# Research Papers — 2026-02 · bundle page 125 of 210 > Full-text markdown of papers #6201–6250 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/125 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/124.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/126.md) ### TraceMem: Weaving Narrative Memory Schemata from User Conversational Traces Authors: Yiming Shu, Pei Liu, Tiange Zhang, Ruiyang Gao, Jun Ma, Chen Sun Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09712v1 Sustaining long-term interactions remains a bottleneck for Large Language Models (LLMs), as their limited context windows struggle to manage dialogue histories that extend over time. Existing memory systems often treat interactions as disjointed snippets, failing to capture the underlying narrative coherence of the dialogue stream. We propose TraceMem, a cognitively-inspired framework that weaves structured, narrative memory schemata from user conversational traces through a three-stage pipeline: (1) Short-term Memory Processing, which employs a deductive topic segmentation approach to demarcate episode boundaries and extract semantic representation; (2) Synaptic Memory Consolidation, a process that summarizes episodes into episodic memories before distilling them alongside semantics into user-specific traces; and (3) Systems Memory Consolidation, which utilizes two-stage hierarchical clustering to organize these traces into coherent, time-evolving narrative threads under unifying themes. These threads are encapsulated into structured user memory cards, forming narrative memory schemata. For memory utilization, we provide an agentic search mechanism to enhance reasoning process. Evaluation on the LoCoMo benchmark shows that TraceMem achieves state-of-the-art performance with a brain-inspired architecture. Analysis shows that by constructing coherent narratives, it surpasses baselines in multi-hop and temporal reasoning, underscoring its essential role in deep narrative comprehension. Additionally, we provide an open discussion on memory systems, offering our perspectives and future outlook on the field. Our code implementation is available at: https://github.com/YimingShu-teay/TraceMem --- ### Physics-informed diffusion models in spectral space Authors: Davide Gallon, Philippe von Wurstemberger, Patrick Cheridito, Arnulf Jentzen Published: 2026-02-10 Categories: cs.LG, cs.AI, cs.CV, math.NA arXiv: https://arxiv.org/abs/2602.09708v2 We propose physics-informed spectral diffusion (PISD), a methodology that combines generative latent diffusion models with physics-informed machine learning to generate solutions of partial differential equations (PDEs) conditioned on partial observations, which includes, in particular, forward and inverse PDE problems. We learn the joint distribution of PDE parameters and solutions via a diffusion process in a latent space of scaled spectral representations, where Gaussian noise corresponds to functions with controlled regularity. This spectral formulation enables significant dimensionality reduction compared to grid-based diffusion models and ensures that the induced process in function space remains within a class of functions for which the PDE operators are well defined. Building on diffusion posterior sampling, we enforce physics-informed constraints and measurement conditions during inference, applying Adam-based updates at each diffusion step. We evaluate the proposed approach on Poisson, Helmholtz, and incompressible Navier-Stokes equations, demonstrating improved accuracy and computational efficiency compared with existing diffusion-based PDE solvers, which are state of the art for sparse observations. Code is available at https://github.com/deeplearningmethods/PISD. --- ### Extended Isolation Forest with feature sensitivities Authors: Illia Donhauzer Published: 2026-02-10 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.09704v1 Compared to theoretical frameworks that assume equal sensitivity to deviations in all features of data, the theory of anomaly detection allowing for variable sensitivity across features is less developed. To the best of our knowledge, this issue has not yet been addressed in the context of isolation-based methods, and this paper represents the first attempt to do so. This paper introduces an Extended Isolation Forest with feature sensitivities, which we refer to as the Anisotropic Isolation Forest (AIF). In contrast to the standard EIF, the AIF enables anomaly detection with controllable sensitivity to deviations in different features or directions in the feature space. The paper also introduces novel measures of directional sensitivity, which allow quantification of AIF's sensitivity in different directions in the feature space. These measures enable adjustment of the AIF's sensitivity to task-specific requirements. We demonstrate the performance of the algorithm by applying it to synthetic and real-world datasets. The results show that the AIF enables anomaly detection that focuses on directions in the feature space where deviations from typical behavior are more important. --- ### Maastricht University at AMIYA: Adapting LLMs for Dialectal Arabic using Fine-tuning and MBR Decoding Authors: Abdulhai Alali, Abderrahmane Issam Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.09703v1 Large Language Models (LLMs) are becoming increasingly multilingual, supporting hundreds of languages, especially high resource ones. Unfortunately, Dialect variations are still underrepresented due to limited data and linguistic variation. In this work, we adapt a pre-trained LLM to improve dialectal performance. Specifically, we use Low Rank Adaptation (LoRA) fine-tuning on monolingual and English Dialect parallel data, adapter merging and dialect-aware MBR decoding to improve dialectal fidelity generation and translation. Experiments on Syrian, Moroccan, and Saudi Arabic show that merging and MBR improve dialectal fidelity while preserving semantic accuracy. This combination provides a compact and effective framework for robust dialectal Arabic generation. --- ### GenSeg-R1: RL-Driven Vision-Language Grounding for Fine-Grained Referring Segmentation Authors: Sandesh Hegde, Jaison Saji Chacko, Debarshi Banerjee, Uma Mahesh Published: 2026-02-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.09701v1 We study fine-grained referring image segmentation via a decoupled reason-then-segment pipeline. A vision-language model (VLM) receives an image and a natural-language query, reasons about the scene, and emits structured spatial prompts: a bounding box plus two interior keypoints for every referred instance. A frozen promptable segmenter (SAM 2) converts these prompts into high-quality masks. Within our GenSeg-R1 framework we finetune Qwen3-VL models (4B and 8B parameters) using Group Relative Policy Optimization (GRPO), requiring no supervised reasoning-chain annotations. On RefCOCOg validation our best model (GenSeg-R1-8B) achieves 0.7127 cIoU and 0.7382 mIoU, substantially outperforming the corresponding Qwen3-VL Instruct baselines (+15.3 and +21.9 points, respectively) and surpassing Seg-Zero-7B (3) by +3.3 cIoU under identical evaluation. We further introduce GenSeg-R1-G, a variant trained on GRefCOCO (9) with a SAM 2 in-the-loop reward that directly optimizes mask quality. On GRefCOCO validation GenSeg-R1-G achieves 76.69% target mIoU with 82.40% accuracy on negative (no-target) prompts, substantially outperforming Seg-R1-7B and Seg-Zero-7B, which lack no-target detection capability. On ReasonSeg test, GenSeg-R1-4B reaches 68.40% mIoU, surpassing Seg-Zero-7B by +7.0 and Seg-R1-7B by +10.7 points. --- ### Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation Authors: Joseph Attieh, Timothee Mickus, Anne-Laure Ligozat, Aurélie Névéol, Jörg Tiedemann Published: 2026-02-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.09691v2 Knowledge distillation (KD) is a technique to compress a larger teacher system into a smaller student. In machine translation, KD is commonly evaluated through translation quality and inference efficiency, without jointly accounting for the environmental costs of producing and deploying the distilled system. We evaluate representative KD methods both on bespoke MT models and LLMs, by considering both translation quality and computational cost, using the Machine Learning Life Cycle Assessment tool, which accounts for costs throughout the KD model life cycle. Our key finding is that the deployment volume required to amortize KD is serving-dependent and can shift by several orders of magnitude under batching. We include actionable guidance for selecting, developing, and evaluating KD methods under quality and compute-induced constraints. --- ### Life Cycle-Aware Evaluation of Knowledge Distillation for Machine Translation: Environmental Impact and Translation Quality Trade-offs Authors: Joseph Attieh, Timothee Mickus, Anne-Laure Ligozat, Aurélie Névéol, Jörg Tiedemann Published: 2026-02-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.09691v1 Knowledge distillation (KD) is a tool to compress a larger system (teacher) into a smaller one (student). In machine translation, studies typically report only the translation quality of the student and omit the computational complexity of performing KD, making it difficult to select among the many available KD choices under compute-induced constraints. In this study, we evaluate representative KD methods by considering both translation quality and computational cost. We express computational cost as a