.09961v2 - math.OC - cs.DM - Tue, 09 Dec 2025 00:00:00 -0500 + Minimal dispersion on the sphere + https://arxiv.org/abs/2505.10929 + arXiv:2505.10929v2 Announce Type: replace-cross +Abstract: The minimal spherical cap dispersion ${\rm disp}_{\mathcal{C}}(n,d)$ is the largest number $\varepsilon\in (0,1]$ such that, for every $n$ points on the $d$-dimensional Euclidean unit sphere $\mathbb{S}^d$, there exists a spherical cap with normalized area $\varepsilon$ not containing any of these points. We study the behavior of ${\rm disp}_{\mathcal{C}}(n,d)$ as $n$ and $d$ grow to infinity. We develop connections to the problems of sphere covering and approximation of the Euclidean unit ball by inscribed polytopes. Existing and new results are presented in a unified way. Upper bounds on ${\rm disp}_{\mathcal{C}}(n,d)$ result from choosing the points independently and uniformly at random and possibly adding some well-separated points to close large gaps. Moreover, we study dispersion with respect to intersections of caps. + oai:arXiv.org:2505.10929v2 + math.MG + cs.NA + math.NA + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Helen Thomas, Tarun Rambha + Alexander E. Litvak, Mathias Sonnleitner, Tomasz Szczepanski - Robust brain age estimation from structural MRI with contrastive learning - https://arxiv.org/abs/2507.01794 - arXiv:2507.01794v2 Announce Type: replace-cross -Abstract: Estimating brain age from structural MRI has emerged as a powerful tool for characterizing normative and pathological aging. In this work, we explore contrastive learning as a scalable and robust alternative to L1-supervised approaches for brain age estimation. We introduce a novel contrastive loss function, $\mathcal{L}^{exp}$, and evaluate it across multiple public neuroimaging datasets comprising over 20,000 scans. Our experiments reveal four key findings. First, scaling pre-training on diverse, multi-site data consistently improves generalization performance, cutting external mean absolute error (MAE) nearly in half. Second, $\mathcal{L}^{exp}$ is robust to site-related confounds, maintaining low scanner-predictability as training size increases. Third, contrastive models reliably capture accelerated aging in patients with cognitive impairment and Alzheimer's disease, as shown through brain age gap analysis, ROC curves, and longitudinal trends. Lastly, unlike L1-supervised baselines, $\mathcal{L}^{exp}$ maintains a strong correlation between brain age accuracy and downstream diagnostic performance, supporting its potential as a foundation model for neuroimaging. These results position contrastive learning as a promising direction for building generalizable and clinically meaningful brain representations. - oai:arXiv.org:2507.01794v2 + From Fibers to Cells: Fourier-Based Registration Enables Virtual Cresyl Violet Staining From 3D Polarized Light Imaging + https://arxiv.org/abs/2505.11394 + arXiv:2505.11394v2 Announce Type: replace-cross +Abstract: Comprehensive assessment of the various aspects of the brain's microstructure requires the use of complementary imaging techniques. This includes measuring the spatial distribution of cell bodies (cytoarchitecture) and nerve fibers (myeloarchitecture). The gold standard for cytoarchitectonic analysis is light microscopic imaging of cell-body stained tissue sections. To reveal the 3D orientations of nerve fibers, 3D Polarized Light Imaging (3D-PLI) has been introduced, a method that is label-free and allows subsequent staining of sections after 3D-PLI measurement. By post-staining for cell bodies, a direct link between fiber- and cytoarchitecture can potentially be established in the same section. However, inevitable distortions introduced during the staining process make a costly nonlinear and cross-modal registration necessary in order to study the detailed relationships between cells and fibers in the images. In addition, the complexity of processing histological sections for post-staining only allows for a limited number of such samples. In this work, we take advantage of deep learning methods for image-to-image translation to generate a virtual staining of 3D-PLI that is spatially aligned at the cellular level. We use a supervised setting, building on a unique dataset of brain sections, to which Cresyl violet staining has been applied after 3D-PLI measurement. To ensure high correspondence between both modalities, we address the misalignment of training data using Fourier-based registration. In this way, registration can be efficiently calculated during training for local image patches of target and predicted staining. We demonstrate that the proposed method can predict a Cresyl violet staining from 3D-PLI, resulting in a virtual staining that exhibits plausible patterns of cell organization in gray matter, with larger cell bodies being localized at their expected positions. + oai:arXiv.org:2505.11394v2 eess.IV cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://creativecommons.org/licenses/by/4.0/ - Carlo Alberto Barbano, Benoit Dufumier, Edouard Duchesnay, Marco Grangetto, Pietro Gori + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + 10.1162/IMAG.a.1079 + Alexander Oberstrass, Esteban Vaca, Eric Upschulte, Meiqi Niu, Nicola Palomero-Gallagher, David Graessel, Christian Schiffer, Markus Axer, Katrin Amunts, Timo Dickscheid - Fast prediction of plasma instabilities with sparse-grid-accelerated optimized dynamic mode decomposition - https://arxiv.org/abs/2507.03245 - arXiv:2507.03245v2 Announce Type: replace-cross -Abstract: Parametric data-driven reduced-order models (ROMs) that embed dependencies in a large number of input parameters are crucial for enabling many-query tasks in large-scale problems. These tasks, including design optimization, control, and uncertainty quantification, are essential for developing digital twins in real-world applications. However, standard grid-based data generation methods are computationally prohibitive due to the curse of dimensionality. This paper investigates efficient training of parametric data-driven ROMs using sparse grid interpolation with (L)-Leja points, specifically targeting scenarios with higher-dimensional input parameter spaces. (L)-Leja points are nested and exhibit slow growth, resulting in sparse grids with low cardinality in low-to-medium dimensional settings, making them ideal for large-scale, computationally expensive problems. Focusing on gyrokinetic simulations of plasma micro-instabilities in fusion experiments as a representative real-world application, we construct parametric ROMs for the full 5D gyrokinetic distribution function via optimized dynamic mode decomposition (optDMD) and sparse grids based on (L)-Leja points. We perform detailed experiments in two scenarios: First, the Cyclone Base Case benchmark assesses optDMD ROM prediction capabilities beyond training time horizons and across variations in the binormal wave number. Second, for a real-world electron-temperature-gradient-driven micro-instability simulation with six input parameters, we demonstrate that a predictive parametric optDMD ROM that is up to three orders of magnitude cheaper to evaluate can be constructed using only 28 high-fidelity gyrokinetic simulations, enabled by the use of sparse grids. In the broader context of fusion research, these results demonstrate the potential of sparse grid-based parametric ROMs to enable otherwise intractable many-query tasks. - oai:arXiv.org:2507.03245v2 - physics.comp-ph - cs.CE - cs.NA - math.NA - physics.plasm-ph - Tue, 09 Dec 2025 00:00:00 -0500 + Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations + https://arxiv.org/abs/2507.00269 + arXiv:2507.00269v2 Announce Type: replace-cross +Abstract: Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs consistently fail to eliminate polysemanticity and exhibit pathological behavioral errors. We propose that neural networks encode information in two complementary spaces compressed into the same substrate: feature identity and feature integration. To test this dual encoding hypothesis, we develop sequential and joint-training architectures to capture identity and integration patterns simultaneously. Joint training achieves 41.3% reconstruction improvement and 51.6% reduction in KL divergence errors. This architecture spontaneously develops bimodal feature organization: low squared norm features contributing to integration pathways and the rest contributing directly to the residual. Small nonlinear components (3% of parameters) achieve 16.5% standalone improvements, demonstrating parameter-efficient capture of computational relationships crucial for behavior. Additionally, intervention experiments using 2x2 factorial stimulus designs demonstrated that integration features exhibit selective sensitivity to experimental manipulations and produce systematic behavioral effects on model outputs, including significant statistical interaction effects across semantic dimensions. This work provides systematic evidence for (1) dual encoding in neural representations, (2) meaningful nonlinearly encoded feature interactions, and (3) introduces an architectural paradigm shift from post-hoc feature analysis to integrated computational design, establishing foundations for next-generation SAEs. + oai:arXiv.org:2507.00269v2 + q-bio.NC + cs.AI + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Kevin Gill, Ionut-Gabriel Farcas, Silke Glas, Benjamin J. Faber + Omar Claflin - Generalized Probabilistic Approximate Optimization Algorithm - https://arxiv.org/abs/2507.07420 - arXiv:2507.07420v3 Announce Type: replace-cross -Abstract: We introduce a generalized \textit{Probabilistic Approximate Optimization Algorithm (PAOA)}, a classical variational Monte Carlo framework that extends and formalizes prior work by Weitz \textit{et al.