# Research Papers — 2026-02 · bundle page 171 of 210 > Full-text markdown of papers #8501–8550 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/171 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/170.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/172.md) ### Temporal Pair Consistency for Variance-Reduced Flow Matching Authors: Chika Maduabuchi, Jindong Wang Published: 2026-02-04 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.04908v2 Continuous-time generative models, such as diffusion models, flow matching, and rectified flow, learn time-dependent vector fields but are typically trained with objectives that treat timesteps independently, leading to high estimator variance and inefficient sampling. Prior approaches mitigate this via explicit smoothness penalties, trajectory regularization, or modified probability paths and solvers. We introduce Temporal Pair Consistency (TPC), a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path, operating entirely at the estimator level without modifying the model architecture, probability path, or solver. We provide a theoretical analysis showing that TPC induces a quadratic, trajectory-coupled regularization that provably reduces gradient variance while preserving the underlying flow-matching objective. Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions, achieving lower FID at identical or lower computational cost than prior methods, and extends seamlessly to modern SOTA-style pipelines with noise-augmented training, score-based denoising, and rectified flow. --- ### Reinforced Attention Learning Authors: Bangzheng Li, Jianmo Ni, Chen Qu, Ian Miao, Liu Yang, Xingyu Fu, Muhao Chen, Derek Zhiyuan Cheng Published: 2026-02-04 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.04884v2 Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited gains for perception and can even degrade performance. We propose Reinforced Attention Learning (RAL), a policy-gradient framework that directly optimizes internal attention distributions rather than output token sequences. By shifting optimization from what to generate to where to attend, RAL promotes effective information allocation and improved grounding in complex multimodal inputs. Experiments across diverse image and video benchmarks show consistent gains over GRPO and other baselines. We further introduce On-Policy Attention Distillation, demonstrating that transferring latent attention behaviors yields stronger cross-modal alignment than standard knowledge distillation. Our results position attention policies as a principled and general alternative for multimodal post-training. --- ### Protein Autoregressive Modeling via Multiscale Structure Generation Authors: Yanru Qu, Cheng-Yen Hsieh, Zaixiang Zheng, Ge Liu, Quanquan Gu Published: 2026-02-04 Categories: cs.LG, cs.AI, q-bio.BM, q-bio.QM arXiv: https://arxiv.org/abs/2602.04883v2 We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation via coarse-to-fine next-scale prediction. Using the hierarchical nature of proteins, PAR generates structures that mimic sculpting a statue, forming a coarse topology and refining structural details over scales. To achieve this, PAR consists of three key components: (i) multi-scale downsampling operations that represent protein structures across multiple scales during training; (ii) an autoregressive transformer that encodes multi-scale information and produces conditional embeddings to guide structure generation; (iii) a flow-based backbone decoder that generates backbone atoms conditioned on these embeddings. Moreover, autoregressive models suffer from exposure bias, caused by the training and the generation procedure mismatch, and substantially degrades structure generation quality. We effectively alleviate this issue by adopting noisy context learning and scheduled sampling, enabling robust backbone generation. Notably, PAR exhibits strong zero-shot generalization, supporting flexible human-prompted conditional generation and motif scaffolding without requiring fine-tuning. On the unconditional generation benchmark, PAR effectively learns protein distributions and produces backbones of high design quality, and exhibits favorable scaling behavior. Together, these properties establish PAR as a promising framework for protein structure generation. --- ### Contrastive Continual Learning for Model Adaptability in Internet of Things Authors: Ajesh Koyatan Chathoth Published: 2026-02-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04881v1 Internet of Things (IoT) deployments operate in nonstationary, dynamic environments where factors such as sensor drift, evolving user behavior, and heterogeneous user privacy requirements can affect application utility. Continual learning (CL) addresses this by adapting models over time without catastrophic forgetting. Meanwhile, contrastive learning has emerged as a powerful representation-learning paradigm that improves robustness and sample efficiency in a self-supervised manner. This paper reviews the usage of \emph{contrastive continual learning} (CCL) for IoT, connecting algorithmic design (replay, regularization, distillation, prompts) with IoT system realities (TinyML constraints, intermittent connectivity, privacy). We present a unifying problem formulation, derive common objectives that blend contrastive and distillation losses, propose an IoT-oriented reference architecture for on-device, edge, and cloud-based CCL, and provide guidance on evaluation protocols and metrics. Finally, we highlight open unique challenges with respect to the IoT domain, such as spanning tabular and streaming IoT data, concept drift, federated settings, and energy-aware training. --- ### Rethinking the Trust Region in LLM Reinforcement Learning Authors: Penghui Qi, Xiangxin Zhou, Zichen Liu, Tianyu Pang, Chao Du, Min Lin, Wee Sun Lee Published: 2026-02-04 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.04879v3 Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inherent to LLMs. PPO constrains policy updates based on the probability ratio of sampled tokens, which serves as a noisy single-sample Monte Carlo estimate of the true policy divergence. This creates a sub-optimal learning dynamic: updates to low-probability tokens are aggressively over-penalized, while potentially catastrophic shifts in high-probability tokens are under-constrained, leading to training inefficiency and instability. To address this, we propose Divergence Proximal Policy Optimization (DPPO), which substitutes heuristic clipping with a more principled constraint based on a direct estimate of policy divergence (e.g., Total Variation or KL). To avoid huge memory footprint, we introduce the efficient Binary and Top-K approximations to capture the essential divergence with negligible overhead. Extensive empirical evaluations demonstrate that DPPO achieves superior training stability and efficiency compared to existing methods, offering a more robust foundation for RL-based LLM fine-tuning. Our code is available at https://github.com/sail-sg/Stable-RL. --- ### CoWTracker: Tracking by Warping instead of Correlation Authors: Zihang Lai, Eldar Insafutdinov, Edgar Sucar, Andrea Vedaldi Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04877v1 Dense point tracking is a fundamental problem in computer vision, with applications ranging from video analysis to robotic manipulation. State-of-the-art trackers typically rely on cost volumes to match features across frames, but this approach incurs quadratic complexity in spatial resolution, limiting scalability and efficiency. In this paper, we propose \method, a novel dense point tracker that eschews cost volumes in favor of warping. Inspired by recent advances in optical flow, our approach iteratively refines track estimates by warping features from the target frame to the query frame based on the current estimate. Combined with a transformer architecture that performs joint spatiotemporal reasoning across all tracks, our design establishes long-range correspondences without computing feature correlations. Our model is simple and achieves state-of-the-art performance on standard dense point tracking benchmarks, including TAP-Vid-DAVIS, TAP-Vid-Kinetics, and Robo-TAP. Remarkably, the model also excels at optical flow, sometimes outperforming specialized methods on the Sintel, KITTI, and Spring benchmarks. These results suggest that warping-based architectures can unify dense point tracking and optical flow estimation. --- ### PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation Authors: Jiahao Zhan, Zizhang Li, Hong-Xing Yu, Jiajun Wu Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04876v2 We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works fail at this task because their physical state is decoupled from their visual representation, which prevents generative refinements to update the underlying physics for subsequent interactions. PerpetualWonder solves this by introducing the first true closed-loop system. It features a novel unified representation that creates a bidirectional link between the physical state and visual primitives, allowing generative refinements to correct both the dynamics and appearance. It also introduces a robust update mechanism that gathers supervision from multiple viewpoints to resolve optimization ambiguity. Experiments demonstrate that from a single image, PerpetualWonder can successfully simulate complex, multi-step interactions from long-horizon actions, maintaining physical plausibility and visual consistency. --- ### Laminating Representation Autoencoders for