# Research Papers — 2026-02 · bundle page 160 of 210 > Full-text markdown of papers #7951–8000 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/160 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/159.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/161.md) ### Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching Authors: Junwan Kim, Jiho Park, Seonghu Jeon, Seungryong Kim Published: 2026-02-05 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.05951v2 Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely on a standard Gaussian distribution, a choice inherited from diffusion models, and rarely consider the source distribution itself as an optimization target in such settings. In this work, we show that principled design of the source distribution is not only feasible but also beneficial at the scale of modern text-to-image systems. Specifically, we propose learning a condition-dependent source distribution under flow matching objective that better exploit rich conditioning signals. We identify key failure modes that arise when directly incorporating conditioning into the source, including distributional collapse and instability, and show that appropriate variance regularization and directional alignment between source and target are critical for stable and effective learning. We further analyze how the choice of target representation space impacts flow matching with structured sources, revealing regimes in which such designs are most effective. Extensive experiments across multiple text-to-image benchmarks demonstrate consistent and robust improvements, including up to a 3x faster convergence in FID, highlighting the practical benefits of a principled source distribution design for conditional flow matching. --- ### Breaking Symmetry Bottlenecks in GNN Readouts Authors: Mouad Talhi, Arne Wolf, Anthea Monod Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05950v1 Graph neural networks (GNNs) are widely used for learning on structured data, yet their ability to distinguish non-isomorphic graphs is fundamentally limited. These limitations are usually attributed to message passing; in this work we show that an independent bottleneck arises at the readout stage. Using finite-dimensional representation theory, we prove that all linear permutation-invariant readouts, including sum and mean pooling, factor through the Reynolds (group-averaging) operator and therefore project node embeddings onto the fixed subspace of the permutation action, erasing all non-trivial symmetry-aware components regardless of encoder expressivity. This yields both a new expressivity barrier and an interpretable characterization of what global pooling preserves or destroys. To overcome this collapse, we introduce projector-based invariant readouts that decompose node representations into symmetry-aware channels and summarize them with nonlinear invariant statistics, preserving permutation invariance while retaining information provably invisible to averaging. Empirically, swapping only the readout enables fixed encoders to separate WL-hard graph pairs and improves performance across multiple benchmarks, demonstrating that readout design is a decisive and under-appreciated factor in GNN expressivity. --- ### f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment Authors: Rajdeep Haldar, Lantao Mei, Guang Lin, Yue Xing, Qifan Song Published: 2026-02-05 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.05946v3 Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However, this view has so far been limited to preference-based supervision. We extend it to general LLM alignment, including reinforcement learning with verifiable rewards (RLVR), where alignment feedback is given only as scalar rewards. We introduce $f$-Group Relative Policy Optimization ($f$-GRPO), a class of on-policy RL objectives, and $f$-Hybrid Alignment Loss ($f$-HAL), which combines on-policy reward optimization with off-policy preference supervision. We show that these objectives estimate $f$-divergences between reward-aligned & reward-unaligned distributions induced by above- & below-average reward responses, and prove expected reward improvement after alignment. Empirically, $f$-GRPO improves over GRPO on math-reasoning RLVR tasks, while hybrid $f$-HAL mitigates reward hacking in on-policy safety alignment when verifiable rewards are unavailable and learned reward models must be used. --- ### Orthogonal Model Merging Authors: Sihan Yang, Kexuan Shi, Weiyang Liu Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05943v1 Merging finetuned Large Language Models (LLMs) has become increasingly important for integrating diverse capabilities into a single unified model. However, prevailing model merging methods rely on linear arithmetic in Euclidean space, which often destroys the intrinsic geometric properties of pretrained weights, such as hyperspherical energy. To address this, we propose Orthogonal Model Merging (OrthoMerge), a method that performs merging operations on the Riemannian manifold formed by the orthogonal group to preserve the geometric structure of the model's weights. By mapping task-specific orthogonal matrices learned by Orthogonal Finetuning (OFT) to the Lie algebra, OrthoMerge enables a principled yet efficient integration that takes into account both the direction and intensity of adaptations. In addition to directly leveraging orthogonal matrices obtained by OFT, we further extend this approach to general models finetuned with non-OFT methods (i.e., low-rank finetuning, full finetuning) via an Orthogonal-Residual Decoupling strategy. This technique extracts the orthogonal components of expert models by solving the orthogonal Procrustes problem, which are then merged on the manifold of the orthogonal group, while the remaining linear residuals are processed through standard additive merging. Extensive empirical results demonstrate the effectiveness of OrthoMerge in mitigating catastrophic forgetting and maintaining model performance across diverse tasks. --- ### R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning Authors: Junxiao Liu, Zhijun Wang, Yixiao Li, Zhejian Lai, Liqian Huang, Xin Huang, Xue Han, Junlan Feng, Shujian Huang Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05940v2 Large reasoning models often default to English reasoning when processing non-English questions, yet their performance drops substantially when reasoning in the question language. Even with the same reasoning language, semantically equivalent English and non-English questions still exhibit a clear performance gap. Together, these phenomena reveal two distinct bottlenecks: target-language question understanding and target-language reasoning. Existing methods typically optimize only one of these capabilities. However, simply combining them may not be sufficient to optimize both effectively, as answer correctness alone cannot distinguish failures in question understanding from those in reasoning. We propose R3S, a reinforcement learning framework that disentangles the optimization of the two capabilities. R3S refines translation rewards derived from downstream reasoning accuracy through English-solvability filtering and recovers target-language RLVR signals using self-generated English hints. Together, these designs require neither external model feedback nor external multilingual training data. Experiments across three backbone models and five languages show that R3S improves language-consistent accuracy over the target-language RLVR baseline on MMATH by an average of 10.3 percentage points, while maintaining near-perfect language consistency. Consistent gains on MMLU-ProX further demonstrate its generalization beyond math problems. --- ### Self-Improving Multilingual Long Reasoning via Translation-Reasoning Integrated Training Authors: Junxiao Liu, Zhijun Wang, Yixiao Li, Zhejian Lai, Liqian Huang, Xin Huang, Xue Han, Junlan Feng, Shujian Huang Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05940v1 Long reasoning models often struggle in multilingual settings: they tend to reason in English for non-English questions; when constrained to reasoning in the question language, accuracies drop substantially. The struggle is caused by the limited abilities for both multilingual question understanding and multilingual reasoning. To address both problems, we propose TRIT (Translation-Reasoning Integrated Training), a self-improving framework that integrates the training of translation into multilingual reasoning. Without external feedback or additional multilingual data, our method jointly enhances multilingual question understanding and response generation. On MMATH, our method outperforms multiple baselines by an average of 7 percentage points, improving both answer correctness and language consistency. Further analysis reveals that integrating translation training improves cross-lingual question alignment by over 10 percentage points and enhances translation quality for both mathematical questions and general-domain text, with gains up to 8.4 COMET points on FLORES-200. --- ### Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation Authors: Lingrui Li, Yanfeng Zhou, Nan Pu, Xin Chen, Zhun Zhong Published: 2026-02-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.05937v1 Distribution shift is a common challenge in medical images obtained from different clinical centers, significantly hindering the deployment of pre-trained semantic segmentation models in real-world applications across multiple domains. Continual Test-Time Adaptation(CTTA) has emerged as a promising approach to address cross-domain shifts during continually evolving target domains. Most