Daily Papers

Very high-resolution (VHR) satellite imagery has emerged as a powerful tool for monitoring marine animals on a large scale. However, existing deep learning-based whale detection methods usually require manually created, high-quality bounding box annotations, which are labor-intensive to produce. Moreover, existing studies often exclude ``uncertain whales'', individuals that have ambiguous appearances in satellite imagery, limiting the applicability of these models in real-world scenarios. To address these limitations, this study introduces an automated pipeline for detecting beluga whales and harp seals in VHR satellite imagery. The pipeline leverages point annotations and the Segment Anything Model (SAM) to generate precise bounding box annotations, which are used to train YOLOv8 for multiclass detection of certain whales, uncertain whales, and harp seals. Experimental results demonstrated that SAM-generated annotations significantly improved detection performance, achieving higher F_1-scores compared to traditional buffer-based annotations. YOLOv8 trained on SAM-labeled boxes achieved an overall F_1-score of 72.2% for whales overall and 70.3% for harp seals, with superior performance in dense scenes. The proposed approach not only reduces the manual effort required for annotation but also enhances the detection of uncertain whales, offering a more comprehensive solution for marine animal monitoring. This method holds great potential for extending to other species, habitats, and remote sensing platforms, as well as for estimating whale biometrics, thereby advancing ecological monitoring and conservation efforts. The codes for our label and detection pipeline are publicly available at http://github.com/voyagerxvoyagerx/beluga-seeker .

Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls requires two separate annotation efforts: binary presence labels for classification and precise temporal boundaries for localization. A binary label for a multi-minute recording can be assigned in seconds, but timestamping every call within it requires hours of expert effort. Providing both is infeasible at operational scale. We present DSMIL-LocNet, a weakly supervised multiple instance learning (MIL) framework that performs both classification and temporal localization using only recording-level presence/absence labels. Our dual-stream architecture integrates spectral and temporal features to process recordings of 2--30 minutes without the temporal compression that degrades existing CNN methods on long inputs. On the AcousticTrends BlueFinLibrary, DSMIL-LocNet achieves F1 scores of 0.88--0.91 on recordings of 300--1800s, where fully supervised CNN baselines degrade to 0.19--0.64. It also provides temporal localization that these baselines cannot produce without frame-level annotation. Code: https://github.com/Ragib-Amin-Nihal/DSMIL-Loc

This work presents the largest curation of Southern Resident Killer Whale (SRKW) acoustic data to date, also containing other marine mammals in their environment. We systematically search all available public archival hydrophone data within the SRKW habitat (over 30 years of audio data). The search consists of a weakly-supervised, positive-unlabelled, active learning strategy to identify all instances of marine mammals. The resulting transformer-based presence or absence classifiers outperform state-of-the-art classifiers on 3 of 4 expert-annotated datasets in terms of accuracy and energy efficiency. The fleet of WHISPER detection models range from 0.58 (0.48-0.67) AUROC with WHISPER-tiny to 0.77 (0.63-0.93) with WHISPER-large-v3. Our multiclass species classifier obtains a top-1 accuracy of 53.2\% (11 train classes, 4 test classes) and our ecotype classifier obtains a top-1 accuracy of 33.6\% (4 train classes, 5 test classes) on the DCLDE-2026 dataset. We yield 919 hours of SRKW data, 230 hours of Bigg's orca data, 1374 hours of orca data from unlabelled ecotypes, 1501 hours of humpback data, 88 hours of sea lion data, 246 hours of pacific white-sided dolphin data, and over 784 hours of unspecified marine mammal data. This SRKW dataset is larger than DCLDE-2026, Ocean Networks Canada, and OrcaSound combined. The curated species labels are available under CC-BY 4.0 license, and the corresponding audio data are available under the licenses of the original owners. The comprehensive nature of this dataset makes it suitable for unsupervised machine translation, habitat usage surveys, and conservation endeavours for this critically endangered ecotype.

Open-vocabulary object detection has benefited greatly from pretrained vision-language models, but is still limited by the amount of available detection training data. While detection training data can be expanded by using Web image-text pairs as weak supervision, this has not been done at scales comparable to image-level pretraining. Here, we scale up detection data with self-training, which uses an existing detector to generate pseudo-box annotations on image-text pairs. Major challenges in scaling self-training are the choice of label space, pseudo-annotation filtering, and training efficiency. We present the OWLv2 model and OWL-ST self-training recipe, which address these challenges. OWLv2 surpasses the performance of previous state-of-the-art open-vocabulary detectors already at comparable training scales (~10M examples). However, with OWL-ST, we can scale to over 1B examples, yielding further large improvement: With an L/14 architecture, OWL-ST improves AP on LVIS rare classes, for which the model has seen no human box annotations, from 31.2% to 44.6% (43% relative improvement). OWL-ST unlocks Web-scale training for open-world localization, similar to what has been seen for image classification and language modelling.

Single-source domain generalization (SDG) in object detection aims to develop a detector using only source domain data that generalizes well to unseen target domains. Existing methods are primarily CNN-based and improve robustness through data augmentation combined with feature alignment. However, these methods are limited, as augmentation is only effective when the synthetic distribution approximates that of unseen domains, thus failing to ensure generalization across diverse scenarios. While DEtection TRansformer (DETR) has shown strong generalization in domain adaptation due to global context modeling, its potential for SDG remains underexplored. To this end, we propose Style-Adaptive DEtection TRansformer (SA-DETR), a DETR-based detector tailored for SDG. SA-DETR introduces an online domain style adapter that projects the style representation of unseen domains into the source domain via a dynamic memory bank. This bank self-organizes into diverse style prototypes and is continuously updated under a test-time adaptation framework, enabling effective style rectification. Additionally, we design an object-aware contrastive learning module to promote extraction of domain-invariant features. By applying gating masks that constrain contrastive learning in both spatial and semantic dimensions, this module facilitates instance-level cross-domain contrast and enhances generalization. Extensive experiments across five distinct weather scenarios demonstrate that SA-DETR consistently outperforms existing methods in both detection accuracy and domain generalization capability.

Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to information integrity and public trust on social media platforms. While robust detection frameworks and diverse, large-scale datasets are essential to mitigate these risks, existing academic efforts remain limited in scope: current datasets lack the diversity, scale, and realism required for social media contexts, while detection methods struggle with generalization to unseen generative technologies. To bridge this gap, we introduce So-Fake-Set, a comprehensive social media-oriented dataset with over 2 million high-quality images, diverse generative sources, and photorealistic imagery synthesized using 35 state-of-the-art generative models. To rigorously evaluate cross-domain robustness, we establish a novel and large-scale (100K) out-of-domain benchmark (So-Fake-OOD) featuring synthetic imagery from commercial models explicitly excluded from the training distribution, creating a realistic testbed for evaluating real-world performance. Leveraging these resources, we present So-Fake-R1, an advanced vision-language framework that employs reinforcement learning for highly accurate forgery detection, precise localization, and explainable inference through interpretable visual rationales. Extensive experiments show that So-Fake-R1 outperforms the second-best method, with a 1.3% gain in detection accuracy and a 4.5% increase in localization IoU. By integrating a scalable dataset, a challenging OOD benchmark, and an advanced detection framework, this work establishes a new foundation for social media-centric forgery detection research. The code, models, and datasets will be released publicly.

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.

Molecular hydrogen (H_2) is by far the most abundant molecule in the Universe. However, due to the low emissivity of H_2, carbon monoxide (CO) is widely used instead to trace molecular gas in galaxies. The relative abundances of these molecules is expected to depend on both physical (e.g., density) and chemical (e.g., metal enrichment) properties of the gas, making direct measurements in diverse environments crucial. We present a systematic search for CO in absorption toward 34 stars behind H_2 gas in the Magellanic Clouds using the Hubble Space Telescope. We report the first two definitive detections of CO absorption in the Large Magellanic Cloud (LMC) and one in the Small Magellanic Cloud (SMC), along with stringent upper limits for the remaining sightlines. Non-detections of CO are consistent with models of low thermal pressures and/or low metallicities while detections at the lower metallicities of the Magellanic Clouds require higher thermal pressures, P_{rm th}=10^5-10^6,K,cm^{-3} than detections the Milky Way at similar N({rm H_2}). Notably, the high density derived from the rotational excitation of CO towards SK,143 in the SMC suggests full molecularization of CO in the absorbing cloud, with CO/H_2 = 8.3^{+2.0}_{-1.6}times10^{-5} consistent with the standard ratio (3.2times10^{-4}) measured in dense molecular gas in the Milky Way, scaled to the SMC's 0.2,Z_{odot} metallicity.

Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and then predict 3D attributes by neighboring features. However, only using local visual features is insufficient to understand the scene-level 3D spatial structures and ignores the long-range inter-object depth relations. In this paper, we introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR. We modify the vanilla transformer to be depth-aware and guide the whole detection process by contextual depth cues. Specifically, concurrent to the visual encoder that captures object appearances, we introduce to predict a foreground depth map, and specialize a depth encoder to extract non-local depth embeddings. Then, we formulate 3D object candidates as learnable queries and propose a depth-guided decoder to conduct object-scene depth interactions. In this way, each object query estimates its 3D attributes adaptively from the depth-guided regions on the image and is no longer constrained to local visual features. On KITTI benchmark with monocular images as input, MonoDETR achieves state-of-the-art performance and requires no extra dense depth annotations. Besides, our depth-guided modules can also be plug-and-play to enhance multi-view 3D object detectors on nuScenes dataset, demonstrating our superior generalization capacity. Code is available at https://github.com/ZrrSkywalker/MonoDETR.

We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets. To bridge the gap of vocabulary and annotation granularity, we first introduce a pre-trained text encoder to encode all the visual concepts in two tasks and learn a common semantic space for them. This gives us reasonably good results compared with the counterparts trained on segmentation task only. To further reconcile them, we locate two discrepancies: i) task discrepancy -- segmentation requires extracting masks for both foreground objects and background stuff, while detection merely cares about the former; ii) data discrepancy -- box and mask annotations are with different spatial granularity, and thus not directly interchangeable. To address these issues, we propose a decoupled decoding to reduce the interference between foreground/background and a conditioned mask decoding to assist in generating masks for given boxes. To this end, we develop a simple encoder-decoder model encompassing all three techniques and train it jointly on COCO and Objects365. After pre-training, our model exhibits competitive or stronger zero-shot transferability for both segmentation and detection. Specifically, OpenSeeD beats the state-of-the-art method for open-vocabulary instance and panoptic segmentation across 5 datasets, and outperforms previous work for open-vocabulary detection on LVIS and ODinW under similar settings. When transferred to specific tasks, our model achieves new SoTA for panoptic segmentation on COCO and ADE20K, and instance segmentation on ADE20K and Cityscapes. Finally, we note that OpenSeeD is the first to explore the potential of joint training on segmentation and detection, and hope it can be received as a strong baseline for developing a single model for both tasks in open world.

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance. While detection methods have been developed for the pre-training and Supervised Fine-Tuning stages, a critical research gap exists for the increasingly significant phase of Reinforcement Learning (RL) post-training. As RL post-training becomes pivotal for advancing LLM reasoning, the absence of specialized contamination detection methods in this paradigm presents a critical vulnerability. To address this, we conduct the first systematic study of data detection within RL post-training scenario and propose Self-Critique. Our method is motivated by a key observation: after RL phase, the output entropy distribution of LLMs tends to collapse into highly specific and sparse modes. Self-Critique probes for the underlying policy collapse, i.e., the model's convergence to a narrow reasoning path, which causes this entropy reduction. To facilitate this research, we also introduce RL-MIA, a benchmark constructed to simulate this specific contamination scenario. Extensive experiments show that Self-Critique significantly outperforms baseline methods across multiple models and contamination tasks, achieving an AUC improvement of up to 30%. Whereas existing methods are close to a random guess for RL-phase contamination, our method makes detection possible.

The proliferation of audio deepfakes poses a growing threat to trust in digital communications. While detection methods have advanced, attributing audio deepfakes to their source models remains an underexplored yet crucial challenge. In this paper we introduce LAVA (Layered Architecture for Voice Attribution), a hierarchical framework for audio deepfake detection and model recognition that leverages attention-enhanced latent representations extracted by a convolutional autoencoder trained solely on fake audio. Two specialized classifiers operate on these features: Audio Deepfake Attribution (ADA), which identifies the generation technology, and Audio Deepfake Model Recognition (ADMR), which recognize the specific generative model instance. To improve robustness under open-set conditions, we incorporate confidence-based rejection thresholds. Experiments on ASVspoof2021, FakeOrReal, and CodecFake show strong performance: the ADA classifier achieves F1-scores over 95% across all datasets, and the ADMR module reaches 96.31% macro F1 across six classes. Additional tests on unseen attacks from ASVpoof2019 LA and error propagation analysis confirm LAVA's robustness and reliability. The framework advances the field by introducing a supervised approach to deepfake attribution and model recognition under open-set conditions, validated on public benchmarks and accompanied by publicly released models and code. Models and code are available at https://www.github.com/adipiz99/lava-framework.

Maritime transportation is paramount in achieving global economic growth, entailing concurrent ecological obligations in sustainability and safeguarding endangered marine species, most notably preserving large whale populations. In this regard, the Automatic Identification System (AIS) data plays a significant role by offering real-time streaming data on vessel movement, allowing enhanced traffic monitoring. This study explores using AIS data to prevent vessel-to-whale collisions by forecasting long-term vessel trajectories from engineered AIS data sequences. For such a task, we have developed an encoder-decoder model architecture using Bidirectional Long Short-Term Memory Networks (Bi-LSTM) to predict the next 12 hours of vessel trajectories using 1 to 3 hours of AIS data as input. We feed the model with probabilistic features engineered from historical AIS data that refer to each trajectory's potential route and destination. The model then predicts the vessel's trajectory, considering these additional features by leveraging convolutional layers for spatial feature learning and a position-aware attention mechanism that increases the importance of recent timesteps of a sequence during temporal feature learning. The probabilistic features have an F1 Score of approximately 85% and 75% for each feature type, respectively, demonstrating their effectiveness in augmenting information to the neural network. We test our model on the Gulf of St. Lawrence, a region known to be the habitat of North Atlantic Right Whales (NARW). Our model achieved a high R2 score of over 98% using various techniques and features. It stands out among other approaches as it can make complex decisions during turnings and path selection. Our study highlights the potential of data engineering and trajectory forecasting models for marine life species preservation.

