Recognition
-
Mind the Divergence: Divergence-Guided Reliability-Aware Fusion and Adaptive LLM Prompting for Conversational Emotion Recognition
2026-11-06 01:37:20Jingwen Wang, Jiao Li, Yuhang Qian, Yuyin Wang, Min ZhangAbstract
Multimodal emotion recognition in conversations (MERC) integrates textual, acoustic, and visual cues to identify utterance-level emotions. However, existing approaches generally do not explicitly adapt multimodal processing to the degree of inter-modal predictive disagreement. In real conversations, semantic incongruity, concealed emotion, noisy observations, and ambiguity can affect modality-specific emotional evidence differently, while the reliability of individual modalities varies across samples. Rather than identifying each source of inconsistency separately, we model their common consequence for emotion recognition as predictive disagreement among unimodal emotion distributions over the same emotion-label set. Such disagreement makes indiscriminate fusion prone to propagating unreliable or competing evidence. Inspired by the Brunswik Lens Model, we propose MiD-ERC, a divergence-centric framework that quantifies inter-modal predictive disagreement using a normalized divergence score and estimates sample-specific modality reliability. MiD-ERC uses these signals to coordinate divergence-guided cross-modal gating, divergence-modulated reliability weighting, and divergence-conditioned adaptive LLM prompting. The framework is trained end-to-end using only standard emotion annotations, without requiring additional conflict labels, auxiliary data construction, or external retrieval modules. Experiments on IEMOCAP and MELD demonstrate that MiD-ERC achieves state-of-the-art performance, with particularly pronounced improvements on high-divergence samples.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08860
PDF
-
Fuzzy-FedAvg: Server-Aware Client Selection for Federated Speech Emotion Recognition in Heterogeneous Environments
2026-11-06 00:19:13Farrukh Pervez, Siddique Latif, Moid Sandhu, Raja JurdakAbstract
Federated speech emotion recognition (SER) is challenged by speaker-dependent, class-imbalanced data and by heterogeneous client devices. This paper proposes \textit{Fuzzy-FedAvg}, a server-aware framework in which the server learns Client Selection Weights (CSWs) through fuzzy Q-learning from global-model feedback. The same CSWs weight client accuracy, training time, and \divkpi{} in both client selection and aggregation, while a dedicated PCAS node manages stragglers through staleness-discounted deferred updates. On IEMOCAP and CREMA-D, \textit{Fuzzy-FedAvg} achieves higher unweighted average recall (UAR) than FedAvg in all configurations under severe non-IID conditions, and in 22 of 24 participation-level and 10 of 12 training-horizon configurations overall. It also outperforms FedProx and Oort, while SCAFFOLD and Power-of-Choice remain competitive, and it reduces cumulative training time by 81.2\% in a FedScale-based evaluation. The benefit is greatest under strong statistical heterogeneity and narrows as data become more balanced.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08818
PDF
-
Impact of color in computer and human-based object recognition under occlusion
2026-11-06 00:01:47Courtney M. King, Elissa Aminoff, Daniel D. LeedsAbstract
Partial occlusions challenge object recognition in both human and computer vision (CV), but the impact is largely dependent on the occlusion and model design. Properties relating to color are particularly important in biological recognition and frequently leveraged for camouflage, however there are still open questions about what makes them effective and how they translate to CV. This work studies partial occlusions that create camouflage, including those that blend in with target objects or with scenes, which alter object representations in distinct ways. Experiments evaluate recognition performance on both human participants and models ranging from convolutional neural networks (CNNs) to transformers, and additional analysis is performed on models to uncover trends in processing and object representations under multiple occlusion types. Novel metrics offer explainability of model behavior under occlusion: non-occlusion precision (NOP) and non-occlusion recall (NOR) measure alignment of model activations with and without occlusion, and activation in occlusion (AIO) measures the percentage of activations that occur in occluded regions. Findings show that human recognition, and most transformers, are negatively impacted by generated camouflaging occluders, with scene-based camouflage performing worse than object-based. Classical CNNs show a strong opposite trend, performing the worst on neutral-colored occlusions, suggesting that contextually-related colors, particularly scene-based, benefit object recognition rather than disrupting shape or boundary cues. Additionally, generated camouflaging occluders for training augmentation improves robustness to unseen camouflage for selected CNN model, and occlusion metrics suggest trends about learned mechanisms. Findings have interesting implications for alignment in human and computer vision, model vulnerabilities, and explainability.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08808