carbon footprint using the machine learning life cycle assessment (MLCA) tool. This assessment accounts for runtime operational emissions and amortized hardware production costs throughout the KD model life cycle (teacher training, distillation, and inference). We find that (i) distillation overhead dominates the total footprint at small deployment volumes, (ii) inference dominates at scale, making KD beneficial only beyond a task-dependent usage threshold, and (iii) word-level distillation typically offers more favorable footprint-quality trade-offs than sequence-level distillation. Our protocol provides reproducible guidance for selecting KD methods under explicit quality and compute-induced constraints. --- ### Contextual and Seasonal LSTMs for Time Series Anomaly Detection Authors: Lingpei Zhang, Qingming Li, Yong Yang, Jiahao Chen, Rui Zeng, Chenyang Lyu, Shouling Ji Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09690v1 Univariate time series (UTS), where each timestamp records a single variable, serve as crucial indicators in web systems and cloud servers. Anomaly detection in UTS plays an essential role in both data mining and system reliability management. However, existing reconstruction-based and prediction-based methods struggle to capture certain subtle anomalies, particularly small point anomalies and slowly rising anomalies. To address these challenges, we propose a novel prediction-based framework named Contextual and Seasonal LSTMs (CS-LSTMs). CS-LSTMs are built upon a noise decomposition strategy and jointly leverage contextual dependencies and seasonal patterns, thereby strengthening the detection of subtle anomalies. By integrating both time-domain and frequency-domain representations, CS-LSTMs achieve more accurate modeling of periodic trends and anomaly localization. Extensive evaluations on public benchmark datasets demonstrate that CS-LSTMs consistently outperform state-of-the-art methods, highlighting their effectiveness and practical value in robust time series anomaly detection. --- ### Model soups need only one ingredient Authors: Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09689v2 Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data. Weight-space ensembling methods, such as Model Soups, mitigate this effect by averaging multiple checkpoints, but they are computationally prohibitive, requiring the training and storage of dozens of fine-tuned models. In this paper, we introduce MonoSoup, a simple, data-free, hyperparameter-free, post-hoc method that achieves a strong ID-OOD balance using only a single checkpoint. Our method applies Singular Value Decomposition (SVD) to each layer's update and decomposes it into high-energy directions that capture task-specific adaptation and low-energy directions that introduce noise but may still encode residual signals useful for robustness. MonoSoup then uses entropy-based effective rank to automatically re-weigh these components with layer-wise coefficients that account for the spectral and geometric structure of the model. Experiments on CLIP models fine-tuned on ImageNet and evaluated under natural distribution shifts, as well as on Qwen language models tested on mathematical reasoning and multiple-choice benchmarks, show that this plug-and-play approach is a practical and effective alternative to multi-checkpoint methods, retaining much of their benefits without their computational overhead. --- ### Semi-supervised Liver Segmentation and Patch-based Fibrosis Staging with Registration-aided Multi-parametric MRI Authors: Boya Wang, Ruizhe Li, Chao Chen, Xin Chen Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09686v1 Liver fibrosis poses a substantial challenge in clinical practice, emphasizing the necessity for precise liver segmentation and accurate disease staging. Based on the CARE Liver 2025 Track 4 Challenge, this study introduces a multi-task deep learning framework developed for liver segmentation (LiSeg) and liver fibrosis staging (LiFS) using multiparametric MRI. The LiSeg phase addresses the challenge of limited annotated images and the complexities of multi-parametric MRI data by employing a semi-supervised learning model that integrates image segmentation and registration. By leveraging both labeled and unlabeled data, the model overcomes the difficulties introduced by domain shifts and variations across modalities. In the LiFS phase, we employed a patchbased method which allows the visualization of liver fibrosis stages based on the classification outputs. Our approach effectively handles multimodality imaging data, limited labels, and domain shifts. The proposed method has been tested by the challenge organizer on an independent test set that includes in-distribution (ID) and out-of-distribution (OOD) cases using three-channel MRIs (T1, T2, DWI) and seven-channel MRIs (T1, T2, DWI, GED1-GED4). The code is freely available. Github link: https://github.com/mileywang3061/Care-Liver --- ### Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams Authors: Jin Li, Kleanthis Malialis, Marios Polycarpou Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.09681v1 In today's connected world, the generation of massive streaming data across diverse domains has become commonplace. In the presence of concept drift, class imbalance, label scarcity, and new class emergence, they jointly degrade representation stability, bias learning toward outdated distributions, and reduce the resilience and reliability of detection in dynamic environments. This paper proposes SCIL (Streaming Class-Incremental Learning) to address these challenges. The SCIL framework integrates an autoencoder (AE) with a multi-layer perceptron for multi-class prediction, uses a dual-loss strategy (classification and reconstruction) for prediction and new class detection, employs corrected pseudo-labels for online training, manages classes with queues, and applies oversampling to handle imbalance. The rationale behind the method's structure is elucidated through ablation studies and a comprehensive experimental evaluation is performed using both real-world and synthetic datasets that feature class imbalance, incremental classes, and concept drifts. Our results demonstrate that SCIL outperforms strong baselines and state-of-the-art methods. Based on our commitment to Open Science, we make our code and datasets available to the community. --- ### Administrative Law's Fourth Settlement: AI and the Scrutable State Authors: Nicholas Caputo Published: 2026-02-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.09678v3 Since 1887, administrative law has confronted a problem of institutional cognition. Expert agencies are needed to govern technologically complex systems, but expertise makes agency decisions difficult for courts, Congress, and the public to understand and oversee. Administrative law has responded to this "capability-accountability trap" by requiring records, reason-giving, and transparency, drawn together through procedural review. These devices have preserved legality but have piled up, making government both less comprehensible and less effective. This Article offers a new account of the Supreme Court's recent administrative law retrenchment, rooted in problems of institutional structure and information-processing. From Loper Bright through Trump v. Slaughter, the Court has reallocated authority to entities it regards as comprehensible and attributable. It is attempting to restore accountability by making government "scrutable," comprehensible to its overseers and the public, but in doing so it is sacrificing capability and undermining the effectiveness of administration. AI offers a different path. Deployed correctly, AI could help make government both more effective and more transparent, translating technical complexity into accessible terms, surfacing assumptions, and enabling substantive verification of agency reasoning. This technical integration must be accompanied by updated administrative law, built around a Model and System Dossier that extends the administrative record to AI decision-making; a material-model-change trigger specifying when AI updates require new process; and a deference to audit standard that rewards agencies for auditable evaluation of AI uses. The result a "Fourth Settlement," administrative law that escapes the capability-accountability trap by preserving capability while restoring comprehensible oversight of administration. --- ### Knowledge Integration in Differentiable Models: A Comparative Study of Data-Driven, Soft-Constrained, and Hard-Constrained Paradigms for Identification and Control of the Single Machine Infinite Bus System Authors: Shinhoo Kang, Sangwook Kim, Sehyun Yun Published: 2026-02-10 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2602.09667v2 Integrating domain knowledge into neural networks is a central challenge in scientific machine learning. Three paradigms have emerged -- data-driven (Neural Ordinary Differential Equations, NODEs), soft-constrained (Physics-Informed Neural Networks, PINNs), and hard-constrained (Differentiable Programming, DP) -- each encoding physical knowledge at different levels of structural commitment. However, how these strategies impact not only predictive accuracy but also downstream tasks such as control synthesis remains insufficiently understood. This paper presents a comparative study of NODEs, PINNs, and DP for dynamical system modeling, using the Single Machine Infinite Bus power system as a benchmark. We evaluate these paradigms across three