}~\cite{Combes_2023}, enabling parameterized and fast sampling on present-day Ising machines and probabilistic computers. PAOA operates by iteratively modifying the couplings of a network of binary stochastic units, guided by cost evaluations from independent samples. We establish a direct correspondence between derivative-free updates and the gradient of the full Markov flow over the exponentially large state space, showing that PAOA admits a principled variational formulation. Simulated annealing emerges as a limiting case under constrained parameterizations, and we implement this regime on an FPGA-based probabilistic computer with on-chip annealing to solve large 3D spin-glass problems. Benchmarking PAOA against QAOA on the canonical 26-spin Sherrington-Kirkpatrick model with matched parameters reveals superior performance for PAOA. We show that PAOA naturally extends simulated annealing by optimizing multiple temperature profiles, leading to improved performance over SA on heavy-tailed problems such as SK-L\'evy. - oai:arXiv.org:2507.07420v3 - cond-mat.dis-nn + Hebbian Physics Networks: A Self-Organizing Computational Architecture Based on Local Physical Laws + https://arxiv.org/abs/2507.00641 + arXiv:2507.00641v2 Announce Type: replace-cross +Abstract: Physical transport processes organize through local interactions that redistribute imbalance while preserving conservation. Classical solvers enforce this organization by applying fixed discrete operators on rigid grids. We introduce the Hebbian Physics Network (HPN), a computational framework that replaces this rigid scaffolding with a plastic transport geometry. An HPN is a coupled dynamical system of physical states on nodes and constitutive weights on edges in a graph. Residuals--local violations of continuity, momentum balance, or energy conservation--act as thermodynamic forces that drive the joint evolution of both the state and the operator (i.e. the adaptive weights). The weights adapt through a three-factor Hebbian rule, which we prove constitutes a strictly local gradient descent on the residual energy. This mechanism ensures thermodynamic stability: near equilibrium, the learned operator naturally converges to a symmetric, positive-definite form, rigorously reproducing Onsager\'s reciprocal relations without explicit enforcement. Far from equilibrium, the system undergoes a self-organizing search for a transport topology that restores global coercivity. Unlike optimization-based approaches that impose physics through global loss functions, HPNs embed conservation intrinsically: transport is restored locally by the evolving operator itself, without a global Poisson solve or backpropagated objective. We demonstrate the framework on scalar diffusion and incompressible lid-driven cavity flow, showing that physically consistent transport geometries and flow structures emerge from random initial conditions solely through residual-driven local adaptation. HPNs thus reframe computation not as the solution of a fixed equation, but as a thermodynamic relaxation process where the constitutive geometry and physical state co-evolve. + oai:arXiv.org:2507.00641v2 + nlin.AO cs.LG - quant-ph - Tue, 09 Dec 2025 00:00:00 -0500 + stat.CO + stat.ME + Wed, 10 Dec 2025 00:00:00 -0500 + replace-cross + http://creativecommons.org/licenses/by/4.0/ + Gunjan Auti, Hirofumi Daiguji, Gouhei Tanaka + + + Partial decidability protocol for the Wang tiling problem from statistical mechanics and chaotic mapping + https://arxiv.org/abs/2507.13268 + arXiv:2507.13268v2 Announce Type: replace-cross +Abstract: We introduce a partial decidability protocol for the Wang tiling problem (which is the prototype of undecidable problems in combinatorics and statistical physics) by constructing a suitable mapping from tilings of finite squares of different sizes. Such mapping depends on the initial family of Wang tiles (the alphabet) with which one would like to tile the plane. This allows to define effective entropy and temperature associated to the alphabet (together with the corresponding partition function). We identify a subclass of good alphabets by observing that when the entropy and temperature of a given alphabet are well-behaved in the thermodynamical sense then such alphabet is a good candidate to tile the infinite two-dimensional plane. Our proposal is tested successfully with the known available good alphabets (which produce periodic tilings, aperiodic but self-similar tilings as well as tilings which are neither periodic nor self-similar). Our analysis shows that the Kendall Tau coefficient is able to distinguish alphabets with a good thermodynamical behavior from alphabets with bad thermodynamical behavior. The transition from good to bad behavior is related to a transition from non-chaotic to chaotic regime in discrete dynamical systems of logistic type. + oai:arXiv.org:2507.13268v2 + cond-mat.stat-mech + cs.IT + hep-th + math.IT + math.LO + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - 10.1038/s41467-025-67187-5 - Abdelrahman S. Abdelrahman, Shuvro Chowdhury, Flaviano Morone, Kerem Y. Camsari + Fabrizio Canfora, Marco Cedeno - Stochastic Approximation with Block Coordinate Optimal Stepsizes - https://arxiv.org/abs/2507.08963 - arXiv:2507.08963v2 Announce Type: replace-cross -Abstract: We consider stochastic approximation with block-coordinate stepsizes and propose adaptive stepsize rules that aim to minimize the expected distance from the next iterate to an (unknown) target point. These stepsize rules employ online estimates of the second moment of the search direction along each block coordinate. The popular Adam algorithm can be interpreted as a variant with a specific estimator. By leveraging a simple conditional estimator, we derive a new method that obtains competitive performance against Adam but requires less memory and fewer hyper-parameters. We prove that this family of methods converges almost surely to a small neighborhood of the target point, and the radius of the neighborhood depends on the bias and variance of the second-moment estimator. Our analysis relies on a simple aiming condition that assumes neither convexity nor smoothness, thus has broad applicability. - oai:arXiv.org:2507.08963v2 - math.OC + PET Image Reconstruction Using Deep Diffusion Image Prior + https://arxiv.org/abs/2507.15078 + arXiv:2507.15078v2 Announce Type: replace-cross +Abstract: Diffusion models have shown great promise in medical image denoising and reconstruction, but their application to Positron Emission Tomography (PET) imaging remains limited by tracer-specific contrast variability and high computational demands. In this work, we proposed an anatomical prior-guided PET image reconstruction method based on diffusion models, inspired by the deep diffusion image prior (DDIP) framework. The proposed method alternated between diffusion sampling and model fine-tuning guided by the PET sinogram, enabling the reconstruction of high-quality images from various PET tracers using a score function pretrained on a dataset of another tracer. To improve computational efficiency, the half-quadratic splitting (HQS) algorithm was adopted to decouple network optimization from iterative PET reconstruction. The proposed method was evaluated using one simulation and two clinical datasets. For the simulation study, a model pretrained on [$^{18}$F]FDG data was tested on [$^{18}$F]FDG data and amyloid-negative PET data to assess out-of-distribution (OOD) performance. For the clinical-data validation, ten low-dose [$^{18}$F]FDG datasets and one [$^{18}$F]Florbetapir dataset were tested on a model pretrained on data from another tracer. Experiment results show that the proposed PET reconstruction method can generalize robustly across tracer distributions and scanner types, providing an efficient and versatile reconstruction framework for low-dose PET imaging. + oai:arXiv.org:2507.15078v2 + eess.IV + cs.CV + physics.med-ph + Wed, 10 Dec 2025 00:00:00 -0500 + replace-cross + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Fumio Hashimoto, Kuang Gong + + + Amorphous Solid Model of Vectorial Hopfield Neural Networks + https://arxiv.org/abs/2507.22787 + arXiv:2507.22787v5 Announce Type: replace-cross +Abstract: We introduce a three-dimensional vectorial extension of the Hopfield associative-memory model in which each neuron is a unit vector on $S^2$ and synaptic couplings are $3\times 3$ blocks