existing CTTA methods rely on incrementally updating model parameters, which inevitably suffer from error accumulation and catastrophic forgetting, especially in long-term adaptation. Recent prompt-tuning-based works have shown potential to mitigate the two issues above by updating only visual prompts. While these approaches have demonstrated promising performance, several limitations remain:1)lacking multi-scale prompt diversity, 2)inadequate incorporation of instance-specific knowledge, and 3)risk of privacy leakage. To overcome these limitations, we propose Multi-scale Global-Instance Prompt Tuning(MGIPT), to enhance scale diversity of prompts and capture both global- and instance-level knowledge for robust CTTA. Specifically, MGIPT consists of an Adaptive-scale Instance Prompt(AIP) and a Multi-scale Global-level Prompt(MGP). AIP dynamically learns lightweight and instance-specific prompts to mitigate error accumulation with adaptive optimal-scale selection mechanism. MGP captures domain-level knowledge across different scales to ensure robust adaptation with anti-forgetting capabilities. These complementary components are combined through a weighted ensemble approach, enabling effective dual-level adaptation that integrates both global and local information. Extensive experiments on medical image segmentation benchmarks demonstrate that our MGIPT outperforms state-of-the-art methods, achieving robust adaptation across continually changing target domains. --- ### Dimensionality Reduction on Riemannian Manifolds in Data Analysis Authors: Alaa El Ichi, Khalide Jbilou Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05936v1 In this work, we investigate Riemannian geometry based dimensionality reduction methods that respect the underlying manifold structure of the data. In particular, we focus on Principal Geodesic Analysis (PGA) as a nonlinear generalization of PCA for manifold valued data, and extend discriminant analysis through Riemannian adaptations of other known dimensionality reduction methods. These approaches exploit geodesic distances, tangent space representations, and intrinsic statistical measures to achieve more faithful low dimensional embeddings. We also discuss related manifold learning techniques and highlight their theoretical foundations and practical advantages. Experimental results on representative datasets demonstrate that Riemannian methods provide improved representation quality and classification performance compared to their Euclidean counterparts, especially for data constrained to curved spaces such as hyperspheres and symmetric positive definite manifolds. This study underscores the importance of geometry aware dimensionality reduction in modern machine learning and data science applications. --- ### Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data Authors: Sudeepta Mondal, Xinyi Mary Xie, Ruxiao Duan, Alex Wong, Ganesh Sundaramoorthi Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05935v1 Existing out-of-distribution (OOD) detectors are often tuned by a separate dataset deemed OOD with respect to the training distribution of a neural network (NN). OOD detectors process the activations of NN layers and score the output, where parameters of the detectors are determined by fitting to an in-distribution (training) set and the aforementioned dataset chosen adhocly. At detector training time, this adhoc dataset may not be available or difficult to obtain, and even when it's available, it may not be representative of actual OOD data, which is often ''unknown unknowns." Current benchmarks may specify some left-out set from test OOD sets. We show that there can be significant variance in performance of detectors based on the adhoc dataset chosen in current literature, and thus even if such a dataset can be collected, the performance of the detector may be highly dependent on the choice. In this paper, we introduce and formalize the often neglected problem of tuning OOD detectors without a given ``OOD'' dataset. To this end, we present strong baselines as an attempt to approach this problem. Furthermore, we propose a new generic approach to OOD detector tuning that does not require any extra data other than those used to train the NN. We show that our approach improves over baseline methods consistently across higher-parameter OOD detector families, while being comparable across lower-parameter families. --- ### Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training Authors: Zhenghao Xu, Qin Lu, Changlong Yu, Tuo Zhao Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05933v1 Policy mirror descent (PMD) provides a principled framework for reinforcement learning (RL) by iteratively solving KL-regularized policy improvement subproblems. While this approach has been adopted in training advanced LLMs such as Kimi K1.5/K2, the ideal closed-form PMD updates require reliable partition function estimation, a significant challenge when working with limited rollouts in the vast action spaces of LLMs. We investigate a practical algorithm, termed PMD-mean, that approximates the log-partition term with the mean reward under the sampling policy and performs regression in log-policy space. Specifically, we characterize the population solution of PMD-mean and demonstrate that it implicitly optimizes mirror descent subproblems with an adaptive mixed KL--$χ^2$ regularizer. This additional $χ^2$ regularization constrains large probability changes, producing more conservative updates when expected rewards are low and enhancing robustness against finite-sample estimation errors. Experiments on math reasoning tasks show that PMD-mean achieves superior performance with improved stability and time efficiency. These findings deepen our understanding of PMD-mean and illuminate pathways toward principled improvements in RL algorithms for LLMs. Code is available at https://github.com/horizon-rl/OpenKimi. --- ### Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice Questions Authors: Léo Labat, Etienne Ollion, François Yvon Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05932v1 Multiple-Choice Questions (MCQs) are often used to assess knowledge, reasoning abilities, and even values encoded in large language models (LLMs). While the effect of multilingualism has been studied on LLM factual recall, this paper seeks to investigate the less explored question of language-induced variation in value-laden MCQ responses. Are multilingual LLMs consistent in their responses across languages, i.e. behave like theoretical polyglots, or do they answer value-laden MCQs depending on the language of the question, like a multitude of monolingual models expressing different values through a single model? We release a new corpus, the Multilingual European Value Survey (MEVS), which, unlike prior work relying on machine translation or ad hoc prompts, solely comprises human-translated survey questions aligned in 8 European languages. We administer a subset of those questions to over thirty multilingual LLMs of various sizes, manufacturers and alignment-fine-tuning status under comprehensive, controlled prompt variations including answer order, symbol type, and tail character. Our results show that while larger, instruction-tuned models display higher overall consistency, the robustness of their responses varies greatly across questions, with certain MCQs eliciting total agreement within and across models while others leave LLM answers split. Language-specific behavior seems to arise in all consistent, instruction-fine-tuned models, but only on certain questions, warranting a further study of the selective effect of preference fine-tuning. --- ### Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025 Authors: Samar Ansari Published: 2026-02-05 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2602.05930v1 Large language models (LLMs) are increasingly used in academic writing workflows, yet they frequently hallucinate by generating citations to sources that do not exist. This study analyzes 100 AI-generated hallucinated citations that appeared in papers accepted by the 2025 Conference on Neural Information Processing Systems (NeurIPS), one of the world's most prestigious AI conferences. Despite review by 3-5 expert researchers per paper, these fabricated citations evaded detection, appearing in 53 published papers (approx. 