tasks: trajectory prediction, parameter identification, and Linear Quadratic Regulator control synthesis. Our results yield three principal findings. First, knowledge representation determines generalization: NODE, which learns the system operator, enables robust extrapolation, whereas PINN, which approximates a solution map, restricts generalization to the training horizon. Second, hard-constrained formulations (DP) reduce learning to a low-dimensional physical parameter space, achieving faster and more reliable convergence than soft-constrained approaches. Third, knowledge fidelity propagates to control performance: DP produces controllers that closely match those obtained from true system parameters, while NODE provides a viable data-driven alternative by recovering control-relevant Jacobians with $3-4\%$ relative error and yielding LQR gains within $0.36\%$ of the ground truth. Based on these findings, we propose a practical decision framework for selecting knowledge integration strategies in neural modeling of dynamical systems. --- ### TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution Authors: Deyang Jiang, Jing Huang, Xuanle Zhao, Lei Chen, Liming Zheng, Fanfan Liu, Haibo Qiu, Peng Shi, Zhixiong Zeng Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09662v1 Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection. In reality, the exploration process of a CUA across apps/desktops/web pages typically follows a tree structure, with earlier functional entry points often being explored more frequently. Thus, organizing large-scale trajectories into tree structures can reduce data cost and streamline the data scaling of GUI planning. In this work, we propose TreeCUA to efficiently scale GUI automation with tree-structured verifiable evolution. We propose a multi-agent collaborative framework to explore the environment, verify actions, summarize trajectories, and evaluate quality to generate high-quality and scalable GUI trajectories. To improve efficiency, we devise a novel tree-based topology to store and replay duplicate exploration nodes, and design an adaptive exploration algorithm to balance the depth (\emph{i.e.}, trajectory difficulty) and breadth (\emph{i.e.}, trajectory diversity). Moreover, we develop world knowledge guidance and global memory backtracking to avoid low-quality generation. Finally, we naturally extend and propose the TreeCUA-DPO method from abundant tree node information, improving GUI planning capability by referring to the branch information of adjacent trajectories. Experimental results show that TreeCUA and TreeCUA-DPO offer significant improvements, and out-of-domain (OOD) studies further demonstrate strong generalization. All trajectory node information and code will be available at https://github.com/UITron-hub/TreeCUA. --- ### ClinAlign: Scaling Healthcare Alignment from Clinician Preference Authors: Shiwei Lyu, Xidong Wang, Lei Liu, Hao Zhu, Chaohe Zhang, Jian Wang, Jinjie Gu, Benyou Wang, Yue Shen Published: 2026-02-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.09653v2 Although large language models (LLMs) demonstrate expert-level medical knowledge, aligning their open-ended outputs with fine-grained clinician preferences remains challenging. Existing methods often rely on coarse objectives or unreliable automated judges that are weakly grounded in professional guidelines. We propose a two-stage framework to address this gap. First, we introduce HealthRubrics, a dataset of 7,034 physician-verified preference examples in which clinicians refine LLM-drafted rubrics to meet rigorous medical standards. Second, we distill these rubrics into HealthPrinciples: 119 broadly reusable, clinically grounded principles organized by clinical dimensions, enabling scalable supervision beyond manual annotation. We use HealthPrinciples for (1) offline alignment by synthesizing rubrics for unlabeled queries and (2) an inference-time tool for guided self-revision. A 30B-A3B model trained with our framework achieves 33.4% on HealthBench-Hard, outperforming much larger models including Deepseek-R1 and o3, establishing a resource-efficient baseline for clinical alignment. --- ### The Entropic Signature of Class Speciation in Diffusion Models Authors: Florian Handke, Dejan Stančević, Felix Koulischer, Thomas Demeester, Luca Ambrogioni Published: 2026-02-10 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.09651v2 Diffusion models do not recover semantic structure uniformly over time. Instead, samples transition from semantic ambiguity to class commitment within a narrow regime. Recent theoretical work attributes this transition to dynamical instabilities along class-separating directions, but practical methods to detect and exploit these windows in trained models are still limited. We show that tracking the class-conditional entropy of a latent semantic variable given the noisy state provides a reliable signature of these transition regimes. By restricting the entropy to semantic partitions, the entropy can furthermore resolve semantic decisions at different levels of abstraction. We analyze this behavior in high-dimensional Gaussian mixture models and show that the entropy rate concentrates on the same logarithmic time scale as the speciation symmetry-breaking instability previously identified in variance-preserving diffusion. We validate our method on EDM2-XS and Stable Diffusion 1.5, where class-conditional entropy consistently isolates the noise regimes critical for semantic structure formation. Finally, we use our framework to quantify how guidance redistributes semantic information over time. Together, these results connect information-theoretic and statistical physics perspectives on diffusion and provide a principled basis for time-localized control. --- ### Time2General: Learning Spatiotemporal Invariant Representations for Domain-Generalization Video Semantic Segmentation Authors: Siyu Chen, Ting Han, Haoling Huang, Chaolei Wang, Chengzheng Fu, Duxin Zhu, Guorong Cai, Jinhe Su Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09648v2 Domain Generalized Video Semantic Segmentation (DGVSS) is trained on a single labeled driving domain and is directly deployed on unseen domains without target labels and test-time adaptation while maintaining temporally consistent predictions over video streams. In practice, both domain shift and temporal-sampling shift break correspondence-based propagation and fixed-stride temporal aggregation, causing severe frame-to-frame flicker even in label-stable regions. We propose Time2General, a DGVSS framework built on Stability Queries. Time2General introduces a Spatio-Temporal Memory Decoder that aggregates multi-frame context into a clip-level spatio-temporal memory and decodes temporally consistent per-frame masks without explicit correspondence propagation. To further suppress flicker and improve robustness to varying sampling rates, the Masked Temporal Consistency Loss is proposed to regularize temporal prediction discrepancies across different strides, and randomize training strides to expose the model to diverse temporal gaps. Extensive experiments on multiple driving benchmarks show that Time2General achieves a substantial improvement in cross-domain accuracy and temporal stability over prior DGSS and VSS baselines while running at up to 18 FPS. Code will be released after the review process. --- ### MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering Authors: Sieun Hyeon, Jusang Oh, Sunghwan Steve Cho, Jaeyoung Do Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.09642v2 Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring reliability, scalability, and efficiency, especially in resource-constrained or privacy-sensitive environments. In this paper, we introduce MATA, a multi-agent TableQA framework that leverages multiple complementary reasoning paths and a set of tools built with small language models. MATA generates candidate answers through diverse reasoning styles for a given table and question, then refines or selects the optimal answer with the help of these tools. Furthermore, it incorporates an algorithm designed to minimize expensive LLM agent calls, enhancing overall efficiency. MATA maintains strong performance with small, open-source models and adapts easily across various LLM types. Extensive experiments on two benchmarks of varying difficulty with ten different LLMs demonstrate that MATA achieves state-of-the-art accuracy and highly efficient reasoning while avoiding excessive LLM inference. Our results highlight that careful orchestration of multiple reasoning pathways yields scalable and reliable TableQA. The code is available at https://github.com/AIDASLab/MATA. --- ### Blind denoising diffusion models and the blessings of dimensionality Authors: Zahra Kadkhodaie, Aram-Alexandre Pooladian, Sinho Chewi, Eero Simoncelli Published: 2026-02-10 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.09639v2 Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline remain poorly understood. In particular, noise conditioning requires practitioners to incorporate contrived unprincipled noise embeddings into neural network architectures and to use ad hoc noise schedules for sampling. To address these drawbacks, we provide a complete theory for \emph{blind denoising diffusion models} (BDDMs): a variant of DDMs where the noise amplitude is not passed into the neural network during training or sampling, obviating the need for the aforementioned design choices. We justify the correctness of BDDMs as