# Research Papers — 2026-02 · bundle page 138 of 210 > Full-text markdown of papers #6851–6900 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/138 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/137.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/139.md) ### Tighnari v2: Mitigating Label Noise and Distribution Shift in Multimodal Plant Distribution Prediction via Mixture of Experts and Weakly Supervised Learning Authors: Haixu Liu, Yufei Wang, Tianxiang Xu, Chuancheng Shi, Hongsheng Xing Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.08282v1 Large-scale, cross-species plant distribution prediction plays a crucial role in biodiversity conservation, yet modeling efforts in this area still face significant challenges due to the sparsity and bias of observational data. Presence-Absence (PA) data provide accurate and noise-free labels, but are costly to obtain and limited in quantity; Presence-Only (PO) data, by contrast, offer broad spatial coverage and rich spatiotemporal distribution, but suffer from severe label noise in negative samples. To address these real-world constraints, this paper proposes a multimodal fusion framework that fully leverages the strengths of both PA and PO data. We introduce an innovative pseudo-label aggregation strategy for PO data based on the geographic coverage of satellite imagery, enabling geographic alignment between the label space and remote sensing feature space. In terms of model architecture, we adopt Swin Transformer Base as the backbone for satellite imagery, utilize the TabM network for tabular feature extraction, retain the Temporal Swin Transformer for time-series modeling, and employ a stackable serial tri-modal cross-attention mechanism to optimize the fusion of heterogeneous modalities. Furthermore, empirical analysis reveals significant geographic distribution shifts between PA training and test samples, and models trained by directly mixing PO and PA data tend to experience performance degradation due to label noise in PO data. To address this, we draw on the mixture-of-experts paradigm: test samples are partitioned according to their spatial proximity to PA samples, and different models trained on distinct datasets are used for inference and post-processing within each partition. Experiments on the GeoLifeCLEF 2025 dataset demonstrate that our approach achieves superior predictive performance in scenarios with limited PA coverage and pronounced distribution shifts. --- ### New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR Authors: Zhilin Wang, Yafu Li, Shunkai Zhang, Zhi Wang, Haoran Zhang, Xiaoye Qu, Yu Cheng Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08281v1 Whether Reinforcement Learning with Verifiable Rewards (RLVR) endows Large Language Models (LLMs) with new capabilities or merely elicits latent traces remains a central debate. In this work, we align with the former view, proposing a probabilistic framework where capability is defined by instance-level solvability. We hypothesize that the emergence of complex reasoning can be driven by sharpening atomic step probabilities, which enables models to overcome the exponential decay of success rates inherent in multi-step reasoning chains. Utilizing the Algebrarium framework, we train models exclusively on single-step operations and evaluate their performance on unseen multi-step tasks. Our empirical results confirm that: (1) RLVR incentivizes the exploration of previously inaccessible solution paths by amplifying the model's existing skills; (2) composite performance is strictly governed by the joint probability of atomic steps, evidenced by high Pearson correlation coefficients ($ρ\in (0.69, 0.96)$); and (3) RLVR, acting as a global optimizer, can cause specific skills to be sacrificed to maximize aggregate reward. Our work offers a novel explanation for emergent abilities in RLVR, suggesting that the iterative optimization of solvable problems enables models to develop the capabilities to tackle previously unsolvable scenarios. --- ### PISCO: Precise Video Instance Insertion with Sparse Control Authors: Xiangbo Gao, Renjie Li, Xinghao Chen, Yuheng Wu, Suofei Feng, Qing Yin, Zhengzhong Tu Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.08277v2 The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engineering and "cherry-picking" - towards fine-grained, controllable generation and high-fidelity post-processing. In professional AI-assisted filmmaking, it is crucial to perform precise, targeted modifications. A cornerstone of this transition is video instance insertion, which requires inserting a specific instance into existing footage while maintaining scene integrity. Unlike traditional video editing, this task demands several requirements: precise spatial-temporal placement, physically consistent scene interaction, and the faithful preservation of original dynamics - all achieved under minimal user effort. In this paper, we propose PISCO, a video diffusion model for precise video instance insertion with arbitrary sparse keyframe control. PISCO allows users to specify a single keyframe, start-and-end keyframes, or sparse keyframes at arbitrary timestamps, and automatically propagates object appearance, motion, and interaction. To address the severe distribution shift induced by sparse conditioning in pretrained video diffusion models, we introduce Variable-Information Guidance for robust conditioning and Distribution-Preserving Temporal Masking to stabilize temporal generation, together with geometry-aware conditioning for realistic scene adaptation. We further construct PISCO-Bench, a benchmark with verified instance annotations and paired clean background videos, and evaluate performance using both reference-based and reference-free perceptual metrics. Experiments demonstrate that PISCO consistently outperforms strong inpainting and video editing baselines under sparse control, and exhibits clear, monotonic performance improvements as additional control signals are provided. Project page: xiangbogaobarry.github.io/PISCO. --- ### Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis Authors: Haoyu Jia, Kento Kawaharazuka, Kei Okada Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08276v1 Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently intertwined with low-level implementation details, causing both readers and authors to lose track amid a proliferation of superficially distinct concepts. We argue that this fragmentation largely stems from the absence of an analyzable, self-consistent formal model that enables implementation-independent characterization and comparison of LLM agents. To address this gap, we propose the \texttt{Structural Context Model}, a formal model for analyzing and comparing LLM agents from the perspective of context structure. Building upon this foundation, we introduce two complementary components that together span the full lifecycle of LLM agent research and development: (1) a declarative implementation framework; and (2) a sustainable agent engineering workflow, \texttt{Semantic Dynamics Analysis}. The proposed workflow provides principled insights into agent mechanisms and supports rapid, systematic design iteration. We demonstrate the effectiveness of the complete framework on dynamic variants of the monkey-banana problem, where agents engineered using our approach achieve up to a 32 percentage points improvement in success rate on the most challenging setting. --- ### Linguistics and Human Brain: A Perspective of Computational Neuroscience Authors: Fudong Zhang, Bo Chai, Yujie Wu, Wai Ting Siok, Nizhuan Wang Published: 2026-02-09 Categories: q-bio.NC, cs.CL arXiv: https://arxiv.org/abs/2602.08275v3 Elucidating the language-brain relationship requires bridging the methodological gap between the abstract theoretical frameworks of linguistics and the empirical neural data of neuroscience. Serving as an interdisciplinary cornerstone, computational neuroscience formalizes the hierarchical and dynamic structures of language into testable neural models through modeling, simulation, and data analysis. This enables a computational dialogue between linguistic hypotheses and neural mechanisms. Recent advances in deep learning, particularly large language models (LLMs), have powerfully advanced this pursuit. Their high-dimensional representational spaces provide a novel scale for exploring the neural basis of linguistic processing, while the "model-brain alignment" framework offers a methodology to evaluate the biological plausibility of language-related theories. --- ### Language Modeling and Understanding Through Paraphrase Generation and Detection Authors: Jan Philip Wahle Published: 2026-02-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.08274v3 Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable flexibility in how we can express ourselves. We can express the same thoughts in virtually infinite ways using different words and structures - this ability to rephrase and reformulate expressions is known as paraphrase. Modeling paraphrases is a keystone to meaning in computational language models; being able to construct different variations of texts that convey the same meaning or not shows strong abilities of semantic understanding. If computational language models are to represent meaning, they must understand and control the different aspects that construct the same meaning as opposed to different meanings at a fine granularity. Yet most existing approaches reduce paraphrasing to a binary decision between two texts or to producing a single rewrite of a source, obscuring which linguistic factors are responsible for meaning