1% of all accepted papers). We develop a five-category taxonomy that classifies hallucinations by their failure mode: Total Fabrication (66%), Partial Attribute Corruption (27%), Identifier Hijacking (4%), Placeholder Hallucination (2%), and Semantic Hallucination (1%). Our analysis reveals a critical finding: every hallucination (100%) exhibited compound failure modes. The distribution of secondary characteristics was dominated by Semantic Hallucination (63%) and Identifier Hijacking (29%), which often appeared alongside Total Fabrication to create a veneer of plausibility and false verifiability. These compound structures exploit multiple verification heuristics simultaneously, explaining why peer review fails to detect them. The distribution exhibits a bimodal pattern: 92% of contaminated papers contain 1-2 hallucinations (minimal AI use) while 8% contain 4-13 hallucinations (heavy reliance). These findings demonstrate that current peer review processes do not include effective citation verification and that the problem extends beyond NeurIPS to other major conferences, government reports, and professional consulting. We propose mandatory automated citation verification at submission as an implementable solution to prevent fabricated citations from becoming normalized in scientific literature. --- ### KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs Authors: Jian Chen, Zhuoran Wang, Jiayu Qin, Ming Li, Meng Wang, Changyou Chen, Yin Chen, Qizhen Weng, Yirui Liu Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05929v2 Large language models rely on kv-caches to avoid redundant computation during autoregressive decoding, but as context length grows, reading and writing the cache can quickly saturate GPU memory bandwidth. Recent work has explored KV-cache compression, yet most approaches neglect the data-dependent nature of kv-caches and their variation across layers. We introduce KV-CoRE KV-cache Compressibility by Rank Evaluation), an SVD-based method for quantifying the data-dependent low-rank compressibility of kv-caches. KV-CoRE computes the optimal low-rank approximation under the Frobenius norm and, being gradient-free and incremental, enables efficient dataset-level, layer-wise evaluation. Using this method, we analyze multiple models and datasets spanning five English domains and sixteen languages, uncovering systematic patterns that link compressibility to model architecture, training data, and language coverage. As part of this analysis, we employ the Normalized Effective Rank as a metric of compressibility and show that it correlates strongly with performance degradation under compression. Our study establishes a principled evaluation framework and the first large-scale benchmark of kv-cache compressibility in LLMs, offering insights for dynamic, data-aware compression and data-centric model development. --- ### Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences Authors: Siquan Li, Yao Tong, Haonan Wang, Tianyang Hu Published: 2026-02-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.05927v1 Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this assumption by showing that randomly initialized transformers already exhibit strong and systematic structural biases. In particular, untrained models display extreme token preferences: across random input sequences, certain tokens are predicted with probabilities orders of magnitude larger. We provide a mechanistic explanation for this phenomenon by dissecting the transformer architecture at initialization. We show that extreme token preference arises from a contraction of token representations along a random seed-dependent direction. This contraction is driven by two interacting forces: (i) asymmetric nonlinear activations in MLP sublayers induce global (inter-sequence) representation concentration, and (ii) self-attention further amplifies this effect through local (intra-sequence) aggregation. Together, these mechanisms align hidden representations along a direction determined solely by the random initialization, producing highly non-uniform next-token predictions. Beyond mechanistic insight, we demonstrate that these initialization-induced biases persist throughout training, forming a stable and intrinsic model identity. Leveraging this property, we introduce SeedPrint, a fingerprinting method that can reliably distinguish models that differ only in their random initialization, even after extensive training and under substantial distribution shift. Finally, we identify a fundamental positional discrepancy inherent to the attention mechanism's intra-sequence contraction that is causally linked to the attention-sink phenomenon. This discovery provides a principled explanation for the emergence of sinks and offers a pathway for their control. --- ### Quantum Reinforcement Learning with Transformers for the Capacitated Vehicle Routing Problem Authors: Eva Andrés Published: 2026-02-05 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2602.05920v1 This paper addresses the Capacitated Vehicle Routing Problem (CVRP) by comparing classical and quantum Reinforcement Learning (RL) approaches. An Advantage Actor-Critic (A2C) agent is implemented in classical, full quantum, and hybrid variants, integrating transformer architectures to capture the relationships between vehicles, clients, and the depot through self- and cross-attention mechanisms. The experiments focus on multi-vehicle scenarios with capacity constraints, considering 20 clients and 4 vehicles, and are conducted over ten independent runs. Performance is assessed using routing distance, route compactness, and route overlap. The results show that all three approaches are capable of learning effective routing policies. However, quantum-enhanced models outperform the classical baseline and produce more robust route organization, with the hybrid architecture achieving the best overall performance across distance, compactness, and route overlap. In addition to quantitative improvements, qualitative visualizations reveal that quantum-based models generate more structured and coherent routing solutions. These findings highlight the potential of hybrid quantum-classical reinforcement learning models for addressing complex combinatorial optimization problems such as the CVRP. --- ### Chunky Post-Training: Data Driven Failures of Generalization Authors: Seoirse Murray, Allison Qi, Timothy Qian, John Schulman, Collin Burns, Sara Price Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05910v1 LLM post-training involves many diverse datasets, each targeting a specific behavior. But these datasets encode incidental patterns alongside intended ones: correlations between formatting and content, narrow phrasings across diverse problems, and implicit associations arising from the discrete data curation process. These patterns are often invisible to developers yet salient to models, producing behaviors that surprise their creators, such as rejecting true facts presented in a particular question format. We call this chunky post-training: the model learns spurious correlations as a result of distinct chunks of post-training data. We introduce SURF, a black-box pipeline which surfaces these unintended behaviors at run time, and TURF, a tool that traces these failures back to specific post-training data. Applying these tools to frontier models (Claude 4.5, GPT-5.1, Grok 4.1, Gemini 3) and open models (Tülu 3), we show that chunky post-training produces miscalibrated behaviors, which often result from imbalanced or underspecified chunks of post-training data. --- ### CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression Authors: Kangjie Zhang, Wenxuan Huang, Xin Zhou, Boxiang Zhou, Dejia Song, Yuan Xie, Baochang Zhang, Lizhuang Ma, Nemo Chen, Xu Tang, Yao Hu, Shaohui Lin Published: 2026-02-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.05909v1 Contrastive Language-Image Pre-training (CLIP) has achieved widely applications in various computer vision tasks, e.g., text-to-image generation, Image-Text retrieval and Image captioning. However, CLIP suffers from high memory and computation cost, which prohibits its usage to the resource-limited application scenarios. Existing CLIP compression methods typically reduce the size of pre-trained CLIP weights by selecting their subset as weight inheritance for further retraining via mask optimization or important weight measurement. However, these select-based weight inheritance often compromises the feature presentation ability, especially on the extreme compression. In this paper, we propose a novel mapping-based CLIP compression framework, CLIP-Map. It leverages learnable matrices to map and combine pretrained weights by Full-Mapping with Kronecker Factorization, aiming to preserve as much information from the original weights as possible. To mitigate the optimization challenges introduced by the learnable mapping, we propose Diagonal Inheritance Initialization to reduce the distribution shifting problem for efficient and effective mapping learning. Extensive experimental results demonstrate that the proposed CLIP-Map outperforms select-based frameworks across various compression ratios, with particularly significant gains observed under high compression settings. --- ### Codified Finite-state Machines for Role-playing Authors: Letian Peng, Yupeng Hou, Kun Zhou, Jingbo Shang Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05905v1 Modeling latent character states is crucial for consistent and engaging role-playing (RP) with large language models (LLMs). Yet, existing prompting-based approaches mainly capture surface actions, often failing to track the latent states that drive interaction. We revisit finite-state machines (FSMs), long used in game design to model state transitions. While effective in small, well-specified state spaces, traditional hand-crafted, rule-based FSMs struggle to adapt to the open-ended semantic space of RP. To address this, we introduce Codified Finite-State Machines (CFSMs), a framework that automatically codifies textual character profiles into FSMs using LLM-based coding. CFSMs extract key states and transitions directly from the profile, producing interpretable structures that enforce character consistency. To further capture uncertainty and variability, we extend CFSMs into Codified Probabilistic Finite-State Machines (CPFSMs), where transitions are modeled as probability distributions over states. Through both synthetic evaluations and real-world RP scenarios in established artifacts, we demonstrate that CFSM and CPFSM outperform generally applied baselines, verifying effectiveness not only in structured tasks but also in open-ended stochastic state exploration. --- ### Verification of the Implicit World Model in a Generative Model via Adversarial Sequences Authors: András Balogh, Márk Jelasity Published: 2026-02-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.05903v1 Generative sequence models are typically trained on sample