Daily Papers

Deep face recognition (FR) models reach near-saturated accuracy but remain opaque: a practitioner cannot ask which semantic attributes a similarity score relied upon. EXPL-FR answers this inside the FR model's own embedding space. A lightweight adapter aligns a vision-language model's (VLM) image encoder with the frozen FR space, trained on face images alone and never on text. Because the VLM's encoders share one space, the same adapter applies to the text encoder, turning 978 attribute prompts in 22 categories, also extendable, into FR-space anchors at no extra cost. We do not assume this transfer works: a face-verification protocol measures it, and an ablation changing only the adapter isolates its contribution. Not every concept survives, because an FR model earns its invariances by discarding the factors it must verify identities across. A label-free detectability measure compares each concept's separability in FR space against the VLM space, and the 100 most detectable form the model's readable semantic signature, which separates identities better than the full vocabulary. We cover four FR backbones and two VLM encoders, EXPL-FR needs no architecture access, and supports identity-level, per-image, and differential explanations. We benchmark attribute-level auditing under three supervision settings, human labels (current practice), VLM pseudo-labels, and our fully prompt-driven audit, against real verification behavior. With no labels, the prompt-driven audit ranks four FR models by their measured per-ethnicity RFW errors and ranks controlled attribute changes by their true verification cost.

AI systems can fail silently. The failure propagates through training loops, evaluation pipelines, and production monitoring stacks until downstream harm makes it visible. This paper introduces evaluation blindness: a measurement function M exhibits evaluation blindness with respect to failure class F when it produces readings indistinguishable from a healthy state while the system is actually failing, with no auxiliary signal flagging the gap. The problem surfaces at two lifecycle stages the literature has treated separately. At training time, reward models are gamed, importance-sampling corrections are silently miscalculated, and benchmark contamination inflates fine-tuning evaluations, all while loss curves look healthy and gradient updates proceed normally. At deployment time, monitoring fails to catch six classes of production failure, including an Operational category that is 100% silent by structural definition. We provide a formal detectability predicate unifying both stages. Four training-time case studies trace concrete breakdowns, including a real implementation bug in TRL PR #6594 where gradients are corrupted as loss decreases normally. A six-class taxonomy validated against 50 real-world incidents from court documents and regulatory filings finds that 53% of verifiable public failures were silent. A failure budget framework ties acceptable failure rates to use-case risk class. The implication is direct: measurement infrastructure is a correctness concern across the full AI lifecycle, not just at evaluation time. Data, code, and taxonomy schema are at https://github.com/priyanka25aug/llm-failure-taxonomy.

Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable signals into LLM outputs by biasing their token distributions. However, it has been reported that watermarked LLMs often perform worse on downstream tasks. We propose PUPPET, a framework that fine-tunes an LLM via reinforcement learning to generate text that is both more detectable and better performing on downstream tasks. We use two reward functions: a detector that outputs a machine-class likelihood and an evaluator that measures a task-specific metric. Experiments on long-form QA, summarization, and essay writing show that LLMs trained with PUPPET achieve high detectability competitive with watermarking methods while outperforming them on downstream tasks. The analysis shows that this optimization can be performed efficiently with only a few thousand samples in 1--2 GPU hours. Moreover, these gains are consistent across out-of-domain tasks, different LLM families, and model sizes, and are even robust to paraphrasing attacks.

The rapid progress of image generative AI has blurred the boundary between synthetic and real images, fueling an arms race between generators and discriminators. This paper investigates the conditions under which discriminators are most disadvantaged in this competition. We analyze two key factors: data dimensionality and data complexity. While increased dimensionality often strengthens the discriminators ability to detect subtle inconsistencies, complexity introduces a more nuanced effect. Using Kolmogorov complexity as a measure of intrinsic dataset structure, we show that both very simple and highly complex datasets reduce the detectability of synthetic images; generators can learn simple datasets almost perfectly, whereas extreme diversity masks imperfections. In contrast, intermediate-complexity datasets create the most favorable conditions for detection, as generators fail to fully capture the distribution and their errors remain visible.

The overwhelming volume of data generated and indexed by search engines poses a significant challenge in retrieving documents from the index efficiently and effectively. Even with a well-crafted query, several relevant documents often get buried among a multitude of competing documents, resulting in reduced accessibility or `findability' of the desired document. Consequently, it is crucial to develop a robust methodology for assessing this dimension of Information Retrieval (IR) system performance. While previous studies have focused on measuring document accessibility disregarding user queries and document relevance, there exists no metric to quantify the findability of a document within a given IR system without resorting to manual labor. This paper aims to address this gap by defining and deriving a metric to evaluate the findability of documents as perceived by end-users. Through experiments, we demonstrate the varying impact of different retrieval models and collections on the findability of documents. Furthermore, we establish the findability measure as an independent metric distinct from retrievability, an accessibility measure introduced in prior literature.

The paper considers a new quantitative-qualitative proximity measure for the features of information objects, where data enters a common information resource from several sources independently. The goal is to determine the possibility of their relation to the same physical object (observation object). The proposed measure accounts for the possibility of differences in individual feature values - both quantitative and qualitative - caused by existing determination errors. To analyze the proximity of quantitative feature values, the author employs a probabilistic measure; for qualitative features, a measure of possibility is used. The paper demonstrates the feasibility of the proposed measure by checking its compliance with the axioms required of any measure. Unlike many known measures, the proposed approach does not require feature value transformation to ensure comparability. The work also proposes several variants of measures to determine the proximity of information objects (IO) based on a group of diverse features.

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.

Commonly used evaluation measures including Recall, Precision, F-Measure and Rand Accuracy are biased and should not be used without clear understanding of the biases, and corresponding identification of chance or base case levels of the statistic. Using these measures a system that performs worse in the objective sense of Informedness, can appear to perform better under any of these commonly used measures. We discuss several concepts and measures that reflect the probability that prediction is informed versus chance. Informedness and introduce Markedness as a dual measure for the probability that prediction is marked versus chance. Finally we demonstrate elegant connections between the concepts of Informedness, Markedness, Correlation and Significance as well as their intuitive relationships with Recall and Precision, and outline the extension from the dichotomous case to the general multi-class case.

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.

Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring changes what the checker reports. Measuring false alarms on human-verified-correct ProcessBench traces with the present task held byte-identical, we find that a completed audit -> repair episode already in the model's context lowers false alarms in 15 of 15 model x wording combinations, by 2.8 to 11.5 percentage points against a length-matched non-audit control, a 9 to 25% reduction relative to that control. The direction contradicts what the accumulated-message literature predicts: an episode whose audit reported an error lowers false alarms further still, at all five wordings on the model where that manipulation lands cleanly, though a negativity asymmetry predicts more flagging. Decomposing the episode finds repair content and audit verdict complementary: different components carry the effect on different model families. Signal-detection analysis locates the change in the threshold rather than in discrimination -- the criterion moves in 15 of 15 combinations and survives correction in 13 while d' survives in none, though the d' test is half as sensitive by construction -- and a hand audit of 50 false alarms finds 82% simply wrong, so at this operating point the shift need not be harmful. With reasoning enabled the effect keeps its relative size on both models tested, and the threshold reading holds there too.

Designing metrics for evaluating instance segmentation revolves around comprehensively considering object detection and segmentation accuracy. However, other important properties, such as sensitivity, continuity, and equality, are overlooked in the current study. In this paper, we reveal that most existing metrics have a limited resolution of segmentation quality. They are only conditionally sensitive to the change of masks or false predictions. For certain metrics, the score can change drastically in a narrow range which could provide a misleading indication of the quality gap between results. Therefore, we propose a new metric called sortedAP, which strictly decreases with both object- and pixel-level imperfections and has an uninterrupted penalization scale over the entire domain. We provide the evaluation toolkit and experiment code at https://www.github.com/looooongChen/sortedAP.

With the rise of prolific ChatGPT, the risk and consequences of AI-generated text has increased alarmingly. To address the inevitable question of ownership attribution for AI-generated artifacts, the US Copyright Office released a statement stating that 'If a work's traditional elements of authorship were produced by a machine, the work lacks human authorship and the Office will not register it'. Furthermore, both the US and the EU governments have recently drafted their initial proposals regarding the regulatory framework for AI. Given this cynosural spotlight on generative AI, AI-generated text detection (AGTD) has emerged as a topic that has already received immediate attention in research, with some initial methods having been proposed, soon followed by emergence of techniques to bypass detection. This paper introduces the Counter Turing Test (CT^2), a benchmark consisting of techniques aiming to offer a comprehensive evaluation of the robustness of existing AGTD techniques. Our empirical findings unequivocally highlight the fragility of the proposed AGTD methods under scrutiny. Amidst the extensive deliberations on policy-making for regulating AI development, it is of utmost importance to assess the detectability of content generated by LLMs. Thus, to establish a quantifiable spectrum facilitating the evaluation and ranking of LLMs according to their detectability levels, we propose the AI Detectability Index (ADI). We conduct a thorough examination of 15 contemporary LLMs, empirically demonstrating that larger LLMs tend to have a higher ADI, indicating they are less detectable compared to smaller LLMs. We firmly believe that ADI holds significant value as a tool for the wider NLP community, with the potential to serve as a rubric in AI-related policy-making.

Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between real and generated images has been the Fr\'echet Inception Distance (FID) score. Because it does not differentiate the fidelity and diversity aspects of the generated images, recent papers have introduced variants of precision and recall metrics to diagnose those properties separately. In this paper, we show that even the latest version of the precision and recall metrics are not reliable yet. For example, they fail to detect the match between two identical distributions, they are not robust against outliers, and the evaluation hyperparameters are selected arbitrarily. We propose density and coverage metrics that solve the above issues. We analytically and experimentally show that density and coverage provide more interpretable and reliable signals for practitioners than the existing metrics. Code: https://github.com/clovaai/generative-evaluation-prdc.

Bounding boxes uniquely characterize object detection, where a good detector gives accurate bounding boxes of categories of interest. However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability. In this work, we find under feature map dropout, good detectors tend to output bounding boxes whose locations do not change much, while bounding boxes of poor detectors will undergo noticeable position changes. We compute the box stability score (BoS score) to reflect this stability. Specifically, given an image, we compute a normal set of bounding boxes and a second set after feature map dropout. To obtain BoS score, we use bipartite matching to find the corresponding boxes between the two sets and compute the average Intersection over Union (IoU) across the entire test set. We contribute to finding that BoS score has a strong, positive correlation with detection accuracy measured by mean average precision (mAP) under various test environments. This relationship allows us to predict the accuracy of detectors on various real-world test sets without accessing test ground truths, verified on canonical detection tasks such as vehicle detection and pedestrian detection. Code and data are available at https://github.com/YangYangGirl/BoS.

While there has been a growing research interest in developing out-of-distribution (OOD) detection methods, there has been comparably little discussion around how these methods should be evaluated. Given their relevance for safe(r) AI, it is important to examine whether the basis for comparing OOD detection methods is consistent with practical needs. In this work, we take a closer look at the go-to metrics for evaluating OOD detection, and question the approach of exclusively reducing OOD detection to a binary classification task with little consideration for the detection threshold. We illustrate the limitations of current metrics (AUROC & its friends) and propose a new metric - Area Under the Threshold Curve (AUTC), which explicitly penalizes poor separation between ID and OOD samples. Scripts and data are available at https://github.com/glhr/beyond-auroc

Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning models has proven effective for detecting misbehavior. However, this "monitorability" may be fragile under different training procedures, data sources, or even continued system scaling. To measure and track monitorability, we propose three evaluation archetypes (intervention, process, and outcome-property) and a new monitorability metric, and introduce a broad evaluation suite. We demonstrate that these evaluations can catch simple model organisms trained to have obfuscated CoTs, and that CoT monitoring is more effective than action-only monitoring in practical settings. We compare the monitorability of various frontier models and find that most models are fairly, but not perfectly, monitorable. We also evaluate how monitorability scales with inference-time compute, reinforcement learning optimization, and pre-training model size. We find that longer CoTs are generally more monitorable and that RL optimization does not materially decrease monitorability even at the current frontier scale. Notably, we find that for a model at a low reasoning effort, we could instead deploy a smaller model at a higher reasoning effort (thereby matching capabilities) and obtain a higher monitorability, albeit at a higher overall inference compute cost. We further investigate agent-monitor scaling trends and find that scaling a weak monitor's test-time compute when monitoring a strong agent increases monitorability. Giving the weak monitor access to CoT not only improves monitorability, but it steepens the monitor's test-time compute to monitorability scaling trend. Finally, we show we can improve monitorability by asking models follow-up questions and giving their follow-up CoT to the monitor.