Efficient Diffusion Authors: Ramón Calvo-González, François Fleuret Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04873v1 Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents. However, the dense patch grids from encoders like DINOv2 contain significant redundancy, making diffusion needlessly expensive. We introduce FlatDINO, a variational autoencoder that compresses this representation into a one-dimensional sequence of just 32 continuous tokens -an 8x reduction in sequence length and 48x compression in total dimensionality. On ImageNet 256x256, a DiT-XL trained on FlatDINO latents achieves a gFID of 1.80 with classifier-free guidance while requiring 8x fewer FLOPs per forward pass and up to 4.5x fewer FLOPs per training step compared to diffusion on uncompressed DINOv2 features. These are preliminary results and this work is in progress. --- ### Multi-layer Cross-attention is Provably Optimal for Multi-modal In-context Learning Authors: Nicholas Barnfield, Subhabrata Sen, Pragya Sur Published: 2026-02-04 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.04872v3 Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical underpinnings of in-context learning for multi-modal data remain poorly understood. We introduce a mathematically tractable framework for studying multi-modal learning and explore when transformer-like architectures can recover Bayes-optimal performance in-context. To model multi-modal problems, we assume the observed data arises from a latent factor model. Our first result comprises a negative take on expressibility: we prove that single-layer, linear self-attention fails to recover the Bayes-optimal predictor uniformly over the task distribution. To address this limitation, we introduce a novel, linearized cross-attention mechanism, which we study in the regime where both the number of cross-attention layers and the context length are large. We show that this cross-attention mechanism is provably Bayes optimal when optimized using gradient flow. Our results underscore the benefits of depth for in-context learning and establish the provable utility of cross-attention for multi-modal distributions. --- ### Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism Authors: Chenwei Cui, Rockwell Jackson, Benjamin Joseph Herrera, Ana María Tárano, Hannah Kerner Published: 2026-02-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04870v1 Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method. However, EP has three limitations: communication cost grows linearly with the number of activated experts $k$, load imbalance affects latency and memory usage, and data-dependent communication requires metadata exchange. We propose Multi-Head LatentMoE and Head Parallel (HP), a new architecture and parallelism achieving $O(1)$ communication cost regardless of $k$, completely balanced traffic, and deterministic communication, all while remaining compatible with EP. To accelerate Multi-Head LatentMoE, we propose IO-aware routing and expert computation. Compared to MoE with EP, Multi-Head LatentMoE with HP trains up to $1.61\times$ faster while having identical performance. With doubled granularity, it achieves higher overall performance while still being $1.11\times$ faster. Our method makes multi-billion-parameter foundation model research more accessible. --- ### CRoSS: A Continual Robotic Simulation Suite for Scalable Reinforcement Learning with High Task Diversity and Realistic Physics Simulation Authors: Yannick Denker, Alexander Gepperth Published: 2026-02-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04868v1 Continual reinforcement learning (CRL) requires agents to learn from a sequence of tasks without forgetting previously acquired policies. In this work, we introduce a novel benchmark suite for CRL based on realistically simulated robots in the Gazebo simulator. Our Continual Robotic Simulation Suite (CRoSS) benchmarks rely on two robotic platforms: a two-wheeled differential-drive robot with lidar, camera and bumper sensor, and a robotic arm with seven joints. The former represent an agent in line-following and object-pushing scenarios, where variation of visual and structural parameters yields a large number of distinct tasks, whereas the latter is used in two goal-reaching scenarios with high-level cartesian hand position control (modeled after the Continual World benchmark), and low-level control based on joint angles. For the robotic arm benchmarks, we provide additional kinematics-only variants that bypass the need for physical simulation (as long as no sensor readings are required), and which can be run two orders of magnitude faster. CRoSS is designed to be easily extensible and enables controlled studies of continual reinforcement learning in robotic settings with high physical realism, and in particular allow the use of almost arbitrary simulated sensors. To ensure reproducibility and ease of use, we provide a containerized setup (Apptainer) that runs out-of-the-box, and report performances of standard RL algorithms, including Deep Q-Networks (DQN) and policy gradient methods. This highlights the suitability as a scalable and reproducible benchmark for CRL research. --- ### When LLaVA Meets Objects: Token Composition for Vision-Language-Models Authors: Soumya Jahagirdar, Walid Bousselham, Anna Kukleva, Hilde Kuehne Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04864v2 Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute especially at inference time. To address this problem, we propose Mask-LLaVA, a framework that leverages different levels of visual features to create a compact yet information-rich visual representation for autoregressive VLMs. Namely, we combine mask-based object representations together with global tokens and local patch tokens. While all tokens are used during training, it shows that the resulting model can flexibly drop especially the number of mask-based object-tokens at test time, allowing to adapt the number of tokens during inference without the need to retrain the model and without a significant drop in performance. We evaluate the proposed approach on a suite of standard benchmarks showing results competitive to current token efficient methods and comparable to the original LLaVA baseline using only a fraction of visual tokens. Our analysis demonstrates that combining multi-level features enables efficient learning with fewer tokens while allowing dynamic token selection at test time for good performance. --- ### Subliminal Effects in Your Data: A General Mechanism via Log-Linearity Authors: Ishaq Aden-Ali, Noah Golowich, Allen Liu, Abhishek Shetty, Ankur Moitra, Nika Haghtalab Published: 2026-02-04 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2602.04863v1 Training modern large language models (LLMs) has become a veritable smorgasbord of algorithms and datasets designed to elicit particular behaviors, making it critical to develop techniques to understand the effects of datasets on the model's properties. This is exacerbated by recent experiments that show datasets can transmit signals that are not directly observable from individual datapoints, posing a conceptual challenge for dataset-centric understandings of LLM training and suggesting a missing fundamental account of such phenomena. Towards understanding such effects, inspired by recent work on the linear structure of LLMs, we uncover a general mechanism through which hidden subtexts can arise in generic datasets. We introduce Logit-Linear-Selection (LLS), a method that prescribes how to select subsets of a generic preference dataset to elicit a wide range of hidden effects. We apply LLS to discover subsets of real-world datasets so that models trained on them exhibit behaviors ranging from having specific preferences, to responding to prompts in a different language not present in the dataset, to taking on a different persona. Crucially, the effect persists for the selected subset, across models with varying architectures, supporting its generality and universality. --- ### From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures Authors: Ryan Liu, Eric Qu, Tobias Kreiman, Samuel M. Blau, Aditi S. Krishnapriyan Published: 2026-02-04 Categories: cs.LG, cond-mat.mtrl-sci, cs.AI, physics.chem-ph arXiv: https://arxiv.org/abs/2602.04861v2 Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to erroneous behavior in downstream simulations that standard energy and force regression evaluations can miss. Existing evaluations, such as microcanonical molecular dynamics (MD), are computationally expensive and primarily probe near-equilibrium states. To improve evaluation metrics for MLIPs, we introduce the Bond Smoothness Characterization Test (BSCT). This efficient benchmark probes the PES via controlled bond deformations and detects non-smoothness, including discontinuities, artificial minima, and spurious forces, both near and far from equilibrium. We show that BSCT correlates strongly with MD stability while requiring a fraction of the cost of MD. To demonstrate how BSCT can guide iterative model design, we utilize an unconstrained Transformer backbone as a testbed, illustrating how refinements such as a new differentiable $k$-nearest neighbors algorithm and temperature-controlled attention reduce artifacts identified by our metric. By optimizing model design systematically based on BSCT, the resulting MLIP simultaneously achieves a low conventional E/F regression error, stable MD simulations, and robust atomistic property predictions. Our results establish BSCT as both a validation metric for practitioners to assess