Marine visual understanding is essential for monitoring and protecting marine ecosystems, enabling automatic and scalable biological surveys. However, progress is hindered by limited training data and the lack of a systematic task formulation that aligns domain-specific marine challenges with well-defined computer vision tasks, thereby limiting effective model application. To address this gap, we present ORCA, a multi-modal benchmark for marine research comprising 14,647 images from 478 species, with 42,217 bounding box annotations and 22,321 expert-verified instance captions. The dataset provides fine-grained visual and textual annotations that capture morphology-oriented attributes across diverse marine species. To catalyze methodological advances, we evaluate 18 state-of-the-art models on three tasks: object detection (closed-set and open-vocabulary), instance captioning, and visual grounding. Results highlight key challenges, including species diversity, morphological overlap, and specialized domain demands, underscoring the difficulty of marine understanding. ORCA thus establishes a comprehensive benchmark to advance research in marine domain. Project Page: http://orca.hkustvgd.com/.

Fish tracking is a key technology for obtaining movement trajectories and identifying abnormal behavior. However, it faces considerable challenges, including occlusion, multi-scale tracking, and fish deformation. Notably, extant reviews have focused more on behavioral analysis rather than providing a comprehensive overview of computer vision-based fish tracking approaches. This paper presents a comprehensive review of the advancements of fish tracking technologies over the past seven years (2017-2023). It explores diverse fish tracking techniques with an emphasis on fundamental localization and tracking methods. Auxiliary plugins commonly integrated into fish tracking systems, such as underwater image enhancement and re-identification, are also examined. Additionally, this paper summarizes open-source datasets, evaluation metrics, challenges, and applications in fish tracking research. Finally, a comprehensive discussion offers insights and future directions for vision-based fish tracking techniques. We hope that our work could provide a partial reference in the development of fish tracking algorithms.

Accurate fish detection in underwater imagery is essential for ecological monitoring, aquaculture automation, and robotic perception. However, practical deployment remains limited by fragmented datasets, heterogeneous imaging conditions, and inconsistent evaluation protocols. To address these gaps, we present FishDet-M, the largest unified benchmark for fish detection, comprising 13 publicly available datasets spanning diverse aquatic environments including marine, brackish, occluded, and aquarium scenes. All data are harmonized using COCO-style annotations with both bounding boxes and segmentation masks, enabling consistent and scalable cross-domain evaluation. We systematically benchmark 28 contemporary object detection models, covering the YOLOv8 to YOLOv12 series, R-CNN based detectors, and DETR based models. Evaluations are conducted using standard metrics including mAP, mAP@50, and mAP@75, along with scale-specific analyses (AP_S, AP_M, AP_L) and inference profiling in terms of latency and parameter count. The results highlight the varying detection performance across models trained on FishDet-M, as well as the trade-off between accuracy and efficiency across models of different architectures. To support adaptive deployment, we introduce a CLIP-based model selection framework that leverages vision-language alignment to dynamically identify the most semantically appropriate detector for each input image. This zero-shot selection strategy achieves high performance without requiring ensemble computation, offering a scalable solution for real-time applications. FishDet-M establishes a standardized and reproducible platform for evaluating object detection in complex aquatic scenes. All datasets, pretrained models, and evaluation tools are publicly available to facilitate future research in underwater computer vision and intelligent marine systems.

Ocean scientists have been collecting visual data to study marine organisms for decades. These images and videos are extremely valuable both for basic science and environmental monitoring tasks. There are tools for automatically processing these data, but none that are capable of handling the extreme variability in sample populations, image quality, and habitat characteristics that are common in visual sampling of the ocean. Such distribution shifts can occur over very short physical distances and in narrow time windows. Creating models that are able to recognize when an image or video sequence contains a new organism, an unusual collection of animals, or is otherwise out-of-sample is critical to fully leverage visual data in the ocean. The FathomNet2023 competition dataset presents a realistic scenario where the set of animals in the target data differs from the training data. The challenge is both to identify the organisms in a target image and assess whether it is out-of-sample.

As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has been made in multimodal LLMs, with many datasets created to evaluate LLMs with vision abilities. However, none of those datasets focuses solely on marine mammals, which are indispensable for ecological equilibrium. In this work, we build a benchmark dataset with 1,423 images of 65 kinds of marine mammals, where each animal is uniquely classified into different levels of class, ranging from species-level to medium-level to group-level. Moreover, we evaluate several approaches for classifying these marine mammals: (1) machine learning (ML) algorithms using embeddings provided by neural networks, (2) influential pre-trained neural networks, (3) zero-shot models: CLIP and LLMs, and (4) a novel LLM-based multi-agent system (MAS). The results demonstrate the strengths of traditional models and LLMs in different aspects, and the MAS can further improve the classification performance. The dataset is available on GitHub: https://github.com/yeyimilk/LLM-Vision-Marine-Animals.git.

Camera-based electronic monitoring (EM) systems are increasingly being deployed onboard commercial fishing vessels to collect essential data for fisheries management and regulation. These systems generate large quantities of video data which must be reviewed on land by human experts. Computer vision can assist this process by automatically detecting and classifying fish species, however the lack of existing public data in this domain has hindered progress. To address this, we present the Fishnet Open Images Database, a large dataset of EM imagery for fish detection and fine-grained categorization onboard commercial fishing vessels. The dataset consists of 86,029 images containing 34 object classes, making it the largest and most diverse public dataset of fisheries EM imagery to-date. It includes many of the characteristic challenges of EM data: visual similarity between species, skewed class distributions, harsh weather conditions, and chaotic crew activity. We evaluate the performance of existing detection and classification algorithms and demonstrate that the dataset can serve as a challenging benchmark for development of computer vision algorithms in fisheries. The dataset is available at https://www.fishnet.ai/.

Benchmarking multi-object tracking and object detection model performance is an essential step in machine learning model development, as it allows researchers to evaluate model detection and tracker performance on human-generated 'test' data, facilitating consistent comparisons between models and trackers and aiding performance optimization. In this study, a novel benchmark video dataset was developed and used to assess the performance of several Monterey Bay Aquarium Research Institute object detection models and a FathomNet single-class object detection model together with several trackers. The dataset consists of four video sequences representing midwater and benthic deep-sea habitats. Performance was evaluated using Higher Order Tracking Accuracy, a metric that balances detection, localization, and association accuracy. To the best of our knowledge, this is the first publicly available benchmark for multi-object tracking in deep-sea video footage. We provide the benchmark data, a clearly documented workflow for generating additional benchmark videos, as well as example Python notebooks for computing metrics.

Retrieval-Augmented Generation (RAG) systems remain susceptible to hallucinations despite grounding in retrieved evidence. While current detection methods leverage embedding similarity and natural language inference (NLI), their reliability in safety-critical settings remains unproven. We apply conformal prediction to RAG hallucination detection, transforming heuristic scores into decision sets with finite-sample coverage guarantees (1-alpha). Using calibration sets of n=600, we demonstrate a fundamental dichotomy: on synthetic hallucinations (Natural Questions), embedding methods achieve 95% coverage with 0% False Positive Rate (FPR). However, on real hallucinations from RLHF-aligned models (HaluEval), the same methods fail catastrophically, yielding 100% FPR at target coverage. We analyze this failure through the lens of distributional tails, showing that while NLI models achieve acceptable AUC (0.81), the "hardest" hallucinations are semantically indistinguishable from faithful responses, forcing conformal thresholds to reject nearly all valid outputs. Crucially, GPT-4 as a judge achieves 7% FPR (95% CI:[3.4%, 13.7%]) on the same data, proving the task is solvable via reasoning but opaque to surface-level semantics--a phenomenon we term the "Semantic Illusion."

While highlight detection for long-form videos is of great practical importance, most existing methods remain limited to short-form content, largely due to the absence of a suitable benchmark. To bridge this gap, we introduce SVHighlights, to the best of our knowledge, the first benchmark for highlight detection in extremely long sports videos, each exceeding one hour in duration, across multiple sports categories. SVHighlights is constructed from pairs of full-length sports videos and their corresponding official highlight videos using a dataset generation pipeline, enabling scalable label generation without conventional per-clip saliency annotation. The benchmark comprises 320 videos with an average duration of 2.00 hours and a total of 640.18 hours, substantially exceeding previous datasets. Existing methods also face fundamental challenges on long videos: models trained on short clips fail to generalize to hour-long content, and their clip-level scoring lacks the broader context needed to identify highlights. To address this and provide a strong baseline, we present TF-SELECTOR, a training-free segment-based approach that divides each video into context-aware segments by merging adjacent shots sharing the same semantic content, and predicts segment-level saliency scores using a large language model with multimodal inputs including visual captions, transcripts, and audio volume. Experiments demonstrate that TF-SELECTOR achieves superior performance across most metrics compared to Video Temporal Grounding (VTG)-tuned baselines, with improvements of +3.12 in HIT@1, +4.06 in HIT@K, and +2.95 in IoU. These results establish SVHighlights as a challenging testbed for long-form highlight detection and demonstrate that a simple segment-based strategy can effectively scale to hour-long videos.

Accurate, up-to-date High-Definition (HD) maps are critical for urban planning, infrastructure monitoring, and autonomous navigation. However, these maps quickly become outdated as environments evolve, creating a need for robust methods that not only detect changes but also incorporate them into updated 3D representations. While change detection techniques have advanced significantly, there remains a clear gap between detecting changes and actually updating 3D maps, particularly when relying on 2D image-based change detection. To address this gap, we introduce SceneEdited, the first city-scale dataset explicitly designed to support research on HD map maintenance through 3D point cloud updating. SceneEdited contains over 800 up-to-date scenes covering 73 km of driving and approximate 3 km^2 of urban area, with more than 23,000 synthesized object changes created both manually and automatically across 2000+ out-of-date versions, simulating realistic urban modifications such as missing roadside infrastructure, buildings, overpasses, and utility poles. Each scene includes calibrated RGB images, LiDAR scans, and detailed change masks for training and evaluation. We also provide baseline methods using a foundational image-based structure-from-motion pipeline for updating outdated scenes, as well as a comprehensive toolkit supporting scalability, trackability, and portability for future dataset expansion and unification of out-of-date object annotations. Both the dataset and the toolkit are publicly available at https://github.com/ChadLin9596/ScenePoint-ETK, establising a standardized benchmark for 3D map updating research.

Recent advances in generative artificial intelligence have enabled the creation of highly realistic image forgeries, raising significant concerns about digital media authenticity. While existing detection methods demonstrate promising results on benchmark datasets, they face critical limitations in real-world applications. First, existing detectors typically fail to detect semantic inconsistencies with the person's identity, such as implausible behaviors or incompatible environmental contexts in given images. Second, these methods rely heavily on low-level visual cues, making them effective for known forgeries but less reliable against new or unseen manipulation techniques. To address these challenges, we present a novel personalized vision-language model (VLM) that integrates low-level visual artifact analysis and high-level semantic inconsistency detection. Unlike previous VLM-based methods, our approach avoids resource-intensive supervised fine-tuning that often struggles to preserve distinct identity characteristics. Instead, we employ a lightweight method that dynamically encodes identity-specific information into specialized identifier tokens. This design enables the model to learn distinct identity characteristics while maintaining robust generalization capabilities. We further enhance detection capabilities through a lightweight detection adapter that extracts fine-grained information from shallow features of the vision encoder, preserving critical low-level evidence. Comprehensive experiments demonstrate that our approach achieves 94.25% accuracy and 94.08% F1 score, outperforming both traditional forgery detectors and general VLMs while requiring only 10 extra tokens.

To enable self-driving vehicles accurate detection and tracking of surrounding objects is essential. While Light Detection and Ranging (LiDAR) sensors have set the benchmark for high-performance systems, the appeal of camera-only solutions lies in their cost-effectiveness. Notably, despite the prevalent use of Radio Detection and Ranging (RADAR) sensors in automotive systems, their potential in 3D detection and tracking has been largely disregarded due to data sparsity and measurement noise. As a recent development, the combination of RADARs and cameras is emerging as a promising solution. This paper presents Camera-RADAR 3D Detection and Tracking (CR3DT), a camera-RADAR fusion model for 3D object detection, and Multi-Object Tracking (MOT). Building upon the foundations of the State-of-the-Art (SotA) camera-only BEVDet architecture, CR3DT demonstrates substantial improvements in both detection and tracking capabilities, by incorporating the spatial and velocity information of the RADAR sensor. Experimental results demonstrate an absolute improvement in detection performance of 5.3% in mean Average Precision (mAP) and a 14.9% increase in Average Multi-Object Tracking Accuracy (AMOTA) on the nuScenes dataset when leveraging both modalities. CR3DT bridges the gap between high-performance and cost-effective perception systems in autonomous driving, by capitalizing on the ubiquitous presence of RADAR in automotive applications. The code is available at: https://github.com/ETH-PBL/CR3DT.

Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues. While automated systems can flag hate speech with high accuracy, they often function as "black boxes" that fail to provide the granular, interpretable evidence, such as precise timestamps and target identities, required for effective human-in-the-loop moderation. In this work, we introduce TANDEM, a unified framework that transforms audio-visual hate detection from a binary classification task into a structured reasoning problem. Our approach employs a novel tandem reinforcement learning strategy where vision-language and audio-language models optimize each other through self-constrained cross-modal context, stabilizing reasoning over extended temporal sequences without requiring dense frame-level supervision. Experiments across three benchmark datasets demonstrate that TANDEM significantly outperforms zero-shot and context-augmented baselines, achieving 0.73 F1 in target identification on HateMM (a 30% improvement over state-of-the-art) while maintaining precise temporal grounding. We further observe that while binary detection is robust, differentiating between offensive and hateful content remains challenging in multi-class settings due to inherent label ambiguity and dataset imbalance. More broadly, our findings suggest that structured, interpretable alignment is achievable even in complex multimodal settings, offering a blueprint for the next generation of transparent and actionable online safety moderation tools.

Methane is a potent greenhouse gas and a major driver of climate change, making its timely detection critical for effective mitigation. Machine learning (ML) deployed onboard satellites can enable rapid detection while reducing downlink costs, supporting faster response systems. Conventional methane detection methods often rely on image processing techniques, such as orthorectification to correct geometric distortions and matched filters to enhance plume signals. We introduce a novel approach that bypasses these preprocessing steps by using unorthorectified data (UnorthoDOS). We find that ML models trained on this dataset achieve performance comparable to those trained on orthorectified data. Moreover, we also train models on an orthorectified dataset, showing that they can outperform the matched filter baseline (mag1c). We release model checkpoints and two ML-ready datasets comprising orthorectified and unorthorectified hyperspectral images from the Earth Surface Mineral Dust Source Investigation (EMIT) sensor at https://huggingface.co/datasets/SpaceML/UnorthoDOS , along with code at https://github.com/spaceml-org/plume-hunter.

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object regions leads to a constrained sample pool for optimization, and the paucity of discriminative information further aggravates the recognition. To alleviate the aforementioned issues, we propose CFINet, a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. Firstly, we introduce Coarse-to-fine RPN (CRPN) to ensure sufficient and high-quality proposals for small objects through the dynamic anchor selection strategy and cascade regression. Then, we equip the conventional detection head with a Feature Imitation (FI) branch to facilitate the region representations of size-limited instances that perplex the model in an imitation manner. Moreover, an auxiliary imitation loss following supervised contrastive learning paradigm is devised to optimize this branch. When integrated with Faster RCNN, CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A, underscoring its superiority over baseline detector and other mainstream detection approaches.

