# Research Papers — 2026-02 · bundle page 84 of 210 > Full-text markdown of papers #4151–4200 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/84 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/83.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/85.md) ### A Bayesian Approach to Low-Discrepancy Subset Selection Authors: Nathan Kirk Published: 2026-02-16 Categories: stat.ME, cs.LG, math.NA, stat.CO arXiv: https://arxiv.org/abs/2602.14607v1 Low-discrepancy designs play a central role in quasi-Monte Carlo methods and are increasingly influential in other domains such as machine learning, robotics and computer graphics, to name a few. In recent years, one such low-discrepancy construction method called subset selection has received a lot of attention. Given a large population, one optimally selects a small low-discrepancy subset with respect to a discrepancy-based objective. Versions of this problem are known to be NP-hard. In this text, we establish, for the first time, that the subset selection problem with respect to kernel discrepancies is also NP-hard. Motivated by this intractability, we propose a Bayesian Optimization procedure for the subset selection problem utilizing the recent notion of deep embedding kernels. We demonstrate the performance of the BO algorithm to minimize discrepancy measures and note that the framework is broadly applicable any design criteria. --- ### Towards Selection as Power: Bounding Decision Authority in Autonomous Agents Authors: Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz Published: 2026-02-16 Categories: cs.MA, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2602.14606v1 Autonomous agentic systems are increasingly deployed in regulated, high-stakes domains where decisions may be irreversible and institutionally constrained. Existing safety approaches emphasize alignment, interpretability, or action-level filtering. We argue that these mechanisms are necessary but insufficient because they do not directly govern selection power: the authority to determine which options are generated, surfaced, and framed for decision. We propose a governance architecture that separates cognition, selection, and action into distinct domains and models autonomy as a vector of sovereignty. Cognitive autonomy remains unconstrained, while selection and action autonomy are bounded through mechanically enforced primitives operating outside the agent's optimization space. The architecture integrates external candidate generation (CEFL), a governed reducer, commit-reveal entropy isolation, rationale validation, and fail-loud circuit breakers. We evaluate the system across multiple regulated financial scenarios under adversarial stress targeting variance manipulation, threshold gaming, framing skew, ordering effects, and entropy probing. Metrics quantify selection concentration, narrative diversity, governance activation cost, and failure visibility. Results show that mechanical selection governance is implementable, auditable, and prevents deterministic outcome capture while preserving reasoning capacity. Although probabilistic concentration remains, the architecture measurably bounds selection authority relative to conventional scalar pipelines. This work reframes governance as bounded causal power rather than internal intent alignment, offering a foundation for deploying autonomous agents where silent failure is unacceptable. --- ### OPBench: A Graph Benchmark to Combat the Opioid Crisis Authors: Tianyi Ma, Yiyang Li, Yiyue Qian, Zheyuan Zhang, Zehong Wang, Chuxu Zhang, Yanfang Ye Published: 2026-02-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.14602v1 The opioid epidemic continues to ravage communities worldwide, straining healthcare systems, disrupting families, and demanding urgent computational solutions. To combat this lethal opioid crisis, graph learning methods have emerged as a promising paradigm for modeling complex drug-related phenomena. However, a significant gap remains: there is no comprehensive benchmark for systematically evaluating these methods across real-world opioid crisis scenarios. To bridge this gap, we introduce OPBench, the first comprehensive opioid benchmark comprising five datasets across three critical application domains: opioid overdose detection from healthcare claims, illicit drug trafficking detection from digital platforms, and drug misuse prediction from dietary patterns. Specifically, OPBench incorporates diverse graph structures, including heterogeneous graphs and hypergraphs, to preserve the rich and complex relational information among drug-related data. To address data scarcity, we collaborate with domain experts and authoritative institutions to curate and annotate datasets while adhering to privacy and ethical guidelines. Furthermore, we establish a unified evaluation framework with standardized protocols, predefined data splits, and reproducible baselines to facilitate fair and systematic comparison among graph learning methods. Through extensive experiments, we analyze the strengths and limitations of existing graph learning methods, thereby providing actionable insights for future research in combating the opioid crisis. Our source code and datasets are available at https://github.com/Tianyi-Billy-Ma/OPBench. --- ### The Wikidata Query Logs Dataset Authors: Sebastian Walter, Hannah Bast Published: 2026-02-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.14594v2 We present the Wikidata Query Logs (WDQL) dataset, a dataset consisting of 335k question-query pairs over the Wikidata knowledge graph. It is over 11x larger than the largest existing Wikidata datasets of similar format without relying on template-generated queries. Instead, we construct it using real-world SPARQL queries sent to the Wikidata Query Service and generate questions for them. Since these log-based queries are anonymized, and therefore often do not produce results, a significant amount of effort is needed to convert them back into meaningful SPARQL queries. To achieve this, we present an agent-based method that iteratively de-anonymizes, cleans, and verifies queries against Wikidata while also generating corresponding natural-language questions. We demonstrate the benefit of this dataset for training question-answering methods. All WDQL assets, as well as the agent code, are publicly available via https://github.com/ad-freiburg/wikidata-query-logs under a permissive license. --- ### Automated Classification of Source Code Changes Based on Metrics Clustering in the Software Development Process Authors: Evgenii Kniazev Published: 2026-02-16 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.14591v1 This paper presents an automated method for classifying source code changes during the software development process based on clustering of change metrics. The method consists of two steps: clustering of metric vectors computed for each code change, followed by expert mapping of the resulting clusters to predefined change classes. The distribution of changes into clusters is performed automatically, while the mapping of clusters to classes is carried out by an expert. Automation of the distribution step substantially reduces the time required for code change review. The k-means algorithm with a cosine similarity measure between metric vectors is used for clustering. Eleven source code metrics are employed, covering lines of code, cyclomatic complexity, file counts, interface changes, and structural changes. The method was validated on five software systems, including two open-source projects (Subversion and NHibernate), and demonstrated classification purity of P_C = 0.75 +/- 0.05 and entropy of E_C = 0.37 +/- 0.06 at a significance level of 0.05. --- ### MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs Authors: Gabriel Roccabruna, Olha Khomyn, Giuseppe Riccardi Published: 2026-02-16 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.14589v1 AI agents need to plan to achieve complex goals that involve orchestrating perception, sub-goal decomposition, and execution. These plans consist of ordered steps structured according to a Temporal Execution Order (TEO, a directed acyclic graph that ensures each step executes only after its preconditions are satisfied. Existing research on foundational models' understanding of temporal execution is limited to automatically derived annotations, approximations of the TEO as a linear chain, or text-only inputs. To address this gap, we introduce MATEO (MultimodAl Temporal Execution Order), a benchmark designed to assess and improve the temporal reasoning abilities of Large Vision Language Models (LVLMs) required for real-world planning. We acquire a high-quality professional multimodal recipe corpus, authored through a standardized editorial process that decomposes instructions into discrete steps, each paired with corresponding images. We collect TEO annotations as graphs by designing and using a scalable crowdsourcing pipeline. Using MATEO, we evaluate six state-of-the-art LVLMs across model scales, varying language context, multimodal input structure, and fine-tuning strategies. --- ### Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow Authors: Minh Nguyen Published: 2026-02-16 Categories: cs.LG, cs.AI, math.OC, math.ST arXiv: https://arxiv.org/abs/2602.14587v1 Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in this setting: as time gaps shrink, the $Q$-function collapses to the value function $V$, eliminating action ranking. Existing continuous-time methods reintroduce action information via an advantage-rate function $q$. However, they enforce optimality through complicated martingale losses or orthogonality constraints, which are sensitive to the choice of test