sequences from natural or formal languages. It is a crucial question whether -- or to what extent -- sample-based training is able to capture the true structure of these languages, often referred to as the ``world model''. Theoretical results indicate that we can hope for soundness at best, that is, generating valid sequences, but not necessarily all of them. However, it is still important to have practical tools that are able to verify whether a given sequence model is sound. In this study, we focus on chess, as it is a domain that provides enough complexity while having a simple rule-based world model. We propose adversarial sequence generation for verifying the soundness of the sequence model. Our adversaries generate valid sequences so as to force the sequence model to generate an invalid next move prediction. Apart from the falsification of soundness, this method is also suitable for a more fine-grained analysis of the failure modes and the effects of different choices during training. To demonstrate this, we propose a number of methods for adversarial sequence generation and evaluate the approach on a large set of chess models. We train models on random as well as high-quality chess games, using several training recipes. We find that none of the models are sound, but some training techniques and dataset choices are able to improve soundness remarkably. We also investigate the potential application of board state probes in both our training and attack methods. Our findings indicate that the extracted board states have no causal role in next token prediction in most of the models. --- ### CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization Authors: Seohyeon Cha, Huancheng Chen, Dongjun Kim, Haoran Zhang, Kevin Chan, Gustavo de Veciana, Haris Vikalo Published: 2026-02-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.05902v2 Post-training quantization (PTQ) enables efficient deployment of large language models by mapping pretrained weights to low-bit formats without retraining, typically using a small calibration set to minimize a layer-wise calibration objective. However, this sequential procedure induces a mismatch: errors from earlier quantized layers alter the inputs received by later layers, causing the activations to deviate from those of the full-precision model. Recent approaches introduce mismatch-aware calibration objectives to compensate for this effect, but leave open how much of the observed mismatch should shift each layer's calibration target. Fully applying this correction can overfit limited calibration data, while scaling the mismatch correction with a fixed coefficient ignores varying reliability of mismatch estimates across layers. To address these limitations, we propose CoreQ, a learning-free PTQ framework that applies a closed-form coefficient for mismatch correction derived from a geometric decomposition of the mismatch. The resulting coefficient adapts the correction across layers, reduces overfitting to finite calibration data, and requires no hyperparameter tuning. Given the corrected target, CoreQ minimizes the induced triangular least-squares objective with an efficient greedy successive-rounding solver and a bounded beam-search extension, K-CoreQ, that trades modest additional compute for improved performance. Across multiple LLM families, scales, bit-widths, and quantization settings, CoreQ improves perplexity and downstream accuracy over strong PTQ baselines. --- ### Universal approximation with signatures of non-geometric rough paths Authors: Mihriban Ceylan, Anna P. Kwossek, David J. Prömel Published: 2026-02-05 Categories: math.PR, cs.LG, q-fin.MF arXiv: https://arxiv.org/abs/2602.05898v1 We establish a universal approximation theorem for signatures of rough paths that are not necessarily weakly geometric. By extending the path with time and its rough path bracket terms, we prove that linear functionals of the signature of the resulting rough paths approximate continuous functionals on rough path spaces uniformly on compact sets. Moreover, we construct the signature of a path extended by its pathwise quadratic variation terms based on general pathwise stochastic integration à la Föllmer, in particular, allowing for pathwise Itô, Stratonovich, and backward Itô integration. In a probabilistic setting, we obtain a universal approximation result for linear functionals of the signature of continuous semimartingales extended by the quadratic variation terms, defined via stochastic Itô integration. Numerical examples illustrate the use of signatures when the path is extended by time and quadratic variation in the context of model calibration and option pricing in mathematical finance. --- ### Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models Authors: Shuo Nie, Hexuan Deng, Chao Wang, Ruiyu Fang, Xuebo Liu, Shuangyong Song, Yu Li, Min Zhang, Xuelong Li Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05897v2 As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings. However, they are prone to faithfulness hallucinations, especially in intermediate reasoning steps. Existing mitigation methods based on online reinforcement learning rely on outcome-based rewards or coarse-grained CoT evaluation, which can inadvertently reinforce unfaithful reasoning when the final answer is correct. To address these limitations, we propose Faithfulness-Aware Step-Level Reinforcement Learning (FaithRL), introducing step-level supervision via explicit faithfulness rewards from a process reward model, together with an implicit truncated resampling strategy that generates contrastive signals from faithful prefixes, while also mitigating reward hacking from step-level rewards. Experiments across multiple SRMs and Open-Book QA benchmarks demonstrate that FaithRL consistently reduces hallucinations in both the CoT and final answers, leading to more faithful and reliable reasoning. Code is available at https://github.com/Easy195/FaithRL. --- ### Parity, Sensitivity, and Transformers Authors: Alexander Kozachinskiy, Tomasz Steifer, Przemysław Wałȩga Published: 2026-02-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.05896v3 Understanding what neural architectures can and cannot compute is a central challenge in the theory of AI. One of the fundamental problems in this context is the PARITY task, which asks whether the number of 1s in a binary input sequence is even or odd. PARITY is one of the central tasks studied in the theory of computation, yet it remains surprisingly unclear under which conditions transformers can or cannot solve it. In this paper, we show that the minimal number of layers a transformer needs to compute PARITY is two. In particular, we solve the open problem asking whether a one-layer transformer can compute PARITY. We answer it negatively by showing that average sensitivity of a one-layer transformer grows slower than that of PARITY. Furthermore, we show a new construction for transformer that computes PARITY, which improves on the existing constructions by removing a number of impractical assumptions. In particular, the existing transformers for PARITY rely on such impractical assumptions as length-dependent positional encoding, hardmax, layernorm without a regularisation parameter, or incompatibility with causal masking. We show that these assumptions can be removed, at the cost of increasing the number of layers from two to four. Specifically, we show that PARITY can be computed by a four-layer transformer using softmax attention, length-independent and polynomially bounded positional encoding, no layernorm, and compatible with both causal and non-causal masking. --- ### Parity, Sensitivity, and Transformers Authors: Alexander Kozachinskiy, Tomasz Steifer, Przemysław Wałȩga Published: 2026-02-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.05896v2 Understanding what neural architectures can and cannot compute is a central challenge in the theory of AI. One of the fundamental problems in this context is the PARITY task, which asks whether the number of 1s in a binary input sequence is even or odd. PARITY is one of the central tasks studied in the theory of computation, yet it remains surprisingly unclear under which conditions transformers can or cannot solve it. In this paper, we show that the minimal number of layers a transformer needs to compute PARITY is two. In particular, we solve the open problem asking whether a one-layer transformer can compute PARITY. We answer it negatively by showing that average sensitivity of a one-layer transformer grows slower than that of PARITY. Furthermore, we show a new construction for transformer that computes PARITY, which improves on the existing constructions by removing a number of impractical assumptions. In particular, the existing transformers for PARITY rely on such impractical assumptions as length-dependent positional encoding, hardmax, layernorm without a regularisation parameter, or incompatibility with causal masking. We show that these assumptions can be removed, at the cost of increasing the number of layers from two to four. Specifically, we show that PARITY can be computed by a four-layer transformer using softmax attention, length-independent and polynomially bounded positional encoding, no layernorm, and compatible with both causal and non-causal masking. --- ### ContextBench: A Benchmark for Context Retrieval in Coding Agents Authors: Han Li, Letian Zhu, Bohan Zhang, Rili Feng, Jiaming Wang, Yue Pan, Earl T. Barr, Federica Sarro, Zhaoyang Chu, He Ye Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05892v3 LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks. --- ### DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training