a sampling algorithm under an assumption of low intrinsic dimensionality of the underlying data distribution relative to the ambient dimension. This assumption arises through the introduction of the Bayesian problem of estimating noise levels from a single noisy sample, which might be of independent interest. We empirically compare the performance of BDDMs to standard DDMs, showcasing the benefits of an \emph{adaptive} scheme which is rigorously justified by our analysis. --- ### VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model Authors: Hanqing Wang, Mingyu Liu, Xiaoyu Chen, Chengwei MA, Yiming Zhong, Wenti Yin, Yuhao Liu, Zhiqing Cui, Jiahao Yuan, Lu Dai, Zhiyuan Ma, Hui Xiong Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09638v1 3D affordance grounding aims to highlight the actionable regions on 3D objects, which is crucial for robotic manipulation. Previous research primarily focused on learning affordance knowledge from static cues such as language and images, which struggle to provide sufficient dynamic interaction context that can reveal temporal and causal cues. To alleviate this predicament, we collect a comprehensive video-based 3D affordance dataset, \textit{VIDA}, which contains 38K human-object-interaction videos covering 16 affordance types, 38 object categories, and 22K point clouds. Based on \textit{VIDA}, we propose a strong baseline: VideoAfford, which activates multimodal large language models with additional affordance segmentation capabilities, enabling both world knowledge reasoning and fine-grained affordance grounding within a unified framework. To enhance action understanding capability, we leverage a latent action encoder to extract dynamic interaction priors from HOI videos. Moreover, we introduce a \textit{spatial-aware} loss function to enable VideoAfford to obtain comprehensive 3D spatial knowledge. Extensive experimental evaluations demonstrate that our model significantly outperforms well-established methods and exhibits strong open-world generalization with affordance reasoning abilities. All datasets and code will be publicly released to advance research in this area. --- ### Towards Training-free Multimodal Hate Localisation with Large Language Models Authors: Yueming Sun, Long Yang, Jianbo Jiao, Zeyu Fu Published: 2026-02-10 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2602.09637v1 The proliferation of hateful content in online videos poses severe threats to individual well-being and societal harmony. However, existing solutions for video hate detection either rely heavily on large-scale human annotations or lack fine-grained temporal precision. In this work, we propose LELA, the first training-free Large Language Model (LLM) based framework for hate video localization. Distinct from state-of-the-art models that depend on supervised pipelines, LELA leverages LLMs and modality-specific captioning to detect and temporally localize hateful content in a training-free manner. Our method decomposes a video into five modalities, including image, speech, OCR, music, and video context, and uses a multi-stage prompting scheme to compute fine-grained hateful scores for each frame. We further introduce a composition matching mechanism to enhance cross-modal reasoning. Experiments on two challenging benchmarks, HateMM and MultiHateClip, demonstrate that LELA outperforms all existing training-free baselines by a large margin. We also provide extensive ablations and qualitative visualizations, establishing LELA as a strong foundation for scalable and interpretable hate video localization. --- ### LLM-FS: Zero-Shot Feature Selection for Effective and Interpretable Malware Detection Authors: Naveen Gill, Ajvad Haneef K, Madhu Kumar S D Published: 2026-02-10 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.09634v1 Feature selection (FS) remains essential for building accurate and interpretable detection models, particularly in high-dimensional malware datasets. Conventional FS methods such as Extra Trees, Variance Threshold, Tree-based models, Chi-Squared tests, ANOVA, Random Selection, and Sequential Attention rely primarily on statistical heuristics or model-driven importance scores, often overlooking the semantic context of features. Motivated by recent progress in LLM-driven FS, we investigate whether large language models (LLMs) can guide feature selection in a zero-shot setting, using only feature names and task descriptions, as a viable alternative to traditional approaches. We evaluate multiple LLMs (GPT-5.0, GPT-4.0, Gemini-2.5 etc.) on the EMBOD dataset (a fusion of EMBER and BODMAS benchmark datasets), comparing them against established FS methods across several classifiers, including Random Forest, Extra Trees, MLP, and KNN. Performance is assessed using accuracy, precision, recall, F1, AUC, MCC, and runtime. Our results demonstrate that LLM-guided zero-shot feature selection achieves competitive performance with traditional FS methods while offering additional advantages in interpretability, stability, and reduced dependence on labeled data. These findings position zero-shot LLM-based FS as a promising alternative strategy for effective and interpretable malware detection, paving the way for knowledge-guided feature selection in security-critical applications --- ### Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks Authors: Hayfa Dhahbi, Kashyap Thimmaraju Published: 2026-02-10 Categories: cs.CR, cs.AI, cs.CY, cs.ET, cs.HC arXiv: https://arxiv.org/abs/2602.09629v1 Large Language Models (LLMs) deploy safety mechanisms to prevent harmful outputs, yet these defenses remain vulnerable to adversarial prompts. While existing research demonstrates that jailbreak attacks succeed, it does not explain \textit{where} defenses fail or \textit{why}. To address this gap, we propose that LLM safety operates as a sequential pipeline with distinct checkpoints. We introduce the \textbf{Four-Checkpoint Framework}, which organizes safety mechanisms along two dimensions: processing stage (input vs.\ output) and detection level (literal vs.\ intent). This creates four checkpoints, CP1 through CP4, each representing a defensive layer that can be independently evaluated. We design 13 evasion techniques, each targeting a specific checkpoint, enabling controlled testing of individual defensive layers. Using this framework, we evaluate GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro across 3,312 single-turn, black-box test cases. We employ an LLM-as-judge approach for response classification and introduce Weighted Attack Success Rate (WASR), a severity-adjusted metric that captures partial information leakage overlooked by binary evaluation. Our evaluation reveals clear patterns. Traditional Binary ASR reports 22.6\% attack success. However, WASR reveals 52.7\%, a 2.3$\times$ higher vulnerability. Output-stage defenses (CP3, CP4) prove weakest at 72--79\% WASR, while input-literal defenses (CP1) are strongest at 13\% WASR. Claude achieves the strongest safety (42.8\% WASR), followed by GPT-5 (55.9\%) and Gemini (59.5\%). These findings suggest that current defenses are strongest at input-literal checkpoints but remain vulnerable to intent-level manipulation and output-stage techniques. The Four-Checkpoint Framework provides a structured approach for identifying and addressing safety vulnerabilities in deployed systems. --- ### MILE-RefHumEval: A Reference-Free, Multi-Independent LLM Framework for Human-Aligned Evaluation Authors: Nalin Srun, Parisa Rastin, Guénaël Cabanes, Lydia Boudjeloud Assala Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09624v1 We introduce MILE-RefHumEval, a reference-free framework for evaluating Large Language Models (LLMs) without ground-truth annotations or evaluator coordination. It leverages an ensemble of independently prompted evaluators guided by a human-aligned schema, supporting both discrete and continuous scoring judgement. With task-specific prompts from best candidate selection, summarization and image captioning to dialogue, MILE-RefHumEval provides flexible, interpretable, and scalable assessments. Experiments show it aligns closely with human judgments, outperforms prior methods, and reduces computational overhead, offering an efficient, robust, and human-aligned solution for real-world LLM evaluation. --- ### AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models Authors: R E Zera Marveen Lyngkhoi, Chirag Chawla, Pratinav Seth, Utsav Avaiya, Soham Bhattacharjee, Mykola Khandoga, Rui Yuan, Vinay Kumar Sankarapu Published: 2026-02-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.09621v2 Post-training alignment is central to deploying large language models (LLMs), yet practical workflows remain split across backend-specific tools and ad-hoc glue code, making experiments hard to reproduce. We identify backend interference, reward fragmentation, and irreproducible pipelines as key obstacles in alignment research. We introduce AlignTune, a modular toolkit exposing a unified interface for supervised fine-tuning (SFT) and RLHF-style optimization with interchangeable TRL and Unsloth backends. AlignTune standardizes configuration, provides an extensible reward layer (rule-based and learned), and integrates evaluation over standard benchmarks and custom tasks. By isolating backend-specific logic behind a single factory boundary, AlignTune enables controlled comparisons and reproducible alignment experiments. --- ### FLINGO -- Instilling ASP Expressiveness into Linear Integer Constraints Authors: Jorge