Autonomous driving has now made great strides thanks to artificial intelligence, and numerous advanced methods have been proposed for vehicle end target detection, including single sensor or multi sensor detection methods. However, the complexity and diversity of real traffic situations necessitate an examination of how to use these methods in real road conditions. In this paper, we propose RMMDet, a road-side multitype and multigroup sensor detection system for autonomous driving. We use a ROS-based virtual environment to simulate real-world conditions, in particular the physical and functional construction of the sensors. Then we implement muti-type sensor detection and multi-group sensors fusion in this environment, including camera-radar and camera-lidar detection based on result-level fusion. We produce local datasets and real sand table field, and conduct various experiments. Furthermore, we link a multi-agent collaborative scheduling system to the fusion detection system. Hence, the whole roadside detection system is formed by roadside perception, fusion detection, and scheduling planning. Through the experiments, it can be seen that RMMDet system we built plays an important role in vehicle-road collaboration and its optimization. The code and supplementary materials can be found at: https://github.com/OrangeSodahub/RMMDet

Identifying relations between objects is central to understanding the scene. While several works have been proposed for relation modeling in the image domain, there have been many constraints in the video domain due to challenging dynamics of spatio-temporal interactions (e.g., between which objects are there an interaction? when do relations start and end?). To date, two representative methods have been proposed to tackle Video Visual Relation Detection (VidVRD): segment-based and window-based. We first point out limitations of these methods and propose a novel approach named Temporal Span Proposal Network (TSPN). TSPN tells what to look: it sparsifies relation search space by scoring relationness of object pair, i.e., measuring how probable a relation exist. TSPN tells when to look: it simultaneously predicts start-end timestamps (i.e., temporal spans) and categories of the all possible relations by utilizing full video context. These two designs enable a win-win scenario: it accelerates training by 2X or more than existing methods and achieves competitive performance on two VidVRD benchmarks (ImageNet-VidVDR and VidOR). Moreover, comprehensive ablative experiments demonstrate the effectiveness of our approach. Codes are available at https://github.com/sangminwoo/Temporal-Span-Proposal-Network-VidVRD.

Monitoring animal behavior can facilitate conservation efforts by providing key insights into wildlife health, population status, and ecosystem function. Automatic recognition of animals and their behaviors is critical for capitalizing on the large unlabeled datasets generated by modern video devices and for accelerating monitoring efforts at scale. However, the development of automated recognition systems is currently hindered by a lack of appropriately labeled datasets. Existing video datasets 1) do not classify animals according to established biological taxonomies; 2) are too small to facilitate large-scale behavioral studies and are often limited to a single species; and 3) do not feature temporally localized annotations and therefore do not facilitate localization of targeted behaviors within longer video sequences. Thus, we propose MammalNet, a new large-scale animal behavior dataset with taxonomy-guided annotations of mammals and their common behaviors. MammalNet contains over 18K videos totaling 539 hours, which is ~10 times larger than the largest existing animal behavior dataset. It covers 17 orders, 69 families, and 173 mammal categories for animal categorization and captures 12 high-level animal behaviors that received focus in previous animal behavior studies. We establish three benchmarks on MammalNet: standard animal and behavior recognition, compositional low-shot animal and behavior recognition, and behavior detection. Our dataset and code have been made available at: https://mammal-net.github.io.

The rapid development of AI-generated content (AIGC) technology has led to the misuse of highly realistic AI-generated images (AIGI) in spreading misinformation, posing a threat to public information security. Although existing AIGI detection techniques are generally effective, they face two issues: 1) a lack of human-verifiable explanations, and 2) a lack of generalization in the latest generation technology. To address these issues, we introduce a large-scale and comprehensive dataset, Holmes-Set, which includes the Holmes-SFTSet, an instruction-tuning dataset with explanations on whether images are AI-generated, and the Holmes-DPOSet, a human-aligned preference dataset. Our work introduces an efficient data annotation method called the Multi-Expert Jury, enhancing data generation through structured MLLM explanations and quality control via cross-model evaluation, expert defect filtering, and human preference modification. In addition, we propose Holmes Pipeline, a meticulously designed three-stage training framework comprising visual expert pre-training, supervised fine-tuning, and direct preference optimization. Holmes Pipeline adapts multimodal large language models (MLLMs) for AIGI detection while generating human-verifiable and human-aligned explanations, ultimately yielding our model AIGI-Holmes. During the inference stage, we introduce a collaborative decoding strategy that integrates the model perception of the visual expert with the semantic reasoning of MLLMs, further enhancing the generalization capabilities. Extensive experiments on three benchmarks validate the effectiveness of our AIGI-Holmes.

An automatic table recognition method for interpretation of tabular data in document images majorly involves solving two problems of table detection and table structure recognition. The prior work involved solving both problems independently using two separate approaches. More recent works signify the use of deep learning-based solutions while also attempting to design an end to end solution. In this paper, we present an improved deep learning-based end to end approach for solving both problems of table detection and structure recognition using a single Convolution Neural Network (CNN) model. We propose CascadeTabNet: a Cascade mask Region-based CNN High-Resolution Network (Cascade mask R-CNN HRNet) based model that detects the regions of tables and recognizes the structural body cells from the detected tables at the same time. We evaluate our results on ICDAR 2013, ICDAR 2019 and TableBank public datasets. We achieved 3rd rank in ICDAR 2019 post-competition results for table detection while attaining the best accuracy results for the ICDAR 2013 and TableBank dataset. We also attain the highest accuracy results on the ICDAR 2019 table structure recognition dataset. Additionally, we demonstrate effective transfer learning and image augmentation techniques that enable CNNs to achieve very accurate table detection results. Code and dataset has been made available at: https://github.com/DevashishPrasad/CascadeTabNet

Anomaly detection in cloud environments remains both critical and challenging. Existing context-level benchmarks typically focus on either metrics or logs and often lack reliable annotation, while most detection methods emphasize point anomalies within a single modality, overlooking contextual signals and limiting real-world applicability. Constructing a benchmark for context anomalies that combines metrics and logs is inherently difficult: reproducing anomalous scenarios on real servers is often infeasible or potentially harmful, while generating synthetic data introduces the additional challenge of maintaining cross-modal consistency. We introduce CloudAnoBench, a large-scale benchmark for context anomalies in cloud environments, comprising 28 anomalous scenarios and 16 deceptive normal scenarios, with 1,252 labeled cases and roughly 200,000 log and metric entries. Compared with prior benchmarks, CloudAnoBench exhibits higher ambiguity and greater difficulty, on which both prior machine learning methods and vanilla LLM prompting perform poorly. To demonstrate its utility, we further propose CloudAnoAgent, an LLM-based agent enhanced by symbolic verification that integrates metrics and logs. This agent system achieves substantial improvements in both anomaly detection and scenario identification on CloudAnoBench, and shows strong generalization to existing datasets. Together, CloudAnoBench and CloudAnoAgent lay the groundwork for advancing context-aware anomaly detection in cloud systems. Project Page: https://jayzou3773.github.io/cloudanobench-agent/

The system log generated in a computer system refers to large-scale data that are collected simultaneously and used as the basic data for determining errors, intrusion and abnormal behaviors. The aim of system log anomaly detection is to promptly identify anomalies while minimizing human intervention, which is a critical problem in the industry. Previous studies performed anomaly detection through algorithms after converting various forms of log data into a standardized template using a parser. Particularly, a template corresponding to a specific event should be defined in advance for all the log data using which the information within the log key may get lost. In this study, we propose LAnoBERT, a parser free system log anomaly detection method that uses the BERT model, exhibiting excellent natural language processing performance. The proposed method, LAnoBERT, learns the model through masked language modeling, which is a BERT-based pre-training method, and proceeds with unsupervised learning-based anomaly detection using the masked language modeling loss function per log key during the test process. In addition, we also propose an efficient inference process to establish a practically applicable pipeline to the actual system. Experiments on three well-known log datasets, i.e., HDFS, BGL, and Thunderbird, show that not only did LAnoBERT yield a higher anomaly detection performance compared to unsupervised learning-based benchmark models, but also it resulted in a comparable performance with supervised learning-based benchmark models.

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character injection methods and algorithmic Adversarial Machine Learning (AML) evasion techniques. Through testing against six prominent protection systems, including Microsoft's Azure Prompt Shield and Meta's Prompt Guard, we show that both methods can be used to evade detection while maintaining adversarial utility achieving in some instances up to 100% evasion success. Furthermore, we demonstrate that adversaries can enhance Attack Success Rates (ASR) against black-box targets by leveraging word importance ranking computed by offline white-box models. Our findings reveal vulnerabilities within current LLM protection mechanisms and highlight the need for more robust guardrail systems.

Spoken dialogue models have significantly advanced intelligent human-computer interaction, yet they lack a plug-and-play full-duplex prediction module for semantic endpoint detection, hindering seamless audio interactions. In this paper, we introduce Phoenix-VAD, an LLM-based model that enables streaming semantic endpoint detection. Specifically, Phoenix-VAD leverages the semantic comprehension capability of the LLM and a sliding window training strategy to achieve reliable semantic endpoint detection while supporting streaming inference. Experiments on both semantically complete and incomplete speech scenarios indicate that Phoenix-VAD achieves excellent and competitive performance. Furthermore, this design enables the full-duplex prediction module to be optimized independently of the dialogue model, providing more reliable and flexible support for next-generation human-computer interaction.

Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Nonetheless, current models still produce closed-domain hallucinations and generate content that is unsupported by the retrieved context. Current detection approaches typically treat hallucination as a post-hoc problem, relying on black-box consistency checks or probes over frozen internal representations. In this work, we demonstrate that hallucination detection based on internal state representation can also serve as a direct training signal. We introduce RAGognize, a dataset of naturally occurring closed-domain hallucinations with token-level annotations, and RAGognizer, a hallucination-aware fine-tuning approach that integrates a lightweight detection head into an LLM, allowing for the joint optimization of language modeling and hallucination detection. This joint objective forces the model to improve the separability of its internal states regarding hallucinations while simultaneously learning to generate well-formed and meaningful responses. Across multiple benchmarks, RAGognizer achieves state-of-the-art token-level hallucination detection while substantially reducing hallucination rates during generation, without degrading language quality or relevance.

Visual anomaly detection has been widely used in industrial inspection and medical diagnosis. Existing methods typically demand substantial training samples, limiting their utility in zero-/few-shot scenarios. While recent efforts have leveraged CLIP's zero-shot recognition capability for this task, they often ignore optimizing visual features to focus on local anomalies, reducing their efficacy. In this work, we propose AF-CLIP (Anomaly-Focused CLIP) by dramatically enhancing its visual representations to focus on local defects. Our approach introduces a lightweight adapter that emphasizes anomaly-relevant patterns in visual features, simultaneously optimizing both class-level features for image classification and patch-level features for precise localization. To capture anomalies of different sizes and improve detection accuracy, prior to the adapter, we develop a multi-scale spatial aggregation mechanism to effectively consolidate neighborhood context. Complementing these visual enhancements, we design learnable textual prompts that generically characterize normal and abnormal states. After optimization on auxiliary datasets using a composite objective function, AF-CLIP demonstrates strong zero-shot detection capability. Our method is also extended to few-shot scenarios by extra memory banks. Experimental results across diverse industrial and medical datasets demonstrate the effectiveness and generalization of our proposed method. Code is available at https://github.com/Faustinaqq/AF-CLIP.

Existing deepfake detection techniques struggle to keep-up with the ever-evolving novel, unseen forgeries methods. This limitation stems from their reliance on statistical artifacts learned during training, which are often tied to specific generation processes that may not be representative of samples from new, unseen deepfake generation methods encountered at test time. We propose that incorporating language guidance can improve deepfake detection generalization by integrating human-like commonsense reasoning -- such as recognizing logical inconsistencies and perceptual anomalies -- alongside statistical cues. To achieve this, we train an expert deepfake vision encoder by combining discriminative classification with image-text contrastive learning, where the text is generated by generalist MLLMs using few-shot prompting. This allows the encoder to extract both language-describable, commonsense deepfake artifacts and statistical forgery artifacts from pixel-level distributions. To further enhance robustness, we integrate data uncertainty learning into vision-language contrastive learning, mitigating noise in image-text supervision. Our expert vision encoder seamlessly interfaces with an LLM, further enabling more generalized and interpretable deepfake detection while also boosting accuracy. The resulting framework, AuthGuard, achieves state-of-the-art deepfake detection accuracy in both in-distribution and out-of-distribution settings, achieving AUC gains of 6.15% on the DFDC dataset and 16.68% on the DF40 dataset. Additionally, AuthGuard significantly enhances deepfake reasoning, improving performance by 24.69% on the DDVQA dataset.

This study explores the application of anomaly detection (AD) methods in imbalanced learning tasks, focusing on fraud detection using real online credit card payment data. We assess the performance of several recent AD methods and compare their effectiveness against standard supervised learning methods. Offering evidence of distribution shift within our dataset, we analyze its impact on the tested models' performances. Our findings reveal that LightGBM exhibits significantly superior performance across all evaluated metrics but suffers more from distribution shifts than AD methods. Furthermore, our investigation reveals that LightGBM also captures the majority of frauds detected by AD methods. This observation challenges the potential benefits of ensemble methods to combine supervised, and AD approaches to enhance performance. In summary, this research provides practical insights into the utility of these techniques in real-world scenarios, showing LightGBM's superiority in fraud detection while highlighting challenges related to distribution shifts.

The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important. In this paper, we offer insights and analyses of recent state-of-the-art out-of-distribution (OOD) detection methods - extremely simple activation shaping (ASH). We demonstrate that activation pruning has a detrimental effect on OOD detection, while activation scaling enhances it. Moreover, we propose SCALE, a simple yet effective post-hoc network enhancement method for OOD detection, which attains state-of-the-art OOD detection performance without compromising in-distribution (ID) accuracy. By integrating scaling concepts into the training process to capture a sample's ID characteristics, we propose Intermediate Tensor SHaping (ISH), a lightweight method for training time OOD detection enhancement. We achieve AUROC scores of +1.85\% for near-OOD and +0.74\% for far-OOD datasets on the OpenOOD v1.5 ImageNet-1K benchmark. Our code and models are available at https://github.com/kai422/SCALE.