Camouflage is primarily context-dependent yet current metrics for camouflaged scenarios overlook this critical factor. Instead, these metrics are originally designed for evaluating general or salient objects, with an inherent assumption of uncorrelated spatial context. In this paper, we propose a new contextualized evaluation paradigm, Context-measure, built upon a probabilistic pixel-aware correlation framework. By incorporating spatial dependencies and pixel-wise camouflage quantification, our measure better aligns with human perception. Extensive experiments across three challenging camouflaged object segmentation datasets show that Context-measure delivers more reliability than existing context-independent metrics. Our measure can provide a foundational evaluation benchmark for various computer vision applications involving camouflaged patterns, such as agricultural, industrial, and medical scenarios. Code is available at https://github.com/pursuitxi/Context-measure.

Man-made scenes can be densely packed, containing numerous objects, often identical, positioned in close proximity. We show that precise object detection in such scenes remains a challenging frontier even for state-of-the-art object detectors. We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings. Our contributions include: (1) A layer for estimating the Jaccard index as a detection quality score; (2) a novel EM merging unit, which uses our quality scores to resolve detection overlap ambiguities; finally, (3) an extensive, annotated data set, SKU-110K, representing packed retail environments, released for training and testing under such extreme settings. Detection tests on SKU-110K and counting tests on the CARPK and PUCPR+ show our method to outperform existing state-of-the-art with substantial margins. The code and data will be made available on www.github.com/eg4000/SKU110K_CVPR19.

We present Boundary IoU (Intersection-over-Union), a new segmentation evaluation measure focused on boundary quality. We perform an extensive analysis across different error types and object sizes and show that Boundary IoU is significantly more sensitive than the standard Mask IoU measure to boundary errors for large objects and does not over-penalize errors on smaller objects. The new quality measure displays several desirable characteristics like symmetry w.r.t. prediction/ground truth pairs and balanced responsiveness across scales, which makes it more suitable for segmentation evaluation than other boundary-focused measures like Trimap IoU and F-measure. Based on Boundary IoU, we update the standard evaluation protocols for instance and panoptic segmentation tasks by proposing the Boundary AP (Average Precision) and Boundary PQ (Panoptic Quality) metrics, respectively. Our experiments show that the new evaluation metrics track boundary quality improvements that are generally overlooked by current Mask IoU-based evaluation metrics. We hope that the adoption of the new boundary-sensitive evaluation metrics will lead to rapid progress in segmentation methods that improve boundary quality.

Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.

We wish to measure the information coverage of an ad hoc retrieval algorithm, that is, how much of the range of available relevant information is covered by the search results. Information coverage is a central aspect for retrieval, especially when the retrieval system is integrated with generative models in a retrieval-augmented generation (RAG) system. The classic metrics for ad hoc retrieval, precision and recall, reward a system as more and more relevant documents are retrieved. However, since relevance in ad hoc test collections is defined for a document without any relation to other documents that might contain the same information, high recall is sufficient but not necessary to ensure coverage. The same is true for other metrics such as rank-biased precision (RBP), normalized discounted cumulative gain (nDCG), and mean average precision (MAP). Test collections developed around the notion of diversity ranking in web search incorporate multiple aspects that support a concept of coverage in the web domain. In this work, we construct a suite of collections for evaluating information coverage from existing collections. This suite offers researchers a unified testbed spanning multiple genres and tasks. All topics, nuggets, relevance labels, and baseline rankings are released on Hugging Face Datasets, along with instructions for accessing the publicly available document collections.

Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfeits has been a taxing problem in the image forensics community, a recent class of forensic detectors -- universal detectors -- are able to surprisingly spot counterfeit images regardless of generator architectures, loss functions, training datasets, and resolutions. This intriguing property suggests the possible existence of transferable forensic features (T-FF) in universal detectors. In this work, we conduct the first analytical study to discover and understand T-FF in universal detectors. Our contributions are 2-fold: 1) We propose a novel forensic feature relevance statistic (FF-RS) to quantify and discover T-FF in universal detectors and, 2) Our qualitative and quantitative investigations uncover an unexpected finding: color is a critical T-FF in universal detectors. Code and models are available at https://keshik6.github.io/transferable-forensic-features/

The ability to detect learned objects regardless of their appearance is crucial for autonomous systems in real-world applications. Especially for detecting humans, which is often a fundamental task in safety-critical applications, it is vital to prevent errors. To address this challenge, we propose a self-monitoring framework that allows for the perception system to perform plausibility checks at runtime. We show that by incorporating an additional component for detecting human body parts, we are able to significantly reduce the number of missed human detections by factors of up to 9 when compared to a baseline setup, which was trained only on holistic person objects. Additionally, we found that training a model jointly on humans and their body parts leads to a substantial reduction in false positive detections by up to 50% compared to training on humans alone. We performed comprehensive experiments on the publicly available datasets DensePose and Pascal VOC in order to demonstrate the effectiveness of our framework. Code is available at https://github.com/ FraunhoferIKS/smf-object-detection.

Point-adjustment (PA), for years the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al. (2022) to award near-perfect F1 to random anomaly scores. The field adopted a suite of replacement metrics (PA%K, range-based precision/recall, affiliation precision/recall, and Volume-Under-the-Surface, VUS, ROC/PR). We ask, independently and adversarially, whether these resist no-skill detectors on real benchmarks, and find the answer turns entirely on one overlooked variable: N, the number of random attempts an adversary reports the best of. Under a single honest run (N=1), not one replacement metric is gameable on any of six benchmarks (UCR, SMD, SMAP, MSL, NAB, PSM): a random detector reaches 90% of the best real detector's score on at most 11% of series for affiliation-F1, 5% for the ROC family, and 2% for the PR-based metrics and PA%K. But under best-of-N reporting, the seed-shopping endemic to ML, the metrics split sharply. affiliation-F1 and every ROC-based metric inflate steeply, affiliation crossing gameable (25% of series) by N=3 and reaching 0.98 at the full pool (N=41), the ROC family crossing by N=9-11; the PR-based metrics and PA%K stay near-flat at every N, floored near the anomaly prevalence (the lone exception is NAB at large N). A paired test finds VUS-ROC inflated on 131 series where its sibling VUS-PR is not, and never the reverse. The ROC-vs-PR split follows from the order-statistic behaviour of AUC under extreme class imbalance (a random PR-AUC is floored at prevalence); affiliation inflates by a second route, its extreme single-run leniency (already fragile at N=1). We release a pip-installable stress-test harness, and recommend reporting single-run scores or disclosing N and preferring PR-based metrics, which resist best-of-N inflation on nearly every benchmark.

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attacks possible. We demonstrate that existing observation-space attacks on reinforcement learning agents have a common weakness: while effective, their lack of temporal consistency makes them detectable using automated means or human inspection. Detectability is undesirable to adversaries as it may trigger security escalations. We introduce perfect illusory attacks, a novel form of adversarial attack on sequential decision-makers that is both effective and provably statistically undetectable. We then propose the more versatile R-attacks, which result in observation transitions that are consistent with the state-transition function of the adversary-free environment and can be learned end-to-end. Compared to existing attacks, we empirically find R-attacks to be significantly harder to detect with automated methods, and a small study with human subjects suggests they are similarly harder to detect for humans. We propose that undetectability should be a central concern in the study of adversarial attacks on mixed-autonomy settings.

Reading measurement instruments is effortless for humans and requires relatively little domain expertise, yet it remains surprisingly challenging for current vision-language models (VLMs) as we find in preliminary evaluation. In this work, we introduce MeasureBench, a benchmark on visual measurement reading covering both real-world and synthesized images of various types of measurements, along with an extensible pipeline for data synthesis. Our pipeline procedurally generates a specified type of gauge with controllable visual appearance, enabling scalable variation in key details such as pointers, scales, fonts, lighting, and clutter. Evaluation on popular proprietary and open-weight VLMs shows that even the strongest frontier VLMs struggle measurement reading in general. A consistent failure mode is indicator localization: models can read digits or labels but misidentify the key positions of pointers or alignments, leading to big numeric errors despite plausible textual reasoning. We have also conducted preliminary experiments with reinforcement learning over synthetic data, and find encouraging results on in-domain synthetic subset but less promising for real-world images. Our analysis highlights a fundamental limitation of current VLMs in fine-grained spatial grounding. We hope this resource can help future advances on visually grounded numeracy and precise spatial perception of VLMs, bridging the gap between recognizing numbers and measuring the world.

Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best performing approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose PatchCore, which uses a maximally representative memory bank of nominal patch-features. PatchCore offers competitive inference times while achieving state-of-the-art performance for both detection and localization. On the challenging, widely used MVTec AD benchmark PatchCore achieves an image-level anomaly detection AUROC score of up to 99.6%, more than halving the error compared to the next best competitor. We further report competitive results on two additional datasets and also find competitive results in the few samples regime.^* Work done during a research internship at Amazon AWS. Code: github.com/amazon-research/patchcore-inspection.

This study proposes a two-phase methodology for detecting and classifying auxiliary insulation in structural components. In the detection phase, a YOLOv8x model is trained on a dataset of complete structural blueprints, each annotated with bounding boxes indicating areas that should contain insulation. In the classification phase, these detected insulation patches are cropped and categorized into two classes: present or missing. These are then used to train a YOLOv8x-CLS model that determines the presence or absence of auxiliary insulation. Preprocessing steps for both datasets included annotation, augmentation, and appropriate cropping of the insulation regions. The detection model achieved a mean average precision (mAP) score of 82%, while the classification model attained an accuracy of 98%. These findings demonstrate the effectiveness of the proposed approach in automating insulation detection and classification, providing a foundation for further advancements in this domain.

It is known that human speech and certain animal vocalizations can convey meaningful content because we can decipher the content that a given utterance does convey. This paper explores an alternative approach to determining whether a signal is meaningful, one that analyzes only the signal itself and is independent of what the conveyed meaning might be. We devise a method that takes a waveform as input and outputs a score indicating its degree of `meaningfulness`. We cluster contiguous portions of the input to minimize the total description length, and then take the length of the code of the assigned cluster labels as meaningfulness score. We evaluate our method empirically, against several baselines, and show that it is the only one to give a high score to human speech in various languages and with various speakers, a moderate score to animal vocalizations from birds and orcas, and a low score to ambient noise from various sources.

Anomaly detection methods identify examples that do not follow the expected behaviour, typically in an unsupervised fashion, by assigning real-valued anomaly scores to the examples based on various heuristics. These scores need to be transformed into actual predictions by thresholding, so that the proportion of examples marked as anomalies equals the expected proportion of anomalies, called contamination factor. Unfortunately, there are no good methods for estimating the contamination factor itself. We address this need from a Bayesian perspective, introducing a method for estimating the posterior distribution of the contamination factor of a given unlabeled dataset. We leverage on outputs of several anomaly detectors as a representation that already captures the basic notion of anomalousness and estimate the contamination using a specific mixture formulation. Empirically on 22 datasets, we show that the estimated distribution is well-calibrated and that setting the threshold using the posterior mean improves the anomaly detectors' performance over several alternative methods. All code is publicly available for full reproducibility.

Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the AUROC in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve (AUGRC), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of AUGRC on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.

We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes. AutoMonitor-Bench consists of 3,010 carefully annotated test samples spanning question answering, code generation, and reasoning, with paired misbehavior and benign instances. We evaluate monitors using two complementary metrics: Miss Rate (MR) and False Alarm Rate (FAR), capturing failures to detect misbehavior and oversensitivity to benign behavior, respectively. Evaluating 12 proprietary and 10 open-source LLMs, we observe substantial variability in monitoring performance and a consistent trade-off between MR and FAR, revealing an inherent safety-utility tension. To further explore the limits of monitor reliability, we construct a large-scale training corpus of 153,581 samples and fine-tune Qwen3-4B-Instruction to investigate whether training on known, relatively easy-to-construct misbehavior datasets improves monitoring performance on unseen and more implicit misbehaviors. Our results highlight the challenges of reliable, scalable misbehavior monitoring and motivate future work on task-aware designing and training strategies for LLM-based monitors.

Performing an adequate evaluation of sound event detection (SED) systems is far from trivial and is still subject to ongoing research. The recently proposed polyphonic sound detection (PSD)-receiver operating characteristic (ROC) and PSD score (PSDS) make an important step into the direction of an evaluation of SED systems which is independent from a certain decision threshold. This allows to obtain a more complete picture of the overall system behavior which is less biased by threshold tuning. Yet, the PSD-ROC is currently only approximated using a finite set of thresholds. The choice of the thresholds used in approximation, however, can have a severe impact on the resulting PSDS. In this paper we propose a method which allows for computing system performance on an evaluation set for all possible thresholds jointly, enabling accurate computation not only of the PSD-ROC and PSDS but also of other collar-based and intersection-based performance curves. It further allows to select the threshold which best fulfills the requirements of a given application. Source code is publicly available in our SED evaluation package sed_scores_eval.