preservation. In this thesis, I propose that decomposing paraphrases into their constituent linguistic aspects (paraphrase types) offers a more fine-grained and cognitively grounded view of semantic equivalence. I show that even advanced machine learning models struggle with this task. Yet, when explicitly trained on paraphrase types, models achieve stronger performance on related paraphrase tasks and downstream applications. For example, in plagiarism detection, language models trained on paraphrase types surpass human baselines: 89.6% accuracy compared to 78.4% for plagiarism cases from Wikipedia, and 66.5% compared to 55.7% for plagiarism of scientific papers from arXiv. In identifying duplicate questions on Quora, models trained with paraphrase types improve over models trained on binary pairs. Furthermore, I demonstrate that... --- ### When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems Authors: Junwei Su, Chuan Wu Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08272v1 Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interactive feedback. Multi-Agent Reinforcement Learning (MARL), in particular, offers a promising avenue by decomposing complex tasks into specialized subtasks learned by distinct interacting agents, potentially enhancing the ability and efficiency of LLM systems. However, theoretical insights regarding when and why MARL outperforms Single-Agent RL (SARL) remain limited, creating uncertainty in selecting the appropriate RL framework. In this paper, we address this critical gap by rigorously analyzing the comparative sample efficiency of MARL and SARL within the context of LLM. Leveraging the Probably Approximately Correct (PAC) framework, we formally define SARL and MARL setups for LLMs, derive explicit sample complexity bounds, and systematically characterize how task decomposition and alignment influence learning efficiency. Our results demonstrate that MARL improves sample complexity when tasks naturally decompose into independent subtasks, whereas dependent subtasks diminish MARL's comparative advantage. Additionally, we introduce and analyze the concept of task alignment, quantifying the trade-offs when enforcing independent task decomposition despite potential misalignments. These theoretical insights clarify empirical inconsistencies and provide practical criteria for deploying MARL strategies effectively in complex LLM scenarios. --- ### Puda: Private User Dataset Agent for User-Sovereign and Privacy-Preserving Personalized AI Authors: Akinori Maeda, Yuto Sekiya, Sota Sugimura, Tomoya Asai, Yu Tsuda, Kohei Ikeda, Hiroshi Fujii, Kohei Watanabe Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08268v2 Personal data centralization among dominant platform providers including search engines, social networking services, and e-commerce has created siloed ecosystems that restrict user sovereignty, thereby impeding data use across services. Meanwhile, the rapid proliferation of Large Language Model (LLM)-based agents has intensified demand for highly personalized services that require the dynamic provision of diverse personal data. This presents a significant challenge: balancing the utilization of such data with privacy protection. To address this challenge, we propose Puda (Private User Dataset Agent), a user-sovereign architecture that aggregates data across services and enables client-side management. Puda allows users to control data sharing at three privacy levels: (i) Detailed Browsing History, (ii) Extracted Keywords, and (iii) Predefined Category Subsets. We implemented Puda as a browser-based system that serves as a common platform across diverse services and evaluated it through a personalized travel planning task. Our results show that providing Predefined Category Subsets achieves 97.2% of the personalization performance (evaluated via an LLM-as-a-Judge framework across three criteria) obtained when sharing Detailed Browsing History. These findings demonstrate that Puda enables effective multi-granularity management, offering practical choices to mitigate the privacy-personalization trade-off. Overall, Puda provides an AI-native foundation for user sovereignty, empowering users to safely leverage the full potential of personalized AI. --- ### Inverting Data Transformations via Diffusion Sampling Authors: Jinwoo Kim, Sékou-Oumar Kaba, Jiyun Park, Seunghoon Hong, Siamak Ravanbakhsh Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08267v2 We study the problem of transformation inversion on general Lie groups: a datum is transformed by an unknown group element, and the goal is to recover an inverse transformation that maps it back to the original data distribution. Such unknown transformations arise widely in machine learning and scientific modeling, where they can significantly distort observations. We take a probabilistic view and model the posterior over transformations as a Boltzmann distribution defined by an energy function on the data space. To sample from this posterior, we introduce a diffusion process on Lie groups that keeps all updates on-manifold and only requires computations in the associated Lie algebra. Our method, Transformation-Inverting Energy Diffusion (TIED), relies on a new trivialized target-score identity that enables efficient score-based sampling of the transformation posterior. As a key application, we focus on test-time equivariance, where the objective is to improve the robustness of pretrained neural networks to input transformations. Experiments on image homographies and PDE symmetries demonstrate that TIED can restore transformed inputs to the training distribution at test time, showing improved performance over strong canonicalization and sampling baselines. Code is available at https://github.com/jw9730/tied. --- ### Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes Authors: Seunghoon Jeong, Eunho Lee, Jeongyun Kim, Ayoung Kim Published: 2026-02-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.08266v1 In cluttered scenes with inevitable occlusions and incomplete observations, selecting informative viewpoints is essential for building a reliable representation. In this context, 3D Gaussian Splatting (3DGS) offers a distinct advantage, as it can explicitly guide the selection of subsequent viewpoints and then refine the representation with new observations. However, existing approaches rely solely on geometric cues, neglect manipulation-relevant semantics, and tend to prioritize exploitation over exploration. To tackle these limitations, we introduce an instance-aware Next Best View (NBV) policy that prioritizes underexplored regions by leveraging object features. Specifically, our object-aware 3DGS distills instancelevel information into one-hot object vectors, which are used to compute confidence-weighted information gain that guides the identification of regions associated with erroneous and uncertain Gaussians. Furthermore, our method can be easily adapted to an object-centric NBV, which focuses view selection on a target object, thereby improving reconstruction robustness to object placement. Experiments demonstrate that our NBV policy reduces depth error by up to 77.14% on the synthetic dataset and 34.10% on the real-world GraspNet dataset compared to baselines. Moreover, compared to targeting the entire scene, performing NBV on a specific object yields an additional reduction of 25.60% in depth error for that object. We further validate the effectiveness of our approach through real-world robotic manipulation tasks. --- ### Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification Authors: Guoqi Yu, Xiaowei Hu, Angelica I. Aviles-Rivero, Anqi Qiu, Shujun Wang Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08262v1 Functional magnetic resonance imaging (fMRI) enables non-invasive brain disorder classification by capturing blood-oxygen-level-dependent (BOLD) signals. However, most existing methods rely on functional connectivity (FC) via Pearson correlation, which reduces 4D BOLD signals to static 2D matrices, discarding temporal dynamics and capturing only linear inter-regional relationships. In this work, we benchmark state-of-the-art temporal models (e.g., time-series models such as PatchTST, TimesNet, and TimeMixer) on raw BOLD signals across five public datasets. Results show these models consistently outperform traditional FC-based approaches, highlighting the value of directly modeling temporal information such as cycle-like oscillatory fluctuations and drift-like slow baseline trends. Building on this insight, we propose DeCI, a simple yet effective framework that integrates two key principles: (i) Cycle and Drift Decomposition to disentangle cycle and drift within each ROI (Region of Interest); and (ii) Channel-Independence to model each ROI separately, improving robustness and reducing overfitting. Extensive experiments demonstrate that DeCI achieves superior classification accuracy and generalization compared to both FC-based and temporal baselines. Our findings advocate for a shift toward end-to-end temporal modeling in fMRI analysis to better capture complex brain dynamics. The code is available at https://github.com/Levi-Ackman/DeCI. --- ### PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding Authors: Binglin Wu, Yingyi Zhang, Xianneng Li, Ruyue Deng, Chuan Yue, Weiru Zhang, Xiaoyi Zeng Published: 2026-02-09 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2602.08261v2 Auto-bidding systems strive to maximize marketing value while maintaining high compliance with efficiency constraints, such as Target Cost-Per-Action (CPA). While Decision Transformers offer powerful sequence modeling