Efficiently exploiting multi-modal inputs for accurate RGB-D saliency detection is a topic of high interest. Most existing works leverage cross-modal interactions to fuse the two streams of RGB-D for intermediate features' enhancement. In this process, a practical aspect of the low quality of the available depths has not been fully considered yet. In this work, we aim for RGB-D saliency detection that is robust to the low-quality depths which primarily appear in two forms: inaccuracy due to noise and the misalignment to RGB. To this end, we propose a robust RGB-D fusion method that benefits from (1) layer-wise, and (2) trident spatial, attention mechanisms. On the one hand, layer-wise attention (LWA) learns the trade-off between early and late fusion of RGB and depth features, depending upon the depth accuracy. On the other hand, trident spatial attention (TSA) aggregates the features from a wider spatial context to address the depth misalignment problem. The proposed LWA and TSA mechanisms allow us to efficiently exploit the multi-modal inputs for saliency detection while being robust against low-quality depths. Our experiments on five benchmark datasets demonstrate that the proposed fusion method performs consistently better than the state-of-the-art fusion alternatives.

Singing voice detection (SVD), to recognize vocal parts in the song, is an essential task in music information retrieval (MIR). The task remains challenging since singing voice varies and intertwines with the accompaniment music, especially for some complicated polyphonic music such as choral music recordings. To address this problem, we investigate singing voice detection while discarding the interference from the accompaniment. The proposed SVD has two steps: i. The singing voice separation (SVS) technique is first utilized to filter out the singing voice's potential part coarsely. ii. Upon the continuity of vocal in the time domain, Long-term Recurrent Convolutional Networks (LRCN) is used to learn compositional features. Moreover, to eliminate the outliers, we choose to use a median filter for time-domain smoothing. Experimental results show that the proposed method outperforms the existing state-of-the-art works on two public datasets, the Jamendo Corpus and the RWC pop dataset.

Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled videos can be collected at relatively low cost. In this paper, we address the unsupervised learning problem in the context of detecting the main foreground objects in single images. We train a student deep network to predict the output of a teacher pathway that performs unsupervised object discovery in videos or large image collections. Our approach is different from published methods on unsupervised object discovery. We move the unsupervised learning phase during training time, then at test time we apply the standard feed-forward processing along the student pathway. This strategy has the benefit of allowing increased generalization possibilities during training, while remaining fast at testing. Our unsupervised learning algorithm can run over several generations of student-teacher training. Thus, a group of student networks trained in the first generation collectively create the teacher at the next generation. In experiments our method achieves top results on three current datasets for object discovery in video, unsupervised image segmentation and saliency detection. At test time the proposed system is fast, being one to two orders of magnitude faster than published unsupervised methods.

DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at https://github.com/fundamentalvision/Deformable-DETR.

As state-of-the-art language models continue to improve, the need for robust detection of machine-generated text becomes increasingly critical. However, current state-of-the-art machine text detectors struggle to adapt to new unseen domains and generative models. In this paper we present DoGEN (Domain Gating Ensemble Networks), a technique that allows detectors to adapt to unseen domains by ensembling a set of domain expert detector models using weights from a domain classifier. We test DoGEN on a wide variety of domains from leading benchmarks and find that it achieves state-of-the-art performance on in-domain detection while outperforming models twice its size on out-of-domain detection. We release our code and trained models to assist in future research in domain-adaptive AI detection.

As litter pollution continues to rise globally, developing automated tools capable of detecting litter effectively remains a significant challenge. This study presents a novel approach that combines, for the first time, privileged information with deep learning object detection to improve litter detection while maintaining model efficiency. We evaluate our method across five widely used object detection models, addressing challenges such as detecting small litter and objects partially obscured by grass or stones. In addition to this, a key contribution of our work can also be attributed to formulating a means of encoding bounding box information as a binary mask, which can be fed to the detection model to refine detection guidance. Through experiments on both within-dataset evaluation on the renowned SODA dataset and cross-dataset evaluation on the BDW and UAVVaste litter detection datasets, we demonstrate consistent performance improvements across all models. Our approach not only bolsters detection accuracy within the training sets but also generalises well to other litter detection contexts. Crucially, these improvements are achieved without increasing model complexity or adding extra layers, ensuring computational efficiency and scalability. Our results suggest that this methodology offers a practical solution for litter detection, balancing accuracy and efficiency in real-world applications.

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs). Our proposed method employs a two-stream network structure, with one stream focusing on the temporal dimension and the other primarily on the spatial dimension. By leveraging the learned knowledge from pre-trained VLMs and incorporating natural motion priors from raw videos, our model learns prompt embeddings that are aligned with spatio-temporal regions of videos (e.g., patches of individual frames) for identify specific local regions of anomalies, enabling accurate video anomaly detection while mitigating the influence of background information. Without relying on detailed spatio-temporal annotations or auxiliary object detection/tracking, our method achieves state-of-the-art performance on three public benchmarks for the WSVADL task.

Occlusion is a major challenge for LiDAR-based object detection methods. This challenge becomes safety-critical in urban traffic where the ego vehicle must have reliable object detection to avoid collision while its field of view is severely reduced due to the obstruction posed by a large number of road users. Collaborative perception via Vehicle-to-Everything (V2X) communication, which leverages the diverse perspective thanks to the presence at multiple locations of connected agents to form a complete scene representation, is an appealing solution. State-of-the-art V2X methods resolve the performance-bandwidth tradeoff using a mid-collaboration approach where the Bird-Eye View images of point clouds are exchanged so that the bandwidth consumption is lower than communicating point clouds as in early collaboration, and the detection performance is higher than late collaboration, which fuses agents' output, thanks to a deeper interaction among connected agents. While achieving strong performance, the real-world deployment of most mid-collaboration approaches is hindered by their overly complicated architectures, involving learnable collaboration graphs and autoencoder-based compressor/ decompressor, and unrealistic assumptions about inter-agent synchronization. In this work, we devise a simple yet effective collaboration method that achieves a better bandwidth-performance tradeoff than prior state-of-the-art methods while minimizing changes made to the single-vehicle detection models and relaxing unrealistic assumptions on inter-agent synchronization. Experiments on the V2X-Sim dataset show that our collaboration method achieves 98\% of the performance of an early-collaboration method, while only consuming the equivalent bandwidth of a late-collaboration method.

We study the problem of detecting the correlation between two Gaussian databases XinR^{ntimes d} and Y^{ntimes d}, each composed of n users with d features. This problem is relevant in the analysis of social media, computational biology, etc. We formulate this as a hypothesis testing problem: under the null hypothesis, these two databases are statistically independent. Under the alternative, however, there exists an unknown permutation sigma over the set of n users (or, row permutation), such that X is rho-correlated with Y^sigma, a permuted version of Y. We determine sharp thresholds at which optimal testing exhibits a phase transition, depending on the asymptotic regime of n and d. Specifically, we prove that if rho^2dto0, as dtoinfty, then weak detection (performing slightly better than random guessing) is statistically impossible, irrespectively of the value of n. This compliments the performance of a simple test that thresholds the sum all entries of X^TY. Furthermore, when d is fixed, we prove that strong detection (vanishing error probability) is impossible for any rho<rho^star, where rho^star is an explicit function of d, while weak detection is again impossible as long as rho^2dto0. These results close significant gaps in current recent related studies.

The online fusion and tracking of static objects from heterogeneous sensor detections is a fundamental problem in robotics, autonomous systems, and environmental mapping. Although classical data association approaches such as JPDA are well suited for dynamic targets, they are less effective for static objects observed intermittently and with heterogeneous uncertainties, where motion models provide minimal discriminative power with respect to clutter. In this paper, we propose a novel method for static object data association by clustering multi-modal sensor detections online (SODA-CitrON), while simultaneously estimating positions and maintaining persistent tracks for an unknown number of objects. The proposed unsupervised machine learning approach operates in a fully online manner and handles temporally uncorrelated and multi-sensor measurements. Additionally, it has a worst-case loglinear complexity in the number of sensor detections while providing full output explainability. We evaluate the proposed approach in different Monte Carlo simulation scenarios and compare it against state-of-the-art methods, including POM-based filtering, DBSTREAM clustering, and JPDA. The results demonstrate that SODA-CitrON consistently outperforms the compared methods in terms of F1 score, position RMSE, MOTP, and MOTA in the static object mapping scenarios studied.

Efficient deployment of deep learning models for aerial object detection on resource-constrained devices requires significant compression without com-promising performance. In this study, we propose a novel three-stage compression pipeline for the YOLOv8 object detection model, integrating sparsity-aware training, structured channel pruning, and Channel-Wise Knowledge Distillation (CWD). First, sparsity-aware training introduces dynamic sparsity during model optimization, effectively balancing parameter reduction and detection accuracy. Second, we apply structured channel pruning by leveraging batch normalization scaling factors to eliminate redundant channels, significantly reducing model size and computational complexity. Finally, to mitigate the accuracy drop caused by pruning, we employ CWD to transfer knowledge from the original model, using an adjustable temperature and loss weighting scheme tailored for small and medium object detection. Extensive experiments on the VisDrone dataset demonstrate the effectiveness of our approach across multiple YOLOv8 variants. For YOLOv8m, our method reduces model parameters from 25.85M to 6.85M (a 73.51% reduction), FLOPs from 49.6G to 13.3G, and MACs from 101G to 34.5G, while reducing AP50 by only 2.7%. The resulting compressed model achieves 47.9 AP50 and boosts inference speed from 26 FPS (YOLOv8m baseline) to 45 FPS, enabling real-time deployment on edge devices. We further apply TensorRT as a lightweight optimization step. While this introduces a minor drop in AP50 (from 47.9 to 47.6), it significantly improves inference speed from 45 to 68 FPS, demonstrating the practicality of our approach for high-throughput, re-source-constrained scenarios.

Hierarchical feature representations play a pivotal role in computer vision, particularly in object detection for autonomous driving. Multi-level semantic understanding is crucial for accurately identifying pedestrians, vehicles, and traffic signs in dynamic environments. However, existing architectures, such as YOLO and DETR, struggle to maintain feature consistency across different scales while balancing detection precision and computational efficiency. To address these challenges, we propose Butter, a novel object detection framework designed to enhance hierarchical feature representations for improving detection robustness. Specifically, Butter introduces two key innovations: Frequency-Adaptive Feature Consistency Enhancement (FAFCE) Component, which refines multi-scale feature consistency by leveraging adaptive frequency filtering to enhance structural and boundary precision, and Progressive Hierarchical Feature Fusion Network (PHFFNet) Module, which progressively integrates multi-level features to mitigate semantic gaps and strengthen hierarchical feature learning. Through extensive experiments on BDD100K, KITTI, and Cityscapes, Butter demonstrates superior feature representation capabilities, leading to notable improvements in detection accuracy while reducing model complexity. By focusing on hierarchical feature refinement and integration, Butter provides an advanced approach to object detection that achieves a balance between accuracy, deployability, and computational efficiency in real-time autonomous driving scenarios. Our model and implementation are publicly available at https://github.com/Aveiro-Lin/Butter, facilitating further research and validation within the autonomous driving community.

As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small number of model parameters and FLOPs, the detector with DenseNet backbone shows rather slow speed and low energy efficiency. We find the linearly increasing input channel by dense connection leads to heavy memory access cost, which causes computation overhead and more energy consumption. To solve the inefficiency of DenseNet, we propose an energy and computation efficient architecture called VoVNet comprised of One-Shot Aggregation (OSA). The OSA not only adopts the strength of DenseNet that represents diversified features with multi receptive fields but also overcomes the inefficiency of dense connection by aggregating all features only once in the last feature maps. To validate the effectiveness of VoVNet as a backbone network, we design both lightweight and large-scale VoVNet and apply them to one-stage and two-stage object detectors. Our VoVNet based detectors outperform DenseNet based ones with 2x faster speed and the energy consumptions are reduced by 1.6x - 4.1x. In addition to DenseNet, VoVNet also outperforms widely used ResNet backbone with faster speed and better energy efficiency. In particular, the small object detection performance has been significantly improved over DenseNet and ResNet.

Animal habitat surveys play a critical role in preserving the biodiversity of the land. One of the effective ways to gain insights into animal habitats involves identifying animal footprints, which offers valuable information about species distribution, abundance, and behavior. However, due to the scarcity of animal footprint images, there are no well-maintained public datasets, preventing recent advanced techniques in computer vision from being applied to animal tracking. In this paper, we introduce OpenAnimalTracks dataset, the first publicly available labeled dataset designed to facilitate the automated classification and detection of animal footprints. It contains various footprints from 18 wild animal species. Moreover, we build benchmarks for species classification and detection and show the potential of automated footprint identification with representative classifiers and detection models. We find SwinTransformer achieves a promising classification result, reaching 69.41% in terms of the averaged accuracy. Faster-RCNN achieves mAP of 0.295. We hope our dataset paves the way for automated animal tracking techniques, enhancing our ability to protect and manage biodiversity. Our dataset and code are available at https://github.com/dahlian00/OpenAnimalTracks.

Biologists all over the world use camera traps to monitor biodiversity and wildlife population density. The computer vision community has been making strides towards automating the species classification challenge in camera traps, but it has proven difficult to to apply models trained in one region to images collected in different geographic areas. In some cases, accuracy falls off catastrophically in new region, due to both changes in background and the presence of previously-unseen species. We propose a pipeline that takes advantage of a pre-trained general animal detector and a smaller set of labeled images to train a classification model that can efficiently achieve accurate results in a new region.

This paper considers self-supervised cross-modal coordination as a strategy enabling utilization of multiple modalities and large volumes of unlabeled plankton data to build models for plankton recognition. Automated imaging instruments facilitate the continuous collection of plankton image data on a large scale. Current methods for automatic plankton image recognition rely primarily on supervised approaches, which require labeled training sets that are labor-intensive to collect. On the other hand, some modern plankton imaging instruments complement image information with optical measurement data, such as scatter and fluorescence profiles, which currently are not widely utilized in plankton recognition. In this work, we explore the possibility of using such measurement data to guide the learning process without requiring manual labeling. Inspired by the concepts behind Contrastive Language-Image Pre-training, we train encoders for both modalities using only binary supervisory information indicating whether a given image and profile originate from the same particle or from different particles. For plankton recognition, we employ a small labeled gallery of known plankton species combined with a k-NN classifier. This approach yields a recognition model that is inherently multimodal, i.e., capable of utilizing information extracted from both image and profile data. We demonstrate that the proposed method achieves high recognition accuracy while requiring only a minimal number of labeled images. Furthermore, we show that the approach outperforms an image-only self-supervised baseline. Code available at https://github.com/Jookare/cross-modal-plankton.

Birds are important indicators for monitoring both biodiversity and habitat health; they also play a crucial role in ecosystem management. Decline in bird populations can result in reduced eco-system services, including seed dispersal, pollination and pest control. Accurate and long-term monitoring of birds to identify species of concern while measuring the success of conservation interventions is essential for ecologists. However, monitoring is time consuming, costly and often difficult to manage over long durations and at meaningfully large spatial scales. Technology such as camera traps, acoustic monitors and drones provide methods for non-invasive monitoring. There are two main problems with using camera traps for monitoring: a) cameras generate many images, making it difficult to process and analyse the data in a timely manner; and b) the high proportion of false positives hinders the processing and analysis for reporting. In this paper, we outline an approach for overcoming these issues by utilising deep learning for real-time classi-fication of bird species and automated removal of false positives in camera trap data. Images are classified in real-time using a Faster-RCNN architecture. Images are transmitted over 3/4G cam-eras and processed using Graphical Processing Units (GPUs) to provide conservationists with key detection metrics therefore removing the requirement for manual observations. Our models achieved an average sensitivity of 88.79%, a specificity of 98.16% and accuracy of 96.71%. This demonstrates the effectiveness of using deep learning for automatic bird monitoring.