generated through a vectorial Hebbian rule. The resulting block-structured operator is mathematically analogous to the Hessian of amorphous solids and induces a rigid energy landscape with deep minima for stored patterns. Simulations and spectral analysis show that the vectorial network substantially outperforms the classical binary Hopfield model. For moderate connectivity, the critical storage ratio $\gamma_c$ grows approximately linearly with the coordination number $Z$, while for $Z\gtrsim 40$ a high-connectivity regime emerges in which $\gamma_c$ systematically exceeds the extrapolated low-$Z$ linear fit. At the same time, a persistent spectral gap separates pattern modes from the bulk and basins of attraction enlarge, yielding enhanced robustness to initialization noise. Thus geometric constraints combined with amorphous-solid-inspired structure produce associative memories with superior storage and retrieval performance, especially in the high-connectivity ($Z \gtrsim 20$-$30$) regime. + oai:arXiv.org:2507.22787v5 + cond-mat.dis-nn + cond-mat.soft + cond-mat.stat-mech cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + cs.NE + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tao Jiang, Lin Xiao + F. Gallavotti, A. Zaccone A General Approach to Visualizing Uncertainty in Statistical Graphics https://arxiv.org/abs/2508.00937 - arXiv:2508.00937v2 Announce Type: replace-cross + arXiv:2508.00937v3 Announce Type: replace-cross Abstract: We present a general approach to visualizing uncertainty in static 2-D statistical graphics. If we treat a visualization as a function of its underlying quantities, uncertainty in those quantities induces a distribution over images. We show how to aggregate these images into a single visualization that represents the uncertainty. The approach can be viewed as a generalization of sample-based approaches that use overlay. Notably, standard representations, such as confidence intervals and bands, emerge with their usual coverage guarantees without being explicitly quantified or visualized. As a proof of concept, we implement our approach in the IID setting using resampling, provided as an open-source Python library. Because the approach operates directly on images, the user needs only to supply the data and the code for visualizing the quantities of interest without uncertainty. Through several examples, we show how both familiar and novel forms of uncertainty visualization can be created. The implementation is not only a practical validation of the underlying theory but also an immediately usable tool that can complement existing uncertainty-visualization libraries. - oai:arXiv.org:2508.00937v2 + oai:arXiv.org:2508.00937v3 stat.ME cs.GR cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Bernarda Petek, David Nabergoj, Erik \v{S}trumbelj - Solving Sudoku using oscillatory neural networks - https://arxiv.org/abs/2508.02250 - arXiv:2508.02250v2 Announce Type: replace-cross -Abstract: We explore the capabilities of physical computing with Oscillatory Neural Networks (ONN) to solve combinatorial optimization problems. To solve Sudokus with ONNs, we define a novel mapping strategy that utilizes the unique characteristics of the computation paradigm. The problem is encoded through a puzzle specific graph-embedding, which implements the constraints through different subgraphs. These subgraphs are then combined into a single adjacency matrix, which allows the natural dynamics of the phases of coupled oscillators to find a solution to the puzzle. We model the phase dynamics of the ONN by means of the Kuramoto differential equation. This novel approach is then compared to the well-established iterative method to solve Sudoku already used in binary Hopfield networks (HNN). Solving optimization problems typically requires a large amount of energy to solve on conventional hardware. Therefore, we are motivated to explore the mapping of Sudoku from a theoretical point of view to establish the validity of this approach. The simulation results show that the novel ONN mapping outperforms the established HNN methodology. - oai:arXiv.org:2508.02250v2 - cond-mat.dis-nn - cs.ET - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by/4.0/ - Bram F. Haverkort, Federico Sbravati, Stefan Porfir, Aida Todri-Sanial - - - Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network - https://arxiv.org/abs/2508.03183 - arXiv:2508.03183v2 Announce Type: replace-cross -Abstract: The wall pressure is of great importance in understanding the forces and structural responses induced by fluid. Recent works have investigated the potential of deep learning techniques in predicting mean pressure coefficients and fluctuating pressure coefficients, but most of existing deep learning frameworks are limited to predicting a single snapshot using full spatial information. To forecast spatiotemporal wall pressure of flow past a rectangular cylinder, this study develops a physics-aware DeepU-Fourier neural Network (DeepUFNet) deep learning model. DeepUFNet comprises the UNet structure and the Fourier neural network, with physical high-frequency loss control embedded in the model training stage to optimize model performance. Wind tunnel testing was performed to collect wall pressures on two-dimensional rectangular cylinders using high-frequency pressure scanning, thereby constructing a database for DeepUFNet training and testing. The DeepUFNet model is found capable of forecasting spatiotemporal wall pressure information with high accuracy on the rectangular cylinder with side ratio 1.5. The comparison between forecast results and experimental data presents agreement in statistical information and physical interpretation. It is also found that embedding a physical high-frequency loss control coefficient b in the DeepUFNet model can significantly improve model performance in forecasting spatiotemporal wall pressure information, particularly, high-order frequency fluctuation and wall pressure variance. Furthermore, the DeepUFNet extrapolation capability is tested with sparse spatial information input, and the model presents a satisfactory extrapolation ability. Last, the DeepUFNet is tested for generalization in unseen cases, rectangular cylinders with side ratio 4 and 3.75, and the model presents satisfactory generalization ability. - oai:arXiv.org:2508.03183v2 - physics.flu-dyn - cs.AI - cs.CE - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by/4.0/ - 10.1063/5.0298947 - Junle Liu, Chang Liu, Yanyu Ke, Wenliang Chen, Kihing Shum, Tim K. T. Tse, Gang Hu - - - An exact multiple-time-step variational formulation for the committor and the transition rate - https://arxiv.org/abs/2509.03539 - arXiv:2509.03539v2 Announce Type: replace-cross -Abstract: For a transition between two stable states, the committor is the probability that the dynamics leads to one stable state before the other. It can be estimated from trajectory data by minimizing an expression for the transition rate that depends on a lag time. We show that an existing such expression is minimized by the exact committor only when the lag time is a single time step, resulting in a biased estimate in practical applications. We introduce an alternative expression that is minimized by the exact committor at any lag time. The key idea is that, when trajectories enter the stable states, the times that they enter (stopping times) must be used for estimating the committor and transition rate instead of the lag time. Numerical tests on benchmark systems demonstrate that our committor and transition rate estimates are much less sensitive to the choice of lag time. We show how further accuracy for the transition rate can be achieved by combining results from two lag times. We also relate the transition rate expression to a variational approach for kinetic statistics based on the mean-squared residual and discuss further numerical considerations with the aid of a decomposition of the error into dynamic modes. - oai:arXiv.org:2509.03539v2 - cond-mat.stat-mech + Automated Construction of Artificial Lattice Structures with Designer Electronic States + https://arxiv.org/abs/2508.02581 + arXiv:2508.02581v2 Announce Type: replace-cross +Abstract: Manipulating matter with a scanning tunneling microscope (STM) enables creation of atomically defined artificial structures that host designer quantum states. However, the time-consuming nature of the manipulation process, coupled with the sensitivity of the STM tip, constrains the exploration of diverse configurations and limits the size of designed features. In this study, we present a reinforcement learning (RL)-based framework for creating artificial structures by spatially manipulating carbon monoxide (CO) molecules on a copper substrate using the STM tip. The automated workflow combines molecule detection and manipulation, employing deep learning-based object detection to locate CO molecules and linear assignment algorithms to allocate these molecules to designated target sites. We initially perform molecule maneuvering based on randomized parameter sampling for sample bias, tunneling current setpoint