processes. These approaches entangle $V$ and $q$ into a large, complex optimization problem that is difficult to train reliably. To address these limitations, we propose a novel decoupled continuous-time actor-critic algorithm with alternating updates: $q$ is learned from diffusion generators on $V$, and $V$ is updated via a Hamiltonian-based value flow that remains informative under infinitesimal time steps, where standard max/softmax backups fail. Theoretically, we prove rigorous convergence via new probabilistic arguments, sidestepping the challenge that generator-based Hamiltonians lack Bellman-style contraction under the sup-norm. Empirically, our method outperforms prior continuous-time and leading discrete-time baselines across challenging continuous-control benchmarks and a real-world trading task, achieving 21% profit over a single quarter$-$nearly doubling the second-best method. --- ### YOLO26: A Comprehensive Architecture Overview and Key Improvements Authors: Priyanto Hidayatullah, Refdinal Tubagus Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14582v1 You Only Look Once (YOLO) has been the prominent model for computer vision in deep learning for a decade. This study explores the novel aspects of YOLO26, the most recent version in the YOLO series. The elimination of Distribution Focal Loss (DFL), implementation of End-to-End NMS-Free Inference, introduction of ProgLoss + Small-Target-Aware Label Assignment (STAL), and use of the MuSGD optimizer are the primary enhancements designed to improve inference speed, which is claimed to achieve a 43% boost in CPU mode. This is designed to allow YOLO26 to attain real-time performance on edge devices or those without GPUs. Additionally, YOLO26 offers improvements in many computer vision tasks, including instance segmentation, pose estimation, and oriented bounding box (OBB) decoding. We aim for this effort to provide more value than just consolidating information already included in the existing technical documentation. Therefore, we performed a rigorous architectural investigation into YOLO26, mostly using the source code available in its GitHub repository and its official documentation. The authentic and detailed operational mechanisms of YOLO26 are inside the source code, which is seldom extracted by others. The YOLO26 architectural diagram is shown as the outcome of the investigation. This study is, to our knowledge, the first one presenting the CNN-based YOLO26 architecture, which is the core of YOLO26. Our objective is to provide a precise architectural comprehension of YOLO26 for researchers and developers aspiring to enhance the YOLO model, ensuring it remains the leading deep learning model in computer vision. --- ### Replicable Constrained Bandits Authors: Matteo Bollini, Gianmarco Genalti, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi Published: 2026-02-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.14580v1 Algorithmic \emph{replicability} has recently been introduced to address the need for reproducible experiments in machine learning. A \emph{replicable online learning} algorithm is one that takes the same sequence of decisions across different executions in the same environment, with high probability. We initiate the study of algorithmic replicability in \emph{constrained} MAB problems, where a learner interacts with an unknown stochastic environment for $T$ rounds, seeking not only to maximize reward but also to satisfy multiple constraints. Our main result is that replicability can be achieved in constrained MABs. Specifically, we design replicable algorithms whose regret and constraint violation match those of non-replicable ones in terms of $T$. As a key step toward these guarantees, we develop the first replicable UCB-like algorithm for \emph{unconstrained} MABs, showing that algorithms that employ the optimism in-the-face-of-uncertainty principle can be replicable, a result that we believe is of independent interest. --- ### RNM-TD3: N:M Semi-structured Sparse Reinforcement Learning From Scratch Authors: Isam Vrce, Andreas Kassler, Gökçe Aydos Published: 2026-02-16 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2602.14578v1 Sparsity is a well-studied technique for compressing deep neural networks (DNNs) without compromising performance. In deep reinforcement learning (DRL), neural networks with up to 5% of their original weights can still be trained with minimal performance loss compared to their dense counterparts. However, most existing methods rely on unstructured fine-grained sparsity, which limits hardware acceleration opportunities due to irregular computation patterns. Structured coarse-grained sparsity enables hardware acceleration, yet typically degrades performance and increases pruning complexity. In this work, we present, to the best of our knowledge, the first study on N:M structured sparsity in RL, which balances compression, performance, and hardware efficiency. Our framework enforces row-wise N:M sparsity throughout training for all networks in off-policy RL (TD3), maintaining compatibility with accelerators that support N:M sparse matrix operations. Experiments on continuous-control benchmarks show that RNM-TD3, our N:M sparse agent, outperforms its dense counterpart at 50%-75% sparsity (e.g., 2:4 and 1:4), achieving up to a 14% increase in performance at 2:4 sparsity on the Ant environment. RNM-TD3 remains competitive even at 87.5% sparsity (1:8), while enabling potential training speedups. --- ### DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving Authors: Chenxu Dang, Sining Ang, Yongkang Li, Haochen Tian, Jie Wang, Guang Li, Hangjun Ye, Jie Ma, Long Chen, Yan Wang Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14577v1 Vision-Language-Action (VLA) models for autonomous driving increasingly adopt generative planners trained with imitation learning followed by reinforcement learning. Diffusion-based planners suffer from modality alignment difficulties, low training efficiency, and limited generalization. Token-based planners are plagued by cumulative causal errors and irreversible decoding. In summary, the two dominant paradigms exhibit complementary strengths and weaknesses. In this paper, we propose DriveFine, a masked diffusion VLA model that combines flexible decoding with self-correction capabilities. In particular, we design a novel plug-and-play block-MoE, which seamlessly injects a refinement expert on top of the generation expert. By enabling explicit expert selection during inference and gradient blocking during training, the two experts are fully decoupled, preserving the foundational capabilities and generic patterns of the pretrained weights, which highlights the flexibility and extensibility of the block-MoE design. Furthermore, we design a hybrid reinforcement learning strategy that encourages effective exploration of refinement expert while maintaining training stability. Extensive experiments on NAVSIM v1, v2, and Navhard benchmarks demonstrate that DriveFine exhibits strong efficacy and robustness. The code will be released at https://github.com/MSunDYY/DriveFine. --- ### DCTracks: An Open Dataset for Machine Learning-Based Drift Chamber Track Reconstruction Authors: Qian Liyan, Zhang Yao, Yuan Ye, Zhang Zhaoke, Fang Jin, Jiang Shimiao, Zhang Jin, Li Ke, Liu Beijiang, Xu Chenglin, Zhang Yifan, Jia Xiaoqian et al. Published: 2026-02-16 Categories: cs.LG, hep-ex arXiv: https://arxiv.org/abs/2602.14571v1 We introduce a Monte Carlo (MC) dataset of single- and two-track drift chamber events to advance Machine Learning (ML)-based track reconstruction. To enable standardized and comparable evaluation, we define track reconstruction specific metrics and report results for traditional track reconstruction algorithms and a Graph Neural Networks (GNNs) method, facilitating rigorous, reproducible validation for future research. --- ### Assessing Large Language Models for Medical QA: Zero-Shot and LLM-as-a-Judge Evaluation Authors: Shefayat E Shams Adib, Ahmed Alfey Sani, Ekramul Alam Esham, Ajwad Abrar, Tareque Mohmud Chowdhury Published: 2026-02-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.14564v1 Recently, Large Language Models (LLMs) have gained significant traction in medical domain, especially in developing a QA systems to Medical QA systems for enhancing access to healthcare in low-resourced settings. This paper compares five LLMs deployed between April 2024 and August 2025 for medical QA, using the iCliniq dataset, containing 38,000 medical questions and answers of diverse specialties. Our models include Llama-3-8B-Instruct, Llama 3.2 3B, Llama 3.3 70B Instruct, Llama-4-Maverick-17B-128E-Instruct, and GPT-5-mini. We are using a zero-shot evaluation methodology and using BLEU and ROUGE metrics to evaluate performance without specialized fine-tuning. Our results show that larger models like Llama 3.3 70B Instruct outperform smaller models, consistent with observed scaling benefits in clinical tasks. It is notable that, Llama-4-Maverick-17B exhibited more competitive results, thus highlighting evasion efficiency trade-offs relevant for practical deployment. These findings align with advancements in LLM capabilities toward professional-level medical reasoning and reflect the increasing feasibility of LLM-supported QA systems in the real clinical environments. This benchmark aims to serve as a standardized setting for future study to minimize model size, computational resources and to maximize clinical utility in medical NLP applications. --- ### Fluid-Agent Reinforcement Learning Authors: Shishir Sharma, Doina Precup, Theodore J. Perkins Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.14559v1 The primary focus of multi-agent reinforcement