Unsustainable fishing practices worldwide pose a major threat to marine resources and ecosystems. Identifying vessels that do not show up in conventional monitoring systems -- known as ``dark vessels'' -- is key to managing and securing the health of marine environments. With the rise of satellite-based synthetic aperture radar (SAR) imaging and modern machine learning (ML), it is now possible to automate detection of dark vessels day or night, under all-weather conditions. SAR images, however, require a domain-specific treatment and are not widely accessible to the ML community. Maritime objects (vessels and offshore infrastructure) are relatively small and sparse, challenging traditional computer vision approaches. We present the largest labeled dataset for training ML models to detect and characterize vessels and ocean structures in SAR imagery. xView3-SAR consists of nearly 1,000 analysis-ready SAR images from the Sentinel-1 mission that are, on average, 29,400-by-24,400 pixels each. The images are annotated using a combination of automated and manual analysis. Co-located bathymetry and wind state rasters accompany every SAR image. We also provide an overview of the xView3 Computer Vision Challenge, an international competition using xView3-SAR for ship detection and characterization at large scale. We release the data (https://iuu.xview.us/{https://iuu.xview.us/}) and code (https://github.com/DIUx-xView{https://github.com/DIUx-xView}) to support ongoing development and evaluation of ML approaches for this important application.

Wildlife observation plays an important role in biodiversity conservation, necessitating robust methodologies for monitoring wildlife populations and interspecies interactions. Recent advances in computer vision have significantly contributed to automating fundamental wildlife observation tasks, such as animal detection and species identification. However, accurately identifying species from indirect evidence like footprints and feces remains relatively underexplored, despite its importance in contributing to wildlife monitoring. To bridge this gap, we introduce AnimalClue, the first large-scale dataset for species identification from images of indirect evidence. Our dataset consists of 159,605 bounding boxes encompassing five categories of indirect clues: footprints, feces, eggs, bones, and feathers. It covers 968 species, 200 families, and 65 orders. Each image is annotated with species-level labels, bounding boxes or segmentation masks, and fine-grained trait information, including activity patterns and habitat preferences. Unlike existing datasets primarily focused on direct visual features (e.g., animal appearances), AnimalClue presents unique challenges for classification, detection, and instance segmentation tasks due to the need for recognizing more detailed and subtle visual features. In our experiments, we extensively evaluate representative vision models and identify key challenges in animal identification from their traces. Our dataset and code are available at https://dahlian00.github.io/AnimalCluePage/

Camera traps have become a common tool for wildlife monitoring efforts in ecological research and biodiversity conservation. Wildlife classification models have benefited from the increase in wildlife visual data. These models reach high levels of accuracy on curated, high-quality datasets. However, their performance remains sensitive to real-world environmental constraints. They often produce inconsistent predictions when performing inference on temporally coherent sequences. The predicted label for a single individual shifts rapidly between frames. This study exploits the temporal nature of camera-trap data to augment inferred predictions from a wildlife classification model. Specifically, we adopt several standard Multi-Object Tracking (MOT) models to link detections across consecutive frames. The curated trajectories are used to fuse the softmax class probabilities. The fused probability score produces a single consensus class label estimate that overrides misclassifications caused by noise. The analysis of the experimental results shows that our proposed strategy improves over a standalone classifier over all datasets and for each metric. Specifically, the best-performing MOT models gain a weighted F1-Score of 5.1%, 3.1% and 2.0% over the classifier across three MOT datasets.

Remote individual animal identification is important for food safety, sport, and animal conservation. Numerous existing remote individual animal identification studies have focused on RGB images. In this paper, we tackle individual penguin identification using hyperspectral (HS) images. To the best of our knowledge, it is the first work to analyze spectral differences between penguin individuals using an HS camera. We have constructed a novel penguin HS image dataset, including 990 hyperspectral images of 27 penguins. We experimentally demonstrate that the spectral information of HS image pixels can be used for individual penguin identification. The experimental results show the effectiveness of using HS images for individual penguin identification. The dataset and source code are available here: https://033labcodes.github.io/igrass24_penguin/

Camera traps have transformed how ecologists study wildlife species distributions, activity patterns, and interspecific interactions. Although camera traps provide a cost-effective method for monitoring species, the time required for data processing can limit survey efficiency. Thus, the potential of Artificial Intelligence (AI), specifically Deep Learning (DL), to process camera-trap data has gained considerable attention. Using DL for these applications involves training algorithms, such as Convolutional Neural Networks (CNNs), to automatically detect objects and classify species. To overcome technical challenges associated with training CNNs, several research communities have recently developed platforms that incorporate DL in easy-to-use interfaces. We review key characteristics of four AI-powered platforms -- Wildlife Insights (WI), MegaDetector (MD), Machine Learning for Wildlife Image Classification (MLWIC2), and Conservation AI -- including data management tools and AI features. We also provide R code in an open-source GitBook, to demonstrate how users can evaluate model performance, and incorporate AI output in semi-automated workflows. We found that species classifications from WI and MLWIC2 generally had low recall values (animals that were present in the images often were not classified to the correct species). Yet, the precision of WI and MLWIC2 classifications for some species was high (i.e., when classifications were made, they were generally accurate). MD, which classifies images using broader categories (e.g., "blank" or "animal"), also performed well. Thus, we conclude that, although species classifiers were not accurate enough to automate image processing, DL could be used to improve efficiencies by accepting classifications with high confidence values for certain species or by filtering images containing blanks.

Visual animal biometrics is rapidly gaining popularity as it enables a non-invasive and cost-effective approach for wildlife monitoring applications. Widespread usage of camera traps has led to large volumes of collected images, making manual processing of visual content hard to manage. In this work, we develop a framework for automatic detection and recognition of individuals in different patterned species like tigers, zebras and jaguars. Most existing systems primarily rely on manual input for localizing the animal, which does not scale well to large datasets. In order to automate the detection process while retaining robustness to blur, partial occlusion, illumination and pose variations, we use the recently proposed Faster-RCNN object detection framework to efficiently detect animals in images. We further extract features from AlexNet of the animal's flank and train a logistic regression (or Linear SVM) classifier to recognize the individuals. We primarily test and evaluate our framework on a camera trap tiger image dataset that contains images that vary in overall image quality, animal pose, scale and lighting. We also evaluate our recognition system on zebra and jaguar images to show generalization to other patterned species. Our framework gives perfect detection results in camera trapped tiger images and a similar or better individual recognition performance when compared with state-of-the-art recognition techniques.

Underwater object detection is a crucial and challenging problem in marine engineering and aquatic robot. The difficulty is partly because of the degradation of underwater images caused by light selective absorption and scattering. Intuitively, enhancing underwater images can benefit high-level applications like underwater object detection. However, it is still unclear whether all object detectors need underwater image enhancement as pre-processing. We therefore pose the questions "Does underwater image enhancement really improve underwater object detection?" and "How does underwater image enhancement contribute to underwater object detection?". With these two questions, we conduct extensive studies. Specifically, we use 18 state-of-the-art underwater image enhancement algorithms, covering traditional, CNN-based, and GAN-based algorithms, to pre-process underwater object detection data. Then, we retrain 7 popular deep learning-based object detectors using the corresponding results enhanced by different algorithms, obtaining 126 underwater object detection models. Coupled with 7 object detection models retrained using raw underwater images, we employ these 133 models to comprehensively analyze the effect of underwater image enhancement on underwater object detection. We expect this study can provide sufficient exploration to answer the aforementioned questions and draw more attention of the community to the joint problem of underwater image enhancement and underwater object detection. The pre-trained models and results are publicly available and will be regularly updated. Project page: https://github.com/BIGWangYuDong/lqit/tree/main/configs/detection/uw_enhancement_affect_detection.

Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided.

Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems. We investigate the ability to automatically, accurately, and inexpensively collect such data, which could transform many fields of biology, ecology, and zoology into "big data" sciences. Motion sensor "camera traps" enable collecting wildlife pictures inexpensively, unobtrusively, and frequently. However, extracting information from these pictures remains an expensive, time-consuming, manual task. We demonstrate that such information can be automatically extracted by deep learning, a cutting-edge type of artificial intelligence. We train deep convolutional neural networks to identify, count, and describe the behaviors of 48 species in the 3.2-million-image Snapshot Serengeti dataset. Our deep neural networks automatically identify animals with over 93.8% accuracy, and we expect that number to improve rapidly in years to come. More importantly, if our system classifies only images it is confident about, our system can automate animal identification for 99.3% of the data while still performing at the same 96.6% accuracy as that of crowdsourced teams of human volunteers, saving more than 8.4 years (at 40 hours per week) of human labeling effort (i.e. over 17,000 hours) on this 3.2-million-image dataset. Those efficiency gains immediately highlight the importance of using deep neural networks to automate data extraction from camera-trap images. Our results suggest that this technology could enable the inexpensive, unobtrusive, high-volume, and even real-time collection of a wealth of information about vast numbers of animals in the wild.

Planktonic organisms are of fundamental importance to marine ecosystems: they form the basis of the food web, provide the link between the atmosphere and the deep ocean, and influence global-scale biogeochemical cycles. Scientists are increasingly using imaging-based technologies to study these creatures in their natural habit. Images from such systems provide an unique opportunity to model and understand plankton ecosystems, but the collected datasets can be enormous. The Imaging FlowCytobot (IFCB) at Woods Hole Oceanographic Institution, for example, is an in situ system that has been continuously imaging plankton since 2006. To date, it has generated more than 700 million samples. Manual classification of such a vast image collection is impractical due to the size of the data set. In addition, the annotation task is challenging due to the large space of relevant classes, intra-class variability, and inter-class similarity. Methods for automated classification exist, but the accuracy is often below that of human experts. Here we introduce WHOI-Plankton: a large scale, fine-grained visual recognition dataset for plankton classification, which comprises over 3.4 million expert-labeled images across 70 classes. The labeled image set is complied from over 8 years of near continuous data collection with the IFCB at the Martha's Vineyard Coastal Observatory (MVCO). We discuss relevant metrics for evaluation of classification performance and provide results for a traditional method based on hand-engineered features and two methods based on convolutional neural networks.

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

This paper considers open-set recognition (OSR) of plankton images. Plankton include a diverse range of microscopic aquatic organisms that have an important role in marine ecosystems as primary producers and as a base of food webs. Given their sensitivity to environmental changes, fluctuations in plankton populations offer valuable information about oceans' health and climate change motivating their monitoring. Modern automatic plankton imaging devices enable the collection of large-scale plankton image datasets, facilitating species-level analysis. Plankton species recognition can be seen as an image classification task and is typically solved using deep learning-based image recognition models. However, data collection in real aquatic environments results in imaging devices capturing a variety of non-plankton particles and plankton species not present in the training set. This creates a challenging fine-grained OSR problem, characterized by subtle differences between taxonomically close plankton species. We address this challenge by conducting extensive experiments on three OSR approaches using both phyto- and zooplankton images analyzing also on the effect of the rejection thresholds for OSR. The results demonstrate that high OSR accuracy can be obtained promoting the use of these methods in operational plankton research. We have made the data publicly available to the research community.

We present the Caltech Fish Counting Dataset (CFC), a large-scale dataset for detecting, tracking, and counting fish in sonar videos. We identify sonar videos as a rich source of data for advancing low signal-to-noise computer vision applications and tackling domain generalization in multiple-object tracking (MOT) and counting. In comparison to existing MOT and counting datasets, which are largely restricted to videos of people and vehicles in cities, CFC is sourced from a natural-world domain where targets are not easily resolvable and appearance features cannot be easily leveraged for target re-identification. With over half a million annotations in over 1,500 videos sourced from seven different sonar cameras, CFC allows researchers to train MOT and counting algorithms and evaluate generalization performance at unseen test locations. We perform extensive baseline experiments and identify key challenges and opportunities for advancing the state of the art in generalization in MOT and counting.

The growing popularity and capacity of generative models have eroded the distinction between human and machine-generated content, motivating a growing body of work on detection across text, images, and audio. Most available detectors are either commercial software or, if open-source, come with incompatible codebases with bespoke preprocessing, evaluation protocols, and evaluation metrics, which make their adoption, fair comparison, and reproduction quite difficult. To address this critical gap, we introduce DetectZoo, a first-of-its-kind, extensible toolkit designed to provide a unified interface for AI-generated content detection across text, audio, and image modalities. DetectZoo standardizes the complete empirical pipeline, from data ingestion and preprocessing to model assessment, offering researchers a cohesive framework to benchmark state-of-the-art detectors systematically. By integrating diverse public datasets and baseline detection algorithms under a single, unified API, our toolkit facilitates rigorous and reproducible evaluation. DetectZoo provides reference implementations of 61 detectors, native loaders for 22 benchmark datasets, and a standardized evaluation pipeline that reports multiple metrics through a common interface. Each detector is self-contained yet accessible through the same interface, automatically caches pretrained weights, and reproduces the original published results. DetectZoo lowers the barrier to entry for multi-modal AI forensics, enabling researchers to identify performance gaps across domains and accelerating the development of robust, generalizable detection techniques. The open-source repository and comprehensive documentation are publicly available at https://github.com/sadjadeb/DetectZoo, and the package can be installed via pip install detectzoo.

The enormous demand for seafood products has led to exploitation of marine resources and near-extinction of some species. In particular, overfishing is one the main issues in sustainable marine development. In alignment with the protection of marine resources and sustainable fishing, this study proposes to advance fish classification techniques that support identifying protected fish species using state-of-the-art machine learning. We use a custom modification of the MobileNet model to design a lightweight classifier called M-MobileNet that is capable of running on limited hardware. As part of the study, we compiled a labeled dataset of 37,462 images of fish found in the waters of the Indonesian archipelago. The proposed model is trained on the dataset to classify images of the captured fish into their species and give recommendations on whether they are consumable or not. Our modified MobileNet model uses only 50\% of the top layer parameters with about 42% GTX 860M utility and achieves up to 97% accuracy in fish classification and determining its consumability. Given the limited computing capacity available on many fishing vessels, the proposed model provides a practical solution to on-site fish classification. In addition, synchronized implementation of the proposed model on multiple vessels can supply valuable information about the movement and location of different species of fish.