and manipulation speed. This dataset is then structured into an action trajectory used to train an RL agent. The model is subsequently deployed on the STM for real-time fine-tuning of manipulation parameters during structure construction. Our approach incorporates path planning protocols coupled with active drift compensation to enable atomically precise fabrication of structures with significantly reduced human input while realizing larger-scale artificial lattices with desired electronic properties. Using our approach, we demonstrate the automated construction of an extended artificial graphene lattice and confirm the existence of characteristic Dirac point in its electronic structure. Further challenges to RL-based structural assembly scalability are discussed. + oai:arXiv.org:2508.02581v2 + cond-mat.mtrl-sci cs.LG - physics.comp-ph - physics.data-an - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Chatipat Lorpaiboon, Jonathan Weare, Aaron R. Dinner + Ganesh Narasimha, Mykola Telychko, Wooin Yang, Arthur P. Baddorf, P. Ganesh, An-Ping Li, Rama Vasudevan - SADA: Safe and Adaptive Aggregation of Multiple Black-Box Predictions in Semi-Supervised Learning - https://arxiv.org/abs/2509.21707 - arXiv:2509.21707v2 Announce Type: replace-cross -Abstract: Semi-supervised learning (SSL) arises in practice when labeled data are scarce or expensive to obtain, while large quantities of unlabeled data are readily available. - With the growing adoption of machine learning techniques, it has become increasingly feasible to generate multiple predicted labels using a variety of models and algorithms, including deep learning, large language models, and generative AI. In this paper, we propose a novel approach that safely and adaptively aggregates multiple black-box predictions of uncertain quality for both inference and prediction tasks. Our method provides two key guarantees: (i) it never performs worse than using the labeled data alone, regardless of the quality of the predictions; and (ii) if any one of the predictions (without knowing which one) perfectly fits the ground truth, the algorithm adaptively exploits this to achieve either a faster convergence rate or the semiparametric efficiency bound. We demonstrate the effectiveness of the proposed algorithm through small-scale simulations and two real-data analyses with distinct scientific goals. A user-friendly R package, sada, is provided to facilitate practical implementation. - oai:arXiv.org:2509.21707v2 + Gaussian Approximation for Two-Timescale Linear Stochastic Approximation + https://arxiv.org/abs/2508.07928 + arXiv:2508.07928v2 Announce Type: replace-cross +Abstract: In this paper, we establish non-asymptotic bounds for accuracy of normal approximation for linear two-timescale stochastic approximation (TTSA) algorithms driven by martingale difference or Markov noise. Focusing on both the last iterate and Polyak-Ruppert averaging regimes, we derive bounds for normal approximation in terms of the convex distance between probability distributions. Our analysis reveals a non-trivial interaction between the fast and slow timescales: the normal approximation rate for the last iterate improves as the timescale separation increases, while it decreases in the Polyak-Ruppert averaged setting. We also provide the high-order moment bounds for the error of linear TTSA algorithm, which may be of independent interest. + oai:arXiv.org:2508.07928v2 stat.ML cs.LG - stat.ME - Tue, 09 Dec 2025 00:00:00 -0500 + math.OC + math.PR + math.ST + stat.TH + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jiawei Shan, Zhifeng Chen, Yiming Dong, Yazhen Wang, Jiwei Zhao - - - Inferring Cosmological Parameters with Evidential Physics-Informed Neural Networks - https://arxiv.org/abs/2509.24327 - arXiv:2509.24327v2 Announce Type: replace-cross -Abstract: We examine the use of a novel variant of Physics-Informed Neural Networks to predict cosmological parameters from recent supernovae and baryon acoustic oscillations (BAO) datasets. Our machine learning framework generates uncertainty estimates for target variables and the inferred unknown parameters of the underlying PDE descriptions. Built upon a hybrid of the principles of Evidential Deep Learning, Physics-Informed Neural Networks, Bayesian Neural Networks and Gaussian Processes, our model enables learning of the posterior distribution of the unknown PDE parameters through standard gradient-descent based training. We apply our model to an up-to-date BAO dataset (Bousis et al. 2024) calibrated with the CMB-inferred sound horizon, and the Pantheon$+$ Sne Ia distances (Scolnic et al. 2018), examining the relative effectiveness and mutual consistency among the standard $\Lambda$CDM, $w$CDM and $\Lambda_s$CDM models. Unlike previous results arising from the standard approach of minimizing an appropriate $\chi^2$ function, the posterior distributions for parameters in various models trained purely on Pantheon$+$ data were found to be largely contained within the $2\sigma$ contours of their counterparts trained on BAO data. Their posterior medians for $h_0$ were within about $2\sigma$ of one another, indicating that our machine learning-guided approach provides a different measure of the Hubble tension. - oai:arXiv.org:2509.24327v2 - astro-ph.CO - cs.LG - gr-qc - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by/4.0/ - 10.3390/universe11120403 - Universe 2025, 11(12), 403 - Hai Siong Tan + Bogdan Butyrin, Artemy Rubtsov, Alexey Naumov, Vladimir Ulyanov, Sergey Samsonov - The AI Productivity Index (APEX) - https://arxiv.org/abs/2509.25721 - arXiv:2509.25721v5 Announce Type: replace-cross -Abstract: We present an extended version of the AI Productivity Index (APEX-v1-extended), a benchmark for assessing whether frontier models are capable of performing economically valuable tasks in four jobs: investment banking associate, management consultant, big law associate, and primary care physician (MD). This technical report details the extensions to APEX-v1, including an increase in the held-out evaluation set from n = 50 to n = 100 cases per job (n = 400 total) and updates to the grading methodology. We present a new leaderboard, where GPT5 (Thinking = High) remains the top performing model with a score of 67.0%. APEX-v1-extended shows that frontier models still have substantial limitations when performing typical professional tasks. To support further research, we are open sourcing n = 25 non-benchmark example cases per role (n = 100 total) along with our evaluation harness. - oai:arXiv.org:2509.25721v5 - econ.GN - cs.AI - cs.CL - cs.HC - q-fin.EC - Tue, 09 Dec 2025 00:00:00 -0500 + Guiding WaveMamba with Frequency Maps for Image Debanding + https://arxiv.org/abs/2508.11331 + arXiv:2508.11331v2 Announce Type: replace-cross +Abstract: Compression at low bitrates in modern codecs often introduces banding artifacts, especially in smooth regions such as skies. These artifacts degrade visual quality and are common in user-generated content due to repeated transcoding. We propose a banding restoration method that employs the Wavelet State Space Model and a frequency masking map to preserve high-frequency details. Furthermore, we provide a benchmark of open-source banding restoration methods and evaluate their performance on two public banding image datasets. Experimentation on the available datasets suggests that the proposed post-processing approach effectively suppresses banding compared to the state-of-the-art method (a DBI value of 0.082 on BAND-2k) while preserving image textures. Visual inspections of the results confirm this. Code and supplementary material are available at: https://github.com/xinyiW915/Debanding-PCS2025. + oai:arXiv.org:2508.11331v2 + eess.IV + cs.CV + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://creativecommons.org/licenses/by/4.0/ - Bertie Vidgen, Abby Fennelly, Evan Pinnix, Julien Benchek, Daniyal Khan, Zach Richards, Austin Bridges, Calix Huang, Ben Hunsberger, Isaac Robinson, Akul Datta, Chirag Mahapatra, Dominic Barton, Cass R. Sunstein, Eric Topol, Brendan Foody, Osvald Nitski + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Xinyi Wang, Smaranda Tasmoc, Nantheera Anantrasirichai, Angeliki Katsenou - Learning from the electronic structure of molecules across the periodic table - https://arxiv.org/abs/2510.00224 - arXiv:2510.00224v2 Announce Type: replace-cross -Abstract: Machine-Learned Interatomic Potentials (MLIPs) require vast amounts of atomic structure data to learn forces and energies, and their performance continues to improve with training set size. Meanwhile, the even greater quantities of accompanying data in the Hamiltonian matrix H behind these datasets has so far gone unused for this purpose. Here, we provide a recipe for integrating the orbital interaction data within H towards training pipelines for atomic-level properties. We first introduce HELM ("Hamiltonian-trained Electronic-structure Learning for Molecules"), a state-of-the-art Hamiltonian prediction model which bridges the gap between Hamiltonian prediction and universal MLIPs by scaling to H of structures