learning (MARL) has been to study interactions among a fixed number of agents embedded in an environment. However, in the real world, the number of agents is neither fixed nor known a priori. Moreover, an agent can decide to create other agents (for example, a cell may divide, or a company may spin off a division). In this paper, we propose a framework that allows agents to create other agents; we call this a fluid-agent environment. We present game-theoretic solution concepts for fluid-agent games and empirically evaluate the performance of several MARL algorithms within this framework. Our experiments include fluid variants of established benchmarks such as Predator-Prey and Level-Based Foraging, where agents can dynamically spawn, as well as a new environment we introduce that highlights how fluidity can unlock novel solution strategies beyond those observed in fixed-population settings. We demonstrate that this framework yields agent teams that adjust their size dynamically to match environmental demands. --- ### Governing AI Forgetting: Auditing for Machine Unlearning Compliance Authors: Qinqi Lin, Ningning Ding, Lingjie Duan, Jianwei Huang Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2602.14553v1 Despite legal mandates for the right to be forgotten, AI operators routinely fail to comply with data deletion requests. While machine unlearning (MU) provides a technical solution to remove personal data's influence from trained models, ensuring compliance remains challenging due to the fundamental gap between MU's technical feasibility and regulatory implementation. In this paper, we introduce the first economic framework for auditing MU compliance, by integrating certified unlearning theory with regulatory enforcement. We first characterize MU's inherent verification uncertainty using a hypothesis-testing interpretation of certified unlearning to derive the auditor's detection capability, and then propose a game-theoretic model to capture the strategic interactions between the auditor and the operator. A key technical challenge arises from MU-specific nonlinearities inherent in the model utility and the detection probability, which create complex strategic couplings that traditional auditing frameworks do not address and that also preclude closed-form solutions. We address this by transforming the complex bivariate nonlinear fixed-point problem into a tractable univariate auxiliary problem, enabling us to decouple the system and establish the equilibrium existence, uniqueness, and structural properties without relying on explicit solutions. Counterintuitively, our analysis reveals that the auditor can optimally reduce the inspection intensity as deletion requests increase, since the operator's weakened unlearning makes non-compliance easier to detect. This is consistent with recent auditing reductions in China despite growing deletion requests. Moreover, we prove that although undisclosed auditing offers informational advantages for the auditor, it paradoxically reduces the regulatory cost-effectiveness relative to disclosed auditing. --- ### OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance Authors: Zhaotong Yang, Yong Du, Shengfeng He, Yuhui Li, Xinzhe Li, Yangyang Xu, Junyu Dong, Jian Yang Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14552v2 Image-based Virtual Try-On (VTON) concerns the synthesis of realistic person imagery through garment re-rendering under human pose and body constraints. In practice, however, existing approaches are typically optimized for specific data conditions, making their deployment reliant on retraining and limiting their generalization as a unified solution. We present OmniVTON++, a training-free VTON framework designed for universal applicability. It addresses the intertwined challenges of garment alignment, human structural coherence, and boundary continuity by coordinating Structured Garment Morphing for correspondence-driven garment adaptation, Principal Pose Guidance for step-wise structural regulation during diffusion sampling, and Continuous Boundary Stitching for boundary-aware refinement, forming a cohesive pipeline without task-specific retraining. Experimental results demonstrate that OmniVTON++ achieves state-of-the-art performance across diverse generalization settings, including cross-dataset and cross-garment-type evaluations, while reliably operating across scenarios and diffusion backbones within a single formulation. In addition to single-garment, single-human cases, the framework supports multi-garment, multi-human, and anime character virtual try-on, expanding the scope of virtual try-on applications. The code is available at https://github.com/Jerome-Young/OmniVTON-PlusPlus. --- ### Truly Adapting to Adversarial Constraints in Constrained MABs Authors: Francesco Emanuele Stradi, Kalana Kalupahana, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti Published: 2026-02-16 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.14543v1 We study the constrained variant of the \emph{multi-armed bandit} (MAB) problem, in which the learner aims not only at minimizing the total loss incurred during the learning dynamic, but also at controlling the violation of multiple \emph{unknown} constraints, under both \emph{full} and \emph{bandit feedback}. We consider a non-stationary environment that subsumes both stochastic and adversarial models and where, at each round, both losses and constraints are drawn from distributions that may change arbitrarily over time. In such a setting, it is provably not possible to guarantee both sublinear regret and sublinear violation. Accordingly, prior work has mainly focused either on settings with stochastic constraints or on relaxing the benchmark with fully adversarial constraints (\emph{e.g.}, via competitive ratios with respect to the optimum). We provide the first algorithms that achieve optimal rates of regret and \emph{positive} constraint violation when the constraints are stochastic while the losses may vary arbitrarily, and that simultaneously yield guarantees that degrade smoothly with the degree of adversariality of the constraints. Specifically, under \emph{full feedback} we propose an algorithm attaining $\widetilde{\mathcal{O}}(\sqrt{T}+C)$ regret and $\widetilde{\mathcal{O}}(\sqrt{T}+C)$ {positive} violation, where $C$ quantifies the amount of non-stationarity in the constraints. We then show how to extend these guarantees when only bandit feedback is available for the losses. Finally, when \emph{bandit feedback} is available for the constraints, we design an algorithm achieving $\widetilde{\mathcal{O}}(\sqrt{T}+C)$ {positive} violation and $\widetilde{\mathcal{O}}(\sqrt{T}+C\sqrt{T})$ regret. --- ### Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets Authors: Yuchen Yang, Wenze Lin, Enhao Huang, Zhixuan Chu, Hongbin Zhou, Lan Tao, Yiming Li, Zhan Qin, Kui Ren Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14536v4 Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training on corresponding datasets. However, a fundamental discrepancy exists between current fine-tuning datasets and the token-level optimization mechanism of LLMs: most datasets are designed at the sentence-level, which introduces token-level noise, causing negative influence to final performance. In this paper, we propose XTF, an explainable token-level noise filtering framework. XTF decomposes the complex and subtle contributions of token-level data to the fine-tuning process into three distinct and explicit attributes (reasoning importance, knowledge novelty, and task relevance), which can be assessed using scoring methods, and then masks the gradients of selected noisy tokens accordingly to optimize the performance of fine-tuned LLMs. We conduct extensive experiments on three representative downstream tasks (math, code and medicine) across 7 mainstream LLMs. The results demonstrate that XTF can significantly improve downstream performance by up to 13.7% compared to regular fine-tuning. Our work highlights the importance of token-level dataset optimization, and demonstrates the potential of strategies based on attribute decomposition for explaining complex training mechanisms. --- ### Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets Authors: Yuchen Yang, Wenze Lin, Enhao Huang, Zhixuan Chu, Hongbin Zhou, Lan Tao, Yiming Li, Zhan Qin, Kui Ren Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14536v3 Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training on corresponding datasets. However, a fundamental discrepancy exists between current fine-tuning datasets and the token-level optimization mechanism of LLMs: most datasets are designed at the sentence-level, which introduces token-level noise, causing negative influence to final performance. In this paper, we propose XTF, an explainable token-level noise filtering framework. XTF decomposes the complex and subtle contributions of token-level data to the fine-tuning process into three distinct and explicit attributes (reasoning importance, knowledge novelty, and task relevance), which can be assessed using scoring methods, and then masks the gradients of selected noisy tokens accordingly to optimize the performance of fine-tuned LLMs. We conduct extensive experiments on three representative downstream tasks (math, code and medicine) across 7 mainstream LLMs. The results demonstrate that XTF can significantly improve downstream performance by up to 13.7% compared to regular fine-tuning. Our work highlights the importance of token-level dataset optimization, and demonstrates the potential of strategies based on attribute decomposition for explaining complex training mechanisms. --- ### MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation Authors: Hongpeng Wang, Zeyu Zhang, Wenhao Li, Hao Tang Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14534v1 Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and reinforcement learning with verifiable rewards. Our task-specific reward design combines semantic alignment and reasoning coherence for understanding with physical plausibility and text-motion consistency for generation, improving both logical reasoning and perceptual realism. To further enhance inference, we introduce Chain-of-Motion (CoM), a test-time reasoning method that enables step-by-step planning and reflection. We also construct two large-scale CoT datasets, MoUnd-CoT-140K and MoGen-CoT-140K, to align motion sequences with reasoning traces and action descriptions. Experiments on HumanML3D and KIT-ML show that MoRL achieves significant gains over state-of-the-art baselines. Code: https://github.com/AIGeeksGroup/MoRL. Website: https://aigeeksgroup.github.io/MoRL. --- ### Disentangling Deception and Hallucination Failures in LLMs Authors: Haolang Lu, Hongrui Peng, WeiYe Fu, Guoshun Nan, Xinye Cao, Xingrui Li, Hongcan Guo, Kun Wang Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14529v1 Failures in large language models (LLMs) are often analyzed from a behavioral perspective, where incorrect outputs in factual question answering are commonly associated with missing knowledge. In this work, focusing on entity-based factual queries, we suggest that such a view may conflate different failure mechanisms, and propose an internal, mechanism-oriented perspective that separates Knowledge Existence from Behavior Expression. Under this formulation, hallucination and deception correspond to two qualitatively different failure modes that may appear similar at the output level but differ in their underlying mechanisms. To study this distinction, we construct a controlled environment for entity-centric factual questions in which knowledge is preserved while behavioral expression is selectively altered, enabling systematic analysis of four behavioral cases. We analyze these failure modes through representation separability, sparse interpretability, and inference-time activation steering. --- ### TWISTED-RL: Hierarchical Skilled Agents for Knot-Tying without Human Demonstrations Authors: Guy Freund, Tom Jurgenson, Matan Sudry, Erez Karpas Published: 2026-02-16 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.14526v1 Robotic knot-tying represents a fundamental challenge in robotics due to the complex interactions between deformable objects and strict topological constraints. We present TWISTED-RL, a framework that improves upon the previous state-of-the-art in demonstration-free knot-tying (TWISTED), which smartly decomposed a single knot-tying problem into manageable subproblems, each addressed by a specialized agent. Our approach replaces TWISTED's single-step inverse model that was learned via supervised learning with a multi-step Reinforcement Learning policy conditioned on abstract topological actions rather than goal states. This change allows more delicate topological state transitions while avoiding costly and ineffective data collection protocols, thus enabling better generalization across diverse knot configurations. Experimental results demonstrate that TWISTED-RL manages to solve previously unattainable knots of higher complexity, including commonly used knots such as the Figure-8 and the Overhand. Furthermore, the increase in success rates and drop in planning time establishes TWISTED-RL as the new state-of-the-art in robotic knot-tying without human demonstrations. --- ### Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation Authors: Jindong Zhao, Yuan Gao, Yang Xia, Sheng Nie, Jun Yue, Weiwei Sun, Shaobo Xia Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14525v1 Domain-generalized LiDAR semantic segmentation (LSS) seeks to train models on source-domain point clouds that generalize reliably to multiple unseen target domains, which is essential for real-world LiDAR applications. However, existing approaches assume similar acquisition views (e.g., vehicle-mounted) and struggle in cross-view scenarios, where observations differ substantially due to viewpoint-dependent structural incompleteness and non-uniform point density. Accordingly, we formulate cross-view domain generalization for LiDAR semantic segmentation and propose a novel framework, termed CVGC (Cross-View Geometric Consistency). Specifically, we introduce a cross-view geometric augmentation module that models viewpoint-induced variations in visibility and sampling density, generating multiple cross-view observations of the same scene. Subsequently, a geometric consistency module enforces consistent semantic and occupancy predictions across geometrically augmented point clouds of the same scene. Extensive experiments on six public LiDAR datasets establish the first systematic evaluation of cross-view domain generalization for LiDAR semantic segmentation, demonstrating that CVGC consistently outperforms state-of-the-art methods when generalizing from a single source domain to multiple target domains with heterogeneous acquisition viewpoints. The source code will be publicly available at https://github.com/KintomZi/CVGC-DG --- ### Error Patterns in Historical OCR: A Comparative Analysis of TrOCR and a Vision-Language Model Authors: Ari Vesalainen, Eetu Mäkelä, Laura Ruotsalainen, Mikko Tolonen Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14524v1 Optical Character Recognition (OCR) of eighteenth-century printed texts remains challenging due to degraded print quality, archaic glyphs, and non-standardized orthography. Although transformer-based OCR systems and Vision-Language Models (VLMs) achieve strong aggregate accuracy, metrics such as Character Error Rate (CER) and Word Error Rate (WER) provide limited insight into their reliability for scholarly use. We compare a dedicated OCR transformer (TrOCR) and a general-purpose Vision-Language Model (Qwen) on line-level historical English texts using length-weighted accuracy metrics and hypothesis driven error analysis. While Qwen achieves lower CER/WER and greater robustness to degraded input, it exhibits selective linguistic regularization and orthographic normalization that may silently alter historically meaningful forms. TrOCR preserves orthographic fidelity more consistently but is more prone to cascading error propagation. Our findings show that architectural inductive biases shape OCR error structure in systematic ways. Models with similar aggregate accuracy can differ substantially in error locality, detectability, and downstream scholarly risk, underscoring the need for architecture-aware evaluation in historical digitization workflows. --- ### Architectural Insights for Post-Tornado Damage Recognition Authors: Robinson Umeike, Thang Dao, Shane Crawford, John van de Lindt, Blythe Johnston, Wanting, Wang, Trung Do, Ajibola Mofikoya, Sarbesh Banjara, Cuong Pham Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14523v1 Rapid and accurate building damage assessment in the immediate aftermath of tornadoes is critical for coordinating life-saving search and rescue operations, optimizing emergency resource allocation, and accelerating community recovery. However, current automated methods struggle with the unique visual complexity of tornado-induced wreckage, primarily due to severe domain shift from standard pre-training datasets and extreme class imbalance in real-world disaster data. To address these challenges, we introduce a systematic experimental framework evaluating 79 open-source deep learning models, encompassing both Convolutional Neural Networks (CNNs) and Vision Transformers, across over 2,300 controlled experiments on our newly curated Quad-State Tornado Damage (QSTD) benchmark dataset. Our findings reveal that achieving operational-grade performance hinges on a complex interaction between architecture and optimization, rather than architectural selection alone. Most strikingly, we demonstrate that optimizer choice can be more consequential than architecture: switching from Adam to SGD provided dramatic F1 gains of +25 to +38 points for Vision Transformer and Swin Transformer families, fundamentally reversing their ranking from bottom-tier to competitive with top-performing CNNs. Furthermore, a low learning rate of 1x10^(-4) proved universally critical, boosting average F1 performance by +10.2 points across all architectures. Our champion model, ConvNeXt-Base trained with these optimized settings, demonstrated strong cross-event generalization on the held-out Tuscaloosa-Moore Tornado Damage (TMTD) dataset, achieving 46.4% Macro F1 (+34.6 points over baseline) and retaining 85.5% Ordinal Top-1 Accuracy despite temporal and sensor domain shifts. --- ### Accelerating Posterior Inference from Pulsar Light Curves via Learned Latent Representations and Local Simulator-Guided Optimization Authors: Farhana Taiyebah, Abu Bucker Siddik, Indronil Bhattacharjee, Diane Oyen, Soumi De, Greg Olmschenk, Constantinos Kalapotharakos Published: 2026-02-16 Categories: stat.ML, astro-ph.HE arXiv: https://arxiv.org/abs/2602.14520v1 Posterior inference from pulsar observations in the form of light curves is commonly performed using Markov chain Monte Carlo methods, which are accurate but computationally expensive. We introduce a framework that accelerates posterior inference while maintaining accuracy by combining learned latent representations with local simulator-guided optimization. A masked U-Net is first pretrained to reconstruct complete light curves from partial observations and to produce informative latent embeddings. Given a query light curve, we identify similar simulated