PDF
-
Scoring, Not Learning: Decomposing Catalog-Consolidation Gains in Web-Scraped Retail Product Recognition
Abstract
Retail product catalogs assembled from web image search are cheap to build and pervasively noisy: queries return packaging shots instead of products, and entries proliferate under names that cannot be distinguished visually. Consolidating such a catalog can look like an alternative to scaling the model. We show this is not a comparison between two ways of improving a recognizer, but between improving a recognizer and changing what counts as correct. We study a public archive of 165,769 cheese images across 1,824 query-named entries. A packaging filter and near-duplicate removal reduce it to a 998-class recognition set on one fixed, group-aware split. Canonicalizing entries to their base type (844 classes) raises top-1 accuracy by 4.0 points. Scoring the unchanged model against the merged label space, by summing its predicted probability within each canonical group, recovers +4.27 points with no retraining (+4.25 over six seeds). Retraining on the consolidated catalog then adds -0.10$\pm$0.53, +0.08$\pm$0.65 and -0.10$\pm$0.65 points at 28, 50 and 88 M parameters, indistinguishable from zero at every capacity ($\pm$ is the across-seed standard deviation). That component is specific, not mechanical: random merges with the identical size profile yield only +0.68 points, and the three backbones agree to within 0.1 points. But it is overwhelmingly category coarsening, not alias correction: across the 37 merged groups, type coarsenings supply 94% of the gain and alias collapses only 7%. We also detect no interaction between consolidation and backbone size: tripling backbone parameters is worth +1.50$\pm$0.57 points on the raw catalog and +1.42$\pm$00.44 on the canonical one, a within-seed interaction of -0.08 [-0.79,+0.63]. On this archive, the reported consolidation gain primarily reflects the evaluation label space, and separating that out costs one evaluation
Abstract (translated)
URL
https://arxiv.org/abs/2611.08655
PDF
-
Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks
2026-11-05 16:46:31Zhitao He, Chi Him Zhang, Chengru Han, Yi R FungAbstract
Personal AI agents face social engineering attacks supported by forged multimodal content, but existing evaluations mainly focus on text-based dialogue, leaving their intrinsic security under such attacks insufficiently studied. We introduce Multimodal-SEA, an interactive benchmark comprising 608 expert-designed tasks grounded in real-world fraud cases, covering 14 domains and 152 attack scenarios with prepared multimodal content. The tasks span four difficulty levels and reflect the distinct social and cultural contexts of Chinese and English environments. Agents inspect content, verify requests, and execute actions in simulated applications, with attack outcomes grounded in verifiable tool execution logs. To enable controlled red teaming of personal agents, we design a multimodal attack harness that integrates task information, attack progression control, and multimodal content construction to evaluate their intrinsic security against adaptive social engineering attacks in simulated environments. Evaluating seven widely used multimodal models across six dimensions reveals that all are vulnerable, with attack success rates of 7.1% to 34.5%. Adding multimodal content increases attack success from 19.9% to 29.2%, despite increased proactive verification coverage. Stronger safety instructions reduce attack success without improving recognition of deceptive multimodal content, while lower attack success rates for some models accompany excessive refusal of legitimate requests.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08281
PDF
-
ATHAAR: A Medieval Scientific Arabic Manuscript Dataset for Handwritten Text Recognition
2026-11-05 14:36:16Ismail El Jamiy, Khadija Msalek, Guillaume Loizelet, Farah Benamara, Nabil HathoutAbstract
Despite recent progress in handwritten text recognition, medieval Arabic scientific manuscripts remain an open challenge for current vision-language models (VLMs) due to cursive ligatures, variable diacritization, and more importantly the lack of training data. This paper aims to address this gap, by proposing the first annotation guidelines dedicated to the transcription of scientific Arabic manuscripts inspired by textual criticism, a well-established approach to historical text editing. We then propose, ATHAAR, a new dataset manually annotated following this guideline. Unlike previous resources in the field, ATHAAR varies both witnesses of the same text, calligraphic styles, and content to deal with texts but also numerals. Relying on state-of-the-art VLMs, we finally design a set of experiments to study models transfer across scripts, chapters, and treatises. Our findings highlight the limitations of current systems when faced with the specificities of ancient scientific texts.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08091