MLIP utility and as an "in-the-loop" model design proxy that alerts MLIP developers to physical challenges that cannot be efficiently evaluated by current MLIP benchmarks. The BSCT dataset and evaluation are available on https://github.com/ryanliu30/bsct.git --- ### CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation Authors: Zhao Tong, Chunlin Gong, Yiping Zhang, Haichao Shi, Qiang Liu, Xingcheng Xu, Shu Wu, Xiao-Yu Zhang Published: 2026-02-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.04856v4 From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process. Challenging this assumption, our study reveals that during fake news generation, even when a model rejects a harmful request, its Chain-of-Thought (CoT) reasoning may still internally contain and propagate unsafe narratives. To analyze this phenomenon, we introduce a unified safety-analysis framework that systematically deconstructs CoT generation across model layers and evaluates the role of individual attention heads through Jacobian-based spectral metrics. Within this framework, we introduce three interpretable measures: stability, geometry, and energy to quantify how specific attention heads respond or embed deceptive reasoning patterns. Extensive experiments on multiple reasoning-oriented LLMs show that the generation risk rises significantly when the thinking mode is activated, where the critical routing decisions are concentrated in only a few contiguous mid-depth layers. By precisely identifying the attention heads responsible for this divergence, our work challenges the assumption that refusal implies safety and provides a new understanding perspective for mitigating latent reasoning risks. --- ### CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation Authors: Zhao Tong, Chunlin Gong, Yiping Zhang, Haichao Shi, Qiang Liu, Xingcheng Xu, Shu Wu, Xiao-Yu Zhang Published: 2026-02-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.04856v3 From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process. Challenging this assumption, our study reveals that during fake news generation, even when a model rejects a harmful request, its Chain-of-Thought (CoT) reasoning may still internally contain and propagate unsafe narratives. To analyze this phenomenon, we introduce a unified safety-analysis framework that systematically deconstructs CoT generation across model layers and evaluates the role of individual attention heads through Jacobian-based spectral metrics. Within this framework, we introduce three interpretable measures: stability, geometry, and energy to quantify how specific attention heads respond or embed deceptive reasoning patterns. Extensive experiments on multiple reasoning-oriented LLMs show that the generation risk rise significantly when the thinking mode is activated, where the critical routing decisions concentrated in only a few contiguous mid-depth layers. By precisely identifying the attention heads responsible for this divergence, our work challenges the assumption that refusal implies safety and provides a new understanding perspective for mitigating latent reasoning risks. --- ### Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know" Authors: Dhruv Madhwal, Lyuxin David Zhang, Dan Roth, Tomer Wolfson, Vivek Gupta Published: 2026-02-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.04853v2 Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks. We find that although accuracy gains from decomposition diminish in frontier models, disagreements between prompting regimes remain highly indicative of potential errors. Because factual knowledge is typically stable while hallucinations are stochastic, cross-regime agreement provides a precise signal of internal uncertainty. We leverage this signal to implement a training-free abstention policy that requires no retrieval or fine-tuning. Our results show that disagreement-based abstention outperforms standard uncertainty baselines as an error detector, improving both F1 and AUROC across settings. This demonstrates that decomposition-based prompting can serve as a practical diagnostic probe for model reliability in closed-book QA. --- ### The Key to State Reduction in Linear Attention: A Rank-based Perspective Authors: Philipp Nazari, T. Konstantin Rusch Published: 2026-02-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04852v2 Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden state of trained linear attention models often exhibits a low-rank structure, suggesting that these models underexploit their capacity in practice. To illuminate this phenomenon, we provide a theoretical analysis of the role of rank in linear attention, revealing that low effective rank can affect retrieval error by amplifying query noise. In addition to these theoretical insights, we conjecture that the low-rank states can be substantially reduced post-training with only minimal performance degradation, yielding faster and more memory-efficient models. To this end, we propose a novel hardware-aware approach that structurally prunes key and query matrices, reducing the state size while retaining compatibility with existing CUDA kernels. We adapt several existing pruning strategies to fit our framework and, building on our theoretical analysis, propose a novel structured pruning method based on a rank-revealing QR decomposition. Our empirical results, evaluated across models of varying sizes and on various downstream tasks, demonstrate the effectiveness of our state reduction framework. We highlight that our framework enables the removal of 50% of the query and key channels at only a marginal increase in perplexity. The code for this project can be found at https://github.com/camail-official/LinearAttentionPruning. --- ### PDF-HR: Pose Distance Fields for Humanoid Robots Authors: Yi Gu, Yukang Gao, Yangchen Zhou, Xingyu Chen, Yixiao Feng, Mingle Zhao, Yunyang Mo, Zhaorui Wang, Lixin Xu, Renjing Xu Published: 2026-02-04 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.04851v1 Pose and motion priors play a crucial role in humanoid robotics. Although such priors have been widely studied in human motion recovery (HMR) domain with a range of models, their adoption for humanoid robots remains limited, largely due to the scarcity of high-quality humanoid motion data. In this work, we introduce Pose Distance Fields for Humanoid Robots (PDF-HR), a lightweight prior that represents the robot pose distribution as a continuous and differentiable manifold. Given an arbitrary pose, PDF-HR predicts its distance to a large corpus of retargeted robot poses, yielding a smooth measure of pose plausibility that is well suited for optimization and control. PDF-HR can be integrated as a reward shaping term, a regularizer, or a standalone plausibility scorer across diverse pipelines. We evaluate PDF-HR on various humanoid tasks, including single-trajectory motion tracking, general motion tracking, style-based motion mimicry, and general motion retargeting. Experiments show that this plug-and-play prior consistently and substantially strengthens strong baselines. Code and models will be released. --- ### El Agente Quntur: A research collaborator agent for quantum chemistry Authors: Juan B. Pérez-Sánchez, Yunheng Zou, Jorge A. Campos-Gonzalez-Angulo, Marcel Müller, Ignacio Gustin, Andrew Wang, Han Hao, Tsz Wai Ko, Changhyeok Choi, Eric S. Isbrandt, Mohammad Ghazi Vakili, Hanyong Xu et al. Published: 2026-02-04 Categories: physics.chem-ph, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.04850v3 Quantum chemistry is a foundational enabling tool for the fields of chemistry, materials science, computational biology and others. Despite of its power, the practical application of quantum chemistry simulations remains in the hands of qualified experts due to methodological complexity, software heterogeneity, and the need for informed interpretation of results. To bridge the accessibility gap for these tools and expand their reach to chemists with broader backgrounds, we introduce El Agente Quntur, a hierarchical, multi-agent AI system designed to operate not merely as an automation tool but as a research collaborator for computational quantum chemistry. Quntur was designed following three main strategies: i) elimination of hard-coded procedural policies in favour of reasoning-driven decisions, ii) construction of general and composable actions that facilitate generalization and efficiency, and iii) implementation of guided deep research to integrate abstract quantum-chemical reasoning across subdisciplines and a detailed understanding of the software's internal logic and syntax. Although instantiated in ORCA, these design principles are applicable to research agents more generally and easily expandable to additional quantum chemistry packages and beyond. Quntur supports the full range of calculations available in ORCA 6.0 and reasons over software documentation and scientific literature to plan, execute, adapt, and analyze in silico chemistry experiments following best practices. We discuss the advances and current bottlenecks in agentic systems operating at the research level in computational chemistry, and outline a roadmap toward a fully autonomous end-to-end computational chemistry research agent. --- ### El Agente Quntur: A research collaborator agent for quantum chemistry Authors: Juan B. Pérez-Sánchez, Yunheng Zou, Jorge A. Campos-Gonzalez-Angulo, Marcel Müller, Ignacio Gustin, Andrew Wang, Han Hao, Tsz Wai Ko, Changhyeok Choi, Eric S. Isbrandt, Mohammad Ghazi Vakili, Hanyong Xu et al. Published: 2026-02-04 Categories: physics.chem-ph, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.04850v2 Quantum chemistry is a foundational enabling tool for the fields of chemistry, materials science, computational biology and others. Despite of its power, the practical application of quantum chemistry simulations remains in the hands of qualified experts due to methodological complexity, software heterogeneity, and the need for informed interpretation of results. To bridge the accessibility gap for these tools and expand their reach to chemists with broader backgrounds, we introduce El Agente Quntur, a hierarchical, multi-agent AI system designed to operate not merely as an automation tool but as a research collaborator for computational quantum chemistry. Quntur was designed following three main strategies: i) elimination of hard-coded procedural policies in favour of reasoning-driven decisions, ii) construction of general and composable actions that facilitate generalization and efficiency, and iii) implementation of guided deep research to integrate abstract quantum-chemical reasoning across subdisciplines and a detailed understanding of the software's internal logic and syntax. Although instantiated in ORCA, these design principles are applicable to research agents more generally and easily expandable to additional quantum chemistry packages and beyond. Quntur supports the full range of calculations available in ORCA 6.0 and reasons over software documentation and scientific literature to plan, execute, adapt, and analyze in silico chemistry experiments following best practices. We discuss the advances and current bottlenecks in agentic systems operating at the research level in computational chemistry, and outline a roadmap toward a fully autonomous end-to-end computational chemistry research agent. --- ### El Agente Estructural: An Artificially Intelligent Molecular Editor Authors: Changhyeok Choi, Yunheng Zou, Marcel Müller, Han Hao, Yeonghun Kang, Juan B. Pérez-Sánchez, Ignacio Gustin, Hanyong Xu, Andrew Wang, Mohammad Ghazi Vakili, Chris Crebolder, Alán Aspuru-Guzik et al. Published: 2026-02-04 Categories: physics.chem-ph, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.04849v2 We present El Agente Estructural, a multimodal, natural-language-driven geometry-generation and manipulation agent for autonomous chemistry and molecular modelling. Unlike molecular generation or editing via generative models, Estructural mimics how human experts directly manipulate molecular systems in three dimensions by integrating a comprehensive set of domain-informed tools and vision-language models. This design enables precise control over atomic or functional group replacements, atomic connectivity, and stereochemistry without the need to rebuild extensive core molecular frameworks. Through a series of representative case studies, we demonstrate that Estructural enables chemically meaningful geometry manipulation across a wide range of real-world scenarios. These include site-selective functionalization, ligand binding, ligand exchange, stereochemically controlled structure construction, isomer interconversion, fragment-level structural analysis, image-guided generation of structures from schematic reaction mechanisms, and mechanism-driven geometry generation and modification. These examples illustrate how multimodal reasoning, when combined with specialized geometry-aware tools, supports interactive and context-aware molecular modelling beyond structure generation. Looking forward, the integration of Estructural into El Agente Quntur, an autonomous multi-agent quantum chemistry platform, enhances its capabilities by adding sophisticated tools for the generation and editing of three-dimensional structures. --- ### Fluid Reasoning Representations Authors: Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin Published: 2026-02-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.04843v2 Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking. Yet we lack a mechanistic account of how extended thinking changes hidden-state representations over the course of a reasoning trace. We introduce \textit{Fluid Reasoning Representations} (FRRs), a representation-level account of how LLMs organize action and predicate concepts during self-generated reasoning, and test them on obfuscated planning, symbolic, and mathematical tasks where task-relevant words are replaced while problem structure is preserved. Across open-weight base, instruction-tuned, and extended-thinking LLMs, representations of the same action or predicate become more similar across wordings and move toward the corresponding unobfuscated concepts over the reasoning trace. Causal probes show that these representations affect behavior: cross-naming steering improves held-out accuracy beyond Gaussian and shuffled controls, symbolic patching retains more action information than shuffled patching, and subtracting refined directions degrades accuracy; together, these results suggest that extended thinking strengthens a representation dynamic already present at lower magnitude in base and instruction-tuned LLMs. Our codebase is open-sourced \href{https://github.com/AI4Collaboration/Fluid-Reasoning-Representation}{here}. --- ### LitS: A novel Neighborhood Descriptor for Point Clouds Authors: Jonatan B. Bastos, Francisco F. Rivera, Oscar G. Lorenzo, David L. Vilariño, José C. Cabaleiro, Alberto M. Esmorís, Tomás F. Pena Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04838v1 With the advancement of 3D scanning technologies, point clouds have become fundamental for representing 3D spatial data, with applications that span across various scientific and technological fields. Practical analysis of this data depends crucially on available neighborhood descriptors to accurately characterize the local geometries of the point cloud. This paper introduces LitS, a novel neighborhood descriptor for 2D and 3D point clouds. LitS are piecewise constant functions on the unit circle that allow points to keep track of their surroundings. Each element in LitS' domain represents a direction with respect to a local reference system. Once constructed, evaluating LitS at any given direction gives us information about the number of neighbors in a cone-like region centered around that same direction. Thus, LitS conveys a lot of information about the local neighborhood of a point, which can be leveraged to gain global structural understanding by analyzing how LitS changes between close points. In addition, LitS comes in two versions ('regular' and 'cumulative') and has two parameters, allowing them to adapt to various contexts and types of point clouds. Overall, they are a versatile neighborhood descriptor, capable of capturing the nuances of local point arrangements and resilient to common point cloud data issues such as variable density and noise. --- ### Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing Authors: Zhaotian Weng, Antonis Antoniades, Deepak Nathani, Zhen Zhang, Xiao Pu, Xin Eric Wang Published: 2026-02-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.04837v1 Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce Group-Evolving Agents (GEA), a new paradigm for open-ended self-improvements, which treats a group of agents as the fundamental evolutionary unit, enabling explicit experience sharing and reuse within the group throughout evolution. Unlike existing open-ended self-evolving paradigms that adopt tree-structured evolution, GEA overcomes the limitation of inefficient utilization of exploratory diversity caused by isolated evolutionary branches. We evaluate GEA on challenging coding benchmarks, where it significantly outperforms state-of-the-art self-evolving methods (71.0% vs. 56.7% on SWE-bench Verified, 88.3% vs. 68.3% on Polyglot) and matches or exceeds top human-designed agent frameworks (71.8% and 52.0% on two benchmarks, respectively). Analysis reveals that GEA more effectively converts early-stage exploratory diversity into sustained, long-term progress, achieving stronger performance under the same number of evolved agents. Furthermore, GEA exhibits consistent transferability across different coding models and greater robustness, fixing framework-level bugs in 1.4 iterations on average, versus 5 for self-evolving methods. --- ### Are AI Capabilities Increasing Exponentially? A Competing Hypothesis Authors: Haosen Ge, Hamsa Bastani, Osbert Bastani Published: 2026-02-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.04836v2 Rapidly increasing AI capabilities have substantial real-world consequences, ranging from AI safety concerns to labor market consequences. The Model Evaluation & Threat Research (METR) report argues that AI capabilities have exhibited exponential growth since 2019. In this note, we argue that the data does not support exponential growth, even in shorter-term horizons. Whereas the METR study claims that fitting sigmoid/logistic curves results in inflection points far in the future, we fit a sigmoid curve to their current data and find that the inflection point has already passed. In addition, we propose a more complex model that decomposes AI capabilities into base and reasoning capabilities, exhibiting individual rates of improvement. We prove that this model supports our hypothesis that AI capabilities will exhibit an inflection point in the near future. Our goal is not to establish a rigorous forecast of our own, but to highlight the fragility of existing forecasts of exponential growth. --- ### It's Not a Lottery, It's a Race: Understanding How Gradient Descent Adapts the Network's Capacity to the Task