with 100+ atoms, high elemental diversity, and large basis sets including diffuse functions. To accompany HELM, we release a curated Hamiltonian matrix dataset, 'OMol_CSH_58k', with unprecedented elemental diversity (58 elements), molecular size (up to 150 atoms), and basis set (def2-TZVPD). Finally, we introduce 'Hamiltonian pretraining' as a method to extract meaningful descriptors of atomic environments even from a limited number atomic structures, and repurpose this shared embedding space to improve performance on energy-prediction in low-data regimes. Our results highlight the use of electronic interactions as a rich and transferable data source for representing chemical space. - oai:arXiv.org:2510.00224v2 - physics.chem-ph - cond-mat.mtrl-sci + Random forest-based out-of-distribution detection for robust lung cancer segmentation + https://arxiv.org/abs/2508.19112 + arXiv:2508.19112v3 Announce Type: replace-cross +Abstract: Accurate detection and segmentation of cancerous lesions from computed tomography (CT) scans is essential for automated treatment planning and cancer treatment response assessment. Transformer-based models with self-supervised pretraining can produce reliably accurate segmentation from in-distribution (ID) data but degrade when applied to out-of-distribution (OOD) datasets. We address this challenge with RF-Deep, a random forest classifier that utilizes deep features from a pretrained transformer encoder of the segmentation model to detect OOD scans and enhance segmentation reliability. The segmentation model comprises a Swin Transformer encoder, pretrained with masked image modeling (SimMIM) on 10,432 unlabeled 3D CT scans covering cancerous and non-cancerous conditions, with a convolution decoder, trained to segment lung cancers in 317 3D scans. Independent testing was performed on 603 3D CT public datasets that included one ID dataset and four OOD datasets comprising chest CTs with pulmonary embolism (PE) and COVID-19, and abdominal CTs with kidney cancers and healthy volunteers. RF-Deep detected OOD cases with a FPR95 of 18.26%, 27.66%, and less than 0.1% on PE, COVID-19, and abdominal CTs, consistently outperforming established OOD approaches. The RF-Deep classifier provides a simple and effective approach to enhance reliability of cancer segmentation in ID and OOD scenarios. + oai:arXiv.org:2508.19112v3 + eess.IV + cs.CV cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Manasa Kaniselvan, Benjamin Kurt Miller, Meng Gao, Juno Nam, Daniel S. Levine + Aneesh Rangnekar, Harini Veeraraghavan - Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero - https://arxiv.org/abs/2510.01874 - arXiv:2510.01874v2 Announce Type: replace-cross -Abstract: This paper examines replication portfolio construction in incomplete markets - a key problem in financial engineering with applications in pricing, hedging, balance sheet management, and energy storage planning. We model this as a two-player game between an investor and the market, where the investor makes strategic bets on future states while the market reveals outcomes. Inspired by the success of Monte Carlo Tree Search in stochastic games, we introduce an AlphaZero-based system and compare its performance to deep hedging - a widely used industry method based on gradient descent. Through theoretical analysis and experiments, we show that deep hedging struggles in environments where the optimal action-value function is not subject to convexity constraints - such as those involving non-convex transaction costs, capital constraints, or regulatory limitations - converging to local optima. We construct specific market environments to highlight these limitations and demonstrate that AlphaZero consistently finds near-optimal replication strategies. On the theoretical side, we establish a connection between deep hedging and convex optimization, suggesting that its effectiveness is contingent on convexity assumptions. Our experiments further suggest that AlphaZero is more sample-efficient - an important advantage in data-scarce, overfitting-prone derivative markets. - oai:arXiv.org:2510.01874v2 - stat.ML + Universal Representation of Generalized Convex Functions and their Gradients + https://arxiv.org/abs/2509.04477 + arXiv:2509.04477v2 Announce Type: replace-cross +Abstract: A wide range of optimization problems can often be written in terms of generalized convex functions (GCFs). When this structure is present, it can convert certain nested bilevel objectives into single-level problems amenable to standard first-order optimization methods. We provide a new differentiable layer with a convex parameter space and show (Theorems 5.1 and 5.2) that it and its gradient are universal approximators for GCFs and their gradients. We demonstrate how this parameterization can be leveraged in practice by (i) learning optimal transport maps with general cost functions and (ii) learning optimal auctions of multiple goods. In both these cases, we show how our layer can be used to convert the existing bilevel or min-max formulations into single-level problems that can be solved efficiently with first-order methods. + oai:arXiv.org:2509.04477v2 + math.OC cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Matteo Maggiolo, Giuseppe Nuti, Miroslav \v{S}trupl, Oleg Szehr + Moeen Nehzati - Model Monitoring: A General Framework with an Application to Non-life Insurance Pricing - https://arxiv.org/abs/2510.04556 - arXiv:2510.04556v2 Announce Type: replace-cross -Abstract: Maintaining the predictive performance of pricing models is challenging when insurance portfolios and data-generating mechanisms evolve over time. Focusing on non-life insurance, we adopt the concept-drift terminology from machine learning and distinguish virtual drift from real concept drift in an actuarial setting. Methodologically, we (i) formalize deviance loss and Murphy's score decomposition to assess global and local auto-calibration; (ii) study the Gini score as a rank-based performance measure, derive its asymptotic distribution, and develop a consistent bootstrap estimator of its asymptotic variance; and (iii) combine these results into a statistically grounded, model-agnostic monitoring framework that integrates a Gini-based ranking drift test with global and local auto-calibration tests. An application to a modified motor insurance portfolio with controlled concept-drift scenarios illustrates how the framework guides decisions on refitting or recalibrating pricing models. - oai:arXiv.org:2510.04556v2 + Contractive kinetic Langevin samplers beyond global Lipschitz continuity + https://arxiv.org/abs/2509.12031 + arXiv:2509.12031v2 Announce Type: replace-cross +Abstract: In this paper, we examine the problem of sampling from log-concave distributions with (possibly) superlinear gradient growth under kinetic (underdamped) Langevin algorithms. Using a carefully tailored taming scheme, we propose two novel discretizations of the kinetic Langevin SDE, and we show that they are both contractive and satisfy a log-Sobolev inequality. Building on this, we establish a series of non-asymptotic bounds in $2$-Wasserstein distance between the law reached by each algorithm and the underlying target measure. + oai:arXiv.org:2509.12031v2 + math.PR + cs.NA + math.NA stat.ML - cs.LG - math.ST - q-fin.ST - stat.AP - stat.TH - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by-nc-nd/4.0/ - Alexej Brauer, Paul Menzel, Mario V. W\"uthrich - - - A Biophysically-Conditioned Generative Framework for 3D Brain Tumor MRI Synthesis - https://arxiv.org/abs/2510.09365 - arXiv:2510.09365v2 Announce Type: replace-cross -Abstract: Magnetic resonance imaging (MRI) inpainting supports numerous clinical and research applications. We introduce the first generative model that conditions on voxel-level, continuous tumor concentrations to synthesize high-fidelity brain tumor MRIs. For the BraTS 2025 Inpainting Challenge, we adapt this architecture to the complementary task of healthy tissue restoration by setting the tumor concentrations to zero. Our latent diffusion model conditioned on both tissue segmentations and the tumor concentrations generates 3D spatially coherent and anatomically consistent images for both tumor synthesis and healthy tissue inpainting. For healthy inpainting, we achieve a PSNR of 18.5, and for tumor inpainting, we achieve 17.4. Our code is available at: https://github.com/valentin-biller/ldm.git - oai:arXiv.org:2510.09365v2 - eess.IV - cs.CV - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Valentin Biller, Lucas Zimmer, Ayhan Can Erdur, Sandeep Nagar, Daniel R\"uckert, Niklas Bubeck, Jonas Weidner + Iosif Lytras, Panayotis Mertikopoulos - In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning - https://arxiv.org/abs/2510.10981 - arXiv:2510.10981v2 Announce Type: replace-cross -Abstract: This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We introduce a principled risk decomposition that separates the total ICL risk into two orthogonal components: Bayes Gap and Posterior Variance. The Bayes Gap quantifies how well the trained model approximates the Bayes-optimal