capabilities, their application to this setting faces two challenges: 1) standard Return-to-Go conditioning causes state aliasing by ignoring the cost dimension, preventing precise resource pacing; and 2) standard regression constrains the policy to mimic historical averages, limiting its capacity to optimize performance near the high-efficiency boundary. To tackle these challenges, we propose PRO-Bid, a constraint-aware generative auto-bidding framework featuring systematic redesigns across data, architecture, and training via two synergistic mechanisms: 1) Constraint-Decoupled Pareto Representation (CDPR) separates global constraints into recursive cost and value contexts to restore resource perception, while reweighting trajectories based on the empirical Pareto frontier to prioritize high-efficiency data; and 2) Counterfactual Regret Optimization (CRO) employs a global predictor to evaluate alternative actions and identify promising local adjustments. By utilizing these high-utility outcomes as weighted regression targets, the model overcomes mean regression and approaches the empirical high-efficiency boundary. Extensive experiments on two public benchmarks and online A/B tests show that PRO-Bid achieves better constraint satisfaction and value acquisition than state-of-the-art baselines. --- ### Constraint-Aware Generative Auto-bidding via Pareto-Prioritized Regret Optimization Authors: Binglin Wu, Yingyi Zhang, Xianneng Li, Ruyue Deng, Chuan Yue, Weiru Zhang, Xiaoyi Zeng Published: 2026-02-09 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2602.08261v1 Auto-bidding systems aim to maximize marketing value while satisfying strict efficiency constraints such as Target Cost-Per-Action (CPA). Although Decision Transformers provide powerful sequence modeling capabilities, applying them to this constrained setting encounters two challenges: 1) standard Return-to-Go conditioning causes state aliasing by neglecting the cost dimension, preventing precise resource pacing; and 2) standard regression forces the policy to mimic average historical behaviors, thereby limiting the capacity to optimize performance toward the constraint boundary. To address these challenges, we propose PRO-Bid, a constraint-aware generative auto-bidding framework based on two synergistic mechanisms: 1) Constraint-Decoupled Pareto Representation (CDPR) decomposes global constraints into recursive cost and value contexts to restore resource perception, while reweighting trajectories based on the Pareto frontier to focus on high-efficiency data; and 2) Counterfactual Regret Optimization (CRO) facilitates active improvement by utilizing a global outcome predictor to identify superior counterfactual actions. By treating these high-utility outcomes as weighted regression targets, the model transcends historical averages to approach the optimal constraint boundary. Extensive experiments on two public benchmarks and online A/B tests demonstrate that PRO-Bid achieves superior constraint satisfaction and value acquisition compared to state-of-the-art baselines. --- ### A Statistical Framework for Alignment with Biased AI Feedback Authors: Xintao Xia, Zhiqiu Xia, Linjun Zhang, Zhanrui Cai Published: 2026-02-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.08259v1 Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback datasets. In this paper, we develop two debiased alignment methods within a general framework that accommodates heterogeneous prompt-response distributions and external human feedback sources. Debiased Direct Preference Optimization (DDPO) augments standard DPO with a residual-based correction and density-ratio reweighting to mitigate systematic bias, while retaining DPO's computational efficiency. Debiased Identity Preference Optimization (DIPO) directly estimates human preference probabilities without imposing a parametric reward model. We provide theoretical guarantees for both methods: DDPO offers a practical and computationally efficient solution for large-scale alignment, whereas DIPO serves as a robust, statistically optimal alternative that attains the semiparametric efficiency bound. Empirical studies on sentiment generation, summarization, and single-turn dialogue demonstrate that the proposed methods substantially improve alignment efficiency and recover performance close to that of an oracle trained on fully human-labeled data. --- ### SynthAgent: A Multi-Agent LLM Framework for Realistic Patient Simulation -- A Case Study in Obesity with Mental Health Comorbidities Authors: Arman Aghaee, Sepehr Asgarian, Jouhyun Jeon Published: 2026-02-09 Categories: cs.AI, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2602.08254v1 Simulating high-fidelity patients offers a powerful avenue for studying complex diseases while addressing the challenges of fragmented, biased, and privacy-restricted real-world data. In this study, we introduce SynthAgent, a novel Multi-Agent System (MAS) framework designed to model obesity patients with comorbid mental disorders, including depression, anxiety, social phobia, and binge eating disorder. SynthAgent integrates clinical and medical evidence from claims data, population surveys, and patient-centered literature to construct personalized virtual patients enriched with personality traits that influence adherence, emotion regulation, and lifestyle behaviors. Through autonomous agent interactions, the system simulates disease progression, treatment response, and life management across diverse psychosocial contexts. Evaluation of more than 100 generated patients demonstrated that GPT-5 and Claude 4.5 Sonnet achieved the highest fidelity as the core engine in the proposed MAS framework, outperforming Gemini 2.5 Pro and DeepSeek-R1. SynthAgent thus provides a scalable and privacy-preserving framework for exploring patient journeys, behavioral dynamics, and decision-making processes in both medical and psychological domains. --- ### G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design Authors: Baoyun Zhao, He Wang, Liang Zeng Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08253v1 While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing approaches typically formulate AHD around constructive priority rules or parameterized local search guidance, thereby restricting the search space to fixed heuristic forms. Such designs offer limited capacity for structural exploration, making it difficult to escape deep local optima in complex Combinatorial Optimization Problems (COPs). In this work, we propose G-LNS, a generative evolutionary framework that extends LLM-based AHD to the automated design of Large Neighborhood Search (LNS) operators. Unlike prior methods that evolve heuristics in isolation, G-LNS leverages LLMs to co-evolve tightly coupled pairs of destroy and repair operators. A cooperative evaluation mechanism explicitly captures their interaction, enabling the discovery of complementary operator logic that jointly performs effective structural disruption and reconstruction. Extensive experiments on challenging COP benchmarks, such as Traveling Salesman Problems (TSP) and Capacitated Vehicle Routing Problems (CVRP), demonstrate that G-LNS significantly outperforms LLM-based AHD methods as well as strong classical solvers. The discovered heuristics not only achieve near-optimal solutions with reduced computational budgets but also exhibit robust generalization across diverse and unseen instance distributions. --- ### Language Predicts Identity Fusion Across Cultures and Reveals Divergent Pathways to Violence Authors: Devin R. Wright, Justin E. Lane, F. LeRon Shults Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08252v1 In light of increasing polarization and political violence, understanding the psychological roots of extremism is increasingly important. Prior research shows that identity fusion predicts willingness to engage in extreme acts. We evaluate the Cognitive Linguistic Identity Fusion Score, a method that uses cognitive linguistic patterns, LLMs, and implicit metaphor to measure fusion from language. Across datasets from the United Kingdom and Singapore, this approach outperforms existing methods in predicting validated fusion scores. Applied to extremist manifestos, two distinct high-fusion pathways to violence emerge: ideologues tend to frame themselves in terms of group, forming kinship bonds; whereas grievance-driven individuals frame the group in terms of their personal identity. These results refine theories of identity fusion and provide a scalable tool aiding fusion research and extremism detection. --- ### A Unified Framework for Multimodal Image Reconstruction and Synthesis using Denoising Diffusion Models Authors: Weijie Gan, Xucheng Wang, Tongyao Wang, Wenshang Wang, Chunwei Ying, Yuyang Hu, Yasheng Chen, Hongyu An, Ulugbek S. Kamilov Published: 2026-02-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.08249v1 Image reconstruction and image synthesis are important for handling incomplete multimodal imaging data, but existing methods require various task-specific models, complicating training and deployment workflows. We introduce Any2all, a unified framework that addresses this limitation by formulating these disparate tasks as a single virtual inpainting problem. We train a single, unconditional diffusion model on the complete multimodal data stack. This model is then adapted at inference time to ``inpaint'' all target modalities from any combination of inputs of available clean images or noisy measurements. We validated Any2all on a PET/MR/CT brain dataset. Our results show that Any2all can achieve excellent performance on both multimodal