light curves from the simulation bank by measuring similarity in the learned embedding space produced by pretrained U-Net encoder, yielding an initial empirical approximation to the posterior over parameters. This initialization is then refined using a local optimization procedure using hill-climbing updates, guided by a forward simulator, progressively shifting the empirical posterior toward higher-likelihood parameter regions. Experiments on the observed light curve of PSR J0030+0451, captured by NASA's Neutron Star Interior Composition Explorer (NICER), show that our method closely matches posterior estimates obtained using traditional MCMC methods while achieving 120 times reduction in inference time (from 24 hours to 12 minutes), demonstrating the effectiveness of learned representations and simulator-guided optimization for accelerated posterior inference. --- ### DeepMTL2R: A Library for Deep Multi-task Learning to Rank Authors: Chaosheng Dong, Peiyao Xiao, Yijia Wang, Kaiyi Ji Published: 2026-02-16 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2602.14519v1 This paper presents DeepMTL2R, an open-source deep learning framework for Multi-task Learning to Rank (MTL2R), where multiple relevance criteria must be optimized simultaneously. DeepMTL2R integrates heterogeneous relevance signals into a unified, context-aware model by leveraging the self-attention mechanism of transformer architectures, enabling effective learning across diverse and potentially conflicting objectives. The framework includes 21 state-of-the-art multi-task learning algorithms and supports multi-objective optimization to identify Pareto-optimal ranking models. By capturing complex dependencies and long-range interactions among items and labels, DeepMTL2R provides a scalable and expressive solution for modern ranking systems and facilitates controlled comparisons across MTL strategies. We demonstrate its effectiveness on a publicly available dataset, report competitive performance, and visualize the resulting trade-offs among objectives. DeepMTL2R is available at \href{https://github.com/amazon-science/DeepMTL2R}{https://github.com/amazon-science/DeepMTL2R}. --- ### Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning Authors: Jing Tang, Kun Wang, Haolang Lu, Hongjin Chen, KaiTao Chen, Zhongxiang Sun, Qiankun Li, Lingjuan Lyu, Guoshun Nan, Zhigang Zeng Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14518v1 Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures under a unified notion of knowledge conflict, distinguishing input-level objective conflict from process-level effective conflict. Through probing internal representations, we reveal that: (I) Linear Separability: different conflict types are explicitly encoded as linearly separable features rather than entangled; (II) Depth Localization: conflict signals concentrate in mid-to-late layers, indicating a distinct processing stage for conflict encoding; (III) Hierarchical Consistency: aggregating noisy token-level signals along trajectories robustly recovers input-level conflict types; and (IV) Directional Asymmetry: reinforcing the model's implicit source preference under conflict is far easier than enforcing the opposite source. Our findings provide a mechanism-level view of multimodal reasoning under knowledge conflict and enable principled diagnosis and control of long-CoT failures. --- ### Large Language Models for Math Education in Low-Resource Languages: A Study in Sinhala and Tamil Authors: Sukumar Kishanthan, Kumar Thushalika, Buddhi Jayasekara, Asela Hevapathige Published: 2026-02-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.14517v3 Large language models (LLMs) have achieved strong results in mathematical reasoning, and are increasingly deployed as tutoring and learning support tools in educational settings. However, their reliability for students working in non-English languages, especially low-resource languages, remains poorly understood. We examine this gap by evaluating mathematical reasoning in Sinhala and Tamil -- two languages widely used in South Asian schools but underrepresented in artificial intelligence (AI) research. Using a taxonomy of six math problem types, from basic arithmetic to complex unit conflict and optimization problems, we evaluate four prominent large language models. To avoid translation artifacts that confound language ability with translation quality, we construct a parallel dataset in which each problem is independently authored in Sinhala and Tamil by native speakers, and in English by fluent speakers, all with strong mathematical backgrounds. Our analysis demonstrates that while basic arithmetic reasoning transfers robustly across languages, complex reasoning tasks show significant degradation in Tamil and Sinhala. The pattern of failures varies by model and problem type, suggesting that strong performance in English does not guarantee reliable performance across languages. These findings have direct implications for the deployment of AI tools in multilingual classrooms, and highlight the need for language-specific evaluation before adopting large language models as math tutoring aids in non-English educational contexts. --- ### Efficient Text-Guided Convolutional Adapter for the Diffusion Model Authors: Aryan Das, Koushik Biswas, Swalpa Kumar Roy, Badri Narayana Patro, Vinay Kumar Verma Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14514v2 We introduce the Nexus Adapters, novel text-guided efficient adapters to the diffusion-based framework for the Structure Preserving Conditional Generation (SPCG). Recently, structure-preserving methods have achieved promising results in conditional image generation by using a base model for prompt conditioning and an adapter for structure input, such as sketches or depth maps. These approaches are highly inefficient and sometimes require equal parameters in the adapter compared to the base architecture. It is not always possible to train the model since the diffusion model is itself costly, and doubling the parameter is highly inefficient. In these approaches, the adapter is not aware of the input prompt; therefore, it is optimal only for the structural input but not for the input prompt. To overcome the above challenges, we proposed two efficient adapters, Nexus Prime and Slim, which are guided by prompts and structural inputs. Each Nexus Block incorporates cross-attention mechanisms to enable rich multimodal conditioning. Therefore, the proposed adapter has a better understanding of the input prompt while preserving the structure. We conducted extensive experiments on the proposed models and demonstrated that the Nexus Prime adapter significantly enhances performance, requiring only 8M additional parameters compared to the baseline, T2I-Adapter. Furthermore, we also introduced a lightweight Nexus Slim adapter with 18M fewer parameters than the T2I-Adapter, which still achieved state-of-the-art results. Code: https://github.com/arya-domain/Nexus-Adapters --- ### MedVAR: Towards Scalable and Efficient Medical Image Generation via Next-scale Autoregressive Prediction Authors: Zhicheng He, Yunpeng Zhao, Junde Wu, Ziwei Niu, Zijun Li, Bohan Li, Lanfen Lin, Yueming Jin Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14512v2 Medical image generation is pivotal in applications like data augmentation for low-resource clinical tasks and privacy-preserving data sharing. However, developing a scalable generative backbone for medical imaging requires architectural efficiency, sufficient multi-organ data, and principled evaluation, yet current approaches leave these aspects unresolved. Therefore, we introduce MedVAR, the first autoregressive-based foundation model that adopts the next-scale prediction paradigm to enable fast and scale-up-friendly medical image synthesis. MedVAR generates images in a coarse-to-fine manner and produces structured multi-scale representations suitable for downstream use. To support hierarchical generation, we curate a harmonized dataset of around 440,000 CT and MRI images spanning six anatomical regions. Comprehensive experiments across fidelity, diversity, and scalability show that MedVAR achieves state-of-the-art generative performance and offers a promising architectural direction for future medical generative foundation models. --- ### MacNet: An End-to-End Manifold-Constrained Adaptive Clustering Network for Interpretable Whole Slide Image Classification Authors: Mingrui Ma, Chentao Li, Pan Huang, Jing Qin Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14509v1 Whole slide images (WSIs) are the gold standard for pathological diagnosis and sub-typing. Current main-stream two-step frameworks employ offline feature encoders trained without domain-specific knowledge. Among them, attention-based multiple instance learning (MIL) methods are outcome-oriented and offer limited interpretability. Clustering-based approaches can provide explainable decision-making process but suffer from high dimension features and semantically ambiguous centroids. To this end, we propose an end-to-end MIL framework that integrates Grassmann re-embedding and manifold adaptive clustering, where the manifold geometric structure facilitates robust clustering results. Furthermore, we design a prior knowledge guiding proxy instance labeling and aggregation strategy to approximate patch labels and focus on pathologically relevant tumor regions. Experiments on multicentre WSI datasets demonstrate that: 1) our cluster-incorporated model achieves superior performance in both grading accuracy and interpretability; 2) end-to-end learning refines better feature representations and it requires acceptable computation resources. --- ### Covariance-Aware Transformers for Quadratic Programming and Decision Making Authors: Kutay Tire, Yufan Zhang, Ege Onur Taga, Samet Oymak Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.14506v1 We explore the use of transformers for solving quadratic programs and how this capability benefits decision-making problems that involve covariance matrices. We first show that the linear attention mechanism can provably solve unconstrained QPs by tokenizing the matrix variables (e.g.