in-context predictor. For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts and their context length. The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty. Our key finding is that this term is determined solely by the difficulty of the true underlying task, while the uncertainty arising from the task mixture vanishes exponentially fast with only a few in-context examples. Together, these results provide a unified view of ICL: the Transformer selects the optimal meta-algorithm during pretraining and rapidly converges to the optimal algorithm for the true task at test time. - oai:arXiv.org:2510.10981v2 - stat.ML - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Fourier Spectrum of Noisy Quantum Algorithms + https://arxiv.org/abs/2510.06385 + arXiv:2510.06385v2 Announce Type: replace-cross +Abstract: Quantum computing promises exponential speedups for certain problems, yet fully universal quantum computers remain out of reach and near-term devices are inherently noisy. Motivated by this, we study noisy quantum algorithms and the landscape between $\mathsf{BQP}$ and $\mathsf{BPP}$. We build on a powerful technique to differentiate quantum and classical algorithms called the level-$\ell$ Fourier growth (the sum of absolute values of Fourier coefficients of sets of size $\ell$) and show that it can also be used to differentiate quantum algorithms based on the types of resources used. We show that noise acting on a quantum algorithm dampens its Fourier growth in ways intricately linked to the type of noise. + Concretely, we study noisy models of quantum computation where highly mixed states are prevalent, namely: $\mathsf{DQC}_k$ algorithms, where $k$ qubits are clean and the rest are maximally mixed, and $\frac{1}{2}\mathsf {BQP}$ algorithms, where the initial state is maximally mixed, but the algorithm is given knowledge of the initial state at the end of the computation. We establish upper bounds on the Fourier growth of $\mathsf{DQC}_k$, $\frac{1}{2}\mathsf{BQP}$ and $\mathsf{BQP}$ algorithms and leverage the differences between these bounds to derive oracle separations between these models. In particular, we show that 2-Forrelation and 3-Forrelation require $N^{\Omega(1)}$ queries in the $\mathsf{DQC}_1$ and $\frac{1}{2}\mathsf{BQP}$ models respectively. Our results are proved using a new matrix decomposition lemma that might be of independent interest. + oai:arXiv.org:2510.06385v2 + quant-ph + cs.CC + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Tomoya Wakayama, Taiji Suzuki - - - The Neuroticism Paradox: How Emotional Instability Fuels Collective Feelings - https://arxiv.org/abs/2510.16046 - arXiv:2510.16046v2 Announce Type: replace-cross -Abstract: Collective emotions shape organizations, communities, and societies, yet the traits that determine who drives them remain unknown. Conventional wisdom holds that stable, extraverted individuals act as emotional leaders, calming and coordinating the feelings of others. Here we challenge this view by analyzing a 30.5-month longitudinal dataset of daily emotions from 38 co-located professionals (733,534 records). Using Granger-causality network reconstruction, we find that emotionally unstable individuals -- those high in neuroticism (r = 0.478, p = 0.002) and low in conscientiousness (r = -0.512, p = 0.001) -- are the true "emotional super-spreaders," while extraversion shows no effect (r = 0.238, p = 0.150). This "Neuroticism Paradox" reveals that emotional volatility, not stability, drives contagion. Emotions propagate with a reproduction rate (R_0 = 15.58) comparable to measles, yet the system avoids collapse through high clustering (C = 0.705) that creates "emotional quarantine zones." Emotional variance increased 22.9% over time, contradicting homeostasis theories and revealing entropy-driven dynamics. We propose an Affective Epidemiology framework showing that collective emotions are governed by network position and volatility rather than personality stability -- transforming how we understand emotional leadership in human systems. - oai:arXiv.org:2510.16046v2 - physics.soc-ph - cs.CY - cs.SI - Tue, 09 Dec 2025 00:00:00 -0500 - replace-cross - http://creativecommons.org/licenses/by/4.0/ - Xiao Sun + Uma Girish - DualHash: A Stochastic Primal-Dual Algorithm with Theoretical Guarantee for Deep Hashing - https://arxiv.org/abs/2510.18218 - arXiv:2510.18218v2 Announce Type: replace-cross -Abstract: Deep hashing converts high-dimensional feature vectors into compact binary codes, enabling efficient large-scale retrieval. A fundamental challenge in deep hashing stems from the discrete nature of quantization in generating the codes. W-type regularizations, such as $||z|-1|$, have been proven effective as they encourage variables toward binary values. However, existing methods often directly optimize these regularizations without convergence guarantees. While proximal gradient methods offer a promising solution, the coupling between W-type regularizers and neural network outputs results in composite forms that generally lack closed-form proximal solutions. In this paper, we present a stochastic primal-dual hashing algorithm, referred to as DualHash, that provides rigorous complexity bounds. Using Fenchel duality, we partially transform the nonconvex W-type regularization optimization into the dual space, which results in a proximal operator that admits closed-form solutions. We derive two algorithm instances: a momentum-accelerated version with $\mathcal{O}(\varepsilon^{-4})$ complexity and an improved $\mathcal{O}(\varepsilon^{-3})$ version using variance reduction. Experiments on three image retrieval databases demonstrate the superior performance of DualHash. - oai:arXiv.org:2510.18218v2 - math.OC - cs.CV - Tue, 09 Dec 2025 00:00:00 -0500 + Trickle-down Theorems via C-Lorentzian Polynomials II: Pairwise Spectral Influence and Improved Dobrushin's Condition + https://arxiv.org/abs/2510.06549 + arXiv:2510.06549v2 Announce Type: replace-cross +Abstract: Let $\mu$ be a probability distribution on a multi-state spin system on a set $V$ of sites. Equivalently, we can think of this as a $d$-partite simplical complex with distribution $\mu$ on maximal faces. For any pair of vertices $u,v\in V$, define the pairwise spectral influence $\mathcal{I}_{u,v}$ as follows. Let $\sigma$ be a choice of spins $s_w\in S_w$ for every $w\in V \setminus \{u,v\}$, and construct a matrix in $\mathbb{R}^{(S_u\cup S_v)\times (S_u\cup S_v)}$ where for any $s_u\in S_u, s_v\in S_v$, the $(us_u,vs_v)$-entry is the probability that $s_v$ is the spin of $v$ conditioned on $s_u$ being the spin of $u$ and on $\sigma$. Then $\mathcal{I}_{u,v}$ is the maximal second eigenvalue of this matrix, over all choices of spins for all $w \in V \setminus \{u,v\}$. Equivalently, $\mathcal{I}_{u,v}$ is the maximum local spectral expansion of links of codimension $2$ that include a spin for every $w \in V \setminus \{u,v\}$. + We show that if the largest eigenvalue of the pairwise spectral influence matrix with entries $\mathcal{I}_{u,v}$ is bounded away from 1, i.e. $\lambda_{\max}(\mathcal{I})\leq 1-\epsilon$ (and $X$ is connected), then the Glauber dynamics mixes rapidly and generate samples from $\mu$. This improves/generalizes the classical Dobrushin's influence matrix as the $\mathcal{I}_{u,v}$ lower-bounds the classical influence of $u\to v$. As a by-product, we also prove improved/almost optimal trickle-down theorems for partite simplicial complexes. The proof builds on the trickle-down theorems via $\mathcal{C}$-Lorentzian polynomials machinery recently developed by the authors and Lindberg. + oai:arXiv.org:2510.06549v2 + math.CO + cs.CC + cs.DS + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://creativecommons.org/licenses/by/4.0/ - Luxuan Li, Xiao Wang, Chunfeng Cui + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Jonathan Leake, Shayan Oveis Gharan - HPC-Driven Modeling with ML-Based Surrogates for Magnon-Photon Dynamics in Hybrid Quantum Systems - https://arxiv.org/abs/2510.22221 - arXiv:2510.22221v2 Announce Type: replace-cross -Abstract: Simulating hybrid magnonic quantum systems remains a challenge due to the large disparity between the timescales of the two systems. We present a massively parallel GPU-based simulation framework that enables fully coupled, large-scale modeling of on-chip magnon-photon circuits. Our approach resolves the dynamic interaction between ferromagnetic and electromagnetic fields with high spatiotemporal fidelity. To accelerate design workflows, we develop a physics-informed machine learning surrogate trained on the simulation data, reducing computational cost while maintaining accuracy. This combined approach reveals real-time energy exchange dynamics and reproduces key phenomena such as anti-crossing behavior and the suppression of ferromagnetic resonance under strong electromagnetic fields. By addressing the multiscale and multiphysics challenges in magnon-photon modeling, our framework enables scalable simulation and rapid prototyping of next-generation quantum and spintronic devices. - oai:arXiv.org:2510.22221v2 + Beyond Hoeffding and Chernoff: Trading conclusiveness for advantages in quantum hypothesis testing + https://arxiv.org/abs/2510.07601 + arXiv:2510.07601v2 Announce Type: replace-cross +Abstract: The ultimate limits of quantum state discrimination are often thought to be captured by asymptotic bounds that restrict the achievable error probabilities, notably the quantum Chernoff and Hoeffding bounds. Here we study hypothesis testing protocols that are permitted a probability of producing an inconclusive discrimination outcome, and investigate their performance when this probability is suitably constrained. We show that even by allowing an arbitrarily small probability of inconclusiveness, the limits imposed by the quantum Hoeffding and Chernoff bounds can be significantly exceeded. This completely circumvents the conventional trade-offs between error exponents in hypothesis testing while incurring only a vanishingly small overhead over conventional approaches. Such improvements over standard state discrimination are robust and can be obtained even when an exponentially vanishing probability of inconclusive outcomes is demanded. Relaxing the constraints on the inconclusive probability can enable even larger advantages, but this comes at a price. We show a 'strong converse' property of this setting: targeting error exponents beyond those achievable with vanishing inconclusiveness necessarily forces the probability of inconclusive outcomes to converge to one. By exactly quantifying the rate of this convergence, we give a complete characterisation of the trade-offs between error exponents and rates of conclusive outcome probabilities. Overall, our results provide a comprehensive asymptotic picture of how the allowance for inconclusive measurement outcomes reshapes optimal quantum hypothesis testing. + oai:arXiv.org:2510.07601v2 quant-ph - cs.LG - physics.comp-ph - Tue, 09 Dec 2025 00:00:00 -0500 + cs.IT + math-ph + math.IT + math.MP + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Jialin Song, Yingheng Tang, Pu Ren, Shintaro Takayoshi, Saurabh Sawant, Yujie Zhu, Jia-Mian Hu, Andy Nonaka, Michael W. Mahoney, Benjamin Erichson, Zhi Yao + Kaiyuan Ji, Bartosz Regula - BondBERT: What we learn when assigning sentiment in the bond market - https://arxiv.org/abs/2511.01869 - arXiv:2511.01869v2 Announce Type: replace-cross -Abstract: Bond markets respond differently to macroeconomic news compared to equity markets, yet most sentiment models are trained primarily on general financial or equity news data. However, bond prices often move in the opposite direction to economic optimism, making general or equity-based sentiment tools potentially misleading. We introduce BondBERT, a transformer-based language model fine-tuned on bond-specific news. BondBERT can act as the perception and reasoning component of a financial decision-support agent, providing sentiment signals that integrate with forecasting models. We propose a generalisable framework for adapting transformers to low-volatility, domain-inverse sentiment tasks by compiling and cleaning 30,000 UK bond market articles (2018-2025). BondBERT's sentiment predictions are compared against FinBERT, FinGPT, and Instruct-FinGPT using event-based correlation, up/down accuracy analyses, and LSTM forecasting across ten UK sovereign bonds. We find that BondBERT consistently produces positive correlations with bond returns, and achieves higher alignment and forecasting accuracy than the three baseline models. These results demonstrate that domain-specific sentiment adaptation better captures fixed income dynamics, bridging a gap between NLP advances and bond market analytics. - oai:arXiv.org:2511.01869v2 - q-fin.CP - cs.LG - Tue, 09 Dec 2025 00:00:00 -0500 + Formalization of Auslander--Buchsbaum--Serre criterion in Lean4 + https://arxiv.org/abs/2510.24818 + arXiv:2510.24818v3 Announce Type: replace-cross +Abstract: We present a comprehensive formalization in the Lean4 theorem prover of the Auslander--Buchsbaum--Serre criterion, which characterizes regular local rings as those Noetherian local rings with finite global dimension. Rather than following the well-known proof that computes the projective dimension of the residue field via quotient by regular sequences and uses the Koszul complex to bound the cotangent space dimension by the global dimension, our approach is built systematically on the formalization of depth defined via the vanishing of Ext functors. We establish key homological results including Rees' theorem, the Auslander--Buchsbaum formula, and Ischebeck's theorem, and further develop the theories of Cohen--Macaulay modules and rings, including a complete formalization of the unmixedness theorem for Cohen--Macaulay rings. To prove the Auslander--Buchsbaum--Serre criterion, we show that maximal Cohen--Macaulay modules over regular local rings are free and establish a weakened form of the Ferrand--Vasconcelos theorem specific for the unique maximal ideal. As corollaries, we deduce that regularity can be checked at maximal ideals and formalize Hilbert's Syzygy Theorem. This work demonstrates how homological algebra can be effectively employed in the formalization of commutative algebra, providing extensive infrastructure for future developments in the field. + oai:arXiv.org:2510.24818v3 + math.AC + cs.FL + cs.LO + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Toby Barter, Zheng Gao, Eva Christodoulaki, Jing Chen, John Cartlidge + Naillin Guan, Yongle Hu - Simulating Clifford Circuits with Gaussian Elimination - https://arxiv.org/abs/2511.06127 - arXiv:2511.06127v2 Announce Type: replace-cross -Abstract: Quantum circuits are considered more powerful than classical circuits and require exponential resources to simulate classically. Clifford circuits are a special class of quantum circuits that can be simulated in polynomial time but still show important quantum effects such as entanglement. In this work, we present an algorithm that simulates Clifford circuits by performing Gaussian elimination on a modified adjacency matrix derived from the circuit structure. Our work builds on an ZX-calculus tensor network representation of Clifford circuits that reduces to quantum graph states. We give a concise formula of amplitudes of graph states based on the LDL decomposition of matrices over GF(2), and use it to get efficient algorithms for strong and weak simulation of Clifford circuits using tree-decomposition-based fast LDL algorithm. The complexity of our algorithm matches the state of art for weak graph state simulation and improves the state of art for strong graph state simulation by taking advantage of Strassen-like fast matrix multiplication. Our algorithm is also efficient when computing many amplitudes or samples of a Clifford circuit. Further, our amplitudes formula provides a new characterization of locally Clifford equivalent graph states as well as an efficient protocol to learn graph states with low-rank adjacency matrices. - oai:arXiv.org:2511.06127v2 + A Non-Variational Quantum Approach to the Job Shop Scheduling Problem + https://arxiv.org/abs/2510.26859 + arXiv:2510.26859v2 Announce Type: replace-cross +Abstract: Quantum heuristics offer a potential advantage for combinatorial optimization but are constrained by near-term hardware limitations. We introduce Iterative-QAOA, a variant of QAOA designed to mitigate these constraints. The algorithm combines a non-variational, shallow-depth circuit approach using fixed-parameter schedules with an iterative warm-starting process. We benchmark the algorithm on Just-in-Time Job Shop Scheduling Problem (JIT-JSSP) instances on IonQ Forte Generation QPUs, representing some of the largest such problems ever executed on quantum hardware. We compare the performance of the algorithm against both the Variational Quantum Imaginary Time Evolution (VarQITE) algorithm and the non-variational Linear Ramp (LR) QAOA algorithm. We find that Iterative-QAOA robustly converges to find optimal solutions as well as high-quality, near-optimal solutions for all problem instances evaluated. We evaluate the algorithm on larger problem instances up to 97 qubits using tensor network simulations. The scaling behavior of the algorithm indicates potential for solving industrial-scale problems on fault-tolerant quantum computers. + oai:arXiv.org:2510.26859v2 quant-ph - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 + cs.ET + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Yuchen Pang, Edgar Solomonik + Miguel Angel Lopez-Ruiz, Emily L. Tucker, Emma M. Arnold, Evgeny Epifanovsky, Ananth Kaushik, Martin Roetteler - High-Performance Variance-Covariance Matrix Construction Using an Uncentered Gram Formulation - https://arxiv.org/abs/2511.08223 - arXiv:2511.08223v2 Announce Type: replace-cross -Abstract: Reichel (2025) defined the bariance as a pairwise-difference measure that can be rewritten in linear time using only scalar sums. We extend this idea to the covariance matrix by showing that the standard matrix expression involving the uncentered Gram matrix and a correction term is algebraically identical