reconstruction and synthesis tasks, consistently yielding images with competitive distortion-based performance and superior perceptual quality over specialized methods. --- ### STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction Authors: Jinhao Li, Yuxuan Cong, Yingqiao Wang, Hao Xia, Shan Huang, Yijia Zhang, Ningyi Xu, Guohao Dai Published: 2026-02-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.08245v2 Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the distribution of action sequences and capture multimodality. However, iterative denoising leads to substantial inference latency, limiting control frequency in real-time closed-loop systems. Existing acceleration methods either reduce sampling steps, bypass diffusion through direct prediction, or reuse past actions, but often struggle to jointly preserve action quality and achieve consistently low latency. In this work, we propose STEP, a lightweight spatiotemporal consistency prediction mechanism to construct high-quality warm-start actions that are both distributionally close to the target action and temporally consistent, without compromising the generative capability of the original diffusion policy. Then, we propose a velocity-aware perturbation injection mechanism that adaptively modulates actuation excitation based on temporal action variation to prevent execution stall especially for real-world tasks. We further provide a theoretical analysis showing that the proposed prediction induces a locally contractive mapping, ensuring convergence of action errors during diffusion refinement. We conduct extensive evaluations on nine simulated benchmarks and two real-world tasks. Notably, STEP with 2 steps can achieve an average 21.6% and 27.5% higher success rate than BRIDGER and DDIM on the RoboMimic benchmark and real-world tasks, respectively. These results demonstrate that STEP consistently advances the Pareto frontier of inference latency and success rate over existing methods.The code is publicly available at https://github.com/Kimho666/STEP. --- ### Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers Authors: Juncheng Dong, Bowen He, Moyang Guo, Ethan X. Fang, Zhuoran Yang, Vahid Tarokh Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08244v1 In-context reinforcement learning (ICRL) leverages the in-context learning capabilities of transformer models (TMs) to efficiently generalize to unseen sequential decision-making tasks without parameter updates. However, existing ICRL methods rely on explicit reward signals during pretraining, which limits their applicability when rewards are ambiguous, hard to specify, or costly to obtain. To overcome this limitation, we propose a new learning paradigm, In-Context Preference-based Reinforcement Learning (ICPRL), in which both pretraining and deployment rely solely on preference feedback, eliminating the need for reward supervision. We study two variants that differ in the granularity of feedback: Immediate Preference-based RL (I-PRL) with per-step preferences, and Trajectory Preference-based RL (T-PRL) with trajectory-level comparisons. We first show that supervised pretraining, a standard approach in ICRL, remains effective under preference-only context datasets, demonstrating the feasibility of in-context reinforcement learning using only preference signals. To further improve data efficiency, we introduce alternative preference-native frameworks for I-PRL and T-PRL that directly optimize TM policies from preference data without requiring reward signals nor optimal action labels.Experiments on dueling bandits, navigation, and continuous control tasks demonstrate that ICPRL enables strong in-context generalization to unseen tasks, achieving performance comparable to ICRL methods trained with full reward supervision. --- ### Discrete Adjoint Schrödinger Bridge Sampler Authors: Wei Guo, Yuchen Zhu, Xiaochen Du, Juno Nam, Yongxin Chen, Rafael Gómez-Bombarelli, Guan-Horng Liu, Molei Tao, Jaemoo Choi Published: 2026-02-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.08243v1 Learning discrete neural samplers is challenging due to the lack of gradients and combinatorial complexity. While stochastic optimal control (SOC) and Schrödinger bridge (SB) provide principled solutions, efficient SOC solvers like adjoint matching (AM), which excel in continuous domains, remain unexplored for discrete spaces. We bridge this gap by revealing that the core mechanism of AM is $\mathit{state}\text{-}\mathit{space~agnostic}$, and introduce $\mathbf{discrete~ASBS}$, a unified framework that extends AM and adjoint Schrödinger bridge sampler (ASBS) to discrete spaces. Theoretically, we analyze the optimality conditions of the discrete SB problem and its connection to SOC, identifying a necessary cyclic group structure on the state space to enable this extension. Empirically, discrete ASBS achieves competitive sample quality with significant advantages in training efficiency and scalability. --- ### Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs Authors: Siqu Ou, Tianrui Wan, Zhiyuan Zhao, Junyu Gao, Xuelong Li Published: 2026-02-09 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.08241v1 While chain-of-thought (CoT) reasoning has substantially improved multimodal large language models (MLLMs) on complex reasoning tasks, existing approaches largely rely on long textual reasoning trajectories and provide limited mechanisms for learning stable visual attention policies. Our analysis shows that current MLLMs exhibit weak visual focus: early-stage visual misalignment is rarely corrected during subsequent reasoning, leading to error propagation and failed inferences. We argue that this limitation stems from inadequate credit assignment for visual attention during training. To address this issue, we propose SAYO, a visual reasoning model trained with a reinforcement learning (RL) framework that introduces a region-level visual attention-based reward. This reward explicitly aligns optimization signals with visually grounded reasoning steps, enabling the model to learn more reliable attention behaviors. Extensive experiments across multiple multimodal benchmarks demonstrate that SAYO consistently improves performance on diverse reasoning and perception tasks. --- ### PTS-SNN: A Prompt-Tuned Temporal Shift Spiking Neural Networks for Efficient Speech Emotion Recognition Authors: Xun Su, Huamin Wang, Qi Zhang Published: 2026-02-09 Categories: cs.AI, cs.SD arXiv: https://arxiv.org/abs/2602.08240v1 Speech Emotion Recognition (SER) is widely deployed in Human-Computer Interaction, yet the high computational cost of conventional models hinders their implementation on resource-constrained edge devices. Spiking Neural Networks (SNNs) offer an energy-efficient alternative due to their event-driven nature; however, their integration with continuous Self-Supervised Learning (SSL) representations is fundamentally challenged by distribution mismatch, where high-dynamic-range embeddings degrade the information coding capacity of threshold-based neurons. To resolve this, we propose Prompt-Tuned Spiking Neural Networks (PTS-SNN), a parameter-efficient neuromorphic adaptation framework that aligns frozen SSL backbones with spiking dynamics. Specifically, we introduce a Temporal Shift Spiking Encoder to capture local temporal dependencies via parameter-free channel shifts, establishing a stable feature basis. To bridge the domain gap, we devise a Context-Aware Membrane Potential Calibration strategy. This mechanism leverages a Spiking Sparse Linear Attention module to aggregate global semantic context into learnable soft prompts, which dynamically regulate the bias voltages of Parametric Leaky Integrate-and-Fire (PLIF) neurons. This regulation effectively centers the heterogeneous input distribution within the responsive firing range, mitigating functional silence or saturation. Extensive experiments on five multilingual datasets (e.g., IEMOCAP, CASIA, EMODB) demonstrate that PTS-SNN achieves 73.34\% accuracy on IEMOCAP, comparable to competitive Artificial Neural Networks (ANNs), while requiring only 1.19M trainable parameters and 0.35 mJ inference energy per sample. --- ### Linearization Explains Fine-Tuning in Large Language Models Authors: Zahra Rahimi Afzal, Tara Esmaeilbeig, Mojtaba Soltanalian, Mesrob I. Ohannessian Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08239v1 Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain underexplored. In this paper, we provide several insights into such fine-tuning through the lens of linearization. Fine-tuned models are often implicitly encouraged to remain close to the pretrained model. By making this explicit, using an Euclidean distance inductive bias in parameter space, we show that fine-tuning dynamics become equivalent to learning with the positive-definite neural tangent kernel (NTK). We specifically analyze how close the fully linear and the linearized fine-tuning optimizations are, based on the strength of the regularization. This allows us to be pragmatic about how good a model linearization is when fine-tuning large language models (LLMs). When linearization is a good model, our findings reveal a strong correlation between the eigenvalue spectrum of the NTK and the performance of model adaptation. Motivated by this, we give spectral perturbation bounds on the NTK induced by the choice of layers selected for fine-tuning. We empirically validate our theory on Low Rank Adaptation (LoRA) on LLMs. These insights not only characterize fine-tuning but also have the potential to enhance PEFT techniques, paving the way to better informed and more nimble adaptation in