Authors: Dingwei Zhu, Zhiheng Xi, Shihan Dou, Jiahan Li, Chenhao Huang, Junjie Ye, Sixian Li, Mingxu Chai, Yuhui Wang, Yajie Yang, Ming Zhang, Jiazheng Zhang et al. Published: 2026-02-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.05890v2 Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL methods improve robustness by modeling values with multiple quantile points, but they still learn each quantile independently as a scalar. This results in rough-grained value representations that lack fine-grained conditioning on state information, struggling under complex and OOD conditions. We propose DFPO (Distributional Value Flow Policy Optimization with Conditional Risk and Consistency Control), a robust distributional RL framework that models values as continuous flows across time steps. By scaling value modeling through learning of a value flow field instead of isolated quantile predictions, DFPO captures richer state information for more accurate advantage estimation. To stabilize training under noisy feedback, DFPO further integrates conditional risk control and consistency constraints along value flow trajectories. Experiments on dialogue, math reasoning, and scientific tasks show that DFPO outperforms PPO, FlowRL, and other robust baselines under noisy supervision, achieving improved training stability and generalization. --- ### Metric Hedonic Games on the Line Authors: Merlin de la Haye, Pascal Lenzner, Farehe Soheil, Marcus Wunderlich Published: 2026-02-05 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2602.05888v2 Hedonic games are fundamental models for investigating the formation of coalitions among a set of strategic agents, where every agent has a certain utility for every possible coalition of agents it can be part of. To avoid the intractability of defining exponentially many utilities for all possible coalitions, many variants with succinct representations of the agents' utility functions have been devised and analyzed, e.g., modified fractional hedonic games by Monaco et al. (JAAMAS 2020). We extend this by studying a novel succinct variant that is related to modified fractional hedonic games. In our model, each agent has a fixed type-value and an agent's cost for some given coalition is based on the differences between its value and those of the other members of its coalition. This allows to model natural situations like athletes forming training groups with similar performance levels or voters that partition themselves along a political spectrum. In particular, we investigate natural variants where an agent's cost is defined by distance thresholds, or by the maximum or average value difference to the other agents in its coalition. For these settings, we study the existence of stable coalition structures, their properties, and their quality in terms of the price of anarchy and the price of stability. Further, we investigate the impact of limiting the maximum number of coalitions. Despite the simple setting with metric distances on a line, we uncover a rich landscape of models, partially with counter-intuitive behavior. Also, our focus on both swap stability and jump stability allows us to study the influence of fixing the number and the size of the coalitions. Overall, we find that stable coalition structures always exist but that their properties and quality can vary widely. --- ### Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting Authors: Tianqi Shen, Jinji Yang, Junze He, Kunhan Gao, Zeyu Zheng, Ziye Ma Published: 2026-02-05 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.05887v3 Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local minima, making it difficult for gradient-based optimizers to converge to the global optimum. Recent work has shown that over-parameterization via tensor lifting can convert such local minima into strict saddle points, an insight that also partially explains why massive scaling can improve generalization and performance in modern machine learning. Motivated by this observation, we propose a Simulated Oracle Direction (SOD) escape mechanism that simulates the landscape and escape direction of the over-parametrized space, without resorting to actually lifting the problem, since that would be computationally intractable. In essence, we designed a mathematical framework to project over-parametrized escape directions onto the original parameter space to guarantee a strict decrease of objective value from existing local minima. To the best of our knowledge, this represents the first deterministic framework that could escape spurious local minima with guarantee, especially without using random perturbations or heuristic estimates. Numerical experiments demonstrate that our framework reliably escapes local minima and facilitates convergence to global optima, while incurring minimal computational cost when compared to explicit tensor over-parameterization. We believe this framework has non-trivial implications for nonconvex optimization beyond matrix sensing, by showcasing how simulated over-parameterization can be leveraged to tame challenging optimization landscapes. --- ### Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting Authors: Tianqi Shen, Jinji Yang, Junze He, Kunhan Gao, Ziye Ma Published: 2026-02-05 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.05887v2 Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local minima, making it difficult for gradient-based optimizers to converge to the global optimum. Recent work has shown that over-parameterization via tensor lifting can convert such local minima into strict saddle points, an insight that also partially explains why massive scaling can improve generalization and performance in modern machine learning. Motivated by this observation, we propose a Simulated Oracle Direction (SOD) escape mechanism that simulates the landscape and escape direction of the over-parametrized space, without resorting to actually lifting the problem, since that would be computationally intractable. In essence, we designed a mathematical framework to project over-parametrized escape directions onto the original parameter space to guarantee a strict decrease of objective value from existing local minima. To the best of our knowledge, this represents the first deterministic framework that could escape spurious local minima with guarantee, especially without using random perturbations or heuristic estimates. Numerical experiments demonstrate that our framework reliably escapes local minima and facilitates convergence to global optima, while incurring minimal computational cost when compared to explicit tensor over-parameterization. We believe this framework has non-trivial implications for nonconvex optimization beyond matrix sensing, by showcasing how simulated over-parameterization can be leveraged to tame challenging optimization landscapes. --- ### Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations Authors: Wei Liu, Jiawei Xu, Yingru Li, Longtao Zheng, Tianjian Li, Qian Liu, Junxian He Published: 2026-02-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.05885v2 High-quality kernel is critical for scalable AI systems, and enabling LLMs to generate such code would advance AI development. However, training LLMs for this task requires sufficient data, a robust environment, and the process is often vulnerable to reward hacking and lazy optimization. In these cases, models may hack training rewards and prioritize trivial correctness over meaningful speedup. In this paper, we systematically study reinforcement learning (RL) for kernel generation. We first design KernelGYM, a robust distributed GPU environment that supports reward hacking check, data collection from multi-turn interactions and long-term RL training. Building on KernelGYM, we investigate effective multi-turn RL methods and identify a biased policy gradient issue caused by self-inclusion in GRPO. To solve this, we propose Turn-level Reinforce-Leave-One-Out (TRLOO) to provide unbiased advantage estimation for multi-turn RL. To alleviate lazy optimization, we incorporate mismatch correction for training stability and introduce Profiling-based Rewards (PR) and Profiling-based Rejection Sampling (PRS) to overcome the issue. The trained model, Dr Kernel-14B, reaches performance competitive with Claude-4.5-Sonnet in Kernelbench. Finally, we study sequential test-time scaling for Dr Kernel-14B. On the KernelBench Level-2 subset, 31.6% of the generated kernels achieve at least a 1.2x speedup over the Torch reference, surpassing Claude-4.5-Sonnet (26.7%) and GPT-5 (28.6%). When selecting the best candidate across all turns, this 1.2x speedup rate further increases to 47.8%. All resources, including environment, training code, models, and dataset, are included in https://www.github.com/hkust-nlp/KernelGYM. --- ### Neural Implicit 3D Cardiac Shape Reconstruction from Sparse CT Angiography Slices Mimicking 2D Transthoracic Echocardiography Views Authors: Gino E. Jansen, Carolina Brás, R. Nils Planken, Mark J. Schuuring, Berto J. Bouma, Ivana Išgum Published: 2026-02-05 Categories: cs.CV, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2602.05884v1 Accurate 3D representations of cardiac structures allow quantitative analysis of anatomy and function. In this work, we propose a method for reconstructing complete 3D cardiac shapes from segmentations of sparse planes in CT angiography (CTA) for application in 2D transthoracic echocardiography (TTE). Our method uses a neural implicit function to reconstruct the 3D shape of the cardiac chambers and left-ventricle myocardium from sparse CTA planes. To investigate the feasibility of achieving 3D