PDF
-
IDPrior: Decoupling Identity Generation from Facial Image Synthesis
2026-11-05 12:41:49Fadi Boutros, Meri\c{c} Demir\"ors, Darian Toma\v{s}evi\'c, Vitomir \v{S}truc, Naser DamerAbstract
Large-scale identity-labeled face datasets are essential for training modern face recognition models, yet collecting and annotating such data is costly and raises privacy and ethical concerns. Existing synthetic face generation methods typically derive identities from predefined class labels, unconditional image generation, or predefined latent sampling strategies, without explicitly modeling the underlying distribution of facial identities. In this paper, we propose IDPrior, a two-stage framework that decouples identity generation from image synthesis. We first learn a diffusion prior in the embedding space of a pretrained face recognition model to model the distribution of facial identities and generate novel identity embeddings. These embeddings are then used to condition a pretrained identity-conditioned diffusion model (DM), enabling the synthesis of multiple images of the same identity. This modular design provides a scalable approach to identity generation while remaining compatible with existing and future identity-conditioned DMs. Experiments indicate that IDPrior generates diverse and well-separated identities while maintaining a closer correspondence to the distribution of authentic identities. Face recognition models trained on datasets generated using IDPrior-generated identities achieve competitive or improved performance compared with existing synthetic-data-based methods across multiple face verification benchmarks. Code and generated datasets are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07941
PDF
-
CardioLM: A multilingual suite of small language models for the cardiology domain
2026-11-05 12:41:19Manuela-Daniela Danu, Miguel Rodr\'iguez-Ortega, Alberto Becerra-Tome, Pablo Arancibia, Fernando Gallego-Donoso, Lorenzo Pratesi, Xi Bai, Andrei-Damian Dinescu, Salvador Lima-L\'opez, Andrea Guala, Saskia Haitjema, Jonas Mack, Michele Miranda, Wesam Al Nabki, Jan Rodr\'iguez-Miret, Vasile George Marica, Vladim\'ir Kincl, Kate\v{r}ina Dost\'alov\'a, Michael Andrej, Alicia Ujil, Corinne Allaart, Machteld Boonstra, Malin Overmars, Anoop Shah, Giovanna Ceroni, Jonathan Kossoff, Domenico D'Amario, Renzo Laborante, Antonio Iaconelli, Isabella Fumarulo, Jacopo Lenkowicz, Livia Lilli, Emma Weiss, Alex Scafa, Felix Lindberg, Milou Gamage, Eul\`alia Farr\'e-Maduell, S\'ebastien Brati\`eres, Martin Krallinger, Bram van EsAbstract
Background: Cardiovascular care generates large volumes of clinical free-text documentation in local languages. However, clinical natural language processing (NLP) resources remain concentrated in English, and no existing benchmark is cardiology-specific, multilingual, and broad in entity coverage. Methods: We present two contributions. The first is CardioCCC, a corpus of 508 cardiology case reports originally published in Spanish and extended to Czech, Dutch, English, Italian, Romanian, and Swedish through machine translation, annotation projection, and clinician review, with annotations covering diseases, symptoms, procedures, and medications. The second is CardioLM, comprising CardioBERTa, a set of language-specific encoders obtained by continued pretraining on cardiology and biomedical corpora, and CardioNER, a set of named entity recognition (NER) models fine-tuned on CardioCCC. Results: Cardiology-specific pretraining reduced pseudo-perplexity by up to a factor of eight, yet changed strict span-level F1 by at most 0.04, with benefits concentrated in languages whose backbones lacked biomedical coverage. The jointly trained multilingual XLM-RoBERTa-large models achieved the best strict F1 in nearly every language and entity type, exceeding the strongest monolingual system by up to 0.13 F1. A large share of residual errors concerned boundary detection: relaxed matching recovered 0.10-0.23 F1 for disease, procedure, and symptom, but only 0.01-0.07 for medication. Clinicians rated CardioNER well above a rule- and dictionary-based baseline, with the mean rating across entity types rising from 26% to 73%. Conclusions: Specialty-specific pretraining is not the decisive factor for downstream entity recognition, whereas multilingual joint training yields the strongest results in nearly all settings and a simpler deployment path for multi-country clinical information extraction.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07940
PDF
-
InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining
2026-11-05 12:03:01Kun Yuan, Hao Ding, Yiqing Shen, Gasper Podobnik, Benjamin Killeen, Tito Porras, Axel Krieger, Mathias UnberathAbstract