Fandinno, Pedro Cabalar, Philipp Wanko, Torsten Schaub Published: 2026-02-10 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2602.09620v2 Constraint Answer Set Programming (CASP) is a hybrid paradigm that enriches Answer Set Programming (ASP) with numerical constraint processing, a crucial requirement for many real-world applications. However, the specification of constraints in most CASP solvers aligns more closely with the expressiveness and semantics of the numerical back-end than the ASP paradigm. In the latter, numerical attributes are represented as predicates, which allows declaring default values, leaving the attribute undefined, making non-deterministic assignments with choice rules, or using aggregated values. In CASP, most (if not all) of these features are lost once we switch to a constraint-based representation of those same attributes. In this paper, we present the flingo language (and tool) that incorporates the aforementioned expressiveness within numerical constraints, and we illustrate its use with several examples. Based on previous work that established its semantic foundations, we also present a translation from the newly introduced flingo syntax to regular CASP programs following the clingcon input format. --- ### AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception Authors: Ruoxuan Feng, Yuxuan Zhou, Siyu Mei, Dongzhan Zhou, Pengwei Wang, Shaowei Cui, Bin Fang, Guocai Yao, Di Hu Published: 2026-02-10 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.09617v1 Real-world contact-rich manipulation demands robots to perceive temporal tactile feedback, capture subtle surface deformations, and reason about object properties as well as force dynamics. Although optical tactile sensors are uniquely capable of providing such rich information, existing tactile datasets and models remain limited. These resources primarily focus on object-level attributes (e.g., material) while largely overlooking fine-grained tactile temporal dynamics during physical interactions. We consider that advancing dynamic tactile perception requires a systematic hierarchy of dynamic perception capabilities to guide both data collection and model design. To address the lack of tactile data with rich dynamic information, we present ToucHD, a large-scale hierarchical tactile dataset spanning tactile atomic actions, real-world manipulations, and touch-force paired data. Beyond scale, ToucHD establishes a comprehensive tactile dynamic data ecosystem that explicitly supports hierarchical perception capabilities from the data perspective. Building on it, we propose AnyTouch 2, a general tactile representation learning framework for diverse optical tactile sensors that unifies object-level understanding with fine-grained, force-aware dynamic perception. The framework captures both pixel-level and action-specific deformations across frames, while explicitly modeling physical force dynamics, thereby learning multi-level dynamic perception capabilities from the model perspective. We evaluate our model on benchmarks that covers static object properties and dynamic physical attributes, as well as real-world manipulation tasks spanning multiple tiers of dynamic perception capabilities-from basic object-level understanding to force-aware dexterous manipulation. Experimental results demonstrate consistent and strong performance across sensors and tasks. --- ### With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots Authors: Zeinab Sadat Taghavi, Ali Modarressi, Hinrich Schutze, Andreas Marfurt Published: 2026-02-10 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.09616v2 Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information. We show that neural retrievers used in RAG systems have blind spots, which we define as the failure to retrieve entities that are relevant to the query, but have low similarity to the query embedding. We investigate the training-induced biases that cause such blind spot entities to be mapped to inaccessible parts of the embedding space, resulting in low retrievability. Using a large-scale dataset constructed from Wikidata relations and first paragraphs of Wikipedia, and our proposed Retrieval Probability Score (RPS), we show that blind spot risk in standard retrievers (e.g., CONTRIEVER, REASONIR) can be predicted pre-index from entity embedding geometry, avoiding expensive retrieval evaluations. To address these blind spots, we introduce ARGUS, a pipeline that enables the retrievability of high-risk (low-RPS) entities through targeted document augmentation from a knowledge base (KB), first paragraphs of Wikipedia, in our case. Extensive experiments on BRIGHT, IMPLIRET, and RAR-B show that ARGUS achieves consistent improvements across all evaluated retrievers (averaging +3.4 nDCG@5 and +4.5 nDCG@10 absolute points), with substantially larger gains in challenging subsets. These results establish that preemptively remedying blind spots is critical for building robust and trustworthy RAG systems. --- ### Tracking Finite-Time Lyapunov Exponents to Robustify Neural ODEs Authors: Tobias Wöhrer, Christian Kuehn Published: 2026-02-10 Categories: math.DS, cs.LG arXiv: https://arxiv.org/abs/2602.09613v1 We investigate finite-time Lyapunov exponents (FTLEs), a measure for exponential separation of input perturbations, of deep neural networks within the framework of continuous-depth neural ODEs. We demonstrate that FTLEs are powerful organizers for input-output dynamics, allowing for better interpretability and the comparison of distinct model architectures. We establish a direct connection between Lyapunov exponents and adversarial vulnerability, and propose a novel training algorithm that improves robustness by FTLE regularization. The key idea is to suppress exponents far from zero in the early stage of the input dynamics. This approach enhances robustness and reduces computational cost compared to full-interval regularization, as it avoids a full ``double'' backpropagation. --- ### AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models Authors: Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Linlin Wang Published: 2026-02-10 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.09611v3 Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant tokens and disrupt visual grounding by enforcing indiscriminate pseudo-random biases. Additionally, current vision-specific watermarks rely on a static, one-time estimation of vision-critical weights and ignore the weight distribution density when determining the proportion of protected tokens. This design fails to account for dynamic changes in visual dependence during generation and may introduce low-quality tokens in the long tail. To address these challenges, we propose Attention-Guided Dynamic Watermarking (AGMark), a novel framework that embeds detectable signals while largely preserving visual-semantic fidelity. At each decoding step, AGMark first dynamically identifies semantic-critical evidence based on attention weights for visual relevance, together with context-aware coherence cues, resulting in a more adaptive and well-calibrated evidence-weight distribution. It then determines the proportion of semantic-critical tokens by jointly considering uncertainty awareness (token entropy) and evidence calibration (weight density), thereby enabling more reliable adaptive vocabulary partitioning to avoid irrelevant tokens. Empirical results consistently confirm that AGMark outperforms conventional methods, substantially improving generation quality and yielding particularly strong gains in visual semantic fidelity in the later stages of generation. Our framework maintains highly competitive detection performance (at least 99.36% AUC) and robust attack resilience (at least 88.61% AUC) without sacrificing inference efficiency, taking a significant step toward reliability-preserving multimodal watermarking. --- ### AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models Authors: Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Linlin Wang Published: 2026-02-10 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.09611v2 Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant tokens and disrupt visual grounding by enforcing indiscriminate pseudo-random biases. Additionally, current vision-specific watermarks rely on a static, one-time estimation of vision-critical weights and ignore the weight distribution density when determining the proportion of protected tokens. This design fails to account for dynamic changes in visual dependence during generation and may introduce low-quality tokens in the long tail. To address these challenges, we propose Attention-Guided Dynamic Watermarking (AGMark), a novel framework that embeds detectable signals while largely preserving visual-semantic fidelity. At each decoding step, AGMark first dynamically identifies semantic-critical evidence based on attention weights for visual relevance, together with context-aware coherence cues, resulting in a more adaptive and well-calibrated evidence-weight distribution. It then determines the proportion of semantic-critical tokens by jointly considering uncertainty awareness (token entropy) and evidence calibration (weight density), thereby enabling more reliable adaptive vocabulary partitioning to avoid irrelevant tokens. Empirical results consistently confirm that AGMark outperforms conventional methods, substantially improving generation quality and yielding particularly strong gains in visual semantic fidelity in the later stages of generation. Our framework maintains highly competitive detection performance (at least 99.36% AUC) and robust attack resilience (at least 88.61% AUC) without sacrificing inference efficiency, taking a significant step toward reliability-preserving multimodal watermarking. --- ### Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing Authors: Jialun Liu, Tian Li, Xiao Cao, Yukuo Ma, Gonghu Shang, Haibin Huang, Chi Zhang, Xiangzhen Chang, Zhiyong Huang, Jiakui Hu, Zuoxin Li, Yuanzhi Liang et al. Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09609v2 Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and rely primarily on textual instructions, limiting their ability to handle multimodal inputs, contextual references, and diverse video generation and editing scenarios within a unified framework. Moreover, many video editing methods depend on carefully engineered pipelines tailored to individual operations, which hinders scalability and composability. In this paper, we propose Tele-Omni, a unified multimodal framework for video generation and editing that follows multimodal instructions, including text, images, and reference videos, within a single model. Tele-Omni leverages pretrained multimodal large language models to parse heterogeneous instructions and infer structured generation or editing intents, while diffusion-based generators perform high-quality video synthesis conditioned on these structured signals. To enable joint training across heterogeneous video tasks, we introduce a task-aware data processing pipeline that unifies multimodal inputs into a structured instruction format while preserving task-specific constraints. Tele-Omni supports a wide range of video-centric tasks, including text-to-video generation, image-to-video generation, first-last-frame video generation, in-context video generation, and in-context video editing. By decoupling instruction parsing from video synthesis and combining it with task-aware data design, Tele-Omni achieves flexible multimodal control while maintaining strong temporal coherence and visual consistency. Experimental results demonstrate that Tele-Omni achieves competitive performance across multiple tasks. --- ### Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures Authors: Yuxi Wang, Wenqi Ouyang, Tianyi Wei, Yi Dong, Zhiqi Shen, Xingang Pan Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09600v2 Egocentric interactive world models are essential for augmented reality and embodied AI, where visual generation must respond to user input with low latency, geometric consistency, and long-term stability. We study egocentric interaction generation from a single scene image under free-space hand gestures, aiming to synthesize photorealistic videos in which hands enter the scene, interact with objects, and induce plausible world dynamics under head motion. This setting introduces fundamental challenges, including distribution shift between free-space gestures and contact-heavy training data, ambiguity between hand motion and camera motion in monocular views, and the need for arbitrary-length video generation. We present Hand2World, a unified autoregressive framework that addresses these challenges through occlusion-invariant hand conditioning based on projected 3D hand meshes, allowing visibility and occlusion to be inferred from scene context rather than encoded in the control signal. To stabilize egocentric viewpoint changes, we inject explicit camera geometry via per-pixel Plücker-ray embeddings, disentangling camera motion from hand motion and preventing background drift. We further develop a fully automated monocular annotation pipeline and distill a bidirectional diffusion model into a causal generator, enabling arbitrary-length synthesis. Experiments on three egocentric interaction benchmarks show substantial improvements in perceptual quality and 3D consistency while supporting camera control and long-horizon interactive generation. --- ### Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning Authors: Qiao Liang, Yuke Zhu, Chao Ge, Lei Yang, Ying Shen, Bo Zheng, Sheng Guo Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09598v1 Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak step-level credit assignment. In long-horizon TIR trajectories, an early irrecoverable mistake can determine success or failure, making it crucial to localize the first irrecoverable step and leverage it for fine-grained credit assignment. We propose Error-Localized Policy Optimization (ELPO), which localizes the first irrecoverable step via binary-search rollout trees under a fixed rollout budget, converts the resulting tree into stable learning signals through hierarchical advantage attribution, and applies error-localized adaptive clipping to strengthen corrective updates on the critical step and its suffix. Across TIR benchmarks in math, science QA, and code execution, ELPO consistently outperforms strong Agentic RL baselines under comparable sampling budgets, with additional gains in Pass@K and Major@K scaling, rollout ranking quality, and tool-call efficiency. Our code will be publicly released soon. --- ### Detecting radar targets swarms in range profiles with a partially complex-valued neural network Authors: Martin Bauw Published: 2026-02-10 Categories: cs.AI, eess.SP arXiv: https://arxiv.org/abs/2602.09597v1 Correctly detecting radar targets is usually challenged by clutter and waveform distortion. An additional difficulty stems from the relative proximity of several targets, the latter being perceived as a single target in the worst case, or influencing each other's detection thresholds. The negative impact of targets proximity notably depends on the range resolution defined by the radar parameters and the adaptive threshold adopted. This paper addresses the matter of targets detection in radar range profiles containing multiple targets with varying proximity and distorted echoes. Inspired by recent contributions in the radar and signal processing literature, this work proposes partially complex-valued neural networks as an adaptive range profile processing. Simulated datasets are generated and experiments are conducted to compare a common pulse compression approach with a simple neural network partially defined by complex-valued parameters. Whereas the pulse compression processes one pulse length at a time, the neural network put forward is a generative architecture going through the entire received signal in one go to generate a complete detection profile. --- ### Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models? Authors: Donghwan Kim, Junghun Phee, Hyunsoo Yoon Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.09593v1 Deep generative models with tractable and analytically computable likelihoods, exemplified by normalizing flows, offer an effective basis for anomaly detection through likelihood-based scoring. We demonstrate that, unlike in the image domain where deep generative models frequently assign higher likelihoods to anomalous data, such counterintuitive behavior occurs far less often in tabular settings. We first introduce a domain-agnostic formulation that enables consistent detection and evaluation of the counterintuitive phenomenon, addressing the absence of precise definition. Through extensive experiments on 47 tabular datasets and 10 CV/NLP embedding datasets in ADBench, benchmarked against 13 baseline models, we demonstrate that the phenomenon, as defined, is consistently rare in general tabular data. We further investigate this phenomenon from both theoretical and empirical perspectives, focusing on the roles of data dimensionality and difference in feature correlation. Our results suggest that likelihood-only detection with normalizing flows offers a practical and reliable approach for anomaly detection in tabular domains. --- ### On the Optimal Reasoning Length for RL-Trained Language Models Authors: Daisuke Nohara, Taishi Nakamura, Rio Yokota Published: 2026-02-10 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.09591v3 Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain-of-thought outputs and increase computational cost. Although length-control methods have been proposed, the length-accuracy relationship they induce remains unclear. We train policies with several length-control methods on multiple base models in a controlled setup and find that, across both mathematical reasoning and code generation, accuracy is non-monotonic in output length, peaking at an intermediate value. Mode accuracy, however, continues to improve with length even in settings where sample accuracy plateaus or declines, indicating that the non-monotonic length-accuracy relationship is driven by dispersion around an increasingly correct center. --- ### Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models Authors: Shweta Parihar, Liu Guangliang, Natalie Parde, Lu Cheng Published: 2026-02-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.09590v1 A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for fine-tuning, highlights this issue by generating synthetic data that may align poorly with real-world distributions or creating overly simplistic counterfactuals that ignore the social context of altered sensitive attributes (e.g., gender) in the pretraining corpus. To address these limitations, we propose a simple yet effective context-augmented CDA method, Context-CDA, which uses large LMs to enhance the diversity and contextual relevance of the debiasing corpus. By minimizing discrepancies between the debiasing corpus and pretraining data