reconstruction from 2D TTE, we select planes that mimic the standard apical 2D TTE views. During training, a multi-layer perceptron learns shape priors from 3D segmentations of the target structures in CTA. At test time, the network reconstructs 3D cardiac shapes from segmentations of TTE-mimicking CTA planes by jointly optimizing the latent code and the rigid transforms that map the observed planes into 3D space. For each heart, we simulate four realistic apical views, and we compare reconstructed multi-class volumes with the reference CTA volumes. On a held-out set of CTA segmentations, our approach achieves an average Dice coefficient of 0.86 $\pm$ 0.04 across all structures. Our method also achieves markedly lower volume errors than the clinical standard, Simpson's biplane rule: 4.88 $\pm$ 4.26 mL vs. 8.14 $\pm$ 6.04 mL, respectively, for the left ventricle; and 6.40 $\pm$ 7.37 mL vs. 37.76 $\pm$ 22.96 mL, respectively, for the left atrium. This suggests that our approach offers a viable route to more accurate 3D chamber quantification in 2D transthoracic echocardiography. --- ### A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges Authors: Philippe J. Giabbanelli Published: 2026-02-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.05883v1 Large language models (LLMs) have rapidly become familiar tools to researchers and practitioners. Concepts such as prompting, temperature, or few-shot examples are now widely recognized, and LLMs are increasingly used in Modeling & Simulation (M&S) workflows. However, practices that appear straightforward may introduce subtle issues, unnecessary complexity, or may even lead to inferior results. Adding more data can backfire (e.g., deteriorating performance through model collapse or inadvertently wiping out existing guardrails), spending time on fine-tuning a model can be unnecessary without a prior assessment of what it already knows, setting the temperature to 0 is not sufficient to make LLMs deterministic, providing a large volume of M&S data as input can be excessive (LLMs cannot attend to everything) but naive simplifications can lose information. We aim to provide comprehensive and practical guidance on how to use LLMs, with an emphasis on M&S applications. We discuss common sources of confusion, including non-determinism, knowledge augmentation (including RAG and LoRA), decomposition of M&S data, and hyper-parameter settings. We emphasize principled design choices, diagnostic strategies, and empirical evaluation, with the goal of helping modelers make informed decisions about when, how, and whether to rely on LLMs. --- ### EoCD: Encoder only Remote Sensing Change Detection Authors: Mubashir Noman, Mustansar Fiaz, Hiyam Debary, Abdul Hannan, Shah Nawaz, Fahad Shahbaz Khan, Salman Khan Published: 2026-02-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.05882v1 Being a cornerstone of temporal analysis, change detection has been playing a pivotal role in modern earth observation. Existing change detection methods rely on the Siamese encoder to individually extract temporal features followed by temporal fusion. Subsequently, these methods design sophisticated decoders to improve the change detection performance without taking into consideration the complexity of the model. These aforementioned issues intensify the overall computational cost as well as the network's complexity which is undesirable. Alternatively, few methods utilize the early fusion scheme to combine the temporal images. These methods prevent the extra overhead of Siamese encoder, however, they also rely on sophisticated decoders for better performance. In addition, these methods demonstrate inferior performance as compared to late fusion based methods. To bridge these gaps, we introduce encoder only change detection (EoCD) that is a simple and effective method for the change detection task. The proposed method performs the early fusion of the temporal data and replaces the decoder with a parameter-free multiscale feature fusion module thereby significantly reducing the overall complexity of the model. EoCD demonstrate the optimal balance between the change detection performance and the prediction speed across a variety of encoder architectures. Additionally, EoCD demonstrate that the performance of the model is predominantly dependent on the encoder network, making the decoder an additional component. Extensive experimentation on four challenging change detection datasets reveals the effectiveness of the proposed method. --- ### Contour Refinement using Discrete Diffusion in Low Data Regime Authors: Fei Yu Guan, Ian Keefe, Sophie Wilkinson, Daniel D. B. Perrakis, Steven Waslander Published: 2026-02-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.05880v2 Boundary detection of irregular and translucent objects is an important problem with applications in medical imaging, environmental monitoring and manufacturing, where many of these applications are plagued with scarce labeled data and low in situ computational resources. While recent image segmentation studies focus on segmentation mask alignment with ground-truth, the task of boundary detection remains understudied, especially in the low data regime. In this work, we present a lightweight discrete diffusion contour refinement pipeline for robust boundary detection in the low data regime. We use a Convolutional Neural Network(CNN) architecture with self-attention layers as the core of our pipeline, and condition on a segmentation mask, iteratively denoising a sparse contour representation. We introduce multiple novel adaptations for improved low-data efficacy and inference efficiency, including using a simplified diffusion process, a customized model architecture, and minimal post processing to produce a dense, isolated contour given a dataset of size <500 training images. Our method outperforms several SOTA baselines on the medical imaging dataset KVASIR, is competitive on HAM10K and our custom wildfire dataset, Smoke, while improving inference framerate by 3.5X. --- ### EuroLLM-22B: Technical Report Authors: Miguel Moura Ramos, Duarte M. Alves, Hippolyte Gisserot-Boukhlef, João Alves, Pedro Henrique Martins, Patrick Fernandes, José Pombal, Nuno M. Guerreiro, Ricardo Rei, Nicolas Boizard, Amin Farajian, Mateusz Klimaszewski et al. Published: 2026-02-05 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.05879v1 This report presents EuroLLM-22B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11 additional languages. EuroLLM addresses the issue of European languages being underrepresented and underserved in existing open large language models. We provide a comprehensive overview of EuroLLM-22B's development, including tokenizer design, architectural specifications, data filtering, and training procedures. Across a broad set of multilingual benchmarks, EuroLLM-22B demonstrates strong performance in reasoning, instruction following, and translation, achieving results competitive with models of comparable size. To support future research, we release our base and instruction-tuned models, our multilingual web pretraining data and updated EuroBlocks instruction datasets, as well as our pre-training and evaluation codebases. --- ### Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy Authors: Lukas Stappen, Ahmet Erkan Turan, Johann Hagerer, Georg Groh Published: 2026-02-05 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.05877v1 The integration of Large Language Model (LLM)-based conversational agents into vehicles creates novel security challenges at the intersection of agentic AI, automotive safety, and inter-agent communication. As these intelligent assistants coordinate with external services via protocols such as Google's Agent-to-Agent (A2A), they establish attack surfaces where manipulations can propagate through natural language payloads, potentially causing severe consequences ranging from driver distraction to unauthorized vehicle control. Existing AI security frameworks, while foundational, lack the rigorous "separation of concerns" standard in safety-critical systems engineering by co-mingling the concepts of what is being protected (assets) with how it is attacked (attack paths). This paper addresses this methodological gap by proposing a threat modeling framework called AgentHeLLM (Agent Hazard Exploration for LLM Assistants) that formally separates asset identification from attack path analysis. We introduce a human-centric asset taxonomy derived from harm-oriented "victim modeling" and inspired by the Universal Declaration of Human Rights, and a formal graph-based model that distinguishes poison paths (malicious data propagation) from trigger paths (activation actions). We demonstrate the framework's practical applicability through an open-source attack path suggestion tool AgentHeLLM Attack Path Generator that automates multi-stage threat discovery using a bi-level search strategy. --- ### Beyond Manual Planning: Seating Allocation for Large Organizations Authors: Anton Ipsen, Michael Cashmore, Kirsty Fielding, Nicolas Marchesotti, Parisa Zehtabi, Daniele Magazzeni, Manuela Veloso Published: 2026-02-05 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2602.05875v1 We introduce the Hierarchical Seating Allocation Problem (HSAP) which addresses the optimal assignment of hierarchically structured organizational teams to physical seating arrangements on a floor plan. This problem is driven by the necessity for large organizations with large hierarchies to ensure that teams with close hierarchical relationships are seated in proximity to one another, such as ensuring a research group occupies a contiguous area. Currently, this problem