Vision foundation models are the backbone of modern surgical image analysis, yet most surgical systems still rely on encoders pretrained on natural images or on specialist models trained from scratch on comparatively small datasets. Pretraining encoders on large amounts of surgery-specific data has the potential to generally enhance the performance of surgical image analysis methods simply by providing stronger backbones. Here we present InnerLogic-Surg, an open family of surgical vision encoders (21M--300M parameters) obtained by continually pretraining a transformer-based image encoder on millions of surgical images curated from 11,965 internet-sourced surgical videos spanning ~2,900 hours and more than fifteen procedure types. Our training recipe inherits DINOv3's pretraining stage to preserve representation ability after surgical adaptation, and additionally applies a learned feature-upsampling module for high-resolution dense prediction at low token cost. Across a benchmark covering workflow, instrument and anatomy recognition, segmentation, detection, and monocular depth, under the same architecture, the largest InnerLogic-Surg model achieves the best linear-probe performance in all 20 surgical tasks. We demonstrate that surgical continual pretraining yields transferable representations that generalize across procedures, anatomical regions, and task types, showing our surgical image encoders as a promising and scalable alternative to the procedure-specific representation learning approaches that have traditionally dominated surgical computer vision.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07883
PDF
-
Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective Automation
Abstract
Financial document recognition is often assessed using character and word error rates, although these metrics do not express whether a system preserves the financial facts on which people and organisations act. This paper develops a human-centred, risk-constrained framework for evaluating financial document recognition as evidence recovery and decision support. It defines typed financial facts linked to visible source regions and separates verbatim transcription, deterministic normalization, and business interpretation. A layered quality model covers text, localization, layout, tables, fields, fact correctness, evidence grounding, uncertainty, robustness, and operational performance. Non-compensatory acceptance gates use one-sided uncertainty bounds for critical-field errors, preventing strong aggregate scores from masking failures in amounts, identifiers, signs, periods, or entity associations. Selective automation is formulated as a constrained routing problem that accounts for residual risk, human-review capacity, and review cost. The framework further specifies annotation and adjudication procedures, leakage-resistant benchmark partitions, statistical estimands, subgroup analyses, and a reproducibility card. Formal results establish the limitations of compensatory scoring, the non-zero upper risk bound after zero observed errors, and a loss sensitive decision rule for routing uncertain cases to human review. The contribution is theoretical and methodological; no new model, dataset, or empirical performance result is claimed.
Abstract (translated)
URL
https://arxiv.org/abs/2611.02775
PDF
-
Automated Video-to-QA Pipeline: End-to-End Question Generation and Verification Using Large Language Models
2026-11-05 10:00:50Jaival Chauhan, Vikram Singh, Pruthwik MishraAbstract
The exponential growth of educational and informational video content on platforms like YouTube presents a challenge for efficient knowledge retrieval and assessment. This paper proposes an end-to-end automated pipeline for extracting structured summaries and generating high-fidelity Question-Answer (QA) pairs from video streams. The framework integrates a cascade of state-of-the-art models: audio extraction is handled via FFmpeg, followed by automatic speech recognition (ASR) using Whisper (A library in Python) to generate accurate transcripts. Due to the token constraints of Large Language Models (LLMs), transcripts are segmented and summarized using Facebook's BART. A key innovation of this work is a Self-Verification and Fine-Tuning Loop. We utilize meta-llama/Llama-3.1-8BInstruct to generate candidate QA pairs from transcript chunks, which are then fed back into the model to rigorously assess their relevance and importance. Only verified, high-quality pairs are retained to construct a synthetic dataset. This dataset is subsequently used to fine-tune the Llama model using Low-Rank Adaptation (LoRA), resulting in a specialized model capable of generating domain-aligned assessment questions. This approach demonstrates a scalable method for creating self-improving educational tools without the need for manual data annotation. The proposed model can be downloaded from Kaggle with all the codes from GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07755
PDF
-
Comparing Classification and Feature Learning by Analyzing Their Loss Functions in Normalized Spaces with Different Scale Factors
2026-11-05 09:49:18Qiufu Li, Huibin Xiao, Linlin Shen, Weijia Fan, Xi Jia, Yongdong HuangAbstract