Authors: Hannah Pinson Published: 2026-02-04 Categories: cs.LG, cs.AI, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2602.04832v2 Our theoretical understanding of neural networks is lagging behind their empirical success. One of the important unexplained phenomena is why and how, during the process of training with gradient descent, the theoretical capacity of neural networks is reduced to an effective capacity that fits the task. We here investigate the mechanism by which gradient descent achieves this through analyzing the learning dynamics at the level of individual neurons in single hidden layer ReLU networks. We identify three dynamical principles, namely mutual alignment, unlocking and racing, that together explain why we can often successfully reduce capacity after training through the merging of equivalent neurons or the pruning of low norm weights. We specifically explain the mechanism behind the lottery ticket conjecture, or why the specific, beneficial initial conditions of some neurons lead them to obtain higher weight norms. --- ### Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning Authors: Joydeep Chandra, Satyam Kumar Navneet, Aleksandr Algazinov, Yong Zhang Published: 2026-02-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04821v1 Urban traffic management demands systems that simultaneously predict future conditions, detect anomalies, and take safe corrective actions -- all while providing reliability guarantees. We present STREAM-RL, a unified framework that introduces three novel algorithmic contributions: (1) PU-GAT+, an Uncertainty-Guided Adaptive Conformal Forecaster that uses prediction uncertainty to dynamically reweight graph attention via confidence-monotonic attention, achieving distribution-free coverage guarantees; (2) CRFN-BY, a Conformal Residual Flow Network that models uncertainty-normalized residuals via normalizing flows with Benjamini-Yekutieli FDR control under arbitrary dependence; and (3) LyCon-WRL+, an Uncertainty-Guided Safe World-Model RL agent with Lyapunov stability certificates, certified Lipschitz bounds, and uncertainty-propagated imagination rollouts. To our knowledge, this is the first framework to propagate calibrated uncertainty from forecasting through anomaly detection to safe policy learning with end-to-end theoretical guarantees. Experiments on multiple real-world traffic trajectory data demonstrate that STREAM-RL achieves 91.4\% coverage efficiency, controls FDR at 4.1\% under verified dependence, and improves safety rate to 95.2\% compared to 69\% for standard PPO while achieving higher reward, with 23ms end-to-end inference latency. --- ### Toward Reliable and Explainable Nail Disease Classification: Leveraging Adversarial Training and Grad-CAM Visualization Authors: Farzia Hossain, Samanta Ghosh, Shahida Begum, B. M. Shahria Alam, Mohammad Tahmid Noor, Md Parvez Mia, Nishat Tasnim Niloy Published: 2026-02-04 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.04820v1 Human nail diseases are gradually observed over all age groups, especially among older individuals, often going ignored until they become severe. Early detection and accurate diagnosis of such conditions are important because they sometimes reveal our body's health problems. But it is challenging due to the inferred visual differences between disease types. This paper presents a machine learning-based model for automated classification of nail diseases based on a publicly available dataset, which contains 3,835 images scaling six categories. In 224x224 pixels, all images were resized to ensure consistency. To evaluate performance, four well-known CNN models-InceptionV3, DenseNet201, EfficientNetV2, and ResNet50 were trained and analyzed. Among these, InceptionV3 outperformed the others with an accuracy of 95.57%, while DenseNet201 came next with 94.79%. To make the model stronger and less likely to make mistakes on tricky or noisy images, we used adversarial training. To help understand how the model makes decisions, we used SHAP to highlight important features in the predictions. This system could be a helpful support for doctors, making nail disease diagnosis more accurate and faster. --- ### XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas Authors: Aqsa Sultana, Rayan Afsar, Ahmed Rahu, Surendra P. Singh, Brian Shula, Brandon Combs, Derrick Forchetti, Vijayan K. Asari Published: 2026-02-04 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.04819v5 Accurate risk stratification of precancerous polyps during routine colonoscopy screening is a key strategy to reduce the incidence of colorectal cancer (CRC). However, assessment of low-grade dysplasia remains limited by subjective histopathologic interpretation. Advances in computational pathology and deep learning offer new opportunities to identify subtle, fine morphologic patterns associated with malignant progression that may be imperceptible to the human eye. In this work, we propose XtraLight-MedMamba, an ultra-lightweight state-space-based deep learning framework to classify neoplastic tubular adenomas from whole-slide images (WSIs). The architecture is a blend of a ConvNeXt-based shallow feature extractor with parallel vision mamba blocks to efficiently model local texture cues within global contextual structure. An integration of the Spatial and Channel Attention Bridge (SCAB) module enhances multiscale feature extraction, while the Fixed Non-Negative Orthogonal Classifier (FNOClassifier) enables substantial parameter reduction and improved generalization. The model was evaluated on a curated dataset acquired from patients with low-grade tubular adenomas, stratified into case and control cohorts based on subsequent CRC development. XtraLight-MedMamba achieved an accuracy of 97.18\% and an F1-score of 0.9767 using approximately 32,000 parameters, outperforming transformer-based and conventional Mamba architectures, which have significantly higher model complexity and computational burden, making it suitable for resource-constrained areas. --- ### XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas Authors: Aqsa Sultana, Rayan Afsar, Ahmed Rahu, Surendra P. Singh, Brian Shula, Brandon Combs, Derrick Forchetti, Vijayan K. Asari Published: 2026-02-04 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.04819v4 Accurate risk stratification of precancerous polyps during routine colonoscopy screening is a key strategy to reduce the incidence of colorectal cancer (CRC). However, assessment of low-grade dysplasia remains limited by subjective histopathologic interpretation. Advances in computational pathology and deep learning offer new opportunities to identify subtle, fine morphologic patterns associated with malignant progression that may be imperceptible to the human eye. In this work, we propose XtraLight-MedMamba, an ultra-lightweight state-space-based deep learning framework to classify neoplastic tubular adenomas from whole-slide images (WSIs). The architecture is a blend of a ConvNeXt-based shallow feature extractor with parallel vision mamba blocks to efficiently model local texture cues within global contextual structure. An integration of the Spatial and Channel Attention Bridge (SCAB) module enhances multiscale feature extraction, while the Fixed Non-Negative Orthogonal Classifier (FNOClassifier) enables substantial parameter reduction and improved generalization. The model was evaluated on a curated dataset acquired from patients with low-grade tubular adenomas, stratified into case and control cohorts based on subsequent CRC development. XtraLight-MedMamba achieved an accuracy of 97.18\% and an F1-score of 0.9767 using approximately 32,000 parameters, outperforming transformer-based and conventional Mamba architectures, which have significantly higher model complexity and computational burden, making it suitable for resource-constrained areas. --- ### Horizon-LM: A RAM-Centric Architecture for LLM Training Authors: Zhengqing Yuan, Lichao Sun, Yanfang Ye Published: 2026-02-04 Categories: cs.OS, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2602.04816v3 The rapid growth of large language models (LLMs) has outpaced the evolution of single-GPU hardware, making model scale increasingly constrained by memory capacity rather than computation. While modern training systems extend GPU memory through distributed parallelism and offloading across CPU and storage tiers, they fundamentally retain a GPU-centric execution paradigm in which GPUs host persistent model replicas and full autograd graphs. As a result, scaling large models remains tightly coupled to multi-GPU clusters, complex distributed runtimes, and unpredictable host memory consumption, creating substantial barriers for node-scale post-training workloads such as instruction tuning, alignment, and domain adaptation. We present Horizon-LM, a memory-centric training system that redefines the roles of CPU and GPU for large-model optimization. Horizon-LM treats host memory as the authoritative parameter store and uses GPUs solely as transient compute engines through a CPU-master, GPU-template execution model. By eliminating persistent GPU-resident modules and autograd graphs, employing explicit recomputation with manual gradient propagation, and introducing a pipelined double-buffered execution engine, Horizon-LM decouples model scale from GPU count and bounds memory usage to the theoretical parameter footprint. On a single H200 GPU with 1.5\,TB host RAM, Horizon-LM reliably trains models up to 120B parameters. On a standard single A100 machine, Horizon-LM achieves up to 12.2$\times$ higher