is managed manually leading to infrequent and suboptimal replanning efforts. To alleviate this manual process, we propose an end-to-end framework to solve the HSAP. A scalable approach to calculate the distance between any pair of seats using a probabilistic road map (PRM) and rapidly-exploring random trees (RRT) which is combined with heuristic search and dynamic programming approach to solve the HSAP using integer programming. We demonstrate our approach under different sized instances by evaluating the PRM framework and subsequent allocations both quantitatively and qualitatively. --- ### xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection Authors: Adrián Girón, Pablo Miralles, Javier Huertas-Tato, Sergio D'Antonio, David Camacho Published: 2026-02-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.05874v1 Hate speech detection is commonly framed as a direct binary classification problem despite being a composite concept defined through multiple interacting factors that vary across legal frameworks, platform policies, and annotation guidelines. As a result, supervised models often overfit dataset-specific definitions and exhibit limited robustness under domain shift and annotation noise. We introduce xList-Hate, a diagnostic framework that decomposes hate speech detection into a checklist of explicit, concept-level questions grounded in widely shared normative criteria. Each question is independently answered by a large language model (LLM), producing a binary diagnostic representation that captures hateful content features without directly predicting the final label. These diagnostic signals are then aggregated by a lightweight, fully interpretable decision tree, yielding transparent and auditable predictions. We evaluate it across multiple hate speech benchmarks and model families, comparing it against zero-shot LLM classification and in-domain supervised fine-tuning. While supervised methods typically maximize in-domain performance, we consistently improves cross-dataset robustness and relative performance under domain shift. In addition, qualitative analysis of disagreement cases provides evidence that the framework can be less sensitive to certain forms of annotation inconsistency and contextual ambiguity. Crucially, the approach enables fine-grained interpretability through explicit decision paths and factor-level analysis. Our results suggest that reframing hate speech detection as a diagnostic reasoning task, rather than a monolithic classification problem, provides a robust, explainable, and extensible alternative for content moderation. --- ### Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networks Authors: Minyoung Kim Published: 2026-02-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.05873v2 Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertainty quantification, robustness to noise, resistance to overfitting, and more. The variational inference (VI) is one of the most widely adopted approximate inference methods. Whereas the ELBO-based variational free energy method is a dominant choice in the literature, in this paper we introduce a score-based alternative for BNN variational inference. Score-based VI can address the known issue of mode collapsing in ELBO-based VI. Although several score-based VI methods have been proposed in the community, most are not adequate for large-scale BNNs for various computational and technical reasons. We propose a novel scalable VI method where the learning objective combines the score matching loss and the proximal penalty term in iterations, which helps our method avoid the reparametrized sampling, and allows for noisy unbiased mini-batch scores through stochastic gradients. This in turn makes our method scalable to large-scale neural networks including Vision Transformers. On several benchmarks including visual recognition and time-series forecasting with large-scale deep networks, we empirically show the effectiveness of our approach. --- ### Pathwise Test-Time Correction for Autoregressive Long Video Generation Authors: Xunzhi Xiang, Zixuan Duan, Guiyu Zhang, Haiyu Zhang, Zhe Gao, Junta Wu, Shaofeng Zhang, Tengfei Wang, Qi Fan, Chunchao Guo Published: 2026-02-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.05871v2 Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images or short clips, we identify that they fail to mitigate drift in extended sequences due to unstable reward landscapes and the hypersensitivity of distilled parameters. To overcome these limitations, we introduce Test-Time Correction (TTC), a training-free alternative. Specifically, TTC utilizes the initial frame as a stable reference anchor to calibrate intermediate stochastic states along the sampling trajectory. Extensive experiments demonstrate that our method seamlessly integrates with various distilled models, extending generation lengths with negligible overhead while matching the quality of resource-intensive training-based methods on 30-second benchmarks. --- ### Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity Authors: Hengrui Luo, Anna Ma, Ludovic Stephan, Yizhe Zhu Published: 2026-02-05 Categories: stat.ML, cs.LG, math.NA, math.PR, math.ST arXiv: https://arxiv.org/abs/2602.05869v3 We introduce Wedge Sampling, a new non-adaptive sampling scheme for low-rank tensor completion. We study recovery of an order-$k$ low-rank tensor of dimension $n\times\cdots\times n$ from structured observations of its entries. Unlike the standard uniform entry model (i.e., i.i.d. samples from $(n)^k$), wedge sampling allocates observations to structured length-two patterns (wedges) in an associated bipartite sampling graph. By directly promoting these length-two connections, the sampling design strengthens the spectral signal that underlies efficient initialization, in regimes where uniform sampling is too sparse to generate enough informative correlations. Our main result shows that this change in sampling paradigm enables polynomial-time algorithms to achieve both weak and exact recovery with nearly linear sample complexity in $n$. The approach is also plug-and-play: wedge-sampling-based spectral initialization can be combined with existing refinement procedures (e.g., spectral or gradient-based methods) using only an additional $\tilde O(n)$ uniformly sampled entries, substantially improving over the $\tilde O(n^{k/2})$ sample complexity typically required under uniform entry sampling for efficient methods. We also formulate a noisy wedge-sampling extension for additive Gaussian observations and analyze both the spectral and gradient-descent procedures under suitable signal-to-noise conditions. Thus, the computational barrier in tensor completion is sensitive to the observation model: while it persists under uniform entry sampling, it can be bypassed by non-adaptive structured designs that provide a stronger initialization. --- ### Constrained Group Relative Policy Optimization Authors: Roger Girgis, Rodrigue de Schaetzen, Luke Rowe, Azalée Robitaille, Christopher Pal, Liam Paull Published: 2026-02-05 Categories: cs.LG, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2602.05863v4 Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with constrained policy optimization (e.g. for safety-critical domains) has not been carefully examined. In this work, we introduce Constrained GRPO, a Lagrangian-based extension of GRPO for constrained policy optimization. We show that the standard practice of scalarizing rewards before normalization introduces a critical Lagrangian-specific failure mode: GRPO's within-group normalization makes constrained optimization highly sensitive to how multi-component learning signals are aggregated. We show that scalarizing rewards before normalization introduces shared-denominator coupling, so that changing one multiplier alters not only the emphasis on its corresponding constraint, but also the relative weighting of the reward and other constraints. We address this with a simple but crucial modification: scalarizing standardized advantages rather than rewards. This yields a better-conditioned update by addressing the coupling induced by reward scalarization, resulting in better-behaved multiplier dynamics and more stable constraint enforcement in practice. Empirically, across a controlled gridworld, a real-world autonomous driving benchmark, and a mathematical reasoning task, Constrained GRPO consistently achieves better adherence to specified constraints while maintaining or improving task performance. --- ### Constrained Group Relative Policy Optimization Authors: Roger Girgis, Rodrigue de Schaetzen, Luke Rowe, Azalée Robitaille, Christopher Pal, Liam Paull Published: 2026-02-05 Categories: cs.LG, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2602.05863v2 While Group Relative Policy Optimization (GRPO) has emerged as a scalable framework for critic-free policy learning, extending it to settings with explicit behavioral constraints remains underexplored. We introduce Constrained GRPO, a Lagrangian-based extension of GRPO for constrained policy optimization. Constraints are specified via indicator cost functions, enabling direct optimization of violation rates through a Lagrangian relaxation. We show that a naive multi-component treatment in advantage estimation can break constrained learning: mismatched component-wise standard deviations distort the relative importance of the different objective terms, which in turn corrupts the Lagrangian signal and prevents meaningful constraint enforcement. We formally derive this effect to motivate our scalarized advantage construction that preserves the intended trade-off between reward and constraint terms. Experiments