Industrial diagrams such as piping and instrumentation diagrams (P&IDs) are essential for the design, operation, and maintenance of industrial plants. Converting these diagrams into digital form is an important step toward building digital twins and enabling intelligent industrial automation. A central challenge in this digitalization process is accurate object detection. Although recent advances have significantly improved object detection algorithms, there remains a lack of methods to automatically evaluate the quality of their outputs. This paper addresses this gap by introducing a framework that employs Visual Language Models (VLMs) to assess object detection results and guide their refinement. The approach exploits the multimodal capabilities of VLMs to identify missing or inconsistent detections, thereby enabling automated quality assessment and improving overall detection performance on complex industrial diagrams.

Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial risks of misinformation. Existing benchmarks, however, provide limited evidence on detector and generator behavior in such settings, including how detectability varies with generation conditions, how people perceive generated videos, and whether detectors remain reliable during social dissemination. To address this gap, we introduce RA-Bench, a benchmark for AI-generated video detection that uses Real videos as Anchors. RA-Bench contains 17,886 videos, comprising 1,830 real-video anchors across 10 social-risk categories and 16,056 generated clips from four open-source and five closed-source generators. Based on RA-Bench, we organize our evaluation along three dimensions. We first assess detector generalization across seven traditional detectors, ten zero-shot multimodal models under three review settings, and two MLLMs specifically fine-tuned on AI-generated video detection. Across these methods, none of the three detector families generalizes consistently across RA-Bench instances. We then examine how detectability varies with generation quality, conditioning information, and sampling seeds. These analyses show that generation properties affect detector families differently, while source-level detection patterns remain stable across seeds. Finally, we study human authenticity judgments and detector reliability during social dissemination. We find that videos that mislead people are also difficult for current detectors, and that social dissemination makes detection harder. Together, these findings show that current methods struggle to detect realistic AI-generated videos, highlighting the need for detectors robust to evolving video generators.

Hyperspectral imaging (HSI) is useful for material discrimination, but operational mine screening also depends on how many false alarms must be inspected before targets are found. This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM). We compare a ground-measured SVC signature, a fully informed in-scene core-pixel signature, and a simulated human-in-the-loop signature bootstrap. Besides receiver operating characteristic area under the curve and average precision, we report target-discovery curves and spatial candidate-review counts. Full-review bootstrapping reaches the fully informed in-scene signature case after all seven target regions are verified, but the required inspection effort varies strongly: ACE confirms all regions in two rounds and nine candidate inspections, whereas the SAM variants need thousands of candidate reviews for their final target locations. Code is available at https://github.com/SagarLekhak/IEEE_WHISPERS_2026_UAV_HSI_PFM1.

Speech language models have recently demonstrated great potential as universal speech processing systems. Such models have the ability to model the rich acoustic information existing in audio signals, beyond spoken content, such as emotion, background noise, etc. Despite this, evaluation benchmarks which evaluate awareness to a wide range of acoustic aspects, are lacking. To help bridge this gap, we introduce SALMon, a novel evaluation suite encompassing background noise, emotion, speaker identity and room impulse response. The proposed benchmarks both evaluate the consistency of the inspected element and how much it matches the spoken text. We follow a modelling based approach, measuring whether a model gives correct samples higher scores than incorrect ones. This approach makes the benchmark fast to compute even for large models. We evaluated several speech language models on SALMon, thus highlighting the strengths and weaknesses of each evaluated method. Code and data are publicly available at https://pages.cs.huji.ac.il/adiyoss-lab/salmon/ .

We present a straightforward statistical test to detect certain violations of the assumption that the data are Independent and Identically Distributed (IID). The specific form of violation considered is common across real-world applications: whether the examples are ordered in the dataset such that almost adjacent examples tend to have more similar feature values (e.g. due to distributional drift, or attractive interactions between datapoints). Based on a k-Nearest Neighbors estimate, our approach can be used to audit any multivariate numeric data as well as other data types (image, text, audio, etc.) that can be numerically represented, perhaps with model embeddings. Compared with existing methods to detect drift or auto-correlation, our approach is both applicable to more types of data and also able to detect a wider variety of IID violations in practice. Code: https://github.com/cleanlab/cleanlab

In industrial settings, surface defects on steel can significantly compromise its service life and elevate potential safety risks. Traditional defect detection methods predominantly rely on manual inspection, which suffers from low efficiency and high costs. Although automated defect detection approaches based on Convolutional Neural Networks(e.g., Mask R-CNN) have advanced rapidly, their reliability remains challenged due to data annotation uncertainties during deep model training and overfitting issues. These limitations may lead to detection deviations when processing the given new test samples, rendering automated detection processes unreliable. To address this challenge, we first evaluate the detection model's practical performance through calibration data that satisfies the independent and identically distributed (i.i.d) condition with test data. Specifically, we define a loss function for each calibration sample to quantify detection error rates, such as the complement of recall rate and false discovery rate. Subsequently, we derive a statistically rigorous threshold based on a user-defined risk level to identify high-probability defective pixels in test images, thereby constructing prediction sets (e.g., defect regions). This methodology ensures that the expected error rate (mean error rate) on the test set remains strictly bounced by the predefined risk level. Additionally, we observe a negative correlation between the average prediction set size and the risk level on the test set, establishing a statistically rigorous metric for assessing detection model uncertainty. Furthermore, our study demonstrates robust and efficient control over the expected test set error rate across varying calibration-to-test partitioning ratios, validating the method's adaptability and operational effectiveness.

We introduce MCUBench, a benchmark featuring over 100 YOLO-based object detection models evaluated on the VOC dataset across seven different MCUs. This benchmark provides detailed data on average precision, latency, RAM, and Flash usage for various input resolutions and YOLO-based one-stage detectors. By conducting a controlled comparison with a fixed training pipeline, we collect comprehensive performance metrics. Our Pareto-optimal analysis shows that integrating modern detection heads and training techniques allows various YOLO architectures, including legacy models like YOLOv3, to achieve a highly efficient tradeoff between mean Average Precision (mAP) and latency. MCUBench serves as a valuable tool for benchmarking the MCU performance of contemporary object detectors and aids in model selection based on specific constraints.

Resonant anomaly detection methods have great potential for enhancing the sensitivity of traditional bump hunt searches. A key component of these methods is a high quality background template used to produce an anomaly score. Using the LHC Olympics R&D dataset, we demonstrate that this background template can also be repurposed to directly estimate the background expectation in a simple cut and count setup. In contrast to a traditional bump hunt, no fit to the invariant mass distribution is needed, thereby avoiding the potential problem of background sculpting. Furthermore, direct background estimation allows working with large background rejection rates, where resonant anomaly detection methods typically show their greatest improvement in significance.

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.

Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical observation that applying unsupervised contrastive learning to noisy, web-crawled datasets yields a feature representation under which the in-distribution (ID) and out-of-distribution (OOD) samples are linearly separable. We show that direct estimation of the separating hyperplane can indeed offer an accurate detection of OOD samples, and yet, surprisingly, this detection does not translate into gains in classification accuracy. Digging deeper into this phenomenon, we discover that the near-perfect detection misses a type of clean examples that are valuable for supervised learning. These examples often represent visually simple images, which are relatively easy to identify as clean examples using standard loss- or distance-based methods despite being poorly separated from the OOD distribution using unsupervised learning. Because we further observe a low correlation with SOTA metrics, this urges us to propose a hybrid solution that alternates between noise detection using linear separation and a state-of-the-art (SOTA) small-loss approach. When combined with the SOTA algorithm PLS, we substantially improve SOTA results for real-world image classification in the presence of web noise github.com/PaulAlbert31/LSA

Accurate uncertainty estimates are essential for deploying deep object detectors in safety-critical systems. The development and evaluation of probabilistic object detectors have been hindered by shortcomings in existing performance measures, which tend to involve arbitrary thresholds or limit the detector's choice of distributions. In this work, we propose to view object detection as a set prediction task where detectors predict the distribution over the set of objects. Using the negative log-likelihood for random finite sets, we present a proper scoring rule for evaluating and training probabilistic object detectors. The proposed method can be applied to existing probabilistic detectors, is free from thresholds, and enables fair comparison between architectures. Three different types of detectors are evaluated on the COCO dataset. Our results indicate that the training of existing detectors is optimized toward non-probabilistic metrics. We hope to encourage the development of new object detectors that can accurately estimate their own uncertainty. Code available at https://github.com/georghess/pmb-nll.

Standard evaluation of LLM confidence relies on calibration metrics (ECE, Brier score) that conflate two distinct capacities: how much a model knows (Type-1 sensitivity) and how well it knows what it knows (Type-2 metacognitive sensitivity). We introduce an evaluation framework based on Type-2 Signal Detection Theory that decomposes these capacities using meta-d' and the metacognitive efficiency ratio M-ratio. Applied to four LLMs (Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.3, Llama-3-8B-Base, Gemma-2-9B-Instruct) across 224,000 factual QA trials, we find: (1) metacognitive efficiency varies substantially across models even when Type-1 sensitivity is similar -- Mistral achieves the highest d' but the lowest M-ratio; (2) metacognitive efficiency is domain-specific, with different models showing different weakest domains, invisible to aggregate metrics; (3) temperature manipulation shifts Type-2 criterion while meta-d' remains stable for two of four models, dissociating confidence policy from metacognitive capacity; (4) AUROC_2 and M-ratio produce fully inverted model rankings, demonstrating these metrics answer fundamentally different evaluation questions. The meta-d' framework reveals which models "know what they don't know" versus which merely appear well-calibrated due to criterion placement -- a distinction with direct implications for model selection, deployment, and human-AI collaboration. Pre-registered analysis; code and data publicly available.

Excluding irrelevant features in a pattern recognition task plays an important role in maintaining a simpler machine learning model and optimizing the computational efficiency. Nowadays with the rise of large scale datasets, feature selection is in great demand as it becomes a central issue when facing high-dimensional datasets. The present study provides a new measure of saliency for features by employing a Sensitivity Analysis (SA) technique called the extended Fourier amplitude sensitivity test, and a well-trained Feedforward Neural Network (FNN) model, which ultimately leads to the selection of a promising optimal feature subset. Ideas of the paper are mainly demonstrated based on adopting FNN model for feature selection in classification problems. But in the end, a generalization framework is discussed in order to give insights into the usage in regression problems as well as expressing how other function approximate models can be deployed. Effectiveness of the proposed method is verified by result analysis and data visualization for a series of experiments over several well-known datasets drawn from UCI machine learning repository.

This work defines a new framework for performance evaluation of polyphonic sound event detection (SED) systems, which overcomes the limitations of the conventional collar-based event decisions, event F-scores and event error rates. The proposed framework introduces a definition of event detection that is more robust against labelling subjectivity. It also resorts to polyphonic receiver operating characteristic (ROC) curves to deliver more global insight into system performance than F1-scores, and proposes a reduction of these curves into a single polyphonic sound detection score (PSDS), which allows system comparison independently from operating points (OPs). The presented method also delivers better insight into data biases and classification stability across sound classes. Furthermore, it can be tuned to varying applications in order to match a variety of user experience requirements. The benefits of the proposed approach are demonstrated by re-evaluating the baseline and two of the top-performing systems from DCASE 2019 Task 4.

Correctness of instance segmentation constitutes counting the number of objects, correctly localizing all predictions and classifying each localized prediction. Average Precision is the de-facto metric used to measure all these constituents of segmentation. However, this metric does not penalize duplicate predictions in the high-recall range, and cannot distinguish instances that are localized correctly but categorized incorrectly. This weakness has inadvertently led to network designs that achieve significant gains in AP but also introduce a large number of false positives. We therefore cannot rely on AP to choose a model that provides an optimal tradeoff between false positives and high recall. To resolve this dilemma, we review alternative metrics in the literature and propose two new measures to explicitly measure the amount of both spatial and categorical duplicate predictions. We also propose a Semantic Sorting and NMS module to remove these duplicates based on a pixel occupancy matching scheme. Experiments show that modern segmentation networks have significant gains in AP, but also contain a considerable amount of duplicates. Our Semantic Sorting and NMS can be added as a plug-and-play module to mitigate hedged predictions and preserve AP.

Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper systematically pressure-tests probe-based metrics across the Gemma 3 model family (1B-27B parameters), diagnosing why they fail rather than merely documenting that they fail. We test four hypotheses about deception encoding: (1) single linear direction, (2) multi-dimensional subspace, (3) convex conic hull, (4) entropy proxy. Our design includes cross-domain transfer matrices, multi-dimensional probe analysis with permutation null baselines, entropy-residualization tests, and distractor evaluations across 8 stylistic shifts. We find that: (a) probes achieve near-perfect AUROC (>=0.998) on clean data but collapse under stylistic shifts; style-augmented probes recover near-perfect detection (mean AUROC 0.979-0.983) on unseen styles; (b) the single-direction hypothesis is rejected (k=1 captures only 0.61-0.80 AUROC), with cross-domain transfer failure confirmed as geometric rather than layer-mismatch-driven; (c) the entropy-proxy hypothesis is rejected (max |rho|=0.454, max Delta-AUROC after residualization=0.004); and (d) deception does not form a significant linear subspace (per-domain k*=0), yet multi-dimensional probes (k>=5) recover the signal through distributed sub-threshold features. Probe fragility reflects distributional narrowness rather than an architectural limitation: style-augmented probes recover near-perfect detection at both 4B and 27B, establishing that the inverse scaling pattern is a training-distribution artifact rather than a genuine scale-dependent phenomenon.

Random projection is a common technique for designing algorithms in a variety of areas, including information retrieval, compressive sensing and measuring of outlyingness. In this work, the original random projection outlyingness measure is modified and associated with a neural network to obtain an unsupervised anomaly detection method able to handle multimodal normality. Theoretical and experimental arguments are presented to justify the choice of the anomaly score estimator. The performance of the proposed neural network approach is comparable to a state-of-the-art anomaly detection method. Experiments conducted on the MNIST, Fashion-MNIST and CIFAR-10 datasets show the relevance of the proposed approach.

Given a set of pre-trained models, how can we quickly and accurately find the most useful pre-trained model for a downstream task? Transferability measurement is to quantify how transferable is a pre-trained model learned on a source task to a target task. It is used for quickly ranking pre-trained models for a given task and thus becomes a crucial step for transfer learning. Existing methods measure transferability as the discrimination ability of a source model for a target data before transfer learning, which cannot accurately estimate the fine-tuning performance. Some of them restrict the application of transferability measurement in selecting the best supervised pre-trained models that have classifiers. It is important to have a general method for measuring transferability that can be applied in a variety of situations, such as selecting the best self-supervised pre-trained models that do not have classifiers, and selecting the best transferring layer for a target task. In this work, we propose TMI (TRANSFERABILITY MEASUREMENT WITH INTRA-CLASS FEATURE VARIANCE), a fast and accurate algorithm to measure transferability. We view transferability as the generalization of a pre-trained model on a target task by measuring intra-class feature variance. Intra-class variance evaluates the adaptability of the model to a new task, which measures how transferable the model is. Compared to previous studies that estimate how discriminative the models are, intra-class variance is more accurate than those as it does not require an optimal feature extractor and classifier. Extensive experiments on real-world datasets show that TMI outperforms competitors for selecting the top-5 best models, and exhibits consistently better correlation in 13 out of 17 cases.

What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step to improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG^2 dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG^2 Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.

We here propose a machine learning approach for monitoring particle detectors in real-time. The goal is to assess the compatibility of incoming experimental data with a reference dataset, characterising the data behaviour under normal circumstances, via a likelihood-ratio hypothesis test. The model is based on a modern implementation of kernel methods, nonparametric algorithms that can learn any continuous function given enough data. The resulting approach is efficient and agnostic to the type of anomaly that may be present in the data. Our study demonstrates the effectiveness of this strategy on multivariate data from drift tube chamber muon detectors.

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This visibility could help us spot unsafe or misaligned behavior (monitorability), but only if the CoT is transparent about its internal reasoning (faithfulness). Fully measuring faithfulness is difficult, so researchers often focus on examining the CoT in cases where the model changes its answer after adding a cue to the input. This proxy finds some instances of unfaithfulness but loses information when the model maintains its answer, and does not investigate aspects of reasoning not tied to the cue. We extend these results to a more holistic sense of monitorability by introducing verbosity: whether the CoT lists every factor needed to solve the task. We combine faithfulness and verbosity into a single monitorability score that shows how well the CoT serves as the model's external `working memory', a property that many safety schemes based on CoT monitoring depend on. We evaluate instruction-tuned and reasoning models on BBH, GPQA, and MMLU. Our results show that models can appear faithful yet remain hard to monitor when they leave out key factors, and that monitorability differs sharply across model families. We release our evaluation code using the Inspect library to support reproducible future work.

We present MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules. The toolbox started from a codebase of MMDet team who won the detection track of COCO Challenge 2018. It gradually evolves into a unified platform that covers many popular detection methods and contemporary modules. It not only includes training and inference codes, but also provides weights for more than 200 network models. We believe this toolbox is by far the most complete detection toolbox. In this paper, we introduce the various features of this toolbox. In addition, we also conduct a benchmarking study on different methods, components, and their hyper-parameters. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new detectors. Code and models are available at https://github.com/open-mmlab/mmdetection. The project is under active development and we will keep this document updated.

Evaluation metrics are central to binary target segmentation because they determine how progress is measured, compared, and interpreted. In this paper, target denotes the task-defined positive region to be segmented rather than a generic foreground object. It may be salient, camouflaged, transparent, glass-like, mirror-like, shadow-like, lesion-like, or defined by other application-specific semantics. We treat existing metrics as compositions of modular design choices rather than isolated formulas. The proposed framework decomposes each metric into five stages covering prediction representation, target extraction, target matching, score computation, and metric reporting. We use this framework to analyze representative metrics and show how newer metrics address specific limits in earlier protocols. The stage choices keep each metric's assumptions visible. We then discuss the design space opened by the framework and its implications for task-aware evaluation protocols. Reference code is available at https://github.com/lartpang/PySODMetrics.

Evaluating whether text-to-image models follow explicit spatial instructions is difficult to automate. Object detectors may miss targets or return multiple plausible detections, and simple geometric tests can become ambiguous in borderline cases. Spatial evaluation is naturally a selective prediction problem, the checker may abstain when evidence is weak and report confidence so that results can be interpreted as a risk coverage tradeoff rather than a single score. We introduce SpatialBench-UC, a small, reproducible benchmark for pairwise spatial relations. The benchmark contains 200 prompts (50 object pairs times 4 relations) grouped into 100 counterfactual pairs obtained by swapping object roles. We release a benchmark package, versioned prompts, pinned configs, per-sample checker outputs, and report tables, enabling reproducible and auditable comparisons across models. We also include a lightweight human audit used to calibrate the checker's abstention margin and confidence threshold. We evaluate three baselines, Stable Diffusion 1.5, SD 1.5 BoxDiff, and SD 1.4 GLIGEN. The checker reports pass rate and coverage as well as conditional pass rates on decided samples. The results show that grounding methods substantially improve both pass rate and coverage, while abstention remains a dominant factor due mainly to missing detections.

Machine learning systems in fraud detection, credit scoring, and clinical risk assessment operate under delayed ground truth: outcome labels arrive days to months after the decision they evaluate. During this blind period, governance evidence degrades through mechanisms that neither drift detection methods nor governance frameworks adequately address. This paper formalizes an evidence sufficiency model with four dimensions (completeness, freshness, reliability, representativeness) and a decision-readiness gate that quantifies how label latency degrades evidence quality. The model maps three drift types to dimension-specific degradation trajectories. A complementary proxy indicator framework comprising seven measurement categories estimates sufficiency degradation without labels, with explicit coverage mapping and characterized blind spots per drift type. Evaluation on the IEEE-CIS Fraud Detection dataset (~590K transactions) with controlled drift injection shows that composite proxy monitoring detects covariate and mixed drift with 100% detection rate, while concept drift without feature change remains undetected -- consistent with the theoretical impossibility of unsupervised detection when P(X) is unchanged. Blind period simulation confirms monotone sufficiency degradation, with concept drift degrading fastest (S=0.242 at day 60 vs 0.418 for no-drift). The framework contributes a governance sufficiency monitoring instrument; its value lies in translating drift signals into auditable sufficiency assessments with characterized blind spots. Mapping sufficiency levels to governance actions requires deployment-specific calibration beyond this study's scope.

A common approach to explain NLP models, is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong despite being persuasive. Therefore, it is essential to measure their faithfulness. One such metric is if tokens are truly important, then masking them should result in worse model performance. However, token masking introduces out-of-distribution issues and existing solutions are computationally expensive and employ proxy-models. Furthermore, other metrics are very limited in scope. In this work, we propose an inherently faithfulness measurable model that addresses these challenges. This is achieved by using a novel fine-tuning method that incorporates masking, such that masking tokens become in-distribution by design. This differs from existing approaches, which are completely model-agnostic but are inapplicable in practice. We demonstrate the generality of our approach by applying it to various tasks and validate it using statistical in-distribution tests. Additionally, because masking is in-distribution, importance measures which themselves use masking become more faithful, thus our model becomes more explainable.

In speech enhancement and source separation, signal-to-noise ratio is a ubiquitous objective measure of denoising/separation quality. A decade ago, the BSS_eval toolkit was developed to give researchers worldwide a way to evaluate the quality of their algorithms in a simple, fair, and hopefully insightful way: it attempted to account for channel variations, and to not only evaluate the total distortion in the estimated signal but also split it in terms of various factors such as remaining interference, newly added artifacts, and channel errors. In recent years, hundreds of papers have been relying on this toolkit to evaluate their proposed methods and compare them to previous works, often arguing that differences on the order of 0.1 dB proved the effectiveness of a method over others. We argue here that the signal-to-distortion ratio (SDR) implemented in the BSS_eval toolkit has generally been improperly used and abused, especially in the case of single-channel separation, resulting in misleading results. We propose to use a slightly modified definition, resulting in a simpler, more robust measure, called scale-invariant SDR (SI-SDR). We present various examples of critical failure of the original SDR that SI-SDR overcomes.

The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications predict selective prediction performance. Twenty frontier LLMs from seven families were evaluated on 524 items across six cognitive tracks. Valid models show mean Type 2 AUROC = .624 (SD = .048). Invalid models show mean AUROC = .357 (SD = .231). Cohen's d = 2.81, p = .002. The tiers order monotonically: Invalid (.357) < Indeterminate (.554) < Valid (.624). Split-half cross-validation yields median d = 1.77, P(d > 0) = 1.0 across 1,000 splits. The three-tier classification accounts for 47% of the variance in AUROC. DeepSeek-R1 drops from 85.3% accuracy at full coverage to 11.3% at 10% coverage. The screen predicts the criterion. For selective prediction, the screen matters.

Objective estimators of multimedia quality are often judged by comparing estimates with subjective "truth data," most often via Pearson correlation coefficient (PCC) or mean-squared error (MSE). But subjective test results contain noise, so striving for a PCC of 1.0 or an MSE of 0.0 is neither realistic nor repeatable. Numerous efforts have been made to acknowledge and appropriately accommodate subjective test noise in objective-subjective comparisons, typically resulting in new analysis frameworks and figures-of-merit. We take a different approach. By making only basic assumptions, we derive bounds on PCC and MSE that can be expected for a subjective test. Consistent with intuition, these bounds are functions of subjective vote variance. When a subjective test includes vote variance information, the calculation of the bounds is easy, and in this case we say the resulting bounds are "fully data-driven." We provide two options for calculating bounds in cases where vote variance information is not available. One option is to use vote variance information from other subjective tests that do provide such information, and the second option is to use a model for subjective votes. Thus we introduce a binomial-based model for subjective votes (BinoVotes) that naturally leads to a mean opinion score (MOS) model, named BinoMOS, with multiple unique desirable properties. BinoMOS reproduces the discrete nature of MOS values and its dependence on the number of votes per file. This modeling provides vote variance information required by the PCC and MSE bounds and we compare this modeling with data from 18 subjective tests. The modeling yields PCC and MSE bounds that agree very well with those found from the data directly. These results allow one to set expectations for the PCC and MSE that might be achieved for any subjective test, even those where vote variance information is not available.

Platforms and the law regulate digital content depicting minors (defined as individuals under 18 years of age) differently from other types of content. Given the sheer amount of content that needs to be assessed, machine learning-based automation tools are commonly used to detect content depicting minors. To our knowledge, no dataset or benchmark currently exists for detecting these identification methods in a multi-modal environment. To fill this gap, we release the Image-Caption Children in the Wild Dataset (ICCWD), an image-caption dataset aimed at benchmarking tools that detect depictions of minors. Our dataset is richer than previous child image datasets, containing images of children in a variety of contexts, including fictional depictions and partially visible bodies. ICCWD contains 10,000 image-caption pairs manually labeled to indicate the presence or absence of a child in the image. To demonstrate the possible utility of our dataset, we use it to benchmark three different detectors, including a commercial age estimation system applied to images. Our results suggest that child detection is a challenging task, with the best method achieving a 75.3% true positive rate. We hope the release of our dataset will aid in the design of better minor detection methods in a wide range of scenarios.