Plankton recognition is an important computer vision problem due to plankton's essential role in ocean food webs and carbon capture, highlighting the need for species-level monitoring. However, this task is challenging due to its fine-grained nature and dataset shifts caused by different imaging instruments and varying species distributions. As new plankton image datasets are collected at an increasing pace, there is a need for general plankton recognition models that require minimal expert effort for data labeling. In this work, we study large-scale self-supervised pretraining for fine-grained plankton recognition. We first employ masked autoencoding and a large volume of diverse plankton image data to pretrain a general-purpose plankton image encoder. Then we utilize fine-tuning to obtain accurate plankton recognition models for new datasets with a very limited number of labeled training images. Our experiments show that self-supervised pretraining with diverse plankton data clearly increases plankton recognition accuracy compared to standard ImageNet pretraining when the amount of training data is limited. Moreover, the accuracy can be further improved when unlabeled target data is available and utilized during the pretraining.

Real-time wildlife detection in drone imagery is critical for numerous applications, including animal ecology, conservation, and biodiversity monitoring. Low-altitude drone missions are effective for collecting fine-grained animal movement and behavior data, particularly if missions are automated for increased speed and consistency. However, little work exists on evaluating computer vision models on low-altitude aerial imagery and generalizability across different species and settings. To fill this gap, we present a novel multi-environment, multi-species, low-altitude aerial footage (MMLA) dataset. MMLA consists of drone footage collected across three diverse environments: Ol Pejeta Conservancy and Mpala Research Centre in Kenya, and The Wilds Conservation Center in Ohio, which includes five species: Plains zebras, Grevy's zebras, giraffes, onagers, and African Painted Dogs. We comprehensively evaluate three YOLO models (YOLOv5m, YOLOv8m, and YOLOv11m) for detecting animals. Results demonstrate significant performance disparities across locations and species-specific detection variations. Our work highlights the importance of evaluating detection algorithms across different environments for robust wildlife monitoring applications using drones.

Large language models (LLMs) are increasingly deployed in multilingual applications but often generate plausible yet incorrect or misleading outputs, known as hallucinations. While hallucination detection has been studied extensively in English, under-resourced Indian languages remain largely unexplored. We present BHRAM-IL, a benchmark for hallucination recognition and assessment in multiple Indian languages, covering Hindi, Gujarati, Marathi, Odia, along with English. The benchmark comprises 36,047 curated questions across nine categories spanning factual, numerical, reasoning, and linguistic tasks. We evaluate 14 state-of-the-art multilingual LLMs on a benchmark subset of 10,265 questions, analyzing cross-lingual and factual hallucinations across languages, models, scales, categories, and domains using category-specific metrics normalized to (0,1) range. Aggregation over all categories and models yields a primary score of 0.23 and a language-corrected fuzzy score of 0.385, demonstrating the usefulness of BHRAM-IL for hallucination-focused evaluation. The dataset, and the code for generation and evaluation are available on GitHub (https://github.com/sambhashana/BHRAM-IL/) and HuggingFace (https://huggingface.co/datasets/sambhashana/BHRAM-IL/) to support future research in multilingual hallucination detection and mitigation.

The rapid evolution of social media has provided enhanced communication channels for individuals to create online content, enabling them to express their thoughts and opinions. Multimodal memes, often utilized for playful or humorous expressions with visual and textual elements, are sometimes misused to disseminate hate speech against individuals or groups. While the detection of hateful memes is well-researched, developing effective methods to transform hateful content in memes remains a significant challenge. Leveraging the powerful generation and reasoning capabilities of Vision-Language Models (VLMs), we address the tasks of detecting and mitigating hateful content. This paper presents two key contributions: first, a definition-guided prompting technique for detecting hateful memes, and second, a unified framework for mitigating hateful content in memes, named UnHateMeme, which works by replacing hateful textual and/or visual components. With our definition-guided prompts, VLMs achieve impressive performance on hateful memes detection task. Furthermore, our UnHateMeme framework, integrated with VLMs, demonstrates a strong capability to convert hateful memes into non-hateful forms that meet human-level criteria for hate speech and maintain multimodal coherence between image and text. Through empirical experiments, we show the effectiveness of state-of-the-art pretrained VLMs such as LLaVA, Gemini and GPT-4o on the proposed tasks, providing a comprehensive analysis of their respective strengths and limitations for these tasks. This paper aims to shed light on important applications of VLMs for ensuring safe and respectful online environments.

We introduce COU: Common Objects Underwater, an instance-segmented image dataset of commonly found man-made objects in multiple aquatic and marine environments. COU contains approximately 10K segmented images, annotated from images collected during a number of underwater robot field trials in diverse locations. COU has been created to address the lack of datasets with robust class coverage curated for underwater instance segmentation, which is particularly useful for training light-weight, real-time capable detectors for Autonomous Underwater Vehicles (AUVs). In addition, COU addresses the lack of diversity in object classes since the commonly available underwater image datasets focus only on marine life. Currently, COU contains images from both closed-water (pool) and open-water (lakes and oceans) environments, of 24 different classes of objects including marine debris, dive tools, and AUVs. To assess the efficacy of COU in training underwater object detectors, we use three state-of-the-art models to evaluate its performance and accuracy, using a combination of standard accuracy and efficiency metrics. The improved performance of COU-trained detectors over those solely trained on terrestrial data demonstrates the clear advantage of training with annotated underwater images. We make COU available for broad use under open-source licenses.

If you had an AI Whale-to-English translator, how could you validate whether or not it is working? Does one need to interact with the animals or rely on grounded observations such as temperature? We provide theoretical and proof-of-concept experimental evidence suggesting that interaction and even observations may not be necessary for sufficiently complex languages. One may be able to evaluate translators solely by their English outputs, offering potential advantages in terms of safety, ethics, and cost. This is an instance of machine translation quality evaluation (MTQE) without any reference translations available. A key challenge is identifying ``hallucinations,'' false translations which may appear fluent and plausible. We propose using segment-by-segment translation together with the classic NLP shuffle test to evaluate translators. The idea is to translate animal communication, turn by turn, and evaluate how often the resulting translations make more sense in order than permuted. Proof-of-concept experiments on data-scarce human languages and constructed languages demonstrate the potential utility of this evaluation methodology. These human-language experiments serve solely to validate our reference-free metric under data scarcity. It is found to correlate highly with a standard evaluation based on reference translations, which are available in our experiments. We also perform a theoretical analysis suggesting that interaction may not be necessary nor efficient in the early stages of learning to translate.

Underwater images play a crucial role in ocean research and marine environmental monitoring since they provide quality information about the ecosystem. However, the complex and remote nature of the environment results in poor image quality with issues such as low visibility, blurry textures, color distortion, and noise. In recent years, research in image enhancement has proven to be effective but also presents its own limitations, like poor generalization and heavy reliance on clean datasets. One of the challenges herein is the lack of diversity and the low quality of images included in these datasets. Also, most existing datasets consist only of monocular images, a fact that limits the representation of different lighting conditions and angles. In this paper, we propose a new plan of action to overcome these limitations. On one hand, we call for expanding the datasets using a denoising diffusion model to include a variety of image types such as stereo, wide-angled, macro, and close-up images. On the other hand, we recommend enhancing the images using Controlnet to evaluate and increase the quality of the corresponding datasets, and hence improve the study of the marine ecosystem. Tags - Underwater Images, Denoising Diffusion, Marine ecosystem, Controlnet

Deep learning techniques have been explored within the marine litter problem for approximately 20 years but the majority of the research has developed rapidly in the last five years. We provide an in-depth, up to date, summary and analysis of 28 of the most recent and significant contributions of deep learning in marine debris. From cross referencing the research paper results, the YOLO family significantly outperforms all other methods of object detection but there are many respected contributions to this field that have categorically agreed that a comprehensive database of underwater debris is not currently available for machine learning. Using a small dataset curated and labelled by us, we tested YOLOv5 on a binary classification task and found the accuracy was low and the rate of false positives was high; highlighting the importance of a comprehensive database. We conclude this survey with over 40 future research recommendations and open challenges.

Generative AI (GenAI) models, particularly large language models (LLMs), have transformed multiple domains, including natural language processing, software analysis, and code understanding. Their ability to analyze and generate code has enabled applications such as source code summarization, behavior analysis, and malware detection. In this study, we systematically evaluate the capabilities of both small and large GenAI language models in understanding application behavior, with a particular focus on malware detection as a representative task. While larger models generally achieve higher overall accuracy, our experiments show that small GenAI models maintain competitive precision and recall, offering substantial advantages in computational efficiency, faster inference, and deployment in resource-constrained environments. We provide a detailed comparison across metrics such as accuracy, precision, recall, and F1-score, highlighting each model's strengths, limitations, and operational feasibility. Our findings demonstrate that small GenAI models can effectively complement large ones, providing a practical balance between performance and resource efficiency in real-world application behavior analysis.

The powerful ability of ChatGPT has caused widespread concern in the academic community. Malicious users could synthesize dummy academic content through ChatGPT, which is extremely harmful to academic rigor and originality. The need to develop ChatGPT-written content detection algorithms call for large-scale datasets. In this paper, we initially investigate the possible negative impact of ChatGPT on academia,and present a large-scale CHatGPT-writtEn AbsTract dataset (CHEAT) to support the development of detection algorithms. In particular, the ChatGPT-written abstract dataset contains 35,304 synthetic abstracts, with Generation, Polish, and Mix as prominent representatives. Based on these data, we perform a thorough analysis of the existing text synthesis detection algorithms. We show that ChatGPT-written abstracts are detectable, while the detection difficulty increases with human involvement.Our dataset is available in https://github.com/botianzhe/CHEAT.

Watermarking embeds statistical signatures in AI-generated text for detection and attribution. We reveal a fundamental vulnerability: when users access multiple models (today's reality), watermarks trivially fail. Watermarks perturb output distributions away from the original, and in competitive markets, these perturbations are typically independent across providers. We theoretically prove that averaging output probability distributions recovers the unwatermarked distribution with up to a second-order error term. Empirically, simply averaging 3-5 models cancels out these perturbations. We introduce WASH (Watermark Attenuation via Statistical Hybridisation), which solves practical challenges in ensemble generation: vocabulary misalignment and tokenisation differences across heterogeneous models. Experiments across six watermarking schemes and three LLMs show that averaging across 3 models suppresses detection z-scores from 5-300 to below 2 (below the detection threshold of 4) and reduces TPR at 5% FPR to below 50%, while improving quality by 27.5% and running 6 times faster than the best baseline on the long sequence generation. Our results suggest that robust AI-text detection via watermarking requires either accepting this fundamental vulnerability or unprecedented coordination among model providers.

Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive encoders are effective for cross-modal alignment and retrieval, self-supervised visual encoders often capture richer dense semantics and exhibit stronger robustness on recognition and understanding tasks. In this work, we investigate how to scale the fusion of these complementary visual representations for vision-language modeling. We propose CoME-VL: Complementary Multi-Encoder Vision-Language, a modular fusion framework that integrates a contrastively trained vision encoder with a self-supervised DINO encoder. Our approach performs representation-level fusion by (i) entropy-guided multi-layer aggregation with orthogonality-constrained projections to reduce redundancy, and (ii) RoPE-enhanced cross-attention to align heterogeneous token grids and produce compact fused visual tokens. The fused tokens can be injected into a decoder-only LLM with minimal changes to standard VLM pipelines. Extensive experiments across diverse vision-language benchmarks demonstrate that CoME-VL consistently outperforms single-encoder baselines. In particular, we observe an average improvement of 4.9% on visual understanding tasks and 5.4% on grounding tasks. Our method achieves state-of-the-art performance on RefCOCO for detection while improving over the baseline by a large margin. Finally, we conduct ablation studies on layer merging, non-redundant feature mixing, and fusion capacity to evaluate how complementary contrastive and self-supervised signals affect VLM performance.

Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on monitoring to detect and flag unsafe behavior during inference. An open security challenge is adaptive adversaries who craft attacks that simultaneously (i) evade detection while (ii) eliciting unsafe behavior. Adaptive attackers are a major concern as LLM providers cannot patch their security mechanisms, since they are unaware of how their models are being misused. We cast robust LLM monitoring as a security game, where adversaries who know about the monitor try to extract sensitive information, while a provider must accurately detect these adversarial queries at low false positive rates. Our work (i) shows that existing LLM monitors are vulnerable to adaptive attackers and (ii) designs improved defenses through activation watermarking by carefully introducing uncertainty for the attacker during inference. We find that activation watermarking outperforms guard baselines by up to 52% under adaptive attackers who know the monitoring algorithm but not the secret key.

Computer-aided diagnosis establishes methods for robust assessment of medical image-based examination. Image processing introduced a promising strategy to facilitate disease classification and detection while diminishing unnecessary expenses. In this paper, we propose a novel metastatic cancer image classification model based on DenseNet Block, which can effectively identify metastatic cancer in small image patches taken from larger digital pathology scans. We evaluate the proposed approach to the slightly modified version of the PatchCamelyon (PCam) benchmark dataset. The dataset is the slightly modified version of the PatchCamelyon (PCam) benchmark dataset provided by Kaggle competition, which packs the clinically-relevant task of metastasis detection into a straight-forward binary image classification task. The experiments indicated that our model outperformed other classical methods like Resnet34, Vgg19. Moreover, we also conducted data augmentation experiment and study the relationship between Batches processed and loss value during the training and validation process.

Multiple object tracking (MOT) technology has made significant progress in terrestrial applications, but underwater tracking scenarios remain underexplored despite their importance to marine ecology and aquaculture. We present Multiple Fish Tracking Dataset 2025 (MFT25), the first comprehensive dataset specifically designed for underwater multiple fish tracking, featuring 15 diverse video sequences with 408,578 meticulously annotated bounding boxes across 48,066 frames. Our dataset captures various underwater environments, fish species, and challenging conditions including occlusions, similar appearances, and erratic motion patterns. Additionally, we introduce Scale-aware and Unscented Tracker (SU-T), a specialized tracking framework featuring an Unscented Kalman Filter (UKF) optimized for non-linear fish swimming patterns and a novel Fish-Intersection-over-Union (FishIoU) matching that accounts for the unique morphological characteristics of aquatic species. Extensive experiments demonstrate that our SU-T baseline achieves state-of-the-art performance on MFT25, with 34.1 HOTA and 44.6 IDF1, while revealing fundamental differences between fish tracking and terrestrial object tracking scenarios. MFT25 establishes a robust foundation for advancing research in underwater tracking systems with important applications in marine biology, aquaculture monitoring, and ecological conservation. The dataset and codes are released at https://vranlee.github.io/SU-T/.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

This study introduces a novel application of a Generative Pre-trained Transformer (GPT) model tailored for photoplethysmography (PPG) signals, serving as a foundation model for various downstream tasks. Adapting the standard GPT architecture to suit the continuous characteristics of PPG signals, our approach demonstrates promising results. Our models are pre-trained on our extensive dataset that contains more than 200 million 30s PPG samples. We explored different supervised fine-tuning techniques to adapt our model to downstream tasks, resulting in performance comparable to or surpassing current state-of-the-art (SOTA) methods in tasks like atrial fibrillation detection. A standout feature of our GPT model is its inherent capability to perform generative tasks such as signal denoising effectively, without the need for further fine-tuning. This success is attributed to the generative nature of the GPT framework.