training throughput than DeepSpeed ZeRO-3 with CPU offloading while preserving numerical correctness. Across platforms and scales, Horizon-LM sustains high device utilization and predictable memory growth, demonstrating that host memory, not GPU memory, defines the true feasibility boundary for node-scale large-model training. --- ### X2HDR: HDR Image Generation in a Perceptually Uniform Space Authors: Ronghuan Wu, Wanchao Su, Kede Ma, Jing Liao, Rafał K. Mantiuk Published: 2026-02-04 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.04814v1 High-dynamic-range (HDR) formats and displays are becoming increasingly prevalent, yet state-of-the-art image generators (e.g., Stable Diffusion and FLUX) typically remain limited to low-dynamic-range (LDR) output due to the lack of large-scale HDR training data. In this work, we show that existing pretrained diffusion models can be easily adapted to HDR generation without retraining from scratch. A key challenge is that HDR images are natively represented in linear RGB, whose intensity and color statistics differ substantially from those of sRGB-encoded LDR images. This gap, however, can be effectively bridged by converting HDR inputs into perceptually uniform encodings (e.g., using PU21 or PQ). Empirically, we find that LDR-pretrained variational autoencoders (VAEs) reconstruct PU21-encoded HDR inputs with fidelity comparable to LDR data, whereas linear RGB inputs cause severe degradations. Motivated by this finding, we describe an efficient adaptation strategy that freezes the VAE and finetunes only the denoiser via low-rank adaptation in a perceptually uniform space. This results in a unified computational method that supports both text-to-HDR synthesis and single-image RAW-to-HDR reconstruction. Experiments demonstrate that our perceptually encoded adaptation consistently improves perceptual fidelity, text-image alignment, and effective dynamic range, relative to previous techniques. --- ### Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents Authors: Shubham Vatsal, Harsh Dubey, Aditi Singh Published: 2026-02-04 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.04813v1 Large Language Model (LLM)-based agents that plan, use tools and act has begun to shape healthcare and medicine. Reported studies demonstrate competence on various tasks ranging from EHR analysis and differential diagnosis to treatment planning and research workflows. Yet the literature largely consists of overviews which are either broad surveys or narrow dives into a single capability (e.g., memory, planning, reasoning), leaving healthcare work without a common frame. We address this by reviewing 49 studies using a seven-dimensional taxonomy: Cognitive Capabilities, Knowledge Management, Interaction Patterns, Adaptation & Learning, Safety & Ethics, Framework Typology and Core Tasks & Subtasks with 29 operational sub-dimensions. Using explicit inclusion and exclusion criteria and a labeling rubric (Fully Implemented, Partially Implemented, Not Implemented), we map each study to the taxonomy and report quantitative summaries of capability prevalence and co-occurrence patterns. Our empirical analysis surfaces clear asymmetries. For instance, the External Knowledge Integration sub-dimension under Knowledge Management is commonly realized (~76% Fully Implemented) whereas Event-Triggered Activation sub-dimenison under Interaction Patterns is largely absent (~92% Not Implemented) and Drift Detection & Mitigation sub-dimension under Adaptation & Learning is rare (~98% Not Implemented). Architecturally, Multi-Agent Design sub-dimension under Framework Typology is the dominant pattern (~82% Fully Implemented) while orchestration layers remain mostly partial. Across Core Tasks & Subtasks, information centric capabilities lead e.g., Medical Question Answering & Decision Support and Benchmarking & Simulation, while action and discovery oriented areas such as Treatment Planning & Prescription still show substantial gaps (~59% Not Implemented). --- ### Robust Generalizable Heterogeneous Legal Link Prediction Authors: Lorenz Wendlinger, Simon Alexander Nonn, Abdullah Al Zubaer, Michael Granitzer Published: 2026-02-04 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2602.04812v1 Recent work has applied link prediction to large heterogeneous legal citation networks \new{with rich meta-features}. We find that this approach can be improved by including edge dropout and feature concatenation for the learning of more robust representations, which reduces error rates by up to 45%. We also propose an approach based on multilingual node features with an improved asymmetric decoder for compatibility, which allows us to generalize and extend the prediction to more, geographically and linguistically disjoint, data from New Zealand. Our adaptations also improve inductive transferability between these disjoint legal systems. --- ### SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization Authors: Jiarui Yuan, Tailin Jin, Weize Chen, Zeyuan Liu Published: 2026-02-04 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.04811v2 True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this foundational capability is hindered by two obstacles: the entanglement of prior knowledge, where ``new'' knowledge may appear in pre-training data, and the entanglement of reasoning complexity, where failures may stem from problem difficulty rather than an inability to recall learned knowledge. We introduce SE-Bench, a diagnostic environment that obfuscates the NumPy library and its API doc into a pseudo-novel package with randomized identifiers. Agents are trained to internalize this package and evaluated on simple coding tasks without access to documentation, yielding a clean setting where tasks are trivial with the new API doc but impossible for base models without it. Our investigation reveals three insights: (1) the Open-Book Paradox, where training with reference documentation inhibits retention, requiring "Closed-Book Training" to force knowledge compression into weights; (2) the RL Gap, where standard RL fails to internalize new knowledge completely due to PPO clipping and negative gradients; and (3) the viability of Self-Play for internalization, proving models can learn from self-generated, noisy tasks when coupled with SFT, but not RL. Overall, SE-Bench establishes a rigorous diagnostic platform for self-evolution with knowledge internalization. Our code and dataset can be found at https://github.com/thunlp/SE-Bench. --- ### Beyond Rewards in Reinforcement Learning for Cyber Defence Authors: Elizabeth Bates, Chris Hicks, Vasilios Mavroudis Published: 2026-02-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04809v3 Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly engineered reward functions which combine many penalties and incentives for a range of (un)desirable states and costly actions. Dense rewards help alleviate the challenge of exploring complex environments but risk biasing agents towards suboptimal and potentially riskier solutions, a critical issue in complex cyber environments. We thoroughly evaluate the impact of reward function structure on learning and policy behavioural characteristics using a variety of sparse and dense reward functions, two well-established cyber gyms, a range of network sizes, and both policy gradient and value-based RL algorithms. Our evaluation is enabled by a novel ground truth evaluation approach which allows directly comparing between different reward functions, illuminating the nuanced inter-relationships between rewards, action space and the risks of suboptimal policies in cyber environments. Our results show that sparse rewards, provided they are goal aligned and can be encountered frequently, uniquely offer both enhanced training reliability and more effective cyber defence agents with lower-risk policies. Surprisingly, sparse rewards can also yield policies that are better aligned with cyber defender goals and make sparing use of costly defensive actions without explicit reward-based numerical penalties. --- ### Evolving Afferent Architectures: Biologically-inspired Models for Damage-Avoidance Learning Authors: Wolfgang Maass, Sabine Janzen, Prajvi Saxena, Sach Mukherjee Published: 2026-02-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04807v1 We introduce Afferent Learning, a framework that produces Computational Afferent Traces (CATs) as adaptive, internal risk signals for damage-avoidance learning. Inspired by biological systems, the framework uses a two-level architecture: evolutionary optimization (outer loop) discovers afferent sensing architectures that enable effective policy learning, while reinforcement learning (inner loop) trains damage-avoidance policies using these signals. This formalizes afferent sensing as providing an inductive bias for efficient learning: architectures are selected based on their ability to enable effective learning (rather than directly minimizing damage). We provide theoretical convergence guarantees under smoothness and bounded-noise assumptions. We illustrate the general approach in the challenging context of biomechanical digital twins operating over long time horizons (multiple decades of the life-course). Here, we find that CAT-based evolved architectures achieve significantly higher efficiency and better age-robustness than hand-designed baselines, enabling policies that exhibit age-dependent behavioral adaptation (23% reduction in high-risk actions). Ablation studies validate CAT signals, evolution, and predictive discrepancy as essential. We release