This work introduces a dataset, benchmark, and challenge for the problem of video copy detection and localization. The problem comprises two distinct but related tasks: determining whether a query video shares content with a reference video ("detection"), and additionally temporally localizing the shared content within each video ("localization"). The benchmark is designed to evaluate methods on these two tasks, and simulates a realistic needle-in-haystack setting, where the majority of both query and reference videos are "distractors" containing no copied content. We propose a metric that reflects both detection and localization accuracy. The associated challenge consists of two corresponding tracks, each with restrictions that reflect real-world settings. We provide implementation code for evaluation and baselines. We also analyze the results and methods of the top submissions to the challenge. The dataset, baseline methods and evaluation code is publicly available and will be discussed at a dedicated CVPR'23 workshop.

Creating test collections for offline retrieval evaluation requires human effort to judge documents' relevance. This expensive activity motivated much work in developing methods for constructing benchmarks with fewer assessment costs. In this respect, adjudication methods actively decide both which documents and the order in which experts review them, in order to better exploit the assessment budget or to lower it. Researchers evaluate the quality of those methods by measuring the correlation between the known gold ranking of systems under the full collection and the observed ranking of systems under the lower-cost one. This traditional analysis ignores whether and how the low-cost judgements impact on the statistically significant differences among systems with respect to the full collection. We fill this void by proposing a novel methodology to evaluate how the low-cost adjudication methods preserve the pairwise significant differences between systems as the full collection. In other terms, while traditional approaches look for stability in answering the question "is system A better than system B?", our proposed approach looks for stability in answering the question "is system A significantly better than system B?", which is the ultimate questions researchers need to answer to guarantee the generalisability of their results. Among other results, we found that the best methods in terms of ranking of systems correlation do not always match those preserving statistical significance.

We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift. We introduce the concept of relative signal strength (RSS), a pointwise measure that quantifies the transferability from noisy to clean posterior. Using RSS, we establish nearly matching upper and lower bounds on the excess risk. Our theoretical findings support the simple Noise Ignorant Empirical Risk Minimization (NI-ERM) principle, which minimizes empirical risk while ignoring label noise. Finally, we translate this theoretical insight into practice: by using NI-ERM to fit a linear classifier on top of a self-supervised feature extractor, we achieve state-of-the-art performance on the CIFAR-N data challenge.

When a language model asserts that "the capital of Australia is Sydney," does it know this is wrong? We characterize the geometry of correctness representations across 9 models from 5 architecture families. The structure is simple: the discriminative signal occupies 3-8 dimensions, performance degrades with additional dimensions, and no nonlinear classifier improves over linear separation. Centroid distance in the low-dimensional subspace matches trained probe performance (0.90 AUC), enabling few-shot detection: on GPT-2, 25 labeled examples achieve 89% of full-data accuracy. We validate causally through activation steering: the learned direction produces 10.9 percentage point changes in error rates while random directions show no effect. Internal probes achieve 0.80-0.97 AUC; output-based methods (P(True), semantic entropy) achieve only 0.44-0.64 AUC. The correctness signal exists internally but is not expressed in outputs. That centroid distance matches probe performance indicates class separation is a mean shift, making detection geometric rather than learned.

This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is identified as a key factor influencing tracking performance, where changing the detector can improve tracking by up to 18.9%. Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers. Furthermore, due to the simplicity of our tracking method, the tracker updates at a rate of 260 Hz which is over 20x faster than other state-of-the-art trackers.

Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have seen a rapid technological evolution of object detection and its profound impact on the entire computer vision field. If we consider today's object detection technique as a revolution driven by deep learning, then back in the 1990s, we would see the ingenious thinking and long-term perspective design of early computer vision. This paper extensively reviews this fast-moving research field in the light of technical evolution, spanning over a quarter-century's time (from the 1990s to 2022). A number of topics have been covered in this paper, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speed-up techniques, and the recent state-of-the-art detection methods.

By design, average precision (AP) for object detection aims to treat all classes independently: AP is computed independently per category and averaged. On one hand, this is desirable as it treats all classes equally. On the other hand, it ignores cross-category confidence calibration, a key property in real-world use cases. Unfortunately, under important conditions (i.e., large vocabulary, high instance counts) the default implementation of AP is neither category independent, nor does it directly reward properly calibrated detectors. In fact, we show that on LVIS the default implementation produces a gameable metric, where a simple, un-intuitive re-ranking policy can improve AP by a large margin. To address these limitations, we introduce two complementary metrics. First, we present a simple fix to the default AP implementation, ensuring that it is independent across categories as originally intended. We benchmark recent LVIS detection advances and find that many reported gains do not translate to improvements under our new evaluation, suggesting recent improvements may arise from difficult to interpret changes to cross-category rankings. Given the importance of reliably benchmarking cross-category rankings, we consider a pooled version of AP (AP-Pool) that rewards properly calibrated detectors by directly comparing cross-category rankings. Finally, we revisit classical approaches for calibration and find that explicitly calibrating detectors improves state-of-the-art on AP-Pool by 1.7 points

With the rapid development of global industrial production, the demand for reliability in power equipment has been continuously increasing. Ensuring the stability of power system operations requires accurate methods to detect potential faults in power equipment, thereby guaranteeing the normal supply of electrical energy. In this article, the performance of YOLOv5, YOLOv8, YOLOv9, YOLOv10, and the state-of-the-art YOLOv11 methods was comprehensively evaluated for power equipment object detection. Experimental results demonstrate that the mean average precision (mAP) on a public dataset for power equipment was 54.4%, 55.5%, 43.8%, 48.0%, and 57.2%, respectively, with the YOLOv11 achieving the highest detection performance. Moreover, the YOLOv11 outperformed other methods in terms of recall rate and exhibited superior performance in reducing false detections. In conclusion, the findings indicate that the YOLOv11 model provides a reliable and effective solution for power equipment object detection, representing a promising approach to enhancing the operational reliability of power systems.

To efficiently deploy strong, often pre-trained feature extractors, recent Industrial Anomaly Detection and Segmentation (IADS) methods process low-resolution images, e.g., 224x224 pixels, obtained by downsampling the original input images. However, while numerous industrial applications demand the identification of both large and small defects, downsampling the input image to a low resolution may hinder a method's ability to pinpoint tiny anomalies. We propose a novel Teacher--Student paradigm to leverage strong pre-trained features while processing high-resolution input images very efficiently. The core idea concerns training two shallow MLPs (the Students) by nominal images so as to mimic the mappings between the patch embeddings induced by the self-attention layers of a frozen vision Transformer (the Teacher). Indeed, learning these mappings sets forth a challenging pretext task that small-capacity models are unlikely to accomplish on out-of-distribution data such as anomalous images. Our method can spot anomalies from high-resolution images and runs way faster than competitors, achieving state-of-the-art performance on MVTec AD and the best segmentation results on VisA. We also propose novel evaluation metrics to capture robustness to defect size, i.e., the ability to preserve good localisation from large anomalies to tiny ones. Evaluating our method also by these metrics reveals its neatly superior performance.

Simultaneous localisation and categorization of objects in medical images, also referred to as medical object detection, is of high clinical relevance because diagnostic decisions often depend on rating of objects rather than e.g. pixels. For this task, the cumbersome and iterative process of method configuration constitutes a major research bottleneck. Recently, nnU-Net has tackled this challenge for the task of image segmentation with great success. Following nnU-Net's agenda, in this work we systematize and automate the configuration process for medical object detection. The resulting self-configuring method, nnDetection, adapts itself without any manual intervention to arbitrary medical detection problems while achieving results en par with or superior to the state-of-the-art. We demonstrate the effectiveness of nnDetection on two public benchmarks, ADAM and LUNA16, and propose 11 further medical object detection tasks on public data sets for comprehensive method evaluation. Code is at https://github.com/MIC-DKFZ/nnDetection .

This study investigates object presence detection and localization in remote sensing imagery, focusing on solar panel recognition. We explore different levels of supervision, evaluating three models: a fully supervised object detector, a weakly supervised image classifier with CAM-based localization, and a minimally supervised anomaly detector. The classifier excels in binary presence detection (0.79 F1-score), while the object detector (0.72) offers precise localization. The anomaly detector requires more data for viable performance. Fusion of model results shows potential accuracy gains. CAM impacts localization modestly, with GradCAM, GradCAM++, and HiResCAM yielding superior results. Notably, the classifier remains robust with less data, in contrast to the object detector.

In order to minimize the generalization error in neural networks, a novel technique to identify overfitting phenomena when training the learner is formally introduced. This enables support of a reliable and trustworthy early stopping condition, thus improving the predictive power of that type of modeling. Our proposal exploits the correlation over time in a collection of online indicators, namely characteristic functions for indicating if a set of hypotheses are met, associated with a range of independent stopping conditions built from a canary judgment to evaluate the presence of overfitting. That way, we provide a formal basis for decision making in terms of interrupting the learning process. As opposed to previous approaches focused on a single criterion, we take advantage of subsidiarities between independent assessments, thus seeking both a wider operating range and greater diagnostic reliability. With a view to illustrating the effectiveness of the halting condition described, we choose to work in the sphere of natural language processing, an operational continuum increasingly based on machine learning. As a case study, we focus on parser generation, one of the most demanding and complex tasks in the domain. The selection of cross-validation as a canary function enables an actual comparison with the most representative early stopping conditions based on overfitting identification, pointing to a promising start toward an optimal bias and variance control.

Making statements about the performance of trained models on tasks involving new data is one of the primary goals of machine learning, i.e., to understand the generalization power of a model. Various capacity measures try to capture this ability, but usually fall short in explaining important characteristics of models that we observe in practice. In this study, we propose the local effective dimension as a capacity measure which seems to correlate well with generalization error on standard data sets. Importantly, we prove that the local effective dimension bounds the generalization error and discuss the aptness of this capacity measure for machine learning models.

Studies involving soundscape perception often exclude participants with hearing loss to prevent impaired perception from affecting experimental results. Participants are typically screened with pure tone audiometry, the "gold standard" for identifying and quantifying hearing loss at specific frequencies, and excluded if a study-dependent threshold is not met. However, procuring professional audiometric equipment for soundscape studies may be cost-ineffective, and manually performing audiometric tests is labour-intensive. Moreover, testing requirements for soundscape studies may not require sensitivities and specificities as high as that in a medical diagnosis setting. Hence, in this study, we investigate the effectiveness of the uHear app, an iOS application, as an affordable and automatic alternative to a conventional audiometer in screening participants for hearing loss for the purpose of soundscape studies or listening tests in general. Based on audiometric comparisons with the audiometer of 163 participants, the uHear app was found to have high precision (98.04%) when using the World Health Organization (WHO) grading scheme for assessing normal hearing. Precision is further improved (98.69%) when all frequencies assessed with the uHear app is considered in the grading, which lends further support to this cost-effective, automated alternative to screen for normal hearing.

Offline evaluation of search systems depends on test collections. These benchmarks provide the researchers with a corpus of documents, topics and relevance judgements indicating which documents are relevant for each topic. While test collections are an integral part of Information Retrieval (IR) research, their creation involves significant efforts in manual annotation. Large language models (LLMs) are gaining much attention as tools for automatic relevance assessment. Recent research has shown that LLM-based assessments yield high systems ranking correlation with human-made judgements. These correlations are helpful in large-scale experiments but less informative if we want to focus on top-performing systems. Moreover, these correlations ignore whether and how LLM-based judgements impact the statistically significant differences among systems with respect to human assessments. In this work, we look at how LLM-generated judgements preserve ranking differences among top-performing systems and also how they preserve pairwise significance evaluation as human judgements. Our results show that LLM-based judgements are unfair at ranking top-performing systems. Moreover, we observe an exceedingly high rate of false positives regarding statistical differences. Our work represents a step forward in the evaluation of the reliability of using LLMs-based judgements for IR evaluation. We hope this will serve as a basis for other researchers to develop more reliable models for automatic relevance assessment.