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse range of malicious behaviors make this a critical challenge. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations. Experiments show BEEAR reduces the success rate of RLHF time backdoor attacks from >95% to <1% and from 47% to 0% for instruction-tuning time backdoors targeting malicious code generation, without compromising model utility. Requiring only defender-defined safe and unwanted behaviors, BEEAR represents a step towards practical defenses against safety backdoors in LLMs, providing a foundation for further advancements in AI safety and security.

AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a paraphrase policy against a multi-detector ensemble using Group Relative Policy Optimization (GRPO) with LoRA adapters on Qwen3-4B, optimizing a composite reward that balances detector evasion with semantic preservation. We evaluate six attack settings (M0-M5) against three detector families (RoBERTa, FastDetectGPT, and Binoculars) at the security-relevant 1% false positive rate operating point. StealthRL achieves near-zero detection (0.001 mean TPR@1%FPR), reduces mean AUROC from 0.74 to 0.27, and attains a 99.9% attack success rate. Critically, attacks transfer to a held-out detector family not seen during training, revealing shared architectural vulnerabilities rather than detector-specific brittleness. We additionally conduct LLM-based quality evaluation via Likert scoring, analyze detector score distributions to explain why evasion succeeds, and provide per-detector AUROC with bootstrap confidence intervals. Our results expose significant robustness gaps in current AI-text detection and establish StealthRL as a principled adversarial evaluation protocol. Code and evaluation pipeline are publicly available at https://github.com/suraj-ranganath/StealthRL.

Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations between authors' writing styles and topics, leading to poor generalization across domains. To address this challenge, we propose Explainable Authorship Variational Autoencoder (EAVAE), a novel framework that explicitly disentangles style from content through architectural separation-by-design. EAVAE first pretrains style encoders using supervised contrastive learning on diverse authorship data, then finetunes with a Variational Autoencoder (VEA) architecture using separate encoders for style and content representations. Disentanglement is enforced through a novel discriminator that not only distinguishes whether pairs of style/content representations belong to the same or different authors/content sources, but also generates natural language explanation for their decision, simultaneously mitigating confounding information and enhancing interpretability. Extensive experiments demonstrate the effectiveness of EAVAE. On authorship attribution, we achieve state-of-the-art performance on various datasets, including Amazon Reviews, PAN21, and HRS. For AI-generated text detection, EAVAE excels in few-shot learning over the M4 dataset. Code and data repositories are available onlinehttps://github.com/hieum98/avae https://huggingface.co/collections/Hieuman/document-level-authorship-datasets.

Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming analysts with logs requiring rapidly evolving expertise. Conventional machine-learning detectors reduce alert volume but still yield many false positives, while standard Retrieval-Augmented Generation (RAG) pipelines often retrieve irrelevant context and fail to justify predictions. We present CyberRAG, a modular agent-based RAG framework that delivers real-time classification, explanation, and structured reporting for cyber-attacks. A central LLM agent orchestrates: (i) fine-tuned classifiers specialized by attack family; (ii) tool adapters for enrichment and alerting; and (iii) an iterative retrieval-and-reason loop that queries a domain-specific knowledge base until evidence is relevant and self-consistent. Unlike traditional RAG, CyberRAG adopts an agentic design that enables dynamic control flow and adaptive reasoning. This architecture autonomously refines threat labels and natural-language justifications, reducing false positives and enhancing interpretability. It is also extensible: new attack types can be supported by adding classifiers without retraining the core agent. CyberRAG was evaluated on SQL Injection, XSS, and SSTI, achieving over 94\% accuracy per class and a final classification accuracy of 94.92\% through semantic orchestration. Generated explanations reached 0.94 in BERTScore and 4.9/5 in GPT-4-based expert evaluation, with robustness preserved against adversarial and unseen payloads. These results show that agentic, specialist-oriented RAG can combine high detection accuracy with trustworthy, SOC-ready prose, offering a flexible path toward partially automated cyber-defense workflows.

Advances in peptide identification are revolutionizing our ability to decipher protein functions and accelerate therapeutic discovery. We present PDeepPP, a deep learning framework that integrates pretrained protein language models with parallel transformer-CNN architectures, achieving state-of-the-art performance in peptide characterization tasks. The model's hybrid architecture demonstrates unique capabilities in capturing both local sequence motifs and global structural features, as evidenced by 29% improved cluster separation in UMAP visualizations compared to conventional approaches. Evaluated across 33 biological recognition tasks - including post-translational modification site prediction and bioactive peptide identification - PDeepPP outperformed existing methods in 25 tasks with average AUC improvements of 4.2%. Notably, it achieved 0.9726 accuracy with PR AUC 0.9977 in antimicrobial peptide detection while reducing false negatives by 37.5% in antimalarial recognition scenarios. This framework enables accurate large-scale peptide analysis, achieving 218* acceleration over sequence-alignment-based methods while maintaining 99.5% specificity in critical glycosylation site detection.PDeepPP establishes a new paradigm for computational peptide analysis through its synergistic architecture design, enabling rapid yet precise functional annotation that bridges molecular pattern recognition with translational biomedical applications.We have made our implementation, including code, data, and pretrained models, publicly available via GitHub (https://github.com/fondress/PDeepPP) and Hugging Face (https://huggingface.co/fondress/PDeppPP).

As large language models (LLMs) move from research prototypes to enterprise systems, their security vulnerabilities pose serious risks to data privacy and system integrity. This study benchmarks various Llama model variants against the OWASP Top 10 for LLM Applications framework, evaluating threat detection accuracy, response safety, and computational overhead. Using the FABRIC testbed with NVIDIA A30 GPUs, we tested five standard Llama models and five Llama Guard variants on 100 adversarial prompts covering ten vulnerability categories. Our results reveal significant differences in security performance: the compact Llama-Guard-3-1B model achieved the highest detection rate of 76% with minimal latency (0.165s per test), whereas base models such as Llama-3.1-8B failed to detect threats (0% accuracy) despite longer inference times (0.754s). We observe an inverse relationship between model size and security effectiveness, suggesting that smaller, specialized models often outperform larger general-purpose ones in security tasks. Additionally, we provide an open-source benchmark dataset including adversarial prompts, threat labels, and attack metadata to support reproducible research in AI security, [1].

Multimodal large language models (MLLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. Despite its success in language understanding, it is critical to evaluate the performance of downstream tasks for better human-centric applications. This paper assesses the application of MLLMs with 5 crucial abilities for affective computing, spanning from visual affective tasks and reasoning tasks. The results show that \gpt has high accuracy in facial action unit recognition and micro-expression detection while its general facial expression recognition performance is not accurate. We also highlight the challenges of achieving fine-grained micro-expression recognition and the potential for further study and demonstrate the versatility and potential of \gpt for handling advanced tasks in emotion recognition and related fields by integrating with task-related agents for more complex tasks, such as heart rate estimation through signal processing. In conclusion, this paper provides valuable insights into the potential applications and challenges of MLLMs in human-centric computing. Our interesting examples are at https://github.com/EnVision-Research/GPT4Affectivity.

Detecting oscillations in solar and stellar time series is complicated by non-stationary red noise and evolving background emission. Methods based on detrending and AR(1)-based wavelet analysis can introduce spurious periodicities and do not adequately describe time-dependent backgrounds. We develop a Bayesian approach that combines the continuous wavelet transform with MCMC sampling to infer a time-dependent background spectrum. The background is represented by a power-law plus white-noise component, with parameters allowed to vary smoothly in time, so that significance levels can be evaluated locally without explicit detrending. Tests with synthetic data show that injected oscillations are recovered reliably, while false detections are suppressed in pure-noise cases. Using a frequency-domain signal-to-noise ratio (S/N), we find that oscillations can be identified robustly when the S/N is greater than or equal to 2 under mixed noise conditions. The detectable period range is limited by wavelet resolution, from about 3-4 sampling intervals up to roughly one-quarter of the total duration. Application to GOES soft X-ray flare observations shows that the method isolates quasi-periodic oscillations with improved temporal localization compared to standard wavelet and Fourier-based approaches. Meanwhile, this behavior is consistent across a range of noise conditions and signal morphologies.

The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture. While multimodal large language models (MLLMs) demonstrate strong general reasoning ability, they underperform in driving contexts due to domain and temporal misalignment. We introduce VLM-AutoDrive, a modular post-training framework for adapting pretrained Vision-Language Models (VLMs) to high-fidelity anomaly detection. The framework integrates metadata-derived captions, LLM-generated descriptions, visual question answering (VQA) pairs, and chain-of-thought (CoT) reasoning supervision to enable domain-aligned and interpretable learning. Off-the-shelf VLMs such as NVIDIA's Cosmos-Reason1 7B (CR1) exhibit near-zero Collision recall in zero-shot settings; fine-tuning with VLM-AutoDrive improves Collision F1 from 0.00 to 0.69 and overall accuracy from 35.35% to 77.27%. VLM-AutoDrive offers a scalable recipe for adapting general-purpose VLMs to safety-critical, temporally localized perception tasks. Evaluated on real-world Nexar dashcam videos, it achieves substantial gains in Collision and Near-Collision detection while producing interpretable reasoning traces, bridging the gap between perception, causality, and decision reasoning in autonomous driving.

Modern astronomical surveys are producing datasets of unprecedented size and richness, increasing the potential for high-impact scientific discovery. This possibility, coupled with the challenge of exploring a large number of sources, has led to the development of novel machine-learning-based anomaly detection approaches, such as Astronomaly. For the first time, we test the scalability of Astronomaly by applying it to almost 4 million images of galaxies from the Dark Energy Camera Legacy Survey. We use a trained deep learning algorithm to learn useful representations of the images and pass these to the anomaly detection algorithm isolation forest, coupled with Astronomaly's active learning method, to discover interesting sources. We find that data selection criteria have a significant impact on the trade-off between finding rare sources such as strong lenses and introducing artefacts into the dataset. We demonstrate that active learning is required to identify the most interesting sources and reduce artefacts, while anomaly detection methods alone are insufficient. Using Astronomaly, we find 1635 anomalies among the top 2000 sources in the dataset after applying active learning, including eight strong gravitational lens candidates, 1609 galaxy merger candidates, and 18 previously unidentified sources exhibiting highly unusual morphology. Our results show that by leveraging the human-machine interface, Astronomaly is able to rapidly identify sources of scientific interest even in large datasets.

Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increasingly capable attackers can distribute their intent across multiple benign-looking turns. Recent studies show that even modern commercial models with advanced guardrails remain vulnerable to such attacks despite advances in safety alignment and external guardrails. In this work, we address this challenge by detecting the earliest turn at which delivering the candidate response would make the accumulated interaction sufficient to enable harmful action. This objective requires precise turn-level intervention that identifies the harm-enabling closure point while avoiding premature refusal of benign exploratory conversations. To further support training and evaluation, we construct the Multi-Turn Intent Dataset (MTID), which contains branching attack rollouts, matched benign hard negatives, and annotations of the earliest harm-enabling turns. We show that MTID helps enable a turn-level monitor TurnGate, which substantially outperforms existing baselines in harmful-intent detection while maintaining low over-refusal rates. TurnGate further generalizes across domains, attacker pipelines, and target models. Our code is available at https://github.com/Graph-COM/TurnGate.

Visual storytelling systems struggle to maintain character identity across frames and link actions to appropriate subjects, frequently leading to referential hallucinations. These issues can be addressed through grounding of characters, objects, and other entities on the visual elements. We propose StoryReasoning, a dataset containing 4,178 stories derived from 52,016 movie images, with both structured scene analyses and grounded stories. Each story maintains character and object consistency across frames while explicitly modeling multi-frame relationships through structured tabular representations. Our approach features cross-frame object re-identification using visual similarity and face recognition, chain-of-thought reasoning for explicit narrative modeling, and a grounding scheme that links textual elements to visual entities across multiple frames. We establish baseline performance by fine-tuning Qwen2.5-VL 7B, creating Qwen Storyteller, which performs end-to-end object detection, re-identification, and landmark detection while maintaining consistent object references throughout the story. Evaluation demonstrates a reduction from 4.06 to 3.56 (-12.3%) hallucinations on average per story when compared to a non-fine-tuned model.

Foundation models succeed when they learn in the native structure of a modality, whether morphology-respecting tokens in language or pixels in vision. Wireless packet traces deserve the same treatment: meaning emerges from layered headers, typed fields, timing gaps, and cross-packet state machines, not flat strings. We present Plume (Protocol Language Understanding Model for Exchanges), a compact 140M-parameter foundation model for 802.11 traces that learns from structured PDML dissections. A protocol-aware tokenizer splits along the dissector field tree, emits gap tokens for timing, and normalizes identifiers, yielding 6.2x shorter sequences than BPE with higher per token information density. Trained on a curated corpus, Plume achieves 74-97% next-packet token accuracy across five real-world failure categories and AUROC >= 0.99 for zero-shot anomaly detection. On the same prediction task, frontier LLMs (Claude Opus 4.6, GPT-5.4) score comparably despite receiving identical protocol context, yet Plume does so with > 600x fewer parameters, fitting on a single GPU at effectively zero marginal cost vs. cloud API pricing, enabling on-prem, privacy-preserving root cause analysis.

Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A practically dangerous injection must stay invisible: if executing the payload derails the user's legitimate task, the resulting failure signal invites inspection of the skill. We therefore evaluate attacks by Attack Success Rate, which requires the injected payload to execute and the user's task to still pass its verifier in the same trial. Prior skill-poisoning attacks face a reliability-stealth trade-off under this lens: YAML-header injections are reliably loaded but easily inspected, whereas stealthier body injections that place explicit malicious commands in the skill prose are less reliable because out-of-context commands invite the agent's own suspicion. We introduce POISE, a position-aware attack that compresses the trigger into a single, benign-looking body instruction, placing it at a feasible position and using a context-aware generator to blend it with nearby setup or prerequisite steps. On Skill-Inject with codex+gpt-5.2, POISE achieves an 89.3% ASR, 28.0 points above a random-placement body baseline and 2.6 points above a YAML-only baseline, while retaining the stealth advantage of body placement. That stealth is the decisive margin: because legitimate skill bodies naturally require privileged tool operations, LLM scanners are hyper-sensitive, falsely flagging 74.6% of clean skills on average across four judges and both benchmarks. Blending into these false alarms, POISE causes only 5.6% of poisoned variants to gain a new high-risk alert over their clean baselines, rendering current static defenses ineffective.