LLMs. --- ### On convexity and efficiency in semantic systems Authors: Nathaniel Imel, Noga Zaslavasky Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08238v1 There are two widely held characterizations of human semantic category systems: (1) they form convex partitions of conceptual spaces, and (2) they are efficient for communication. While prior work observed that convexity and efficiency co-occur in color naming, the analytical relation between them and why they co-occur have not been well understood. We address this gap by combining analytical and empirical analyses that build on the Information Bottleneck (IB) framework for semantic efficiency. First, we show that convexity and efficiency are distinct in the sense that neither entails the other: there are convex systems which are inefficient, and optimally-efficient systems that are non-convex. Crucially, however, the IB-optimal systems are mostly convex in the domain of color naming, explaining the main empirical basis for the convexity approach. Second, we show that efficiency is a stronger predictor for discriminating attested color naming systems from hypothetical variants, with convexity adding negligible improvement on top of that. Finally, we discuss a range of empirical phenomena that convexity cannot account for but efficiency can. Taken together, our work suggests that while convexity and efficiency can yield similar structural observations, they are fundamentally distinct, with efficiency providing a more comprehensive account of semantic typology. --- ### Document Reconstruction Unlocks Scalable Long-Context RLVR Authors: Yao Xiao, Lei Wang, Yue Deng, Guanzheng Chen, Ziqi Jin, Jung-jae Kim, Xiaoli Li, Roy Ka-wei Lee, Lidong Bing Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08237v4 Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it often relies on gold-standard answers or explicit evaluation rubrics provided by powerful teacher models or human experts, which are costly and time-consuming. In this work, we investigate unsupervised approaches to enhance the long-context capabilities of LLMs, eliminating the need for heavy human annotations or teacher models' supervision. Specifically, we first replace a few paragraphs with special placeholders in a long document. LLMs are trained through reinforcement learning to reconstruct the document by correctly identifying and sequencing missing paragraphs from a set of candidate options. This training paradigm enables the model to capture global narrative coherence, significantly boosting long-context performance. We validate the effectiveness of our method on two widely used benchmarks, RULER and LongBench~v2. While acquiring noticeable gains on RULER, it can also achieve a reasonable improvement on LongBench~v2 without any manually curated long-context QA data. Furthermore, we conduct extensive ablation studies to analyze the impact of reward design, data curation strategies, training schemes, and data scaling effects on model performance. We publicly release our code, data, and models. --- ### When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning Authors: Shoubin Yu, Yue Zhang, Zun Wang, Jaehong Yoon, Huaxiu Yao, Mingyu Ding, Mohit Bansal Published: 2026-02-09 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.08236v2 Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under unseen or alternative viewpoints. Recent work addresses this by augmenting reasoning with world models for visual imagination, but questions such as when imagination is actually necessary, how much of it is beneficial, and when it becomes harmful, remain poorly understood. In practice, indiscriminate imagination can increase computation and even degrade performance by introducing misleading evidence. In this work, we present an in-depth analysis of test-time visual imagination as a controllable resource for spatial reasoning. We first study when static visual evidence is sufficient, when imagination improves reasoning, and how excessive or unnecessary imagination affects accuracy and efficiency. To support this analysis, we then introduce AVIC, an adaptive test-time framework with world models that explicitly reasons about the sufficiency of current visual evidence before selectively invoking and scaling visual imagination. Finally, to further learn this gating and planning behavior without any annotation of when and how much to imagine, we introduce AVIC-R, which trains the policy via GRPO from QA-correctness rewards and penalties by imagination cost. Across spatial reasoning benchmarks (SAT, MMSI) and an embodied navigation benchmark (R2R), our results reveal clear scenarios where imagination is critical, marginal, or detrimental, and show that selective control can match or outperform fixed imagination strategies with substantially fewer world-model calls and language tokens. Our AVIC-R surpasses strong proprietary baselines including GPT-4o and GPT-4.1 while invoking the world model less often. Overall, our findings highlight the importance of analyzing and controlling test-time imagination for efficient and reliable spatial reasoning. --- ### When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents Authors: Jaylen Jones, Zhehao Zhang, Yuting Ning, Eric Fosler-Lussier, Pierre-Luc St-Charles, Yoshua Bengio, Dawn Song, Yu Su, Huan Sun Published: 2026-02-09 Categories: cs.CL, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.08235v2 Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts. However, exploration of this risk remains largely anecdotal, lacking concrete characterization and automated methods to proactively surface long-tail unintended behaviors under realistic CUA scenarios. To fill this gap, we introduce the first conceptual and methodological framework for unintended CUA behaviors, by defining their key characteristics, automatically eliciting them, and analyzing how they arise from benign inputs. We propose AutoElicit: an agentic framework that iteratively perturbs benign instructions using CUA execution feedback, and elicits severe harms while keeping perturbations realistic and benign. Using AutoElicit, we surface hundreds of harmful unintended behaviors from state-of-the-art CUAs such as Claude 4.5 Haiku, Claude 4.5 Opus, and Operator. We further evaluate the transferability of human-verified successful perturbations, identifying persistent susceptibility to unintended behaviors across various other frontier CUAs. This work establishes a foundation for systematically analyzing unintended behaviors in realistic computer-use settings. --- ### SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Authors: Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, Zeyu Zheng, Cihang Xie et al. Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.08234v1 Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often redundant and noise-heavy. This prevents agents from extracting high-level, reusable behavioral patterns that are essential for generalization. In this paper, we propose SkillRL, a framework that bridges the gap between raw experience and policy improvement through automatic skill discovery and recursive evolution. Our approach introduces an experience-based distillation mechanism to build a hierarchical skill library SkillBank, an adaptive retrieval strategy for general and task-specific heuristics, and a recursive evolution mechanism that allows the skill library to co-evolve with the agent's policy during reinforcement learning. These innovations significantly reduce the token footprint while enhancing reasoning utility. Experimental results on ALFWorld, WebShop and seven search-augmented tasks demonstrate that SkillRL achieves state-of-the-art performance, outperforming strong baselines over 15.3% and maintaining robustness as task complexity increases. Code is available at this https://github.com/aiming-lab/SkillRL. --- ### Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modeling Authors: Jiatao Chen, Xing Tang, Xiaoyue Duan, Yutang Feng, Jinchao Zhang, Jie Zhou Published: 2026-02-09 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2602.08233v1 While existing Singing Voice Synthesis systems achieve high-fidelity solo performances, they are constrained by global timbre control, failing to address dynamic multi-singer arrangement and vocal texture within a single song. To address this, we propose Tutti, a unified framework designed for structured multi-singer generation. Specifically, we introduce a Structure-Aware Singer Prompt to enable flexible singer scheduling evolving with musical structure, and propose Complementary Texture Learning via Condition-Guided VAE to capture implicit acoustic textures (e.g., spatial reverberation and spectral fusion) that are complementary to explicit controls. Experiments demonstrate that Tutti excels in precise multi-singer scheduling and significantly enhances the acoustic realism of choral generation, offering a novel paradigm for complex multi-singer arrangement. Audio samples are available at https://annoauth123-ctrl.github.io/Tutii_Demo/. --- ### Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization Authors: Ruichen Jiang, Zakaria Mhammedi, Mehryar Mohri, Aryan Mokhtari Published: 2026-02-09 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.08232v1 We study online linear optimization with matrix variables constrained by the operator norm, a setting where the geometry renders designing data-dependent and efficient adaptive algorithms challenging. The best-known adaptive regret bounds are achieved by Shampoo-like methods, but they require solving a costly quadratic projection subproblem. To address this, we extend the