code and data for reproducibility. --- ### Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging Authors: Jia-peng Zhang, Cheng-Feng Pu, Meng-Hao Guo, Yan-Pei Cao, Shi-Min Hu Published: 2026-02-04 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2602.04805v1 The rapid proliferation of generative 3D models has created a critical bottleneck in animation pipelines: rigging. Existing automated methods are fundamentally limited by their approach to skinning, treating it as an ill-posed, high-dimensional regression task that is inefficient to optimize and is typically decoupled from skeleton generation. We posit this is a representation problem and introduce SkinTokens: a learned, compact, and discrete representation for skinning weights. By leveraging an FSQ-CVAE to capture the intrinsic sparsity of skinning, we reframe the task from continuous regression to a more tractable token sequence prediction problem. This representation enables TokenRig, a unified autoregressive framework that models the entire rig as a single sequence of skeletal parameters and SkinTokens, learning the complicated dependencies between skeletons and skin deformations. The unified model is then amenable to a reinforcement learning stage, where tailored geometric and semantic rewards improve generalization to complex, out-of-distribution assets. Quantitatively, the SkinTokens representation leads to a 98%-133% percents improvement in skinning accuracy over state-of-the-art methods, while the full TokenRig framework, refined with RL, enhances bone prediction by 17%-22%. Our work presents a unified, generative approach to rigging that yields higher fidelity and robustness, offering a scalable solution to a long-standing challenge in 3D content creation. --- ### OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models Authors: Yue Ding, Yiyan Ji, Jungang Li, Xuyang Liu, Xinlong Chen, Junfei Wu, Bozhou Li, Bohan Zeng, Yang Shi, Yushuo Guan, Yuanxing Zhang, Jiaheng Liu et al. Published: 2026-02-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.04804v2 Omni-modal Large Language Models (Omni-LLMs) have demonstrated strong capabilities in audio-video understanding tasks. However, their reliance on long multimodal token sequences leads to substantial computational overhead. Despite this challenge, token compression methods designed for Omni-LLMs remain limited. To bridge this gap, we propose OmniSIFT (Omni-modal Spatio-temporal Informed Fine-grained Token compression), a modality-asymmetric token compression framework tailored for Omni-LLMs. Specifically, OmniSIFT adopts a two-stage compression strategy: (i) a spatio-temporal video pruning module that removes video redundancy arising from both intra-frame structure and inter-frame overlap, and (ii) a vision-guided audio selection module that filters audio tokens. The entire framework is optimized end-to-end via a differentiable straight-through estimator. Extensive experiments on five representative benchmarks demonstrate the efficacy and robustness of OmniSIFT. Notably, for Qwen2.5-Omni-7B, OmniSIFT introduces only 4.85M parameters while maintaining lower latency than training-free baselines such as OmniZip. With merely 25% of the original token context, OmniSIFT consistently outperforms all compression baselines and even surpasses the performance of the full-token model on several tasks. --- ### VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text? Authors: Qing'an Liu, Juntong Feng, Yuhao Wang, Xinzhe Han, Yujie Cheng, Yue Zhu, Haiwen Diao, Yunzhi Zhuge, Huchuan Lu Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04802v3 Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also frequently appears as visualized text embedded in images, raising the question of whether current VLMs handle such input requests comparably. We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and visualized-text questions under controlled rendering conditions. Extensive evaluation of over 30 representative VLMs reveals a pronounced modality gap: models that perform well on pure-text queries often degrade substantially when equivalent semantic content is presented as visualized text. This gap is further amplified by increased perceptual difficulty, highlighting sensitivity to rendering variations despite unchanged semantics. Overall, VISTA-Bench provides a principled evaluation framework to diagnose this limitation and to guide progress toward more unified language representations across tokenized text and pixels. The source dataset and code are publicly available at https://github.com/QingAnLiu/VISTA-Bench. --- ### Score-Based Change-Point Detection and Region Localization for Spatio-Temporal Point Processes Authors: Wenbin Zhou, Liyan Xie, Shixiang Zhu Published: 2026-02-04 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.04798v1 We study sequential change-point detection for spatio-temporal point processes, where actionable detection requires not only identifying when a distributional change occurs but also localizing where it manifests in space. While classical quickest change detection methods provide strong guarantees on detection delay and false-alarm rates, existing approaches for point-process data predominantly focus on temporal changes and do not explicitly infer affected spatial regions. We propose a likelihood-free, score-based detection framework that jointly estimates the change time and the change region in continuous space-time without assuming parametric knowledge of the pre- or post-change dynamics. The method leverages a localized and conditionally weighted Hyvärinen score to quantify event-level deviations from nominal behavior and aggregates these scores using a spatio-temporal CUSUM-type statistic over a prescribed class of spatial regions. Operating sequentially, the procedure outputs both a stopping time and an estimated change region, enabling real-time detection with spatial interpretability. We establish theoretical guarantees on false-alarm control, detection delay, and spatial localization accuracy, and demonstrate the effectiveness of the proposed approach through simulations and real-world spatio-temporal event data. --- ### Maximum-Volume Nonnegative Matrix Factorization Authors: Olivier Vu Thanh, Nicolas Gillis Published: 2026-02-04 Categories: cs.LG, eess.SP, math.NA, stat.ML arXiv: https://arxiv.org/abs/2602.04795v3 Nonnegative matrix factorization (NMF) is a popular data embedding technique. Given a nonnegative data matrix $X$, it aims at finding two lower dimensional matrices, $W$ and $H$, such that $X\approx WH$, where the factors $W$ and $H$ are constrained to be element-wise nonnegative. The factor $W$ serves as a basis for the columns of $X$. In order to obtain more interpretable and unique solutions, minimum-volume NMF (MinVol NMF) minimizes the volume of $W$. In this paper, we consider the dual approach, where the volume of $H$ is maximized instead; this is referred to as maximum-volume NMF (MaxVol NMF). MaxVol NMF is identifiable under the same conditions as MinVol NMF in the noiseless case, but it behaves rather differently in the presence of noise. In practice, MaxVol NMF is much more effective to extract a sparse decomposition and does not generate rank-deficient solutions. In fact, we prove that the solutions of MaxVol NMF with the largest volume correspond to clustering the columns of $X$ in disjoint clusters, while the solutions of MinVol NMF with smallest volume are rank deficient. We propose two algorithms to solve MaxVol NMF. We also present a normalized variant of MaxVol NMF that exhibits better performance than MinVol NMF and MaxVol NMF, and can be interpreted as a continuum between standard NMF and orthogonal NMF. We illustrate our results in the context of hyperspectral unmixing. The code is available from https://gitlab.com/vuthanho/maxvolmf.jl. --- ### Maximum-Volume Nonnegative Matrix Factorization Authors: Olivier Vu Thanh, Nicolas Gillis Published: 2026-02-04 Categories: cs.LG, eess.SP, math.NA, stat.ML arXiv: https://arxiv.org/abs/2602.04795v2 Nonnegative matrix factorization (NMF) is a popular data embedding technique. Given a nonnegative data matrix $X$, it aims at finding two lower dimensional matrices, $W$ and $H$, such that $X\approx WH$, where the factors $W$ and $H$ are constrained to be element-wise nonnegative. The factor $W$ serves as a basis for the columns of $X$. In order to obtain more interpretable and unique solutions, minimum-volume NMF (MinVol NMF) minimizes the volume of $W$. In this paper, we consider the dual approach, where the volume of $H$ is maximized instead; this is referred to as maximum-volume NMF (MaxVol NMF). MaxVol NMF is identifiable under the same conditions as MinVol NMF in the noiseless case, but it behaves rather differently in the presence of noise. In practice, MaxVol NMF is much more effective to extract a sparse decomposition and does not generate rank-deficient solutions. In fact, we prove that the solutions of MaxVol NMF with the largest volume correspond to clustering the columns of $X$ in disjoint clusters, while the solutions of MinVol NMF with smallest volume are rank deficient. We propose two algorithms to solve MaxVol NMF. We also present a normalized variant of MaxVol NMF that exhibits better performance than MinVol NMF and MaxVol NMF, and can be interpreted as a continuum between standard NMF and orthogonal NMF. We illustrate our results in the context of hyperspectral unmixing. --- ### Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention Authors: Chengtao Lv, Yumeng Shi, Yushi Huang, Ruihao Gong, Shen Ren, Wenya Wang