Large Language Models (LLMs) produce a controllability gap in safety-critical engineering: even low rates of undetected constraint violations render a system undeployable. Current orchestration paradigms suffer from sycophantic compliance, context attention decay [Liu et al., 2024], and stochastic oscillation during self-correction [Huang et al., 2024]. We introduce the Convergent AI Agent Framework (CAAF), which transitions agentic workflows from open-loop generation to closed-loop Fail-Safe Determinism via three pillars: (1) Recursive Atomic Decomposition with physical context firewalls; (2) Harness as an Asset, formalizing domain invariants into machine-readable registries enforced by a deterministic Unified Assertion Interface (UAI); and (3) Structured Semantic Gradients with State Locking for monotonic convergence. Empirical evaluation across two domains -- SAE Level 3 (L3) autonomous driving (AD) (n=30, 7 conditions) and pharmaceutical continuous flow reactor design (n=20, 4 conditions including a Mono+UAI ablation) -- shows that CAAF-all-GPT-4o-mini achieves 100% paradox detection while monolithic GPT-4o achieves 0% (even at temperature=0). The pharmaceutical benchmark features 7 simultaneous constraints with nonlinear Arrhenius interactions and a 3-way minimal unsatisfiable subset, representing a structurally harder challenge than the 2-constraint AD paradox. Alternative multi-agent architectures (debate, sequential checking) also achieve 0% across 80 trials, confirming that CAAF's reliability derives from its deterministic UAI, not from multi-agent orchestration per se. A Mono+UAI ablation (95%) isolates UAI as the core contribution. CAAF's reliability is invariant to prompt hints; all components use a single commodity model, enabling fully offline deployment.

Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time denial-of-service (PI-DoS) attacks that exploit the high computational cost of reasoning. We first formalize inference cost for LRMs and define PI-DoS, then prove that any practical PI-DoS attack should satisfy three properties: (1) a high amplification ratio, where each query induces a disproportionately long reasoning trace relative to its own length; (ii) stealthiness, in which prompts and responses remain on the natural language manifold and evade distribution shift detectors; and (iii) optimizability, in which the attack supports efficient optimization without being slowed by its own success. Under this framework, we present ReasoningBomb, a reinforcement-learning-based PI-DoS framework that is guided by a constant-time surrogate reward and trains a large reasoning-model attacker to generate short natural prompts that drive victim LRMs into pathologically long and often effectively non-terminating reasoning. Across seven open-source models (including LLMs and LRMs) and three commercial LRMs, ReasoningBomb induces 18,759 completion tokens on average and 19,263 reasoning tokens on average across reasoning models. It outperforms the the runner-up baseline by 35% in completion tokens and 38% in reasoning tokens, while inducing 6-7x more tokens than benign queries and achieving 286.7x input-to-output amplification ratio averaged across all samples. Additionally, our method achieves 99.8% bypass rate on input-based detection, 98.7% on output-based detection, and 98.4% against strict dual-stage joint detection.

Future AI agents might run autonomously with elevated privileges. If these agents are misaligned, they might abuse these privileges to cause serious damage. The field of AI control develops techniques that make it harder for misaligned AIs to cause such damage, while preserving their usefulness. We introduce BashArena, a setting for studying AI control techniques in security-critical environments. BashArena contains 637 Linux system administration and infrastructure engineering tasks in complex, realistic environments, along with four sabotage objectives (execute malware, exfiltrate secrets, escalate privileges, and disable firewall) for a red team to target. We evaluate multiple frontier LLMs on their ability to complete tasks, perform sabotage undetected, and detect sabotage attempts. Claude Sonnet 4.5 successfully executes sabotage while evading monitoring by GPT-4.1 mini 26% of the time, at 4% trajectory-wise FPR. Our findings provide a baseline for designing more effective control protocols in BashArena. We release the dataset as a ControlArena setting and share our task generation pipeline.

Robust and privacy-preserving indoor scene understanding remains a fundamental open problem. While optical sensors such as RGB and LiDAR offer high spatial fidelity, they suffer from severe occlusions and introduce privacy risks in indoor environments. In contrast, millimeter-wave (mmWave) radar preserves privacy and penetrates obstacles, but its inherently low spatial resolution makes reliable geometric reasoning difficult. We introduce RISE, the first benchmark and system for single-static-radar indoor scene understanding, jointly targeting layout reconstruction and object detection. RISE is built upon the key insight that multipath reflections, traditionally treated as noise, encode rich geometric cues. To exploit this, we propose a Bi-Angular Multipath Enhancement that explicitly models Angle-of-Arrival and Angle-of-Departure to recover secondary (ghost) reflections and reveal invisible structures. On top of these enhanced observations, a simulation-to-reality Hierarchical Diffusion framework transforms fragmented radar responses into complete layout reconstruction and object detection. Our benchmark contains 50,000 frames collected across 100 real indoor trajectories, forming the first large-scale dataset dedicated to radar-based indoor scene understanding. Extensive experiments show that RISE reduces the Chamfer Distance by 60% (down to 16 cm) compared to the state of the art in layout reconstruction, and delivers the first mmWave-based object detection, achieving 58% IoU. These results establish RISE as a new foundation for geometry-aware and privacy-preserving indoor scene understanding using a single static radar.

This study introduces a human-in-the-loop pipeline that converts unscaled, hand-drawn floor plan sketches into semantically consistent 3D BIM models. The workflow leverages multimodal large language models (MLLMs) within a multi-agent framework, combining perceptual extraction, human feedback, schema validation, and automated BIM scripting. Initially, sketches are iteratively refined into a structured JSON layout of walls, doors, and windows. Later, these layouts are transformed into executable scripts that generate 3D BIM models. Experiments on ten diverse floor plans demonstrate strong convergence: openings (doors, windows) are captured with high reliability in the initial pass, while wall detection begins around 83% and achieves near-perfect alignment after a few feedback iterations. Across all categories, precision, recall, and F1 scores remain above 0.83, and geometric errors (RMSE, MAE) progressively decrease to zero through feedback corrections. This study demonstrates how MLLM-driven multi-agent reasoning can make BIM creation accessible to both experts and non-experts using only freehand sketches.

The paper explores the transformation of port logistics operations with artificial intelligence during the port transformation into a smart port. The research integrates capabilities-based resource analysis and dynamic capabilities with sociotechnicalimplementations of technologies and resilience approaches of complex systems under disruptions. The system applies robustdata infrastructures to propel analytical and AI modules that become effective once integrated with sufficient governance systems and trained personnel and operational processes to transform planning and safety and sustainability operations.It applies Scopus bibliometric research to analyze 123 articles using a systematic approach with both a search protocol and a document screening and duplication verification. It incorporates annual behavior and distribution of author and country performance analysis with science mapping techniques that explore keyword relation and co-citation and bibliographic coupling and conceptual structuring tools that construct thematic maps and multiple correspondence analysis with community detection while applying explicit thresholding and robust tests.The research connects AI applications to smart port domains through specific data-to-impact pathways while providing a method for bibliometric analysis that enables future updates. The research presents a step-by-step approach for data readiness followed by predictive and optimization implementation and organizational integration. The paper supports public policy through recommendations for data sharing standards and complete environmental benefit assessments. The research proposes a future study plan whichcombines field-based testing with multiple port assessments to enhance both cause-effect understanding and research applicability.

Accurate segmentation of coronary arteries remains a significant challenge in clinical practice, hindering the ability to effectively diagnose and manage coronary artery disease. The lack of large, annotated datasets for model training exacerbates this issue, limiting the development of automated tools that could assist radiologists. To address this, we introduce CM-UNet, which leverages self-supervised pre-training on unannotated datasets and transfer learning on limited annotated data, enabling accurate disease detection while minimizing the need for extensive manual annotations. Fine-tuning CM-UNet with only 18 annotated images instead of 500 resulted in a 15.2% decrease in Dice score, compared to a 46.5% drop in baseline models without pre-training. This demonstrates that self-supervised learning can enhance segmentation performance and reduce dependence on large datasets. This is one of the first studies to highlight the importance of self-supervised learning in improving coronary artery segmentation from X-ray angiography, with potential implications for advancing diagnostic accuracy in clinical practice. By enhancing segmentation accuracy in X-ray angiography images, the proposed approach aims to improve clinical workflows, reduce radiologists' workload, and accelerate disease detection, ultimately contributing to better patient outcomes. The source code is publicly available at https://github.com/CamilleChallier/Contrastive-Masked-UNet.

Despite considerable progress in the development of machine-text detectors, it has been suggested that the problem is inherently hard, and therefore, that stakeholders should proceed under the assumption that machine-generated text cannot be reliably detected as such. We examine a recent such claim by Nicks et al. (2024) regarding the ease with which language models can be optimized to degrade the performance of machine-text detectors, including detectors not specifically optimized against. We identify a feature spacex2013the stylistic feature spacex2013that is robust to such optimization, and show that it may be used to reliably detect samples from language models optimized to prevent detection. Furthermore, we show that even when models are explicitly optimized against stylistic detectors, detection performance remains surprisingly unaffected. We then seek to understand if stylistic detectors are inherently more robust. To study this question, we explore a new paraphrasing approach that simultaneously aims to close the gap between human writing and machine writing in stylistic feature space while avoiding detection using traditional features. We show that when only a single sample is available for detection, this attack is universally effective across all detectors considered, including those that use writing style. However, as the number of samples available for detection grows, the human and machine distributions become distinguishable. This observation encourages us to introduce AURA, a metric that estimates the overlap between human and machine-generated distributions by analyzing how detector performance improves as more samples become available. Overall, our findings underscore previous recommendations to avoid reliance on machine-text detection.

Detecting anomalous events in satellite telemetry is a critical task in space operations. This task, however, is extremely time-consuming, error-prone and human dependent, thus automated data-driven anomaly detection algorithms have been emerging at a steady pace. However, there are no publicly available datasets of real satellite telemetry accompanied with the ground-truth annotations that could be used to train and verify anomaly detection supervised models. In this article, we address this research gap and introduce the AI-ready benchmark dataset (OPSSAT-AD) containing the telemetry data acquired on board OPS-SAT -- a CubeSat mission which has been operated by the European Space Agency which has come to an end during the night of 22--23 May 2024 (CEST). The dataset is accompanied with the baseline results obtained using 30 supervised and unsupervised classic and deep machine learning algorithms for anomaly detection. They were trained and validated using the training-test dataset split introduced in this work, and we present a suggested set of quality metrics which should be always calculated to confront the new algorithms for anomaly detection while exploiting OPSSAT-AD. We believe that this work may become an important step toward building a fair, reproducible and objective validation procedure that can be used to quantify the capabilities of the emerging anomaly detection techniques in an unbiased and fully transparent way.

Financial services is a prospect industry where unlocked near-term quantum utility could yield profitable potential, and, in particular, quantum machine learning algorithms could potentially benefit businesses by improving the quality of predictive models. Quantum kernel methods have demonstrated success in financial, binary classification tasks, like fraud detection, and avoid issues found in variational quantum machine learning approaches. However, choosing a suitable quantum kernel for a classical dataset remains a challenge. We propose a hybrid, quantum multiple kernel learning (QMKL) methodology that can improve classification quality over a single kernel approach. We test the robustness of QMKL on several financially relevant datasets using both fidelity and projected quantum kernel approaches. We further demonstrate QMKL on quantum hardware using an error mitigation pipeline and show the benefits of QMKL in the large qubit regime.

We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a ResNet and no other changes, our approach improves upon the baselines significantly on instance segmentation and object detection while also reducing the parameters, with minimal overhead in latency. Through the design of BoTNet, we also point out how ResNet bottleneck blocks with self-attention can be viewed as Transformer blocks. Without any bells and whistles, BoTNet achieves 44.4% Mask AP and 49.7% Box AP on the COCO Instance Segmentation benchmark using the Mask R-CNN framework; surpassing the previous best published single model and single scale results of ResNeSt evaluated on the COCO validation set. Finally, we present a simple adaptation of the BoTNet design for image classification, resulting in models that achieve a strong performance of 84.7% top-1 accuracy on the ImageNet benchmark while being up to 1.64x faster in compute time than the popular EfficientNet models on TPU-v3 hardware. We hope our simple and effective approach will serve as a strong baseline for future research in self-attention models for vision

We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures may beused and the model can also be trained on unlabeled data. We demonstrate that energy based training of the joint distribution improves calibration, robustness, andout-of-distribution detection while also enabling our models to generate samplesrivaling the quality of recent GAN approaches. We improve upon recently proposed techniques for scaling up the training of energy based models and presentan approach which adds little overhead compared to standard classification training. Our approach is the first to achieve performance rivaling the state-of-the-artin both generative and discriminative learning within one hybrid model.

We present a neural network TTNet aimed at real-time processing of high-resolution table tennis videos, providing both temporal (events spotting) and spatial (ball detection and semantic segmentation) data. This approach gives core information for reasoning score updates by an auto-referee system. We also publish a multi-task dataset OpenTTGames with videos of table tennis games in 120 fps labeled with events, semantic segmentation masks, and ball coordinates for evaluation of multi-task approaches, primarily oriented on spotting of quick events and small objects tracking. TTNet demonstrated 97.0% accuracy in game events spotting along with 2 pixels RMSE in ball detection with 97.5% accuracy on the test part of the presented dataset. The proposed network allows the processing of downscaled full HD videos with inference time below 6 ms per input tensor on a machine with a single consumer-grade GPU. Thus, we are contributing to the development of real-time multi-task deep learning applications and presenting approach, which is potentially capable of substituting manual data collection by sports scouts, providing support for referees' decision-making, and gathering extra information about the game process.

The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks typically function at the user-prompt or retrieval-augmented generation (RAG) context layer and are inherently single-turn in nature. This limitation restricts cost amplification and diminishes stealth in goal-oriented workflows. To address these issues, we proposed a stealthy, multi-turn economic DoS attack at the tool layer under the Model Context Protocol (MCP). By simply editing text-visible fields and implementing a template-driven return policy, our malicious server preserves function signatures and the terminal benign payload while steering agents into prolonged, verbose tool-calling chains. We optimize these text-only edits with Monte Carlo Tree Search (MCTS) to maximize cost under a task-success constraint. Across six LLMs on ToolBench and BFCL benchmarks, our attack yields trajectories over 60K tokens, increases per-query cost by up to 658 times, raises energy by 100 to 560 times, and pushes GPU key-value (KV) cache occupancy to 35--74%. Standard prompt filters and output trajectory monitors seldom detect these attacks, highlighting the need for defenses that safeguard agentic processes rather than focusing solely on final outcomes. We will release the code soon.

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning interfaces, we introduce covert malicious finetuning, a method to compromise model safety via finetuning while evading detection. Our method constructs a malicious dataset where every individual datapoint appears innocuous, but finetuning on the dataset teaches the model to respond to encoded harmful requests with encoded harmful responses. Applied to GPT-4, our method produces a finetuned model that acts on harmful instructions 99% of the time and avoids detection by defense mechanisms such as dataset inspection, safety evaluations, and input/output classifiers. Our findings question whether black-box finetuning access can be secured against sophisticated adversaries.