gradient-based prediction scheme to adaptive matrix online learning and cast algorithm design as constructing a family of smoothed potentials for the nuclear norm. We define a notion of admissibility for such smoothings and prove any admissible smoothing yields a regret bound matching the best-known guarantees of one-sided Shampoo. We instantiate this framework with two efficient methods that avoid quadratic projections. The first is an adaptive Follow-the-Perturbed-Leader (FTPL) method using Gaussian stochastic smoothing. The second is Follow-the-Augmented-Matrix-Leader (FAML), which uses a deterministic hyperbolic smoothing in an augmented matrix space. By analyzing the admissibility of these smoothings, we show both methods admit closed-form updates and match one-sided Shampoo's regret up to a constant factor, while significantly reducing computational cost. Lastly, using the online-to-nonconvex conversion, we derive two matrix-based optimizers, Pion (from FTPL) and Leon (from FAML). We prove convergence guarantees for these methods in nonsmooth nonconvex settings, a guarantee that the popular Muon optimizer lacks. --- ### Generating Adversarial Events: A Motion-Aware Point Cloud Framework Authors: Hongwei Ren, Youxin Jiang, Qifei Gu, Xiangqian Wu Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.08230v1 Event cameras have been widely adopted in safety-critical domains such as autonomous driving, robotics, and human-computer interaction. A pressing challenge arises from the vulnerability of deep neural networks to adversarial examples, which poses a significant threat to the reliability of event-based systems. Nevertheless, research into adversarial attacks on events is scarce. This is primarily due to the non-differentiable nature of mainstream event representations, which hinders the extension of gradient-based attack methods. In this paper, we propose MA-ADV, a novel \textbf{M}otion-\textbf{A}ware \textbf{Adv}ersarial framework. To the best of our knowledge, this is the first work to generate adversarial events by leveraging point cloud representations. MA-ADV accounts for high-frequency noise in events and employs a diffusion-based approach to smooth perturbations, while fully leveraging the spatial and temporal relationships among events. Finally, MA-ADV identifies the minimal-cost perturbation through a combination of sample-wise Adam optimization, iterative refinement, and binary search. Extensive experimental results validate that MA-ADV ensures a 100\% attack success rate with minimal perturbation cost, and also demonstrate enhanced robustness against defenses, underscoring the critical security challenges facing future event-based perception systems. --- ### InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation Authors: Yifan Yang, Jinjia Li, Kunxi Li, Puhao Zheng, Yuanyi Wang, Zheyan Qu, Yang Yu, Jianmin Wu, Ming Li, Hongxia Yang Published: 2026-02-09 Categories: cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.08229v1 The rapid advancement of large language models (LLMs) demands increasingly reliable evaluation, yet current centralized evaluation suffers from opacity, overfitting, and hardware-induced variance. Our empirical analysis reveals an alarming inconsistency in existing evaluations: the standard deviation across ten repeated runs of a single model on HumanEval (1.67) actually exceeds the performance gap among the top-10 models on the official leaderboard (0.91), rendering current rankings statistically precarious. To mitigate these instabilities, we propose a decentralized evaluation framework that enables hardware and parameter diversity through large-scale benchmarking across heterogeneous compute nodes. By leveraging the blockchain-based protocol, the framework incentivizes global contributors to act as independent validators, using a robust reward system to ensure evaluation integrity and discourage dishonest participation. This collective verification transforms evaluation from a "centralized black box" into a "decentralized endorsement" where multi-party consensus and diverse inference environments yield a more stable, representative metric. Experimental results demonstrate that the decentralized evaluation framework reduces the standard deviation across ten runs on the same model to 0.28. This significant improvement over conventional frameworks ensures higher statistical confidence in model rankings. We have completely implemented this platform and will soon release it to the community. --- ### Investigating Writing Professionals' Relationships with Generative AI: How Combined Perceptions of Rivalry and Collaboration Shape Work Practices and Outcomes Authors: Rama Adithya Varanasi, Oded Nov, Batia Mishan Wiesenfeld Published: 2026-02-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.08227v2 This study investigates how professional writers' complex relationship with GenAI shapes their work practices and outcomes. Through a cross-sectional survey with writing professionals (n=403) in diverse roles, we show that collaboration and rivalry orientation are associated with differences in work practices and outcomes. Rivalry is primarily associated with relational crafting and skill maintenance. Collaboration is primarily associated with task crafting, productivity, and satisfaction, at the cost of long-term skill deterioration. Combination of the orientations (high rivalry and high collaboration) reconciles these differences, while boosting the association with the outcomes. Our findings argue for a balanced approach where high levels of rivalry and collaboration are essential to shape work practices and generate outcomes aimed at the long-term success of the job. We present key design implications on how to increase friction (rivalry) and reduce over-reliance (collaboration) to achieve a more balanced relationship with GenAI. --- ### Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval Authors: Jing Zhang, Zhikai Li, Xuewen Liu, Qingyi Gu Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08224v2 Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the efficiency of SAM2, most of them focus on retraining a lightweight backbone, with little exploration into post-training acceleration. In this paper, we observe that SAM2 exhibits sparse perception pattern as biological vision, which provides opportunities for eliminating redundant computation and acceleration: i) In mask decoder, the attention primarily focuses on the foreground objects, whereas the image encoder in the earlier stage exhibits a broad attention span, which results in unnecessary computation to background regions. ii) In memory bank, only a small subset of tokens in each frame contribute significantly to memory attention, and the salient regions exhibit temporal consistency, making full-token computation redundant. With these insights, we propose Efficient-SAM2, which promotes SAM2 to adaptively focus on object regions while eliminating task-irrelevant computations, thereby significantly improving inference efficiency. Specifically, for image encoder, we propose object-aware Sparse Window Routing (SWR), a window-level computation allocation mechanism that leverages the consistency and saliency cues from the previous-frame decoder to route background regions into a lightweight shortcut branch. Moreover, for memory attention, we propose object-aware Sparse Memory Retrieval (SMR), which allows only the salient memory tokens in each frame to participate in computation, with the saliency pattern reused from their first recollection. With negligible additional parameters and minimal training overhead, Efficient-SAM2 delivers 1.68x speedup on SAM2.1-L model with only 1.0% accuracy drop on SA-V test set. --- ### Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Authors: Zehao Chen, Gongxun Li, Tianxiang Ai, Zixuan Huang, Xiaodong Liu, Yifei Li, Wang Zhou, Fuzhen Zhuang, Xianglong Liu, Jianxin Li, Deqing Wang, Yikun Ban Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.08222v2 As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue to reinforce target predictions, we find that informative supervision signals remain latent in models' own historical weak states. Motivated by this observation, we propose WMSS (Weak Agents Can Make Strong Agents Stronger), a post-training paradigm that leverages weak checkpoints to guide continued optimization. By identifying recoverable learning gaps via entropy dynamics and reinforcing them through compensatory learning, WMSS enables strong agents to improve beyond conventional post-training saturation. Experiments on mathematical reasoning and code generation datasets show that agents trained with our approach achieve effective performance improvements, while incurring zero additional inference cost. --- ### CoRect: Context-Aware Logit Contrast for Hidden State Rectification to Resolve Knowledge Conflicts Authors: Xuhua Ma, Richong Zhang, Zhijie Nie Published: 2026-02-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.08221v1 Retrieval-Augmented Generation (RAG) often struggles with knowledge conflicts, where model-internal parametric knowledge overrides retrieved evidence, leading to unfaithful outputs. Existing approaches are often limited, relying either on superficial decoding adjustments or weight editing that necessitates ground-truth targets. Through layer-wise analysis, we attribute this failure to a parametric suppression phenomenon: specifically, in deep layers, certain FFN layers overwrite context-sensitive representations with memorized priors. To address this, we propose CoRect (Context-Aware Logit Contrast for Hidden State Rectification). By contrasting logits