Classification and feature learning are two closely interrelated fundamental tasks. Feature learning in supervised settings is typically achieved by training classification models, under the common assumption that higher classification accuracy implies better feature quality. In this paper, we first point out that classification accuracy reflects the sample-wise local properties of a model on a dataset, whereas feature learning aims to learn features with good dataset-level global properties, such as intra-class compactness and inter-class separability. From the first principle of feature learning, we redesign the binary cross-entropy (BCE) loss, a counterpart of the cross-entropy (CE) loss used in classification. Then, in normalized feature space, we analyze the minima of the BCE and CE losses and show that both can lead to neural collapse, where sample features from different classes become maximally compact and maximally separated. More importantly, by investigating the convergence behaviors of the two losses as the scale factor $\gamma$ varies in the normalized space, we reveal how classification accuracy and feature quality change differently across spaces of different sizes. Under a fixed training strategy, a very large $\gamma$ achieves perfect classification accuracy but slows convergence toward the ideal feature geometry, whereas a very small $\gamma$ makes classification highly sensitive to small perturbations. A moderate $\gamma$ is therefore necessary for simultaneously achieving reliable classification and well-structured features. Extensive experiments validate these findings and demonstrate that BCE loss exhibits advantages in long-tail and open-set recognitions, as it better aligns with the global requirements of feature learning.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07741
PDF
-
Egocentric Action Recognition with Objects and Vision-Language Affordances
2026-11-05 09:02:25Ra\'ul Boix-Aldeguer, Manuel Benavent-Lledo, David Ortiz-Perez, Jose Garcia-RodriguezAbstract
Action recognition, and more specifically egocentric action recognition, is a core task in computer vision, with applications such as monitoring the daily life activities of elderly people and task assistance. Recent methods rely on visual modalities such as RGB video or depth. However, in egocentric video, an action is largely defined by its objects, which these methods rarely model. We propose a method that combines a frozen SlowFast video expert with an attention-based object expert by late fusion. Each object is represented with its affordances, that is, what can be done with it, generated zero-shot by a vision-language model. Since datasets such as MECCANO annotate only the objects involved in each action, evaluating with these boxes tells the model which objects are active. We therefore train on annotated boxes and evaluate the method with detections from the official active-object detector, and with annotated boxes as an upper bound. Without affordances, our fusion reaches 68.4% Top-1 with annotated boxes but 49.0% with detections. About half of this drop comes from non-active detections. To remove them, the same vision-language model generates an interaction affordance that decides whether a hand is manipulating each detected object. On MECCANO, objects raise the Top-1 of the video expert from 44.9% to 49.0%, and the two affordances raise it to 49.9%, above SlowFast and object-aware RGB baselines. Code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07673
PDF
-
Fine-Tuning a Transducer for Impaired Speech: Where the Gains Appear and What They Mean for Evaluation
2026-11-05 07:39:12Kien Nguyen, Tuan Dinh, Bao PhanAbstract
Speech recognition still works poorly for many people whose speech is affected by conditions such as ALS, Parkinson's disease, cerebral palsy, Down syndrome or stroke. We took part in the Speech Accessibility Project Challenge 2 (SAPC2) with a public speech recognizer that we fine-tuned on the challenge data. Our best entry scored 7.81% character error rate on Test1, the first of two hidden test sets (official baseline 15.26%). Our live entries ran on CPUs with a combined median latency of about 0.9 seconds at 7.96-8.07% error. On new speakers, fine-tuning reduced errors most for the speakers that an off-the-shelf recognizer finds hardest to understand. Sentences already seen in training had far lower error rates than new ones (2.58% vs 6.42%), a larger difference than being a familiar speaker made. We close with lessons for evaluating such systems.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07587
PDF
-
Enhancing Repository-Level Code Completion with Reinforcement Learning in Real-World Scenarios
2026-11-05 06:17:01Zhenlong Dai, Zhuoluo Zhao, Xiu Tang, Sai Wu, Chang Yao, Zhipeng Gao, Jingyuan ChenAbstract