Published: 2026-02-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.04789v4 Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions have shown promise on bidirectional models, we identify that applying these solutions to AR models leads to considerable performance degradation for two reasons: isolated consideration of chunk generation and insufficient utilization of past informative context. Motivated by these observations, we propose \textsc{Light Forcing}, the \textit{first} sparse attention solution tailored for AR video generation models. It incorporates a \textit{Chunk-Aware Growth} mechanism to quantitatively estimate the contribution of each chunk, which determines their sparsity allocation. This progressive sparsity increase strategy enables the current chunk to inherit prior knowledge in earlier chunks during generation. Additionally, we introduce a \textit{Hierarchical Sparse Attention} to capture informative historical and local context in a coarse-to-fine manner. Such two-level mask selection strategy (i.e., frame and block level) can adaptively handle diverse attention patterns. Extensive experiments demonstrate that our method outperforms existing sparse attention in quality (e.g., 84.5 on VBench) and efficiency (e.g., $1.2{\sim}1.3\times$ end-to-end speedup). Combined with other efficient solutions, \textsc{Light Forcing} further achieves a $2.0{\sim}3.0\times$ end-to-end speedup across diverse GPUs (e.g., 27.4\,FPS on RTX 5090 and 33.9\,FPS on H100). Code is released via this \href{https://github.com/chengtao-lv/LightForcing}{link}. --- ### Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation Authors: Congjing Zhang, Ryan Feng Lin, Ruoxuan Bao, Shuai Huang Published: 2026-02-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.04785v1 While tabular data is fundamental to many real-world machine learning (ML) applications, acquiring high-quality tabular data is usually labor-intensive and expensive. Limited by the scarcity of observations, tabular datasets often exhibit critical deficiencies, such as class imbalance, selection bias, and low fidelity. To address these challenges, building on recent advances in Large Language Models (LLMs), this paper introduces Team-then-Trim (T$^2$), a framework that synthesizes high-quality tabular data through a collaborative team of LLMs, followed by a rigorous three-stage plug-in data quality control (QC) pipeline. In T$^2$, tabular data generation is conceptualized as a manufacturing process: specialized LLMs, guided by domain knowledge, are tasked with generating different data components sequentially, and the resulting products, i.e., the synthetic data, are systematically evaluated across multiple dimensions of QC. Empirical results on both simulated and real-world datasets demonstrate that T$^2$ outperforms state-of-the-art methods in producing high-quality tabular data, highlighting its potential to support downstream models when direct data collection is practically infeasible. --- ### From independent patches to coordinated attention: Controlling information flow in vision transformers Authors: Kieran A. Murphy Published: 2026-02-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04784v1 We make the information transmitted by attention an explicit, measurable quantity in vision transformers. By inserting variational information bottlenecks on all attention-mediated writes to the residual stream -- without other architectural changes -- we train models with an explicit information cost and obtain a controllable spectrum from independent patch processing to fully expressive global attention. On ImageNet-100, we characterize how classification behavior and information routing evolve across this spectrum, and provide initial insights into how global visual representations emerge from local patch processing by analyzing the first attention heads that transmit information. By biasing learning toward solutions with constrained internal communication, our approach yields models that are more tractable for mechanistic analysis and more amenable to control. --- ### Legendre Memory Unit with A Multi-Slice Compensation Model for Short-Term Wind Speed Forecasting Based on Wind Farm Cluster Data Authors: Mumin Zhang, Haochen Zhang, Xin Zhi Khoo, Yilin Zhang, Nuo Chen, Ting Zhang, Junjie Tang Published: 2026-02-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.04782v1 With more wind farms clustered for integration, the short-term wind speed prediction of such wind farm clusters is critical for normal operation of power systems. This paper focuses on achieving accurate, fast, and robust wind speed prediction by full use of cluster data with spatial-temporal correlation. First, weighted mean filtering (WMF) is applied to denoise wind speed data at the single-farm level. The Legendre memory unit (LMU) is then innovatively applied for the wind speed prediction, in combination with the Compensating Parameter based on Kendall rank correlation coefficient (CPK) of wind farm cluster data, to construct the multi-slice LMU (MSLMU). Finally, an innovative ensemble model WMF-CPK-MSLMU is proposed herein, with three key blocks: data pre-processing, forecasting, and multi-slice compensation. Advantages include: 1) LMU jointly models linear and nonlinear dependencies among farms to capture spatial-temporal correlations through backpropagation; 2) MSLMU enhances forecasting by using CPK-derived weights instead of random initialization, allowing spatial correlations to fully activate hidden nodes across clustered wind farms.; 3) CPK adaptively weights the compensation model in MSLMU and complements missing data spatially, to facilitate the whole model highly accurate and robust. Test results on different wind farm clusters indicate the effectiveness and superiority of proposed ensemble model WMF-CPK-MSLMU in the short-term prediction of wind farm clusters compared to the existing models. --- ### Dynamical Regimes of Multimodal Diffusion Models Authors: Emil Albrychiewicz, Andrés Franco Valiente, Li-Ching Chen Published: 2026-02-04 Categories: cs.LG, cond-mat.dis-nn arXiv: https://arxiv.org/abs/2602.04780v1 Diffusion based generative models have achieved unprecedented fidelity in synthesizing high dimensional data, yet the theoretical mechanisms governing multimodal generation remain poorly understood. Here, we present a theoretical framework for coupled diffusion models, using coupled Ornstein-Uhlenbeck processes as a tractable model. By using the nonequilibrium statistical physics of dynamical phase transitions, we demonstrate that multimodal generation is governed by a spectral hierarchy of interaction timescales rather than simultaneous resolution. A key prediction is the ``synchronization gap'', a temporal window during the reverse generative process where distinct eigenmodes stabilize at different rates, providing a theoretical explanation for common desynchronization artifacts. We derive analytical conditions for speciation and collapse times under both symmetric and anisotropic coupling regimes, establishing strict bounds for coupling strength to avoid unstable symmetry breaking. We show that the coupling strength acts as a spectral filter that enforces a tunable temporal hierarchy on generation. We support these predictions through controlled experiments with diffusion models trained on MNIST datasets and exact score samplers. These results motivate time dependent coupling schedules that target mode specific timescales, offering a potential alternative to ad hoc guidance tuning. --- ### Speaker-Aware Simulation Improves Conversational Speech Recognition Authors: Máté Gedeon, Péter Mihajlik Published: 2026-02-04 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2602.04776v1 Automatic speech recognition (ASR) for conversational speech remains challenging due to the limited availability of large-scale, well-annotated multi-speaker dialogue data and the complex temporal dynamics of natural interactions. Speaker-aware simulated conversations (SASC) offer an effective data augmentation strategy by transforming single-speaker recordings into realistic multi-speaker dialogues. However, prior work has primarily focused on English data, leaving questions about the applicability to lower-resource languages. In this paper, we adapt and implement the SASC framework for Hungarian conversational ASR. We further propose C-SASC, an extended variant that incorporates pause modeling conditioned on utterance duration, enabling a more faithful representation of local temporal dependencies observed in human conversation while retaining the simplicity and efficiency of the original approach. We generate synthetic Hungarian dialogues from the BEA-Large corpus and combine them with real conversational data for ASR training. Both SASC and C-SASC are evaluated extensively under a wide range of simulation configurations, using conversational statistics derived from CallHome, BEA-Dialogue, and GRASS corpora. Experimental results show that speaker-aware conversational simulation consistently improves recognition performance over naive concatenation-based augmentation. While the additional duration conditioning in C-SASC yields modest but systematic gains--most notably in character-level error rates--its effectiveness depends on the match between source conversational statistics and the target domain. Overall, our findings confirm the robustness of speaker-aware conversational simulation for Hungarian ASR and highlight the benefits and limitations of increasingly detailed temporal modeling in synthetic dialogue generation. ---