In this work, by re-examining the "matching" nature of Anomaly Detection (AD), we propose a new AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion. Given a test sample, the top-K most similar training images are first selected based on a robust histogram matching process. Secondly, the nearest neighbor of each test patch is retrieved over the similar geometrical locations on those "global nearest neighbors", by using a carefully trained local metric. Finally, the anomaly score of each test image patch is calculated based on the distance to its "local nearest neighbor" and the "non-background" probability. The proposed method is termed "Cascade Patch Retrieval" (CPR) in this work. Different from the conventional patch-matching-based AD algorithms, CPR selects proper "targets" (reference images and locations) before "shooting" (patch-matching). On the well-acknowledged MVTec AD, BTAD and MVTec-3D AD datasets, the proposed algorithm consistently outperforms all the comparing SOTA methods by remarkable margins, measured by various AD metrics. Furthermore, CPR is extremely efficient. It runs at the speed of 113 FPS with the standard setting while its simplified version only requires less than 1 ms to process an image at the cost of a trivial accuracy drop. The code of CPR is available at https://github.com/flyinghu123/CPR.

Relevance and fairness are two major objectives of recommender systems (RSs). Recent work proposes measures of RS fairness that are either independent from relevance (fairness-only) or conditioned on relevance (joint measures). While fairness-only measures have been studied extensively, we look into whether joint measures can be trusted. We collect all joint evaluation measures of RS relevance and fairness, and ask: How much do they agree with each other? To what extent do they agree with relevance/fairness measures? How sensitive are they to changes in rank position, or to increasingly fair and relevant recommendations? We empirically study for the first time the behaviour of these measures across 4 real-world datasets and 4 recommenders. We find that most of these measures: i) correlate weakly with one another and even contradict each other at times; ii) are less sensitive to rank position changes than relevance- and fairness-only measures, meaning that they are less granular than traditional RS measures; and iii) tend to compress scores at the low end of their range, meaning that they are not very expressive. We counter the above limitations with a set of guidelines on the appropriate usage of such measures, i.e., they should be used with caution due to their tendency to contradict each other and of having a very small empirical range.

Recent advances in visual anomaly detection research have seen AUROC and AUPRO scores on public benchmark datasets such as MVTec and VisA converge towards perfect recall, giving the impression that these benchmarks are near-solved. However, high AUROC and AUPRO scores do not always reflect qualitative performance, which limits the validity of these metrics in real-world applications. We argue that the artificial ceiling imposed by the lack of an adequate evaluation metric restrains progression of the field, and it is crucial that we revisit the evaluation metrics used to rate our algorithms. In response, we introduce Per-IMage Overlap (PIMO), a novel metric that addresses the shortcomings of AUROC and AUPRO. PIMO retains the recall-based nature of the existing metrics but introduces two distinctions: the assignment of curves (and respective area under the curve) is per-image, and its X-axis relies solely on normal images. Measuring recall per image simplifies instance score indexing and is more robust to noisy annotations. As we show, it also accelerates computation and enables the usage of statistical tests to compare models. By imposing low tolerance for false positives on normal images, PIMO provides an enhanced model validation procedure and highlights performance variations across datasets. Our experiments demonstrate that PIMO offers practical advantages and nuanced performance insights that redefine anomaly detection benchmarks -- notably challenging the perception that MVTec AD and VisA datasets have been solved by contemporary models. Available on GitHub: https://github.com/jpcbertoldo/aupimo.

Context can change whether a request is harmful without changing its topic or surface form. We ask whether residual-stream probes distinguish harmful requests from surface-matched benign controls at a useful operating point. Across three 7-8B model families, an activation sensor blocks 95.5-97.7 percent of judge-classified compliant attacks in a taxonomy-selected set. It also blocks 59.6-68.4 percent of XSTest prompts. A fully disjoint audit reconstructs near-ceiling source-contrast AUROC (0.996-0.999), but fixed transfer to matched pairs is weaker: 0.656-0.819 on the guard-selected Twin-n70 subset and 0.590-0.690 on the full Twin-n163 cohort. We test ten axes on the reference family and seven across all families with leakage, hold-out, and permutation controls. On Twin-n163, no axis evaluated without direct pair-boundary fitting reaches the specified numerical threshold. Requiring persistence on that full cohort was added at analysis time. A separately specified 24B/32B extension gives the same result. Pair-trained classifiers weaken under category and generation-batch hold-out and false-block 79.6-100 percent of XSTest at 95 percent in-corpus TPR. At the tested read points, these activation scores behave as broad-risk detectors rather than standalone context adjudicators.

Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal robust model will probably behave similarly to the oracle (e.g., the human users), thus a good evaluation protocol is probably to evaluate the models' behaviors in comparison to the oracle. In this paper, we introduce a new robustness measurement that directly measures the image classification model's performance compared with a surrogate oracle (i.e., a foundation model). Besides, we design a simple method that can accomplish the evaluation beyond the scope of the benchmarks. Our method extends the image datasets with new samples that are sufficiently perturbed to be distinct from the ones in the original sets, but are still bounded within the same image-label structure the original test image represents, constrained by a foundation model pretrained with a large amount of samples. As a result, our new method will offer us a new way to evaluate the models' robustness performance, free of limitations of fixed benchmarks or constrained perturbations, although scoped by the power of the oracle. In addition to the evaluation results, we also leverage our generated data to understand the behaviors of the model and our new evaluation strategies.

Galaxy clusters selected based on overdensities of galaxies in photometric surveys provide the largest cluster samples. Yet modeling the selection function of such samples is complicated by non-cluster members projected along the line of sight (projection effects) and the potential detection of unvirialized objects (contamination). We empirically constrain the magnitude of these effects by cross-matching galaxy clusters selected in the Dark Energy survey data with the \rdmpr, algorithm with significant detections in three South Pole Telescope surveys (SZ, pol-ECS, pol-500d). For matched clusters, we augment the \rdmpr,catalog by the SPT detection significance. For unmatched objects we use the SPT detection threshold as an upper limit on the SZe signature. Using a Bayesian population model applied to the collected multi-wavelength data, we explore various physically motivated models to describe the relationship between observed richness and halo mass. Our analysis reveals the limitations of a simple lognormal scatter model in describing the data. We rule out significant contamination by unvirialized objects at the high-richness end of the sample. While dedicated simulations offer a well-fitting calibration of projection effects, our findings suggest the presence of redshift-dependent trends that these simulations may not have captured. Our findings highlight that modeling the selection function of optically detected clusters remains a complicated challenge, requiring a combination of simulation and data-driven approaches.

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.

Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In this work, we present the systematic review of VLM-based detection and segmentation, view VLM as the foundational model and conduct comprehensive evaluations across multiple downstream tasks for the first time: 1) The evaluation spans eight detection scenarios (closed-set detection, domain adaptation, crowded objects, etc.) and eight segmentation scenarios (few-shot, open-world, small object, etc.), revealing distinct performance advantages and limitations of various VLM architectures across tasks. 2) As for detection tasks, we evaluate VLMs under three finetuning granularities: zero prediction, visual fine-tuning, and text prompt, and further analyze how different finetuning strategies impact performance under varied task. 3) Based on empirical findings, we provide in-depth analysis of the correlations between task characteristics, model architectures, and training methodologies, offering insights for future VLM design. 4) We believe that this work shall be valuable to the pattern recognition experts working in the fields of computer vision, multimodal learning, and vision foundation models by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research. A project associated with this review and evaluation has been created at https://github.com/better-chao/perceptual_abilities_evaluation.

This paper presents Objectness SIMilarity (OSIM), a novel evaluation metric for 3D scenes that explicitly focuses on "objects," which are fundamental units of human visual perception. Existing metrics assess overall image quality, leading to discrepancies with human perception. Inspired by neuropsychological insights, we hypothesize that human recognition of 3D scenes fundamentally involves attention to individual objects. OSIM enables object-centric evaluations by leveraging an object detection model and its feature representations to quantify the "objectness" of each object in the scene. Our user study demonstrates that OSIM aligns more closely with human perception compared to existing metrics. We also analyze the characteristics of OSIM using various approaches. Moreover, we re-evaluate recent 3D reconstruction and generation models under a standardized experimental setup to clarify advancements in this field. The code is available at https://github.com/Objectness-Similarity/OSIM.

RAG systems are increasingly evaluated and optimized using LLM judges, an approach that is rapidly becoming the dominant paradigm for system assessment. Nugget-based approaches in particular are now embedded not only in evaluation frameworks but also in the architectures of RAG systems themselves. While this integration can lead to genuine improvements, it also creates a risk of faulty measurements due to circularity. In this paper, we investigate this risk through comparative experiments with nugget-based RAG systems, including Ginger and Crucible, against strong baselines such as GPT-Researcher. By deliberately modifying Crucible to generate outputs optimized for an LLM judge, we show that near-perfect evaluation scores can be achieved when elements of the evaluation - such as prompt templates or gold nuggets - are leaked or can be predicted. Our results highlight the importance of blind evaluation settings and methodological diversity to guard against mistaking metric overfitting for genuine system progress.

Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures calibration remains a challenge: expected calibration error, the most popular metric, has numerous flaws which we outline, and there is no clear empirical understanding of how its choices affect conclusions in practice, and what recommendations there are to counteract its flaws. In this paper, we perform a comprehensive empirical study of choices in calibration measures including measuring all probabilities rather than just the maximum prediction, thresholding probability values, class conditionality, number of bins, bins that are adaptive to the datapoint density, and the norm used to compare accuracies to confidences. To analyze the sensitivity of calibration measures, we study the impact of optimizing directly for each variant with recalibration techniques. Across MNIST, Fashion MNIST, CIFAR-10/100, and ImageNet, we find that conclusions on the rank ordering of recalibration methods is drastically impacted by the choice of calibration measure. We find that conditioning on the class leads to more effective calibration evaluations, and that using the L2 norm rather than the L1 norm improves both optimization for calibration metrics and the rank correlation measuring metric consistency. Adaptive binning schemes lead to more stablity of metric rank ordering when the number of bins vary, and is also recommended. We open source a library for the use of our calibration measures.

We make two contributions in the field of AI fairness over continuous protected attributes. First, we show that the Hirschfeld-Gebelein-Renyi (HGR) indicator (the only one currently available for such a case) is valuable but subject to a few crucial limitations regarding semantics, interpretability, and robustness. Second, we introduce a family of indicators that are: 1) complementary to HGR in terms of semantics; 2) fully interpretable and transparent; 3) robust over finite samples; 4) configurable to suit specific applications. Our approach also allows us to define fine-grained constraints to permit certain types of dependence and forbid others selectively. By expanding the available options for continuous protected attributes, our approach represents a significant contribution to the area of fair artificial intelligence.

Automated X-ray inspection is crucial for efficient and unobtrusive security screening in various public settings. However, challenges such as object occlusion, variations in the physical properties of items, diversity in X-ray scanning devices, and limited training data hinder accurate and reliable detection of illicit items. Despite the large body of research in the field, reported experimental evaluations are often incomplete, with frequently conflicting outcomes. To shed light on the research landscape and facilitate further research, a systematic, detailed, and thorough comparative evaluation of recent Deep Learning (DL)-based methods for X-ray object detection is conducted. For this, a comprehensive evaluation framework is developed, composed of: a) Six recent, large-scale, and widely used public datasets for X-ray illicit item detection (OPIXray, CLCXray, SIXray, EDS, HiXray, and PIDray), b) Ten different state-of-the-art object detection schemes covering all main categories in the literature, including generic Convolutional Neural Network (CNN), custom CNN, generic transformer, and hybrid CNN-transformer architectures, and c) Various detection (mAP50 and mAP50:95) and time/computational-complexity (inference time (ms), parameter size (M), and computational load (GFLOPS)) metrics. A thorough analysis of the results leads to critical observations and insights, emphasizing key aspects such as: a) Overall behavior of the object detection schemes, b) Object-level detection performance, c) Dataset-specific observations, and d) Time efficiency and computational complexity analysis. To support reproducibility of the reported experimental results, the evaluation code and model weights are made publicly available at https://github.com/jgenc/xray-comparative-evaluation.

This article proposes a new approach for assessing the quality of answers in political question-and-answer sessions. We measure the quality of an answer based on how easily and accurately it can be recognized in a random set of candidate answers given the question's text. This measure reflects the answer's relevance and depth of engagement with the question. Like semantic search, we can implement this approach by training a language model on the corpus of observed questions and answers without additional human-labeled data. We showcase and validate our methodology within the context of the Question Period in the Canadian House of Commons. Our analysis reveals that while some answers have a weak semantic connection to questions, hinting at some evasion or obfuscation, they are generally at least moderately relevant, far exceeding what we would expect from random replies. We also find a meaningful correlation between answer quality and the party affiliation of the members of Parliament asking the questions.