from contextualized and non-contextualized forward passes, CoRect identifies layers that exhibit high parametric bias without requiring ground-truth labels. It then rectifies the hidden states to preserve evidence-grounded information. Across question answering (QA) and summarization benchmarks, CoRect consistently improves faithfulness and reduces hallucinations compared to strong baselines. --- ### Pretraining with Token-Level Adaptive Latent Chain-of-Thought Authors: Boyi Zeng, Yiqin Hao, He Li, Shixiang Song, Feichen Song, Zitong Wang, Siyuan Huang, Yi Xu, ZiWei He, Xinbing Wang, Zhouhan Lin Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.08220v2 Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explores an alternative axis: increasing per-token computation without expanding parameters, by internalizing latent Chain-of-Thought (CoT) into pretraining. We propose Pretraining with Token-Level Adaptive Latent CoT (adaptive latent CoT), where the model generates a variable-length latent CoT trajectory before emitting each token -- allocating longer trajectories to difficult tokens and shorter (or even zero) trajectories to easy ones. Importantly, this behavior emerges naturally from one-stage pretraining on general text and reduces computation in both training and inference via token-wise adaptive halting. Experiments with Llama architectures show that adaptive latent CoT consistently improves language modeling perplexity and broad downstream accuracy, even with fewer training FLOPs than prior recurrent baselines. --- ### Sparsity-Aware Evolution for Model Merging Authors: Huan Zhang, Yanjian Zhang, Guillaume Wisniewski, Nadi Tomeh, Bang Liu Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.08218v1 We propose a sparsity-aware evolutionary (SAE) framework for model merging that involves iterative pruning-merging cycles to act as a novel mutation operator. We incorporate the sparsity constraints into the score function, which steers the evolutionary process to favor more sparse models, in addition to other conventional performance scores. Interestingly, the by-product of \textit{competition} for sparsity introduces an extra local \textit{attraction} and interplay into the evolutionary process: if one competitor has more zero elements, the other competitor's non-zero elements will occupy those positions, even though the less sparse competitor loses to the more sparse competitor in other positions. The proposed pipeline is evaluated on a variety of large-scale LLM benchmarks. Experiments demonstrate that our approach can improve model merging reliability across multiple benchmarks, and is easy to incorporate due to its simplicity and being orthogonal to most existing approaches. --- ### Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators Authors: Gunn Kim Published: 2026-02-09 Categories: cs.LG, cond-mat.stat-mech, stat.ML arXiv: https://arxiv.org/abs/2602.08216v3 We derive two attention operators from generalized statistical entropies. Kaniadakis entropy yields an exact full-support normalization whose weights and low-score sensitivities decay algebraically, rather than exponentially as in Softmax or by exact truncation as in entmax. Classical Abe entropy yields an implicit reciprocal-symmetric operator. With $q=e^ε$, the involution $q\leftrightarrow q^{-1}$ removes every odd correction about Softmax; we obtain the normalized second- and fourth-order terms, including the deformation of the normalization multiplier. These stationary laws follow from a Fisher-metric Lagrangian on the probability simplex, whose Shannon sector recovers scaled dot-product Softmax. We also give a tangent-gradient test for deciding whether changing the entropy changes the attention profile or only its scale. Rényi and two-parameter Sharma--Mittal entropies retain the Tsallis--entmax inverse-gradient shape, but their global moments make the effective temperature input dependent when the external temperature is fixed. Distinguishing profile-shape equivalence from fixed-parameter operator equivalence separates new normalization shapes from adaptive rescalings and organizes the operators by support, tail behavior, and realization complexity. --- ### Thermodynamic Isomorphism of Transformers: A Lagrangian Approach to Attention Dynamics Authors: Gunn Kim Published: 2026-02-09 Categories: cs.LG, cond-mat.stat-mech, stat.ML arXiv: https://arxiv.org/abs/2602.08216v2 We propose an effective field-theoretic framework for analyzing Transformer attention through a thermodynamic lens. By constructing a Lagrangian on the information manifold equipped with the Fisher metric, we show that, within the Shannon--Boltzmann entropy framework, the Softmax function arises as a stationary solution minimizing a Helmholtz free energy functional. This establishes a formal correspondence between scaled dot-product attention and canonical ensemble statistics. Extending this mapping to macroscopic observables, we define an effective specific heat associated with fluctuations of the attention energy landscape. In controlled experiments on the modular addition task ($p = 19$--$113$), we observe a robust peak in this fluctuation measure that consistently precedes the onset of generalization. While no asymptotic power-law divergence is detected in this finite-depth regime, the reproducible enhancement of energy variance suggests a critical-like crossover accompanying representational reorganization. Our framework provides a unified statistical-mechanical perspective on attention scaling, training dynamics, and positional encoding, interpreting the phenomena as emergent properties of an effective thermodynamic system rather than isolated heuristics. Although the present results indicate finite-size crossover behavior rather than a strict phase transition, they motivate further investigation into scaling limits of deep architectures through fluctuation-based observables. --- ### Distribution-Free Robust Predict-Then-Optimize in Function Spaces Authors: Yash Patel, Ambuj Tewari Published: 2026-02-09 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.08215v2 The need to rapidly solve PDEs in engineering design workflows has spurred the rise of neural surrogate models. In particular, neural operator models provide a discretization-invariant surrogate by retaining the infinite-dimensional, functional form of their arguments. Despite improved throughput, such methods lack guarantees on accuracy, unlike classical numerical PDE solvers. Optimizing engineering designs under these potentially miscalibrated surrogates thus runs the risk of producing designs that perform poorly upon deployment. In a similar vein, there is growing interest in automated decision-making under black-box predictors in the finite-dimensional setting, where a similar risk of suboptimality exists under poorly calibrated models. For this reason, methods have emerged that produce adversarially robust decisions under uncertainty estimates of the upstream model. One such framework leverages conformal prediction, a distribution-free post-hoc uncertainty quantification method, to provide these estimates due to its natural pairing with black-box predictors. We herein extend this line of conformally robust decision-making to infinite-dimensional function spaces. We first extend the typical conformal prediction guarantees over finite-dimensional spaces to infinite-dimensional Sobolev spaces. We then demonstrate how such uncertainty can be leveraged to robustly formulate engineering design tasks and characterize the suboptimality of the resulting robust optimal designs. We then empirically demonstrate the generality of our functional conformal coverage method across a diverse collection of PDEs, including the Poisson and heat equations, and showcase the significant improvement of such robust design in a quantum state discrimination task. --- ### RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection Authors: Ziwei Wang, Yuanhe Zhang, Jing Chen, Zhenhong Zhou, Ruichao Liang, Ruiying Du, Ju Jia, Cong Wu, Yang Liu Published: 2026-02-09 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2602.08214v1 Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted inputs can trigger redundant reasoning processes, exposing LRMs to resource-exhaustion vulnerabilities. However, the reasoning process itself, especially its reflective component, has received limited attention, even though it can lead to over-reflection and consume excessive computing power. In this paper, we introduce Recursive Entropy to quantify the risk of resource consumption in reflection, thereby revealing the safety issues inherent in inference itself. Based on Recursive Entropy, we introduce RECUR, a resource exhaustion attack via Recursive Entropy guided Counterfactual Utilization and Reflection. It constructs counterfactual questions to verify the inherent flaws and risks of LRMs. Extensive experiments demonstrate that, under benign inference, recursive entropy exhibits a pronounced decreasing trend. RECUR disrupts this trend, increasing the output length by up to 11x and decreasing throughput by 90%. Our work provides a new perspective on robust reasoning. --- ### DrugR: Optimizing Molecular Drugs through LLM-based Explicit Reasoning Authors: Haoran Liu, Zheni Zeng, Yukun Yan, Yuxuan Chen, Yunduo Xiao Published: 2026-02-09 Categories: cs.LG, cs.AI, cs.CL, q-bio.QM arXiv: https://arxiv.org/abs/2602.08213v1 Molecule generation and optimization is a fundamental task in chemical domain. The rapid development of intelligent tools, especially large language models (LLMs) with powerful knowledge reserves and interactive capabilities, has