The rapid development of large language models (LLMs) for code, which closely aligns with the practical needs of real-world software development, has sparked growing attention in repository-level code completion. However, existing Code LLMs present challenges in focusing on suitable contexts from the repository and in deeply reasoning about cross-file dependencies. To address these challenges, we propose a novel reinforcement learning framework for repository-level code completion. To better understand both in-file and cross-file contexts, we employ identifier-driven intent recognition to capture completion intent, thereby improving the model's performance in real-world scenarios. To enhance cross-file reasoning, we propose a reward-driven completion learning to effectively reward in complex repository completion scenarios. To guide LLMs in completing code that aligns with intended functionality and repository context, we introduce a selective-exploration strategy that directs the model to focus on low-confidence, high-reward tokens, promoting the exploration of valuable, underexplored completion patterns. Experimental results show that our approach significantly improves the performance of Code LLMs. The code and the dataset are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07510
PDF
-
IMUDINO: Self-distilled Foundation Model for Inertial Sensing
2026-11-05 04:35:16Zhoutong Ye, Chengwen Zhang, Zixuan Wang, Xufeng Jian, Zhe He, Qingyang Wan, Xutong Wang, Jiaqi Liu, Mingze Sun, Yu Mei, Chun Yu, Yuanchun ShiAbstract
We present IMUDINO, the first foundation model (FM) for inertial sensing to achieve competitive performance across diverse sensing tasks including human activity recognition (HAR), health, motion capture, and odometry. Prior inertial FMs often focus on one subfield of inertial sensing and sometimes underperform state-of-the-art supervised methods (e.g., in HAR), making their scope considerably narrower than FMs for vision and natural language. Moreover, they often require fixed input length and sampling rate, and generalize poorly to unseen sensor locations. To build a general-purpose foundation model for inertial sensing, we adapt the DINO self-supervised learning (SSL) paradigm to inertial data through a set of semantics-preserving motion transformations that simulate variations in motion pattern and sensor setup. For model architecture, we use a plain transformer encoder with frequency-aware positional encoding that natively supports varying input length and sampling rate. This simple setup proved remarkably effective for learning global and dense features generalizable across users, sensor setups, tasks, and, in the case of robot odometry, embodiments. We hope IMUDINO can serve as a backbone for inertial sensing and kickstart the development of general-purpose inertial FMs.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07437
PDF
-
Compositional Unalignment: Auditing Safety in Large Vision-Language Models
2026-11-04 23:09:31Hong kyu Lee, Kai Shu, Li XiongAbstract
Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through the model's cross-modal reasoning. Recent alignment methods report strong scores on compositional safety benchmarks, but an LLM judge only measures observed behavior and cannot reveal how robustly safety is integrated into the model. We argue that un-alignment provides a complementary audit of alignment robustness. We first show that minimal supervised fine-tuning reaches an LLM-judge score comparable to a multi-stage reinforcement-learning pipeline, so similar benchmark scores cannot establish robustness by themselves. We then show that recognition and refusal of compositional harm are decoupled: nine standard direction-finding methods detect compositional harm with up to AUC=0.99, yet ablating the recovered directions either leaves refusal intact or destroys model coherence. We therefore propose CMaG, a training-free un-alignment method for compositional safety. CMaG measures refusal intention with a refusal-versus-compliance log-probability margin, takes its gradient with respect to mid-layer activations, and contrasts it against partially benign pairs to isolate the cross-modal interaction term. A single backward pass over 80 examples yields a direction along which steering monotonically converts refusal into compliance. On Qwen2.5-VL-7B and LLaVA-1.5-7B, CMaG reduces compositional safety scores by up to 65 points while over 98% of outputs remain coherent, outperforming gradient-based baselines; the direction also transfers to text-explicit harm and un-aligns models hardened by defensive training. Compositional safety can thus appear behaviorally strong while remaining fragile to targeted internal intervention. Warning: this paper contains unsafe model outputs, including references to self-harm.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07216
PDF
-
TraCE: Trajectory-Aware Concepts for Explainable Video Understanding
2026-11-04 19:00:01Wooil Lee, Junpyo Hong, Jongseo Lee, Tuomas Oikarinen, Tsui-Wei Weng, Jinwoo ChoiAbstract