through augmented context, this approach ensures better alignment, enhancing language modeling capability. We then employ uncertainty-based filtering to exclude generated counterfactuals considered low-quality by the target smaller LMs (i.e., LMs to be debiased), further improving the fine-tuning corpus quality. Experimental results on gender bias benchmarks demonstrate that Context-CDA effectively mitigates bias without sacrificing language modeling performance while offering insights into social biases by analyzing distribution shifts in next-token generation probabilities. --- ### MieDB-100k: A Comprehensive Dataset for Medical Image Editing Authors: Yongfan Lai, Wen Qian, Bo Liu, Hongyan Li, Hao Luo, Fan Wang, Bohan Zhuang, Shenda Hong Published: 2026-02-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.09587v2 The scarcity of high-quality data remains a primary bottleneck in adapting multimodal generative models for medical image editing. Existing medical image editing datasets often suffer from limited diversity, neglect of medical image understanding and inability to balance quality with scalability. To address these gaps, we propose MieDB-100k, a large-scale, high-quality and diverse dataset for text-guided medical image editing. It categorizes editing tasks into perspectives of Perception, Modification and Transformation, considering both understanding and generation abilities. We construct MieDB-100k via a data curation pipeline leveraging both modality-specific expert models and rule-based data synthetic methods, followed by rigorous manual inspection to ensure clinical fidelity. Extensive experiments demonstrate that model trained with MieDB-100k consistently outperform both open-source and proprietary models while exhibiting strong generalization ability. We anticipate that this dataset will serve as a cornerstone for future advancements in specialized medical image editing. --- ### Delving into Spectral Clustering with Vision-Language Representations Authors: Bo Peng, Yuanwei Hu, Bo Liu, Ling Chen, Jie Lu, Zhen Fang Published: 2026-02-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.09586v2 Spectral clustering is known as a powerful technique in unsupervised data analysis. The vast majority of approaches to spectral clustering are driven by a single modality, leaving the rich information in multi-modal representations untapped. Inspired by the recent success of vision-language pre-training, this paper enriches the landscape of spectral clustering from a single-modal to a multi-modal regime. Particularly, we propose Neural Tangent Kernel Spectral Clustering that leverages cross-modal alignment in pre-trained vision-language models. By anchoring the neural tangent kernel with positive nouns, i.e., those semantically close to the images of interest, we arrive at formulating the affinity between images as a coupling of their visual proximity and semantic overlap. We show that this formulation amplifies within-cluster connections while suppressing spurious ones across clusters, hence encouraging block-diagonal structures. In addition, we present a regularized affinity diffusion mechanism that adaptively ensembles affinity matrices induced by different prompts. Extensive experiments on \textbf{16} benchmarks -- including classical, large-scale, fine-grained and domain-shifted datasets -- manifest that our method consistently outperforms the state-of-the-art by a large margin. --- ### Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation Authors: Donghwan Kim, Hyunsoo Yoon Published: 2026-02-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.09581v1 Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We mitigate this likelihood paradox by manipulating input entropy based on semantic similarity, applying stronger perturbations to inputs that are less similar to an in-distribution memory bank. We provide a theoretical analysis showing that entropy control increases the expected log-likelihood gap between in-distribution and OOD samples in favor of the in-distribution, and we explain why the procedure works without any additional training of the density model. We then evaluate our method against likelihood-based OOD detectors on standard benchmarks and find consistent AUROC improvements over baselines, supporting our explanation. --- ### SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Authors: Chenyu Yang, Denis Tarasov, Davide Liconti, Romain Guntz, Hehui Zheng, Robert K. Katzschmann Published: 2026-02-10 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.09580v4 Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based policies, while expressive, do not permit conservative likelihood-based updates during fine-tuning because action probabilities are intractable. In contrast, conventional Gaussian policies collapse under multimodality, particularly when actions are executed in chunks, and standard per-step critics fail to align with chunked execution, leading to poor credit assignment. We present SERFN, a sample-efficient off-policy fine-tuning framework with normalizing flow (NF) to address these challenges. The normalizing flow policy yields exact likelihoods for multimodal action chunks, allowing conservative, stable policy updates through likelihood regularization and thereby improving sample efficiency. An action-chunked critic evaluates entire action sequences, aligning value estimation with the policy's temporal structure and improving long-horizon credit assignment. To our knowledge, this is the first demonstration of a likelihood-based, multimodal generative policy combined with chunk-level value learning on real robotic hardware. We evaluate SERFN on two challenging dexterous manipulation tasks in the real world: cutting tape with scissors retrieved from a case, and in-hand cube rotation with a palm-down grasp -- both of which require precise, dexterous control over long horizons. On these tasks, SERFN achieves stable, sample-efficient adaptation where standard methods struggle. --- ### Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning Authors: Zhida Jiang, Zhaolong Xing, Jiawei Lu, Yipei Niu, Qingyuan Sang, Liangxu Zhang, Wenquan Dai, Junhua Shu, Jiaxing Wang, Qiangyu Pei, Qiong Chen, Xinyu Liu et al. Published: 2026-02-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09578v1 Despite algorithm-level innovations for multi-agent reinforcement learning (MARL), the underlying networked infrastructure for large-scale MARL training remains underexplored. Existing training frameworks primarily optimize for single-agent scenarios and fail to address the unique system-level challenges of MARL, including rollout-training synchronization barriers, rollout load imbalance, and training resource underutilization. To bridge this gap, we propose FlexMARL, the first end-to-end training framework that holistically optimizes rollout, training, and their orchestration for large-scale LLM-based MARL. Specifically, FlexMARL introduces the joint orchestrator to manage data flow under the rollout-training disaggregated architecture. Building upon the experience store, a novel micro-batch driven asynchronous pipeline eliminates the synchronization barriers while providing strong consistency guarantees. Rollout engine adopts a parallel sampling scheme combined with hierarchical load balancing, which adapts to skewed inter/intra-agent request patterns. Training engine achieves on-demand hardware binding through agent-centric resource allocation. The training states of different agents are swapped via unified and location-agnostic communication. Empirical results on a large-scale production cluster demonstrate that FlexMARL achieves up to 7.3x speedup and improves hardware utilization by up to 5.6x compared to existing frameworks. --- ### Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs Authors: Sora Miyamoto, Daisuke Oba, Naoaki Okazaki Published: 2026-02-10 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.09574v2 Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment often imposes a fixed per-query token budget that varies across settings. Existing tree-search policies are largely budget-agnostic, treating the budget merely as a termination condition, thereby risking late-stage over-branching or premature termination. We propose Budget-Guided MCTS (BG-MCTS), a tree-search decoding algorithm that aligns its search policy with the remaining token budget: it starts with broad exploration, then prioritizes refinement and answer completion as the remaining budget decreases while reducing late-stage branching from shallow nodes. BG-MCTS consistently outperforms budget-agnostic tree-search baselines across inference budgets on mathematical reasoning benchmarks and an additional physics reasoning benchmark with open-weight LLMs. --- ### Predictive Query Language: A Domain-Specific Language for Predictive Modeling on Relational Databases Authors: Vid Kocijan, Jinu Sunil, Jan Eric Lenssen, Viman Deb, Xinwei Xe, Federico Reyes Gomez, Matthias Fey, Jure Leskovec Published: 2026-02-10 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.09572v3 The purpose of predictive modeling on relational data is to predict future or missing values in a relational database, for example, future purchases of a user, risk of readmission of the patient, or the likelihood that a financial transaction is fraudulent. Typically powered by machine learning methods, predictive models are used in recommendations, financial fraud detection, supply chain optimization, and other systems, providing