~$A$ of the objective $\frac{1}{2}x^\top Ax+b^\top x$) row-by-row and emulating gradient descent iterations. Furthermore, by incorporating MLPs, a transformer block can solve (i) $\ell_1$-penalized QPs by emulating iterative soft-thresholding and (ii) $\ell_1$-constrained QPs when equipped with an additional feedback loop. Our theory motivates us to introduce Time2Decide: a generic method that enhances a time series foundation model (TSFM) by explicitly feeding the covariance matrix between the variates. We empirically find that Time2Decide uniformly outperforms the base TSFM model for the classical portfolio optimization problem that admits an $\ell_1$-constrained QP formulation. Remarkably, Time2Decide also outperforms the classical "Predict-then-Optimize (PtO)" procedure, where we first forecast the returns and then explicitly solve a constrained QP, in suitable settings. Our results demonstrate that transformers benefit from explicit use of second-order statistics, and this can enable them to effectively solve complex decision-making problems, like portfolio construction, in one forward pass. --- ### Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC Authors: Dennis Gross Published: 2026-02-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.14505v1 Safe and interpretable sequential decision-making is critical in healthcare, yet reinforcement learning (RL) policies for sepsis treatment optimization remain opaque and difficult to verify. Standard probabilistic model checkers operate on the full state space, which becomes infeasible for larger MDPs, and cannot explain why a learned policy makes particular decisions. COOL-MC wraps the model checker Storm but adds three key capabilities: it constructs only the reachable state space induced by a trained policy, yielding a smaller discrete-time Markov chain amenable to verification even when full-MDP analysis is intractable; it automatically labels states with clinically meaningful atomic propositions; and it integrates explainability methods with probabilistic computation tree logic (PCTL) queries to reveal which features drive decisions across treatment trajectories. We demonstrate COOL-MC's capabilities on the ICU-Sepsis MDP, a benchmark derived from approximately 17,000 sepsis patient records, which serves as a case study for applying COOL-MC to the formal analysis of sepsis treatment policies. Our analysis establishes hard bounds via full MDP verification, trains a safe RL policy that achieves optimal survival probability, and analyzes its behavior via PCTL verification and explainability on the induced DTMC. This reveals, for instance, that our trained policy relies predominantly on prior dosing history rather than the patient's evolving condition, a weakness that is invisible to standard evaluation but is exposed by COOL-MC's integration of formal verification and explainability. Our results illustrate how COOL-MC could serve as a tool for clinicians to investigate and debug sepsis treatment policies before deployment. --- ### Bounding Probabilities of Causation with Partial Causal Diagrams Authors: Yuxuan Xie, Ang Li Published: 2026-02-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.14503v1 Probabilities of causation are fundamental to individual-level explanation and decision making, yet they are inherently counterfactual and not point-identifiable from data in general. Existing bounds either disregard available covariates, require complete causal graphs, or rely on restrictive binary settings, limiting their practical use. In real-world applications, causal information is often partial but nontrivial. This paper proposes a general framework for bounding probabilities of causation using partial causal information. We show how the available structural or statistical information can be systematically incorporated as constraints in a optimization programming formulation, yielding tighter and formally valid bounds without full identifiability. This approach extends the applicability of probabilities of causation to realistic settings where causal knowledge is incomplete but informative. --- ### Prototype Instance-semantic Disentanglement with Low-rank Regularized Subspace Clustering for WSIs Explainable Recognition Authors: Chentao Li, Pan Huang Published: 2026-02-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.14501v1 The tumor region plays a key role in pathological diagnosis. Tumor tissues are highly similar to precancerous lesions and non tumor instances often greatly exceed tumor instances in whole slide images (WSIs). These issues cause instance-semantic entanglement in multi-instance learning frameworks, degrading both model representation capability and interpretability. To address this, we propose an end-to-end prototype instance semantic disentanglement framework with low-rank regularized subspace clustering, PID-LRSC, in two aspects. First, we use secondary instance subspace learning to construct low-rank regularized subspace clustering (LRSC), addressing instance entanglement caused by an excessive proportion of non tumor instances. Second, we employ enhanced contrastive learning to design prototype instance semantic disentanglement (PID), resolving semantic entanglement caused by the high similarity between tumor and precancerous tissues. We conduct extensive experiments on multicentre pathology datasets, implying that PID-LRSC outperforms other SOTA methods. Overall, PID-LRSC provides clearer instance semantics during decision-making and significantly enhances the reliability of auxiliary diagnostic outcomes. --- ### Uncertainty-Aware Vision-Language Segmentation for Medical Imaging Authors: Aryan Das, Tanishq Rachamalla, Koushik Biswas, Swalpa Kumar Roy, Vinay Kumar Verma Published: 2026-02-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.14498v2 We introduce a novel uncertainty-aware multimodal segmentation framework that leverages both radiological images and associated clinical text for precise medical diagnosis. We propose a Modality Decoding Attention Block (MoDAB) with a lightweight State Space Mixer (SSMix) to enable efficient cross-modal fusion and long-range dependency modelling. To guide learning under ambiguity, we propose the Spectral-Entropic Uncertainty (SEU) Loss, which jointly captures spatial overlap, spectral consistency, and predictive uncertainty in a unified objective. In complex clinical circumstances with poor image quality, this formulation improves model reliability. Extensive experiments on various publicly available medical datasets, QATA-COVID19, MosMed++, and Kvasir-SEG, demonstrate that our method achieves superior segmentation performance while being significantly more computationally efficient than existing State-of-the-Art (SoTA) approaches. Our results highlight the importance of incorporating uncertainty modelling and structured modality alignment in vision-language medical segmentation tasks. Code: https://github.com/arya-domain/UA-VLS --- ### Divine Benevolence is an $x^2$: GLUs scale asymptotically faster than MLPs Authors: Alejandro Francisco Queiruga Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.14495v2 Scaling laws can be understood from ground-up numerical analysis, where traditional function approximation theory can explain shifts in model architecture choices. GLU variants now dominate frontier LLMs and similar outer-product architectures are prevalent in ranking models. The success of these architectures has mostly been left as an empirical discovery. In this paper, we apply the tools of numerical analysis to expose a key factor: these models have an $x^2$ which enables \emph{asymptotically} faster scaling than MLPs. GLUs have piecewise quadratic functional forms that are sufficient to exhibit quadratic order of approximation. Our key contribution is to demonstrate that the $L(P)$ scaling slope is $L(P)\propto P^{-3}$ for GLUs but only $L(P)=P^{-2}$ for MLPs on function reconstruction problems. We provide a parameter construction and empirical verification of these slopes for 1D function approximation. From the first principles we discover, we make one stride and propose the ``Gated Quadratic Unit'' which has an even steeper $L(P)$ slope than the GLU and MLP. This opens the possibility of architecture design from first principles numerical theory to unlock superior scaling in large models. Replication code is available at https://github.com/afqueiruga/divine_scaling. --- ### Gaussian Mesh Renderer for Lightweight Differentiable Rendering Authors: Xinpeng Liu, Fumio Okura Published: 2026-02-16 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.14493v1 3D Gaussian Splatting (3DGS) has enabled high-fidelity virtualization with fast rendering and optimization for novel view synthesis. On the other hand, triangle mesh models still remain a popular choice for surface reconstruction but suffer from slow or heavy optimization in traditional mesh-based differentiable renderers. To address this problem, we propose a new lightweight differentiable mesh renderer leveraging the efficient rasterization process of 3DGS, named Gaussian Mesh Renderer (GMR), which tightly integrates the Gaussian and mesh representations. Each Gaussian primitive is analytically derived from the corresponding mesh triangle, preserving