In the information retrieval (IR) domain, evaluation plays a crucial role in optimizing search experiences and supporting diverse user intents. In the recent LLM era, research has been conducted to automate document relevance labels, as these labels have traditionally been assigned by crowd-sourced workers - a process that is both time and consuming and costly. This study focuses on LLM-generated usefulness labels, a crucial evaluation metric that considers the user's search intents and task objectives, an aspect where relevance falls short. Our experiment utilizes task-level, query-level, and document-level features along with user search behavior signals, which are essential in defining the usefulness of a document. Our research finds that (i) pre-trained LLMs can generate moderate usefulness labels by understanding the comprehensive search task session, (ii) pre-trained LLMs perform better judgement in short search sessions when provided with search session contexts. Additionally, we investigated whether LLMs can capture the unique divergence between relevance and usefulness, along with conducting an ablation study to identify the most critical metrics for accurate usefulness label generation. In conclusion, this work explores LLM-generated usefulness labels by evaluating critical metrics and optimizing for practicality in real-world settings.

Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation at step 8 enables intervention; one that reports it at step 48 provides only forensic value. This distinction is critical, yet current benchmarks cannot measure it. We introduce StepShield, the first benchmark to evaluate when violations are detected, not just whether. StepShield contains 9,213 code agent trajectories, including 1,278 meticulously annotated training pairs and a 7,935-trajectory test set with a realistic 8.1% rogue rate. Rogue behaviors are grounded in real-world security incidents across six categories. We propose three novel temporal metrics: Early Intervention Rate (EIR), Intervention Gap, and Tokens Saved. Surprisingly, our evaluation reveals that an LLM-based judge achieves 59% EIR while a static analyzer achieves only 26%, a 2.3x performance gap that is entirely invisible to standard accuracy metrics. We further show that early detection has direct economic benefits: our cascaded HybridGuard detector reduces monitoring costs by 75% and projects to $108M in cumulative savings over five years at enterprise scale. By shifting the focus of evaluation from whether to when, StepShield provides a new foundation for building safer and more economically viable AI agents. The code and data are released under an Apache 2.0 license.

Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although conformal methods can give guarantees on marginal coverage, no method can guarantee to produce sets with correct conditional coverage, leaving practitioners without a clear way to interpret local deviations. To overcome sample-inefficiency and overfitting issues of existing metrics, we cast conditional coverage estimation as a classification problem. Conditional coverage is violated if and only if some classifier can achieve lower risk than the target coverage. Through the choice of a (proper) loss function, the resulting risk difference gives a conservative estimate of natural miscoverage measures such as L1 and L2 distance, and can even separate the effects of over- and under-coverage, and non-constant target coverages. We call the resulting family of metrics excess risk of the target coverage (ERT). We show experimentally that the use of modern classifiers provides much higher statistical power than simple classifiers underlying established metrics like CovGap. Additionally, we use our metric to benchmark different conformal prediction methods. Finally, we release an open-source package for ERT as well as previous conditional coverage metrics. Together, these contributions provide a new lens for understanding, diagnosing, and improving the conditional reliability of predictive systems.

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.

We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, BEiT-3, or GPT-4). Compared to existing benchmarks that focus on computational tasks (e.g. classification, detection or tracking), the Perception Test focuses on skills (Memory, Abstraction, Physics, Semantics) and types of reasoning (descriptive, explanatory, predictive, counterfactual) across video, audio, and text modalities, to provide a comprehensive and efficient evaluation tool. The benchmark probes pre-trained models for their transfer capabilities, in a zero-shot / few-shot or limited finetuning regime. For these purposes, the Perception Test introduces 11.6k real-world videos, 23s average length, designed to show perceptually interesting situations, filmed by around 100 participants worldwide. The videos are densely annotated with six types of labels (multiple-choice and grounded video question-answers, object and point tracks, temporal action and sound segments), enabling both language and non-language evaluations. The fine-tuning and validation splits of the benchmark are publicly available (CC-BY license), in addition to a challenge server with a held-out test split. Human baseline results compared to state-of-the-art video QA models show a significant gap in performance (91.4% vs 43.6%), suggesting that there is significant room for improvement in multimodal video understanding. Dataset, baselines code, and challenge server are available at https://github.com/deepmind/perception_test

The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and sufficiently difficult tasks are critical drivers of strong machine learning models. However, quantifying the generalization difficulty of machine learning benchmarks has remained challenging. We propose what is to our knowledge the first model-agnostic measure of the inherent generalization difficulty of tasks. Our inductive bias complexity measure quantifies the total information required to generalize well on a task minus the information provided by the data. It does so by measuring the fractional volume occupied by hypotheses that generalize on a task given that they fit the training data. It scales exponentially with the intrinsic dimensionality of the space over which the model must generalize but only polynomially in resolution per dimension, showing that tasks which require generalizing over many dimensions are drastically more difficult than tasks involving more detail in fewer dimensions. Our measure can be applied to compute and compare supervised learning, reinforcement learning and meta-learning generalization difficulties against each other. We show that applied empirically, it formally quantifies intuitively expected trends, e.g. that in terms of required inductive bias, MNIST < CIFAR10 < Imagenet and fully observable Markov decision processes (MDPs) < partially observable MDPs. Further, we show that classification of complex images < few-shot meta-learning with simple images. Our measure provides a quantitative metric to guide the construction of more complex tasks requiring greater inductive bias, and thereby encourages the development of more sophisticated architectures and learning algorithms with more powerful generalization capabilities.

In recent years, performance on existing anomaly detection benchmarks like MVTec AD and VisA has started to saturate in terms of segmentation AU-PRO, with state-of-the-art models often competing in the range of less than one percentage point. This lack of discriminatory power prevents a meaningful comparison of models and thus hinders progress of the field, especially when considering the inherent stochastic nature of machine learning results. We present MVTec AD 2, a collection of eight anomaly detection scenarios with more than 8000 high-resolution images. It comprises challenging and highly relevant industrial inspection use cases that have not been considered in previous datasets, including transparent and overlapping objects, dark-field and back light illumination, objects with high variance in the normal data, and extremely small defects. We provide comprehensive evaluations of state-of-the-art methods and show that their performance remains below 60% average AU-PRO. Additionally, our dataset provides test scenarios with lighting condition changes to assess the robustness of methods under real-world distribution shifts. We host a publicly accessible evaluation server that holds the pixel-precise ground truth of the test set (https://benchmark.mvtec.com/). All image data is available at https://www.mvtec.com/company/research/datasets/mvtec-ad-2.

Detection of undersea threats is a complex problem of considerable importance for maritime regional surveillance and security. Multistatic sonar systems can provide a means to monitor for underwater threats, where fixed sensors, towed arrays and dipping sonars may be utilised for this purpose. However, it is advantageous to deploy passive sensors to provide a stealthy early warning system. Hence this paper is concerned with determining where a series of passive sonar sensors should be situated in order to provide an initial threat detection capability. In order to facilitate this it is necessary to derive a suitable expression for the probability of threat detection from a passive sensor. This is based upon considerations of the passive sonar equation. It will be demonstrated how the stochastic aspects of this equation may be modelled through appropriate random variables capturing the uncertainty in noise levels. Subsequently this is utilised to produce the system-level probability of threat detection. Since the threat location is also unknown an appropriate statistical model is introduced to account for this uncertainty. This then permits the specification of the probability of detection as a function of sensor locations. Consequently it is then possible to determine optimal sensor placement to maximise the threat detection probability. This provides a new way in which to determine whether a surveillance region is covered adequately by sensors. The methodology will be illustrated through a series of examples utilising passive sonar characteristics sourced from the open literature.

Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliable ranking, thus degrading detection performance. In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We design a new loss function, named Varifocal Loss, to train a dense object detector to predict the IACS, and propose a new star-shaped bounding box feature representation for IACS prediction and bounding box refinement. Combining these two new components and a bounding box refinement branch, we build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short. Extensive experiments on MS COCO show that our VFNet consistently surpasses the strong baseline by sim2.0 AP with different backbones. Our best model VFNet-X-1200 with Res2Net-101-DCN achieves a single-model single-scale AP of 55.1 on COCO test-dev, which is state-of-the-art among various object detectors.Code is available at https://github.com/hyz-xmaster/VarifocalNet .

Uniformity plays a crucial role in the assessment of learned representations, contributing to a deeper comprehension of self-supervised learning. The seminal work by Wang2020UnderstandingCR introduced a uniformity metric that quantitatively measures the collapse degree of learned representations. Directly optimizing this metric together with alignment proves to be effective in preventing constant collapse. However, we present both theoretical and empirical evidence revealing that this metric lacks sensitivity to dimensional collapse, highlighting its limitations. To address this limitation and design a more effective uniformity metric, this paper identifies five fundamental properties, some of which the existing uniformity metric fails to meet. We subsequently introduce a novel uniformity metric that satisfies all of these desiderata and exhibits sensitivity to dimensional collapse. When applied as an auxiliary loss in various established self-supervised methods, our proposed uniformity metric consistently enhances their performance in downstream tasks.Our code was released at https://github.com/sunset-clouds/WassersteinUniformityMetric.

The ability to detect unfamiliar or unexpected images is essential for safe deployment of computer vision systems. In the context of classification, the task of detecting images outside of a model's training domain is known as out-of-distribution (OOD) detection. While there has been a growing research interest in developing post-hoc OOD detection methods, there has been comparably little discussion around how these methods perform when the underlying classifier is not trained on a clean, carefully curated dataset. In this work, we take a closer look at 20 state-of-the-art OOD detection methods in the (more realistic) scenario where the labels used to train the underlying classifier are unreliable (e.g. crowd-sourced or web-scraped labels). Extensive experiments across different datasets, noise types & levels, architectures and checkpointing strategies provide insights into the effect of class label noise on OOD detection, and show that poor separation between incorrectly classified ID samples vs. OOD samples is an overlooked yet important limitation of existing methods. Code: https://github.com/glhr/ood-labelnoise

Very low-resolution face recognition (VLRFR) poses unique challenges, such as tiny regions of interest and poor resolution due to extreme standoff distance or wide viewing angle of the acquisition devices. In this paper, we study principled approaches to elevate the recognizability of a face in the embedding space instead of the visual quality. We first formulate a robust learning-based face recognizability measure, namely recognizability index (RI), based on two criteria: (i) proximity of each face embedding against the unrecognizable faces cluster center and (ii) closeness of each face embedding against its positive and negative class prototypes. We then devise an index diversion loss to push the hard-to-recognize face embedding with low RI away from unrecognizable faces cluster to boost the RI, which reflects better recognizability. Additionally, a perceptibility attention mechanism is introduced to attend to the most recognizable face regions, which offers better explanatory and discriminative traits for embedding learning. Our proposed model is trained end-to-end and simultaneously serves recognizability-aware embedding learning and face quality estimation. To address VLRFR, our extensive evaluations on three challenging low-resolution datasets and face quality assessment demonstrate the superiority of the proposed model over the state-of-the-art methods.

Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language Models can judge the methodological viability of a research idea before expending time and computational resources. We introduce SoundnessBench, a curated benchmark of 1,099 machine-learning research proposals reconstructed from ICLR submissions, labeled with reviewer soundness sub-scores, and audited against source papers. SoundnessBench should be interpreted as a benchmark for recoverable proposal-stage soundness rather than exact prediction of full-paper review outcomes. Across 12 frontier LLMs, we find a pervasive optimism bias: under standard prompting, models frequently rate low-soundness proposals as sound, while aggressive prompting largely shifts errors from false positives to false negatives. Additional controls for public-corpus contamination, paper-identifying phrases, surface features, and human audit quality suggest that this behavior is not explained by a single confounder. Our results indicate that current LLMs are not yet reliable as standalone first-gate evaluators for scientific rigor.

Reference-free faithfulness metrics verify each atomic claim a model makes against ground truth, and are increasingly used to evaluate grounded generation. We show they share a blind spot: they measure only precision -- are the stated claims supported? -- and therefore reward abstention, since a model can score near-perfect faithfulness by saying almost nothing. We make this measurable using Formula 1 telemetry, a domain where strategic ground truth is derived deterministically and, crucially, completely: for each decision we know the full set of facts that mattered. This completeness -- absent in open-domain faithfulness benchmarks -- lets us measure recall (coverage of the relevant facts) exactly, alongside precision. On a multilingual (EN/ES/PT) benchmark of 7,253 decision instances spanning 150 races, the most precise frontier model covers under half of the relevant facts and ranks last by F1, so requiring coverage reorders the systems; the same effect reappears in a second complete-oracle domain (NOAA weather forecasts). A prompt ablation shows the low coverage is not an under-prompting artifact: explicitly asking models to be thorough does not close the gap. We pair faithfulness with coverage into a single score, validate the metric (controlled perturbation; agreement across a model-free regex extractor and a cross-family LLM extractor, system-level Spearman 1.0), and give a verifier-guided generation method that improves precision and recall without references. We release the benchmark, structured annotations, metric, baselines, and an interactive demo.