billions of predictions every day. However, training a machine learning model requires manual work to extract the required training examples - prediction entities and target labels - from the database, which is slow, laborious, and prone to mistakes. Here, we present the Predictive Query Language (PQL), an SQL-inspired declarative language for defining predictive tasks on relational databases. PQL allows specifying a predictive task in a single declarative query, enabling the automatic computation of training labels for a large variety of machine learning tasks, such as regression, classification, time-series forecasting, and recommender systems. PQL is already successfully integrated and used in a collection of use cases as part of a predictive AI platform. The versatility of the language can be demonstrated through its many ongoing use cases, including financial fraud, item recommendations, and workload prediction. We demonstrate its versatile design through two implementations; one for small-scale, low-latency use and one that can handle large-scale databases. --- ### LEMUR: A Corpus for Robust Fine-Tuning of Multilingual Law Embedding Models for Retrieval Authors: Narges Baba Ahmadi, Jan Strich, Martin Semmann, Chris Biemann Published: 2026-02-10 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.09570v1 Large language models (LLMs) are increasingly used to access legal information. Yet, their deployment in multilingual legal settings is constrained by unreliable retrieval and the lack of domain-adapted, open-embedding models. In particular, existing multilingual legal corpora are not designed for semantic retrieval, and PDF-based legislative sources introduce substantial noise due to imperfect text extraction. To address these challenges, we introduce LEMUR, a large-scale multilingual corpus of EU environmental legislation constructed from 24,953 official EUR-Lex PDF documents covering 25 languages. We quantify the fidelity of PDF-to-text conversion by measuring lexical consistency against authoritative HTML versions using the Lexical Content Score (LCS). Building on LEMUR, we fine-tune three state-of-the-art multilingual embedding models using contrastive objectives in both monolingual and bilingual settings, reflecting realistic legal-retrieval scenarios. Experiments across low- and high-resource languages demonstrate that legal-domain fine-tuning consistently improves Top-k retrieval accuracy relative to strong baselines, with particularly pronounced gains for low-resource languages. Cross-lingual evaluations show that these improvements transfer to unseen languages, indicating that fine-tuning primarily enhances language-independent, content-level legal representations rather than language-specific cues. We publish code\footnote{\href{https://github.com/nargesbh/eur_lex}{GitHub Repository}} and data\footnote{\href{https://huggingface.co/datasets/G4KMU/LEMUR}{Hugging Face Dataset}}. --- ### Training deep physical neural networks with local physical information bottleneck Authors: Hao Wang, Ziao Wang, Xiangpeng Liang, Han Zhao, Jianqi Hu, Junjie Jiang, Xing Fu, Jianshi Tang, Huaqiang Wu, Sylvain Gigan, Qiang Liu Published: 2026-02-10 Categories: cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2602.09569v1 Deep learning has revolutionized modern society but faces growing energy and latency constraints. Deep physical neural networks (PNNs) are interconnected computing systems that directly exploit analog dynamics for energy-efficient, ultrafast AI execution. Realizing this potential, however, requires universal training methods tailored to physical intricacies. Here, we present the Physical Information Bottleneck (PIB), a general and efficient framework that integrates information theory and local learning, enabling deep PNNs to learn under arbitrary physical dynamics. By allocating matrix-based information bottlenecks to each unit, we demonstrate supervised, unsupervised, and reinforcement learning across electronic memristive chips and optical computing platforms. PIB also adapts to severe hardware faults and allows for parallel training via geographically distributed resources. Bypassing auxiliary digital models and contrastive measurements, PIB recasts PNN training as an intrinsic, scalable information-theoretic process compatible with diverse physical substrates. --- ### ECG-IMN: Interpretable Mesomorphic Neural Networks for 12-Lead Electrocardiogram Interpretation Authors: Vajira Thambawita, Jonas L. Isaksen, Jørgen K. Kanters, Hugo L. Hammer, Pål Halvorsen Published: 2026-02-10 Categories: cs.LG, cs.AI, cs.CV, stat.ME arXiv: https://arxiv.org/abs/2602.09566v1 Deep learning has achieved expert-level performance in automated electrocardiogram (ECG) diagnosis, yet the "black-box" nature of these models hinders their clinical deployment. Trust in medical AI requires not just high accuracy but also transparency regarding the specific physiological features driving predictions. Existing explainability methods for ECGs typically rely on post-hoc approximations (e.g., Grad-CAM and SHAP), which can be unstable, computationally expensive, and unfaithful to the model's actual decision-making process. In this work, we propose the ECG-IMN, an Interpretable Mesomorphic Neural Network tailored for high-resolution 12-lead ECG classification. Unlike standard classifiers, the ECG-IMN functions as a hypernetwork: a deep convolutional backbone generates the parameters of a strictly linear model specific to each input sample. This architecture enforces intrinsic interpretability, as the decision logic is mathematically transparent and the generated weights (W) serve as exact, high-resolution feature attribution maps. We introduce a transition decoder that effectively maps latent features to sample-wise weights, enabling precise localization of pathological evidence (e.g., ST-elevation, T-wave inversion) in both time and lead dimensions. We evaluate our approach on the PTB-XL dataset for classification tasks, demonstrating that the ECG-IMN achieves competitive predictive performance (AUROC comparable to black-box baselines) while providing faithful, instance-specific explanations. By explicitly decoupling parameter generation from prediction execution, our framework bridges the gap between deep learning capability and clinical trustworthiness, offering a principled path toward "white-box" cardiac diagnostics. --- ### Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning Authors: Yi Lu, Deyang Kong, Jianing Wang, Linsen Guo, Xue Wang, Qi Guo, Tao Gui, Xuanjing Huang, Wei Ye, Shikun Zhang, Wei Wang Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09555v3 Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, their test-time compute allocation remains largely unexplored, leaving a critical speed-effectiveness trade-off unresolved in long Chain-of-Thought reasoning. To address this, we propose a unified test-time compute allocation framework that introduces adaptivity in both step-wise decoding and blockwise generation. At the decoding level, we propose Bounded Adaptive Confidence Decoding (BACD), a difficulty-aware sampling strategy that dynamically adjusts denoising based on model confidence, accelerating inference while controlling error accumulation. Beyond step-wise adaptivity, we introduce the Think Coarse, Critic Fine (TCCF) paradigm that allocates large block sizes for exploratory thinking and smaller block sizes for precise refinement. To stabilize training under varying block configurations, we adopt Progressive Block Size Extension, which mitigates quality degradation when scaling up block sizes. Extensive evaluations on six benchmarks show that our TDAR-8B model with BACD and TCCF achieves a 2.38$\times$ speedup and +3.4% average accuracy over the strong TraDo-8B baseline, unlocking the potential of block diffusion in complex reasoning. --- ### Advancing Block Diffusion Language Models for Test-Time Scaling Authors: Yi Lu, Deyang Kong, Jianing Wang, Linsen Guo, Xue Wang, Qi Guo, Tao Gui, Xuanjing Huang, Wei Ye, Shikun Zhang, Wei Wang Published: 2026-02-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09555v2 Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, existing BDLMs have limited exploration under the test-time scaling setting and face more severe decoding challenges in long Chain-of-Thought reasoning, particularly in balancing the decoding speed and effectiveness. In this work, we propose a unified framework for test-time scaling in BDLMs that introduces adaptivity in both decoding and block-wise generation. At the decoding level, we propose Bounded Adaptive Confidence Decoding (BACD), a difficulty-aware sampling strategy that dynamically adjusts denoising based on model confidence, accelerating inference while controlling error accumulation. Beyond step-wise adaptivity, we introduce Think Coarse, Critic Fine (TCCF), a test-time scaling paradigm that allocates large block sizes to exploratory reasoning and smaller block sizes to refinement, achieving an effective efficiency-effectiveness balance. To enable efficient and effective decoding with a large block size, we adopt Progressive Block Size Extension, which mitigates performance degradation when scaling block sizes. Extensive experiments show that applying BACD and TCCF to TDAR-8B yields significant improvements over strong baselines such as TraDo-8B (2.26x speedup, +11.2 points on AIME24). These results mark an important step toward unlocking the potential of BDLMs for test-time scaling in complex reasoning tasks. ---