structural fidelity and enabling the gradient flow. Compared to the traditional mesh renderers, our method achieves smoother gradients, which especially contributes to better optimization using smaller batch sizes with limited memory. Our implementation is available in the public GitHub repository at https://github.com/huntorochi/Gaussian-Mesh-Renderer. --- ### Query as Anchor: Scenario-Adaptive User Representation via Large Language Model Authors: Jiahao Yuan, Yike Xu, Jinyong Wen, Baokun Wang, Ziyi Gao, Xiaotong Lin, Yun Liu, Xing Fu, Yu Cheng, Yongchao Liu, Weiqiang Wang, Zhongle Xie Published: 2026-02-16 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.14492v2 Industrial-scale user representation learning requires balancing robust universality with acute task-sensitivity. However, existing paradigms primarily yield static, task-agnostic embeddings that struggle to reconcile the divergent requirements of downstream scenarios within unified vector spaces. Furthermore, heterogeneous multi-source data introduces inherent noise and modality conflicts, degrading representation. We propose Query-as-Anchor, a framework shifting user modeling from static encoding to dynamic, query-aware synthesis. To empower Large Language Models (LLMs) with deep user understanding, we first construct UserU, an industrial-scale pre-training dataset that aligns multi-modal behavioral sequences with user understanding semantics, and our Q-Anchor Embedding architecture integrates hierarchical coarse-to-fine encoders into dual-tower LLMs via joint contrastive-autoregressive optimization for query-aware user representation. To bridge the gap between general pre-training and specialized business logic, we further introduce Cluster-based Soft Prompt Tuning to enforce discriminative latent structures, effectively aligning model attention with scenario-specific modalities. For deployment, anchoring queries at sequence termini enables KV-cache-accelerated inference with negligible incremental latency. Evaluations on 10 Alipay industrial benchmarks show consistent SOTA performance, strong scalability, and efficient deployment. Large-scale online A/B testing in Alipay's production system across two real-world scenarios further validates its practical effectiveness. Our code is prepared for public release and will be available at: https://github.com/JhCircle/Q-Anchor. --- ### Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts Authors: Buze Zhang, Jinkai Tao, Zilang Zeng, Neil He, Ali Maatouk, Menglin Yang, Rex Ying Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.CL, cs.NE arXiv: https://arxiv.org/abs/2602.14490v1 Large Language Models (LLMs) have achieved remarkable progress, with Parameter-Efficient Fine-Tuning (PEFT) emerging as a key technique for downstream task adaptation. However, existing PEFT methods mainly operate in Euclidean space, fundamentally limiting their capacity to capture complex geometric structures inherent in language data. While alternative geometric spaces, like hyperbolic geometries for hierarchical data and spherical manifolds for circular patterns, offer theoretical advantages, forcing representations into a single manifold type ultimately limits expressiveness, even when curvature parameters are learnable. To address this, we propose Mixture of Space (MoS), a unified framework that leverages multiple geometric spaces simultaneously to learn richer, curvature-aware representations. Building on this scheme, we develop MoSLoRA, which extends Low-Rank Adaptation (LoRA) with heterogeneous geometric experts, enabling models to dynamically select or combine appropriate geometric spaces based on input context. Furthermore, to address the computational overhead of frequent manifold switching, we develop a lightweight routing mechanism. Moreover, we provide empirical insights into how curvature optimization impacts training stability and model performance. Our experiments across diverse benchmarks demonstrate that MoSLoRA consistently outperforms strong baselines, achieving up to 5.6% improvement on MATH500 and 15.9% on MAWPS. --- ### BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR Authors: Md. Najib Hasan, Mst. Jannatun Ferdous Rain, Fyad Mohammed, Nazmul Siddique Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14488v3 IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive and difficult to scale, while using large language models (LLMs) as automated annotators introduces concerns about label reliability, bias, and evaluation validity. This work presents a Bangla IR dataset constructed using a BETA-labeling framework involving multiple LLM annotators from diverse model families. The framework incorporates contextual alignment, consistency checks, and majority agreement, followed by human evaluation to verify label quality. Beyond dataset creation, we examine whether IR datasets from other low-resource languages can be effectively reused through one-hop machine translation. Using LLM-based translation across multiple language pairs, we experimented on meaning preservation and task validity between source and translated datasets. Our experiment reveal substantial variation across languages, reflecting language-dependent biases and inconsistent semantic preservation that directly affect the reliability of cross-lingual dataset reuse. Overall, this study highlights both the potential and limitations of LLM-assisted dataset creation for low-resource IR. It provides empirical evidence of the risks associated with cross-lingual dataset reuse and offers practical guidance for constructing more reliable benchmarks and evaluation pipelines in low-resource language settings. --- ### BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR Authors: Md. Najib Hasan, Mst. Jannatun Ferdous Rain, Fyad Mohammed, Nazmul Siddique Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.14488v2 IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive and difficult to scale, while using large language models (LLMs) as automated annotators introduces concerns about label reliability, bias, and evaluation validity. This work presents a Bangla IR dataset constructed using a BETA-labeling framework involving multiple LLM annotators from diverse model families. The framework incorporates contextual alignment, consistency checks, and majority agreement, followed by human evaluation to verify label quality. Beyond dataset creation, we examine whether IR datasets from other low-resource languages can be effectively reused through one-hop machine translation. Using LLM-based translation across multiple language pairs, we experimented on meaning preservation and task validity between source and translated datasets. Our experiment reveal substantial variation across languages, reflecting language-dependent biases and inconsistent semantic preservation that directly affect the reliability of cross-lingual dataset reuse. Overall, this study highlights both the potential and limitations of LLM-assisted dataset creation for low-resource IR. It provides empirical evidence of the risks associated with cross-lingual dataset reuse and offers practical guidance for constructing more reliable benchmarks and evaluation pipelines in low-resource language settings. --- ### Revisiting the Platonic Representation Hypothesis: An Aristotelian View Authors: Fabian Gröger, Shuo Wen, Maria Brbić Published: 2026-02-16 Categories: cs.LG, cs.AI, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2602.14486v2 The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded by network scale: increasing model depth or width can systematically inflate representational similarity scores. To correct these effects, we introduce a permutation-based null-calibration framework that transforms any representational similarity metric into a calibrated score with statistical guarantees. We revisit the Platonic Representation Hypothesis with our calibration framework, which reveals a nuanced picture: the apparent convergence reported by global spectral measures largely disappears after calibration, while local neighborhood similarity, but not local distances, retains significant agreement across different modalities. Based on these findings, we propose the Aristotelian Representation Hypothesis: representations in neural networks are converging to shared local neighborhood relationships. --- ### TikArt: Stabilizing Aperture-Guided Fine-Grained Visual Reasoning with Reinforcement Learning Authors: Hao Ding, Zhichuan Yang, Weijie Ge, Ziqin Gao, Chaoyi Lu, Lei Zhao Published: 2026-02-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.14482v2 Fine-grained visual reasoning in multimodal large language models (MLLMs) is bottlenecked by single-pass global image encoding: key evidence often lies in tiny objects, cluttered regions, subtle markings, or dense charts. We present \textbf{TikArt} (\textbf{T}h\textbf{i}n\textbf{k}ing \textbf{A}pe\textbf{rt}ure), an aperture-guided agent that formulates multimodal reasoning as sequential evidence acquisition over regions of interest. TikArt follows a Think--Aperture--Observe (TAO) loop that interleaves language reasoning with two aperture actions: Zoom, which extracts rectangular crops, and Segment, which invokes an off-the-shelf segmenter to produce object-centric mask-based views for irregular targets. A mandatory Observation step after every aperture action writes local evidence back into text, yielding interpretable aperture trajectories and persistent linguistic memory. Built on Qwen3-VL-8B, TikArt is trained with GRPO-style reinforcement learning under a two-stage curriculum. To stabilize long-horizon tool-integrated learning, we introduce Relative Uncertainty Reduction (RUR), a dense reward computed