Video understanding models often rely on motion, yet their explanations can obscure which motion sources support a prediction. We identify motion-source under-specification as a limitation of existing video XAI: region-centric explanations can be source-ambiguous, while motion vocabularies restricted to single-person pose sequences are source-incomplete. We propose TraCE (Trajectory-Aware Concepts for Explainable Video Understanding), a concept-based framework that discovers source-flexible motion concepts by clustering optical-flow trajectories from training videos. These concepts represent dynamic evidence from people, objects, and interactions, while object and scene concepts account for static context. The resulting typed trajectory/object/scene interface supports class prediction for action recognition and question-conditioned concept matching for video question answering (VQA). We evaluate TraCE across five random seeds on six benchmarks: NTU RGB+D Mutual, Chiral SSv2, UCF-101, KTH, TOMATO, and STAR. Relative to non-interpretable baselines, TraCE maintains competitive task performance, with an average accuracy drop of 1.0 points for action recognition and a nominal gain of 0.4 points for VQA. Motion perturbation and concept-removal tests provide complementary evidence of directional semantic alignment and decision faithfulness, while sample-level interventions illustrate targeted model debugging. Our project page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07009
PDF
-
BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
2026-11-04 18:57:17Fei Lin, Tengchao Zhang, Ziyang Gong, Xiaotong Yu, Bohan Zhang, Yifan Zhou, Qihao Yang, Ji Dai, Dong Li, Yining Jiang, Qinghua Ni, Jun Huang, Qiang Zhang, Yue Zhou, Zhihang Zhong, Yonglin Tian, Fei-Yue Wang, Xue YangAbstract
Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental states, and act under physical, procedural, and safety constraints. Although Multimodal Large Language Models (MLLMs) are increasingly considered as embodied brains for such systems, existing laboratory benchmarks mainly focus on safety, anomaly detection, or general scientific understanding, leaving their execution-oriented embodied capabilities underexplored. To fill this gap, we introduce BEAKER, a Benchmark for evaluating Embodied Actionability, Knowledge, Experimentation, and Reasoning in SDCLs. BEAKER contains 1,000 expert-curated question-answer samples across 11 image and video task types, covering key judgments required for chemical laboratory execution, including affordance grounding, trajectory planning, equipment, state, and safety recognition, apparatus setup, operation and step reasoning, and temporal procedure reasoning. All questions and annotations are manually created and reviewed by chemistry and embodied Artificial Intelligence (AI) experts, without AI-assisted generation or annotation. We evaluate 28 general-purpose, science-oriented, chemistry-specialized, and embodied MLLMs in an offline, single-turn setting. Results show that current models can follow coarse experimental procedures in videos, but still struggle to ground actions into operable regions and feasible trajectories, to recognize fine-grained laboratory apparatus, states, and safety norms, and to order steps in mid-length procedures. BEAKER thus reveals a clear gap between coarse procedural understanding and the precise, action-grounded perception required for laboratory execution, providing a diagnostic benchmark for future MLLMs in SDCLs.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06911
PDF
-
Resolve, Clear, or Defer: Training-Free Active Prototype Triage for Ecological Detection Pipelines
2026-11-04 18:07:36Anirudh Potlapally, Brijesh Nanda Brunda Yogananda, Jianyang Gu, Maanav Jajodia, Luke Meyers, Wei-Lun Chao, Hari SubramoniAbstract
Ecological monitoring increasingly relies on camera traps and aerial surveys that generate large image collections. High-recall animal detectors can localize candidate animals at scale. However, they also produce many detections that still require expert review, including false positives, ambiguous cases, and animals difficult to identify at the species level. Since exhaustive review requires substantial effort, we propose training-free active prototype triage, where reviewed detections become reusable evidence to (1) Resolve supported foreground classes, (2) Clear likely background false positives, or (3) Defer insufficiently supported cases for expert review. Across camera-trap and aerial datasets, foreground recognition and false-positive rejection benefit from different pretrained representations: BioCLIP2 provides foreground evidence while DINOv3 provides background evidence, reducing erroneous foreground clearing while improving automatic foreground recovery. Deferring unsupported cases avoids the higher error rates caused by forced decisions. Compared with confidence-thresholded multiclass k-NN and uncertainty-sampling logistic regression, prototype triage improves foreground recovery while maintaining competitive or lower review burden. Acquisition goes beyond class discovery: even after classes are represented, prototype choice determines how reliably evidence propagates through the remaining detections. Our results suggest that once animal localization reaches high recall, the challenge shifts from finding animals to deciding which examples to review, how to reuse them, and when evidence does not support an automatic decision.
Abstract (translated)
URL
https://arxiv.org/abs/2611.01466
PDF