in a toy gridworld confirm the predicted optimization pathology and demonstrate that scalarizing advantages restores stable constraint control. In addition, we evaluate Constrained GRPO on robotics tasks, where it improves constraint satisfaction while increasing task success, establishing a simple and effective recipe for constrained policy optimization in embodied AI domains that increasingly rely on large multimodal foundation models. --- ### Distribution-free two-sample testing with blurred total variation distance Authors: Rohan Hore, Rina Foygel Barber Published: 2026-02-05 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2602.05862v2 Two-sample testing, where we aim to determine whether two distributions are equal or not equal based on samples from each one, is challenging if we cannot place assumptions on the properties of the two distributions. In particular, certifying equality of distributions, or even providing a tight upper bound on the total variation (TV) distance between the distributions, is impossible to achieve in a distribution-free regime. In this work, we examine the blurred TV distance, a relaxation of TV distance that enables us to perform inference without assumptions on the distributions. We provide theoretical guarantees for distribution-free upper and lower bounds on the blurred TV distance, and examine its properties in high dimensions. --- ### CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphs Authors: Seyedmasoud Mousavi, Ruomeng Xu, Xiaojing Zhu Published: 2026-02-05 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.05861v1 Graph-structured data is ubiquitous and powerful in representing complex relationships in many online platforms. While graph neural networks (GNNs) are widely used to learn from such data, counterfactual graph learning has emerged as a promising approach to improve model interpretability. Counterfactual explanation research focuses on identifying a counterfactual graph that is similar to the original but leads to different predictions. These explanations optimize two objectives simultaneously: the sparsity of changes in the counterfactual graph and the validity of its predictions. Building on these qualitative optimization goals, this paper introduces CFRecs, a novel framework that transforms counterfactual explanations into actionable insights. CFRecs employs a two-stage architecture consisting of a graph neural network (GNN) and a graph variational auto-encoder (Graph-VAE) to strategically propose minimal yet high-impact changes in graph structure and node attributes to drive desirable outcomes in recommender systems. We apply CFRecs to Zillow's graph-structured data to deliver actionable recommendations for both home buyers and sellers with the goal of helping them navigate the competitive housing market and achieve their homeownership goals. Experimental results on Zillow's user-listing interaction data demonstrate the effectiveness of CFRecs, which also provides a fresh perspective on recommendations using counterfactual reasoning in graphs. --- ### DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders Authors: Xu Wang, Bingqing Jiang, Yu Wan, Baosong Yang, Lingpeng Kong, Difan Zou Published: 2026-02-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.05859v1 Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior. Recently, as diffusion language models (DLMs) have become an increasingly promising alternative to the autoregressive LLMs, it is essential to develop tailored mechanistic interpretability tools for this emerging class of models. In this work, we present DLM-Scope, the first SAE-based interpretability framework for DLMs, and demonstrate that trained Top-K SAEs can faithfully extract interpretable features. Notably, we find that inserting SAEs affects DLMs differently than autoregressive LLMs: while SAE insertion in LLMs typically incurs a loss penalty, in DLMs it can reduce cross-entropy loss when applied to early layers, a phenomenon absent or markedly weaker in LLMs. Additionally, SAE features in DLMs enable more effective diffusion-time interventions, often outperforming LLM steering. Moreover, we pioneer certain new SAE-based research directions for DLMs: we show that SAEs can provide useful signals for DLM decoding order; and the SAE features are stable during the post-training phase of DLMs. Our work establishes a foundation for mechanistic interpretability in DLMs and shows a great potential of applying SAEs to DLM-related tasks and algorithms. --- ### BABE: Biology Arena BEnchmark Authors: Junting Zhou, Jin Chen, Linfeng Hao, Denghui Cao, Zheyu Wang, Qiguang Chen, Chaoyou Fu, Jiaze Chen, Yuchen Wu, Ge Zhang, Mingxuan Wang, Wenhao Huang et al. Published: 2026-02-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.05857v1 The rapid evolution of large language models (LLMs) has expanded their capabilities from basic dialogue to advanced scientific reasoning. However, existing benchmarks in biology often fail to assess a critical skill required of researchers: the ability to integrate experimental results with contextual knowledge to derive meaningful conclusions. To address this gap, we introduce BABE(Biology Arena BEnchmark), a comprehensive benchmark designed to evaluate the experimental reasoning capabilities of biological AI systems. BABE is uniquely constructed from peer-reviewed research papers and real-world biological studies, ensuring that tasks reflect the complexity and interdisciplinary nature of actual scientific inquiry. BABE challenges models to perform causal reasoning and cross-scale inference. Our benchmark provides a robust framework for assessing how well AI systems can reason like practicing scientists, offering a more authentic measure of their potential to contribute to biological research. --- ### A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion Authors: Dennis Bank, Joost Cordes, Thomas Seel, Simon F. G. Ehlers Published: 2026-02-05 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.05855v1 Reliable terrain perception is a critical prerequisite for the deployment of humanoid robots in unstructured, human-centric environments. While traditional systems often rely on manually engineered, single-sensor pipelines, this paper presents a learning-based framework that uses an intermediate, robot-centric heightmap representation. A hybrid Encoder-Decoder Structure (EDS) is introduced, utilizing a Convolutional Neural Network (CNN) for spatial feature extraction fused with a Gated Recurrent Unit (GRU) core for temporal consistency. The architecture integrates multimodal data from an Intel RealSense depth camera, a LIVOX MID-360 LiDAR processed via efficient spherical projection, and an onboard IMU. Quantitative results demonstrate that multimodal fusion improves reconstruction accuracy by 7.2% over depth-only and 9.9% over LiDAR-only configurations. Furthermore, the integration of a 3.2 s temporal context reduces mapping drift. --- ### RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference Authors: Siran Liu, Guoxia Wang, Sa Wang, Jinle Zeng, HaoYang Xie, Siyu Lou, JiaBin Yang, DianHai Yu, Haifeng Wang, Chao Yang Published: 2026-02-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.05853v1 The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs: requiring preprocessing, lacking global evaluation, violating query independence, or incurring high computational overhead. We present RRAttention, a novel dynamic sparse attention method that simultaneously achieves all desirable properties through a head \underline{r}ound-\underline{r}obin (RR) sampling strategy. By rotating query sampling positions across attention heads within each stride, RRAttention maintains query independence while enabling efficient global pattern discovery with stride-level aggregation. Our method reduces complexity from $O(L^2)$ to $O(L^2/S^2)$ and employs adaptive Top-$τ$ selection for optimal sparsity. Extensive experiments on natural language understanding (HELMET) and multimodal video comprehension (Video-MME) demonstrate that RRAttention recovers over 99\% of full attention performance while computing only half of the attention blocks, achieving 2.4$\times$ speedup at 128K context length and outperforming existing dynamic sparse attention methods. --- ### Exact Recovery in the Data Block Model Authors: Amir R. Asadi, Akbar Davoodi, Ramin Javadi, Farzad Parvaresh Published: 2026-02-05 Categories: cs.LG, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2602.05852v1 Community detection in networks is a fundamental problem in machine learning and statistical inference, with applications in social networks, biological systems, and communication networks. The stochastic block model (SBM) serves as a canonical framework for studying community structure, and exact recovery, identifying the true communities with high probability, is a central theoretical question. While classical results characterize the phase transition for exact recovery based solely on graph connectivity, many real-world networks contain additional data, such as node attributes or labels. In this work, we study exact recovery in the Data Block Model (DBM), an SBM augmented with node-associated data, as formalized by Asadi, Abbe, and Verdú (2017). We introduce the Chernoff--TV divergence and use it to characterize a sharp exact recovery threshold for the DBM. We further provide an efficient algorithm that achieves this threshold, along with a matching converse result showing impossibility below the threshold. Finally, simulations validate our findings and demonstrate the benefits of incorporating vertex data as side information in community detection. ---