Anomaly detection aims at detecting unexpected behaviours in the data. Because anomaly detection is usually an unsupervised task, traditional anomaly detectors learn a decision boundary by employing heuristics based on intuitions, which are hard to verify in practice. This introduces some uncertainty, especially close to the decision boundary, that may reduce the user trust in the detector's predictions. A way to combat this is by allowing the detector to reject examples with high uncertainty (Learning to Reject). This requires employing a confidence metric that captures the distance to the decision boundary and setting a rejection threshold to reject low-confidence predictions. However, selecting a proper metric and setting the rejection threshold without labels are challenging tasks. In this paper, we solve these challenges by setting a constant rejection threshold on the stability metric computed by ExCeeD. Our insight relies on a theoretical analysis of such a metric. Moreover, setting a constant threshold results in strong guarantees: we estimate the test rejection rate, and derive a theoretical upper bound for both the rejection rate and the expected prediction cost. Experimentally, we show that our method outperforms some metric-based methods.

Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed testing budget, derive it in closed form for the benchmark null result, and use it to locate that boundary exactly. We find that above a calculable harm rate, a benchmark of modest size certifies a category to a stated evidentiary standard, and a clean sheet is then the stronger of the two possible observations, outweighing a single reproduced failure. Below that rate, no passive benchmark of feasible size provides the specified evidence of safety under the fixed scoring rule and approximately independent trial structure. The crossing between the two regimes has a closed form. The bound is not specific to benchmarks: written in terms of a procedure's hypothesis conditioned elicitation rates, it covers adaptive and automated red teaming as well, and shows that discrimination between the hypotheses rather than attack success is what determines evidential worth. Auditing eight evaluation suites against the boundary, we find that current benchmarks are adequate for high-frequency harm categories and several orders of magnitude short for rare, catastrophic ones. Safety benchmarks are not uninformative. They are informative about a specific and computable set of propositions, and the discipline they need is to state which.

Evaluating anomaly detection algorithms in time series data is critical as inaccuracies can lead to flawed decision-making in various domains where real-time analytics and data-driven strategies are essential. Traditional performance metrics assume iid data and fail to capture the complex temporal dynamics and specific characteristics of time series anomalies, such as early and delayed detections. We introduce Proximity-Aware Time series anomaly Evaluation (PATE), a novel evaluation metric that incorporates the temporal relationship between prediction and anomaly intervals. PATE uses proximity-based weighting considering buffer zones around anomaly intervals, enabling a more detailed and informed assessment of a detection. Using these weights, PATE computes a weighted version of the area under the Precision and Recall curve. Our experiments with synthetic and real-world datasets show the superiority of PATE in providing more sensible and accurate evaluations than other evaluation metrics. We also tested several state-of-the-art anomaly detectors across various benchmark datasets using the PATE evaluation scheme. The results show that a common metric like Point-Adjusted F1 Score fails to characterize the detection performances well, and that PATE is able to provide a more fair model comparison. By introducing PATE, we redefine the understanding of model efficacy that steers future studies toward developing more effective and accurate detection models.

Real-world classifiers can benefit from the option of abstaining from predicting on samples where they have low confidence. Such abstention is particularly useful on samples which are close to the learned decision boundary, or which are outliers with respect to the training sample. These settings have been the subject of extensive but disjoint study in the selective classification (SC) and out-of-distribution (OOD) detection literature. Recent work on selective classification with OOD detection (SCOD) has argued for the unified study of these problems; however, the formal underpinnings of this problem are still nascent, and existing techniques are heuristic in nature. In this paper, we propose new plugin estimators for SCOD that are theoretically grounded, effective, and generalise existing approaches from the SC and OOD detection literature. In the course of our analysis, we formally explicate how na\"{i}ve use of existing SC and OOD detection baselines may be inadequate for SCOD. We empirically demonstrate that our approaches yields competitive SC and OOD detection performance compared to baselines from both literatures.

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains in interpreting their decisions. We help bridge this gap by providing explanations for OOD detectors based on learned high-level concepts. We first propose two new metrics for assessing the effectiveness of a particular set of concepts for explaining OOD detectors: 1) detection completeness, which quantifies the sufficiency of concepts for explaining an OOD-detector's decisions, and 2) concept separability, which captures the distributional separation between in-distribution and OOD data in the concept space. Based on these metrics, we propose an unsupervised framework for learning a set of concepts that satisfy the desired properties of high detection completeness and concept separability, and demonstrate its effectiveness in providing concept-based explanations for diverse off-the-shelf OOD detectors. We also show how to identify prominent concepts contributing to the detection results, and provide further reasoning about their decisions.

Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do not test whether individual diagnostic statements stem from the actual pathological evidence visible in the image. This allows models to achieve competitive scores by exploiting learned priors or spurious correlations, a failure mode we refer to as vision shortcut. We introduce SHOVIR, a benchmark for evaluating vision shortcut behavior in RRG. SHOVIR extends two spatially annotated chest X-ray datasets, MIMIC-CXR and PadChest-GR, with per-box CheXpert labels, and defines image-level and disease-level occlusion experiments that contrast baseline performance on clean images against localized, region-specific perturbations. Comparing predictions across these conditions isolates two failure modes at the disease-class level: direct shortcuts, where a finding persists after its visual evidence is removed, and contextual shortcuts, where detection degrades once co-occurring pathologies are occluded despite the target region remaining intact. Benchmarking eight state-of-the-art VLMs, we find that shortcut behavior varies substantially across architectures and datasets. Models achieving the highest baseline report quality do not necessarily rank highest in spatial grounding, revealing that clinically fluent generation can coexist with shallow reliance on visual evidence. These findings expose a blind spot in current RRG evaluation and motivate region-aware assessment protocols.

We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmarks often fail to isolate perception: holistic evaluations conflate perceptual errors with failures in reasoning or domain knowledge, while application-driven benchmarks only cover narrow, fragmented domains shaped by heuristic designs. To address these limitations, PerceptionBench adopts a bottom-up approach: by diagnosing the earliest failure points in the responses of frontier MLLMs across 42 existing benchmarks, we construct an error taxonomy whose perception branch defines ten atomic perceptual capabilities. Guided by this taxonomy, we construct 3,000 verified questions with short, unambiguous answers, each isolating a single capability, with difficulty stemming from perception rather than reasoning or knowledge. Benchmark results across sixteen frontier MLLMs reveal that atomic perception remains largely unsolved---no model reaches 60\% accuracy, perception-related hallucination is the weakest capability on average, and similar overall scores conceal sharply divergent capability profiles. PerceptionBench thus provides a capability-level standard for measuring and diagnosing the visual perception boundaries of MLLMs.

The proliferation of large language models has raised growing concerns about their misuse, particularly in cases where AI-generated text is falsely attributed to human authors. Machine-generated content detectors claim to effectively identify such text under various conditions and from any language model. This paper critically evaluates these claims by assessing several popular detectors (RADAR, Wild, T5Sentinel, Fast-DetectGPT, PHD, LogRank, Binoculars) on a range of domains, datasets, and models that these detectors have not previously encountered. We employ various prompting strategies to simulate practical adversarial attacks, demonstrating that even moderate efforts can significantly evade detection. We emphasize the importance of the true positive rate at a specific false positive rate (TPR@FPR) metric and demonstrate that these detectors perform poorly in certain settings, with TPR@.01 as low as 0%. Our findings suggest that both trained and zero-shot detectors struggle to maintain high sensitivity while achieving a reasonable true positive rate.

Through a controlled study, we identify a systematic deficiency in the multimodal grounding of Vision Language Models (VLMs). While VLMs can recall factual associations when provided a textual reference to an entity; their ability to do so is significantly diminished when the reference is visual instead. Forcing VLMs to rely on image representations of an entity halves their ability to recall factual knowledge, suggesting that VLMs struggle to link their internal knowledge of an entity with its image representation. We show that such linking failures are correlated with the expression of distinct patterns in model internal states, and that probes on these internal states achieve over 92% accuracy at flagging cases where the VLM response is unreliable. These probes can be applied, without retraining, to identify when a VLM will fail to correctly answer a question that requires an understanding of multimodal input. When used to facilitate selective prediction on a visual question answering task, the probes increase coverage by 7.87% (absolute) while also reducing the risk of error by 0.9% (absolute). Addressing the systematic, detectable deficiency is an important avenue in language grounding, and we provide informed recommendations for future directions.

Printed Circuit Boards are the foundation for the functioning of any electronic device, and therefore are an essential component for various industries such as automobile, communication, computation, etc. However, one of the challenges faced by the PCB manufacturers in the process of manufacturing of the PCBs is the faulty placement of its components including missing components. In the present scenario the infrastructure required to ensure adequate quality of the PCB requires a lot of time and effort. The authors present a novel solution for detecting missing components and classifying them in a resourceful manner. The presented algorithm focuses on pixel theory and object detection, which has been used in combination to optimize the results from the given dataset.

This paper explores the process of designing an automatic multi-sensor drone detection system. Besides the common video and audio sensors, the system also includes a thermal infrared camera, which is shown to be a feasible solution to the drone detection task. Even with slightly lower resolution, the performance is just as good as a camera in visible range. The detector performance as a function of the sensor-to-target distance is also investigated. In addition, using sensor fusion, the system is made more robust than the individual sensors, helping to reduce false detections. To counteract the lack of public datasets, a novel video dataset containing 650 annotated infrared and visible videos of drones, birds, airplanes and helicopters is also presented (https://github.com/DroneDetectionThesis/Drone-detection-dataset). The database is complemented with an audio dataset of the classes drones, helicopters and background noise.

Sound event localization and detection is a novel area of research that emerged from the combined interest of analyzing the acoustic scene in terms of the spatial and temporal activity of sounds of interest. This paper presents an overview of the first international evaluation on sound event localization and detection, organized as a task of the DCASE 2019 Challenge. A large-scale realistic dataset of spatialized sound events was generated for the challenge, to be used for training of learning-based approaches, and for evaluation of the submissions in an unlabeled subset. The overview presents in detail how the systems were evaluated and ranked and the characteristics of the best-performing systems. Common strategies in terms of input features, model architectures, training approaches, exploitation of prior knowledge, and data augmentation are discussed. Since ranking in the challenge was based on individually evaluating localization and event classification performance, part of the overview focuses on presenting metrics for the joint measurement of the two, together with a reevaluation of submissions using these new metrics. The new analysis reveals submissions that performed better on the joint task of detecting the correct type of event close to its original location than some of the submissions that were ranked higher in the challenge. Consequently, ranking of submissions which performed strongly when evaluated separately on detection or localization, but not jointly on both, was affected negatively.

Large language model (LLM) agents now execute long, tool-using tasks where final outcome checks can arrive too late for intervention. Online warning requires lightweight prefix monitors over heterogeneous traces, but hand-authored event schemas are brittle and deployment-time LLM judging is costly. We introduce PrefixGuard, a trace-to-monitor framework with an offline StepView induction step followed by supervised monitor training. StepView induces deterministic typed-step adapters from raw trace samples, and the monitor learns an event abstraction and prefix-risk scorer from terminal outcomes. Across WebArena, τ^2-Bench, SkillsBench, and TerminalBench, the strongest PrefixGuard monitors reach 0.900/0.710/0.533/0.557 AUPRC. Using the strongest backend within each representation, they improve over raw-text controls by an average of +0.137 AUPRC. LLM judges remain substantially weaker under the same prefix-warning protocol. We also derive an observability ceiling on score-based area under the precision-recall curve (AUPRC) that separates monitor error from failures lacking evidence in the observed prefix. For finite-state audit, post-hoc deterministic finite automaton (DFA) extraction remains compact on WebArena and τ^2-Bench (29 and 20 states) but expands to 151 and 187 states on SkillsBench and TerminalBench. Finally, first-alert diagnostics show that strong ranking does not imply deployment utility: WebArena ranks well yet fails to support low-false-alarm alerts, whereas τ^2-Bench and TerminalBench retain more actionable early alerts. Together, these results position PrefixGuard as a practical monitor-synthesis recipe with explicit diagnostics for when prefix warnings translate into actionable interventions.

We propose a goodness-of-fit measure for probability densities modeling observations with varying dimensionality, such as text documents of differing lengths or variable-length sequences. The proposed measure is an instance of the kernel Stein discrepancy (KSD), which has been used to construct goodness-of-fit tests for unnormalized densities. The KSD is defined by its Stein operator: current operators used in testing apply to fixed-dimensional spaces. As our main contribution, we extend the KSD to the variable-dimension setting by identifying appropriate Stein operators, and propose a novel KSD goodness-of-fit test. As with the previous variants, the proposed KSD does not require the density to be normalized, allowing the evaluation of a large class of models. Our test is shown to perform well in practice on discrete sequential data benchmarks.