provided new paradigms for it. Nevertheless, the intrinsic challenge for LLMs lies in the complex implicit relationship between molecular structure and pharmacological properties and the lack of corresponding labeled data. To bridge this gap, we propose DrugR, an LLM-based method that introduces explicit, step-by-step pharmacological reasoning into the optimization process. Our approach integrates domain-specific continual pretraining, supervised fine-tuning via reverse data engineering, and self-balanced multi-granular reinforcement learning. This framework enables DrugR to effectively improve key ADMET properties while preserving the original molecule's core efficacy. Experimental results demonstrate that DrugR achieves comprehensive enhancement across multiple properties without compromising structural similarity or target binding affinity. Importantly, its explicit reasoning process provides clear, interpretable rationales for each optimization step, yielding actionable design insights and advancing toward automated, knowledge-driven scientific discovery. Our code and model checkpoints are open-sourced to foster future research. --- ### Chain-of-Caption: Training-free improvement of multimodal large language model on referring expression comprehension Authors: Yik Lung Pang, Changjae Oh Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08211v1 Given a textual description, the task of referring expression comprehension (REC) involves the localisation of the referred object in an image. Multimodal large language models (MLLMs) have achieved high accuracy on REC benchmarks through scaling up the model size and training data. Moreover, the performance of MLLMs can be further improved using techniques such as Chain-of-Thought and tool use, which provides additional visual or textual context to the model. In this paper, we analyse the effect of various techniques for providing additional visual and textual context via tool use to the MLLM and its effect on the REC task. Furthermore, we propose a training-free framework named Chain-of-Caption to improve the REC performance of MLLMs. We perform experiments on RefCOCO/RefCOCOg/RefCOCO+ and Ref-L4 datasets and show that individual textual or visual context can improve the REC performance without any fine-tuning. By combining multiple contexts, our training-free framework shows between 5% to 30% performance gain over the baseline model on accuracy at various Intersection over Union (IoU) thresholds. --- ### CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial Optimization Authors: Hyungseok Song, Deunsol Yoon, Kanghoon Lee, Han-Seul Jeong, Soonyoung Lee, Woohyung Lim Published: 2026-02-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.08210v2 Heatmap-based solvers have emerged as a promising paradigm for Combinatorial Optimization (CO). However, we argue that the dominant Supervised Learning (SL) training paradigm suffers from a fundamental objective mismatch: minimizing imitation loss (e.g., cross-entropy) does not guarantee solution cost minimization. We dissect this mismatch into two deficiencies: Decoder-Blindness (being oblivious to the non-differentiable decoding process) and Cost-Blindness (prioritizing structural imitation over solution quality). We empirically demonstrate that these intrinsic flaws impose a hard performance ceiling. To overcome this limitation, we propose CADO (Cost-Aware Diffusion models for Optimization), a streamlined Reinforcement Learning fine-tuning framework that formulates the diffusion denoising process as an MDP to directly optimize the post-decoded solution cost. We introduce Label-Centered Reward, which repurposes ground-truth labels as unbiased baselines rather than imitation targets, and Hybrid Fine-Tuning for parameter-efficient adaptation. CADO achieves state-of-the-art performance across diverse benchmarks, validating that objective alignment is essential for unlocking the full potential of heatmap-based solvers. --- ### LLMs and people both learn to form conventions -- just not with each other Authors: Cameron R. Jones, Agnese Lombardi, Kyle Mahowald, Benjamin K. Bergen Published: 2026-02-09 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2602.08208v1 Humans align to one another in conversation -- adopting shared conventions that ease communication. We test whether LLMs form the same kinds of conventions in a multimodal communication game. Both humans and LLMs display evidence of convention-formation (increasing the accuracy and consistency of their turns while decreasing their length) when communicating in same-type dyads (humans with humans, AI with AI). However, heterogenous human-AI pairs fail -- suggesting differences in communicative tendencies. In Experiment 2, we ask whether LLMs can be induced to behave more like human conversants, by prompting them to produce superficially humanlike behavior. While the length of their messages matches that of human pairs, accuracy and lexical overlap in human-LLM pairs continues to lag behind that of both human-human and AI-AI pairs. These results suggest that conversational alignment requires more than just the ability to mimic previous interactions, but also shared interpretative biases toward the meanings that are conveyed. --- ### Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation Authors: Chufeng Zhou, Jian Wang, Xinyuan Liu, Xiaokang Zhang Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08206v2 Open-vocabulary semantic segmentation has become an important direction in remote sensing, as it enables recognition beyond predefined land-cover categories. However, existing methods mainly depend on passive visual-text matching and often struggle with semantic ambiguity in geographically complex scenes, especially when different classes exhibit similar spectral or structural patterns. To address this issue, we propose a Geospatial Reasoning Chain-of-Thought (GR-CoT) framework for remote sensing open-vocabulary semantic segmentation. GR-CoT consists of an offline knowledge distillation stream and an online instance reasoning stream. The former constructs category interpretation standards for confusing classes, while the latter performs macro-scenario anchoring, visual feature decoupling, and knowledge-driven decision synthesis to generate an image-adaptive vocabulary for downstream segmentation. Experiments on the LoveDA and GID5 benchmarks indicate that the proposed framework improves overall segmentation performance and yields more semantically coherent predictions in complex scenes. --- ### Generative Regression for Left Ventricular Ejection Fraction Estimation from Echocardiography Video Authors: Jinrong Lv, Xun Gong, Zhaohuan Li, Weili Jiang Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.08202v1 Estimating Left Ventricular Ejection Fraction (LVEF) from echocardiograms constitutes an ill-posed inverse problem. Inherent noise, artifacts, and limited viewing angles introduce ambiguity, where a single video sequence may map not to a unique ground truth, but rather to a distribution of plausible physiological values. Prevailing deep learning approaches typically formulate this task as a standard regression problem that minimizes the Mean Squared Error (MSE). However, this paradigm compels the model to learn the conditional expectation, which may yield misleading predictions when the underlying posterior distribution is multimodal or heavy-tailed -- a common phenomenon in pathological scenarios. In this paper, we investigate the paradigm shift from deterministic regression toward generative regression. We propose the Multimodal Conditional Score-based Diffusion model for Regression (MCSDR), a probabilistic framework designed to model the continuous posterior distribution of LVEF conditioned on echocardiogram videos and patient demographic attribute priors. Extensive experiments conducted on the EchoNet-Dynamic, EchoNet-Pediatric, and CAMUS datasets demonstrate that MCSDR achieves state-of-the-art performance. Notably, qualitative analysis reveals that the generation trajectories of our model exhibit distinct behaviors in cases characterized by high noise or significant physiological variability, thereby offering a novel layer of interpretability for AI-aided diagnosis. --- ### PEGAsus: 3D Personalization of Geometry and Appearance Authors: Jingyu Hu, Bin Hu, Ka-Hei Hui, Haipeng Li, Zhengzhe Liu, Daniel Cohen-Or, Chi-Wing Fu Published: 2026-02-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.08198v1 We present PEGAsus, a new framework capable of generating Personalized 3D shapes by learning shape concepts at both Geometry and Appearance levels. First, we formulate 3D shape personalization as extracting reusable, category-agnostic geometric and appearance attributes from reference shapes, and composing these attributes with text to generate novel shapes. Second, we design a progressive optimization strategy to learn shape concepts at both the geometry and appearance levels, decoupling the shape concept learning process. Third, we extend our approach to region-wise concept learning, enabling flexible concept extraction, with context-aware and context-free losses. Extensive experimental results show that PEGAsus is able to effectively extract attributes from a wide range of reference shapes and then flexibly compose these concepts with text to synthesize new shapes. This enables fine-grained control over shape generation and supports the creation of diverse, personalized results, even in challenging cross-category scenarios. Both quantitative and qualitative experiments demonstrate that our approach outperforms existing state-of-the-art solutions. ---