to the pairwise-difference definition while avoiding explicit centering. The computation then reduces to one outer product of dimension p-by-p and a single subtraction. Benchmarks in Python show clear runtime gains, especially when BLAS optimizations are absent. Optionally faster Gram-matrix routines such as RXTX (Rybin et al., 2025) further reduce overall cost. - oai:arXiv.org:2511.08223v2 - stat.CO - cs.LG - cs.NA - math.NA - Tue, 09 Dec 2025 00:00:00 -0500 + Tensor rank and dimension expanders + https://arxiv.org/abs/2511.02670 + arXiv:2511.02670v2 Announce Type: replace-cross +Abstract: We prove a lower bound on the rank of tensors constructed from families of linear maps that `expand' the dimension of every subspace. Such families, called {\em dimension expanders} have been studied for many years with several known explicit constructions. Using these constructions we show that one can construct an explicit $[D]\times [n] \times [n]$-tensor with rank at least $(2 - \epsilon)n$, with $D$ a constant depending on $\epsilon$. Our results extend to border rank over the real or complex numbers. + oai:arXiv.org:2511.02670v2 + math.CO + cs.CC + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://creativecommons.org/licenses/by-nc-sa/4.0/ - Felix Reichel + http://arxiv.org/licenses/nonexclusive-distrib/1.0/ + Zeev Dvir - Comparing Two Proxy Methods for Causal Identification - https://arxiv.org/abs/2512.00175 - arXiv:2512.00175v2 Announce Type: replace-cross -Abstract: Identifying causal effects in the presence of unmeasured variables is a fundamental challenge in causal inference, for which proxy variable methods have emerged as a powerful solution. We contrast two major approaches in this framework: (1) bridge equation methods, which leverage solutions to integral equations to recover causal targets, and (2) array decomposition methods, which recover latent factors composing counterfactual quantities by exploiting unique determination of eigenspaces. We compare the model restrictions underlying these two approaches and provide insight into implications of the underlying assumptions, clarifying the scope of applicability for each method. - oai:arXiv.org:2512.00175v2 - stat.ME - cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + The Rainbow Arborescence Problem on Cycles + https://arxiv.org/abs/2511.04953 + arXiv:2511.04953v2 Announce Type: replace-cross +Abstract: The rainbow arborescence conjecture posits that if the arcs of a directed graph with $n$ vertices are colored by $n-1$ colors such that each color class forms a spanning arborescence, then there is a spanning arborescence that contains exactly one arc of every color. We prove that the conjecture is true if the underlying undirected graph is a cycle. + oai:arXiv.org:2511.04953v2 + math.CO + cs.DM + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross http://creativecommons.org/licenses/by/4.0/ - Helen Guo, Elizabeth L. Ogburn, Ilya Shpitser + Krist\'of B\'erczi, Tam\'as Kir\'aly, Yutaro Yamaguchi, Yu Yokoi - Calibrating Geophysical Predictions under Constrained Probabilistic Distributions - https://arxiv.org/abs/2512.03081 - arXiv:2512.03081v2 Announce Type: replace-cross -Abstract: Machine learning (ML) has shown significant promise in studying complex geophysical dynamical systems, including turbulence and climate processes. Such systems often display sensitive dependence on initial conditions, reflected in positive Lyapunov exponents, where even small perturbations in short-term forecasts can lead to large deviations in long-term outcomes. Thus, meaningful inference requires not only accurate short-term predictions, but also consistency with the system's long-term attractor that is captured by the marginal distribution of state variables. Existing approaches attempt to address this challenge by incorporating spatial and temporal dependence, but these strategies become impractical when data are extremely sparse. In this work, we show that prior knowledge of marginal distributions offers valuable complementary information to short-term observations, motivating a distribution-informed learning framework. We introduce a calibration algorithm based on normalization and the Kernelized Stein Discrepancy (KSD) to enhance ML predictions. The method here employs KSD within a reproducing kernel Hilbert space to calibrate model outputs, improving their fidelity to known physical distributions. This not only sharpens pointwise predictions but also enforces consistency with non-local statistical structures rooted in physical principles. Through synthetic experiments-spanning offline climatological CO2 fluxes and online quasi-geostrophic flow simulations-we demonstrate the robustness and broad utility of the proposed framework. - oai:arXiv.org:2512.03081v2 - physics.ao-ph + Report on the Scoping Workshop on AI in Science Education Research 2025 + https://arxiv.org/abs/2511.14318 + arXiv:2511.14318v3 Announce Type: replace-cross +Abstract: This report summarizes the outcomes of a two-day international scoping workshop on the role of artificial intelligence (AI) in science education research. As AI rapidly reshapes scientific practice, classroom learning, and research methods, the field faces both new opportunities and significant challenges. The report clarifies key AI concepts to reduce ambiguity and reviews evidence of how AI influences scientific work, teaching practices, and disciplinary learning. It identifies how AI intersects with major areas of science education research, including curriculum development, assessment, epistemic cognition, inclusion, and teacher professional development, highlighting cases where AI can support human reasoning and cases where it may introduce risks to equity or validity. The report also examines how AI is transforming methodological approaches across quantitative, qualitative, ethnographic, and design-based traditions, giving rise to hybrid forms of analysis that combine human and computational strengths. To guide responsible integration, a systems-thinking heuristic is introduced that helps researchers consider stakeholder needs, potential risks, and ethical constraints. The report concludes with actionable recommendations for training, infrastructure, and standards, along with guidance for funders, policymakers, professional organizations, and academic departments. The goal is to support principled and methodologically sound use of AI in science education research. + oai:arXiv.org:2511.14318v3 + physics.ed-ph + cs.CY + Wed, 10 Dec 2025 00:00:00 -0500 + replace-cross + http://creativecommons.org/licenses/by-nc-nd/4.0/ + Marcus Kubsch, Marit Kastaun, Peter Wulff, Nicole Graulich, Moriah Ariely, Alexander Bergmann-Gering, Sebastian Gombert, Bor Gregorcic, Hendrik H\"artig, Benedikt Heuckmann, Andrea Horbach, Christina Krist, Gerd Kortemeyer, Ben M\"unch, Samuel Pazicni, Joshua M. Rosenberg, Sascha Schanze, Gena Sbeglia, Vidar Skogvoll, Christophe Speroni, Christoph Thyssen, Lars-Jochen Thoms, Brandon J. Yik, Xiaoming Zhai + + + Unifying Entropy Regularization in Optimal Control: From and Back to Classical Objectives via Iterated Soft Policies and Path Integral Solutions + https://arxiv.org/abs/2512.06109 + arXiv:2512.06109v2 Announce Type: replace-cross +Abstract: This paper develops a unified perspective on several stochastic optimal control formulations through the lens of Kullback-Leibler regularization. We propose a central problem that separates the KL penalties on policies and transitions, assigning them independent weights, thereby generalizing the standard trajectory-level KL-regularization commonly used in probabilistic and KL-regularized control. This generalized formulation acts as a generative structure allowing to recover various control problems. These include the classical Stochastic Optimal Control (SOC), Risk-Sensitive Optimal Control (RSOC), and their policy-based KL-regularized counterparts. The latter we refer to as soft-policy SOC and RSOC, facilitating alternative problems with tractable solutions. Beyond serving as regularized variants, we show that these soft-policy formulations majorize the original SOC and RSOC problem. This means that the regularized solution can be iterated to retrieve the original solution. Furthermore, we identify a structurally synchronized case of the risk-seeking soft-policy RSOC formulation, wherein the policy and transition KL-regularization weights coincide. Remarkably, this specific setting gives rise to several powerful properties such as a linear Bellman equation, path integral solution, and, compositionality, thereby extending these computationally favourable properties to a broad class of control problems. + oai:arXiv.org:2512.06109v2 + math.OC cs.LG - stat.ML - Tue, 09 Dec 2025 00:00:00 -0500 + cs.RO + cs.SY + eess.SY + Wed, 10 Dec 2025 00:00:00 -0500 replace-cross - http://arxiv.org/licenses/nonexclusive-distrib/1.0/ - Zhewen Hou, Jiajin Sun, Subashree Venkatasubramanian, Peter Jin, Shuolin Li, Tian Zheng + http://creativecommons.org/licenses/by/4.0/ + Ajinkya Bhole, Mohammad Mahmoudi Filabadi, Guillaume Crevecoeur, Tom Lefebvre