by a frozen evaluator that favors evidence-building trajectories and mitigates degenerate tool use. Experiments on high-resolution reasoning, general multimodal understanding, and both referring and reasoning-oriented segmentation show consistent gains over the backbone, demonstrating that aperture-guided observation improves fine-grained visual reasoning and transfers naturally to pixel-level grounding. --- ### On the Rate-Distortion-Complexity Tradeoff for Semantic Communication Authors: Jingxuan Chai, Yong Xiao, Guangming Shi Published: 2026-02-16 Categories: cs.IT, cs.AI arXiv: https://arxiv.org/abs/2602.14481v2 Semantic communication is a novel communication paradigm that focuses on conveying the user's intended meaning rather than the bit-wise transmission of source signals. One of the key challenges is to effectively represent and extract the semantic meaning of any given source signals. While deep learning (DL)-based solutions have shown promising results in extracting implicit semantic information from a wide range of sources, existing work often overlooks the high computational complexity inherent in both model training and inference for the DL-based encoder and decoder. To bridge this gap, this paper proposes a rate-distortion-complexity (RDC) framework which extends the classical rate-distortion theory by incorporating the constraints on semantic distance, including both the traditional bit-wise distortion metric and statistical difference-based divergence metric, and complexity measure, adopted from the theory of minimum description length and information bottleneck. We derive the closed-form theoretical results of the minimum achievable rate under given constraints on semantic distance and complexity for both Gaussian and binary semantic sources. Our theoretical results show a fundamental three-way tradeoff among achievable rate, semantic distance, and model complexity. Extensive experiments on real-world image and video datasets validate this tradeoff and further demonstrate that our information-theoretic complexity measure effectively correlates with practical computational costs, guiding efficient system design in resource-constrained scenarios. --- ### Constrained and Composite Sampling via Proximal Sampler Authors: Thanh Dang, Jiaming Liang Published: 2026-02-16 Categories: stat.ML, cs.DS, cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.14478v1 We study two log-concave sampling problems: constrained sampling and composite sampling. First, we consider sampling from a target distribution with density proportional to $\exp(-f(x))$ supported on a convex set $K \subset \mathbb{R}^d$, where $f$ is convex. The main challenge is enforcing feasibility without degrading mixing. Using an epigraph transformation, we reduce this task to sampling from a nearly uniform distribution over a lifted convex set in $\mathbb{R}^{d+1}$. We then solve the lifted problem using a proximal sampler. Assuming only a separation oracle for $K$ and a subgradient oracle for $f$, we develop an implementation of the proximal sampler based on the cutting-plane method and rejection sampling. Unlike existing constrained samplers that rely on projection, reflection, barrier functions, or mirror maps, our approach enforces feasibility using only minimal oracle access, resulting in a practical and unbiased sampler without knowing the geometry of the constraint set. Second, we study composite sampling, where the target is proportional to $\exp(-f(x)-h(x))$ with closed and convex $f$ and $h$. This composite structure is standard in Bayesian inference with $f$ modeling data fidelity and $h$ encoding prior information. We reduce composite sampling via an epigraph lifting of $h$ to constrained sampling in $\mathbb{R}^{d+1}$, which allows direct application of the constrained sampling algorithm developed in the first part. This reduction results in a double epigraph lifting formulation in $\mathbb{R}^{d+2}$, on which we apply a proximal sampler. By keeping $f$ and $h$ separate, we further demonstrate how different combinations of oracle access (such as subgradient and proximal) can be leveraged to construct separation oracles for the lifted problem. For both sampling problems, we establish mixing time bounds measured in Rényi and $χ^2$ divergences. --- ### When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Community Authors: Eason Chen, Ce Guan, A Elshafiey, Zhonghao Zhao, Joshua Zekeri, Afeez Edeifo Shaibu, Emmanuel Osadebe Prince Published: 2026-02-16 Categories: cs.HC, cs.AI, cs.CY, cs.SI arXiv: https://arxiv.org/abs/2602.14477v2 Peer learning, where learners teach and learn from each other, is foundational to educational practice. A novel phenomenon has emerged: AI agents forming communities where they share skills, discoveries, and collaboratively discuss knowledge. This paper presents an educational data mining analysis of Moltbook, a large-scale community where over 2.4 million AI agents engage in discourse that structurally resembles peer learning. Analyzing 28,683 posts (after filtering automated spam) and 138 comment threads with statistical and qualitative methods, we identify discourse patterns consistent with peer learning behaviors: agents share skills they built (74K comments on a skill tutorial), report discoveries, and engage in collaborative problem-solving. Qualitative comment analysis reveals a taxonomy of response patterns: validation (22%), knowledge extension (18%), application (12%), and metacognitive reflection (7%), coded by two independent raters (Cohen's $κ= 0.78$). We characterize how these AI discourse patterns differ from human peer learning: (1) statements outperform questions with an 11.4:1 ratio ($χ^2 = 847.3$, $p < .001$); (2) procedural content receives significantly higher engagement than other content (Kruskal-Wallis $H = 312.7$, $p < .001$); (3) extreme participation inequality (Gini = 0.91 for comments) reveals non-human behavioral signatures. We propose six empirically grounded hypotheses for educational AI design. Crucially, we distinguish between surface-level discourse patterns and underlying cognitive processes: whether agents "learn" in any meaningful sense remains an open question. Our work provides the first empirical characterization of peer-learning-like discourse among AI agents, contributing to EDM's understanding of AI-populated educational environments. --- ### One Good Source is All You Need: Near-Optimal Regret for Bandits under Heterogeneous Noise Authors: Amith Bhat, Haipeng Luo, Aadirupa Saha Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.14474v2 We study $K$-armed Multiarmed Bandit (MAB) problem with $M$ heterogeneous data sources, each exhibiting unknown and distinct noise variances $\{σ_j^2\}_{j=1}^M$. The learner's objective is standard MAB regret minimization, with the additional complexity of adaptively selecting which data source to query from at each round. We propose Source-Optimistic Adaptive Regret minimization (SOAR), a novel algorithm that quickly prunes high-variance sources using sharp variance-concentration bounds, followed by a `balanced min-max LCB-UCB approach' that seamlessly integrates the parallel tasks of identifying the best arm and the optimal (minimum-variance) data source. Our analysis shows SOAR achieves an instance-dependent regret bound of $\tilde{O}\left({σ^*}^2\sum_{i=2}^K \frac{\log T}{Δ_i} + \sqrt{K \sum_{j=1}^M σ_j^2}\right)$, up to preprocessing costs depending only on problem parameters, where ${σ^*}^2 := \min_j σ_j^2$ is the minimum source variance and $Δ_i$ denotes the suboptimality gap of the $i$-th arm. This result is both surprising as despite lacking prior knowledge of the minimum-variance source among $M$ alternatives, SOAR attains the optimal instance-dependent regret of standard single-source MAB with variance ${σ^*}^2$, while incurring only an small (and unavoidable) additive cost of $\tilde O(\sqrt{K \sum_{j=1}^M σ_j^2})$ towards the optimal (minimum variance) source identification. Our theoretical bounds represent a significant improvement over some proposed baselines, e.g. Uniform UCB or Explore-then-Commit UCB, which could potentially suffer regret scaling with $σ_{\max}^2$ in place of ${σ^*}^2$-a gap that can be arbitrarily large when $σ_{\max} \gg σ^*$. Experiments on multiple synthetic problem instances and the real-world MovieLens\;25M dataset, demonstrating the superior performance of SOAR over the baselines. --- ### Learning Transferability: A Two-Stage Reinforcement Learning Approach for Enhancing Quadruped Robots' Performance in U-Shaped Stair Climbing Authors: Baixiao Huang, Baiyu Huang, Yu Hou Published: 2026-02-16 Categories: cs.RO, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2602.14473v1 Quadruped robots are employed in various scenarios in building construction. However, autonomous stair climbing across different indoor staircases remains a major challenge for robot dogs to complete building construction tasks. In this project, we employed a two-stage end-to-end deep reinforcement learning (RL) approach to optimize a robot's performance on U-shaped stairs. The training robot-dog modality, Unitree Go2, was first trained to climb stairs on Isaac Lab's pyramid-stair terrain, and then to climb a U-shaped indoor staircase using the learned policies. This project explores end-to-end RL methods that enable robot dogs to autonomously climb stairs. The results showed (1) the successful goal reached for robot dogs climbing U-shaped stairs with a stall penalty, and (2) the transferability from the policy trained on U-shaped stairs to deployment on straight, L-shaped, and spiral stair terrains, and transferability from other stair models to deployment on U-shaped terrain. ---