# Research Papers — 2026-02 · bundle page 20 of 210 > Full-text markdown of papers #951–1000 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/20 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/19.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/21.md) ### TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought Authors: Jianmin Li, Ying Chang, Su-Kit Tang, Yujia Liu, Yanwen Wang, Shuyuan Lin, Binkai Ou Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22828v1 Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chinese medicine (TCM) clinical diagnosis and treatment, traditional RAG methods often exhibit poor performance in this domain. Objective: To address the limitations of conventional RAG approaches in TCM applications, this study aims to develop an improved RAG framework tailored to the characteristics of TCM reasoning. Methods: We developed TCM-DiffRAG, an innovative RAG framework that integrates knowledge graphs (KG) with chains of thought (CoT). TCM-DiffRAG was evaluated on three distinctive TCM test datasets. Results: The experimental results demonstrated that TCM-DiffRAG achieved significant performance improvements over native LLMs. For example, the qwen-plus model achieved scores of 0.927, 0.361, and 0.038, which were significantly enhanced to 0.952, 0.788, and 0.356 with TCM-DiffRAG. The improvements were even more pronounced for non-Chinese LLMs. Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods. Conclusions: TCM-DiffRAG shows that integrating structured TCM knowledge graphs with Chain of Thought based reasoning substantially improves performance in individualized diagnostic tasks. The joint use of universal and personalized knowledge graphs enables effective alignment between general knowledge and clinical reasoning. These results highlight the potential of reasoning-aware RAG frameworks for advancing LLM applications in traditional Chinese medicine. --- ### TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models Authors: Reihaneh Iranmanesh, Saeedeh Davoudi, Pasha Abrishamchian, Ophir Frieder, Nazli Goharian Published: 2026-02-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.22827v2 This paper presents a comprehensive evaluation framework for assessing the cultural competence of large language models (LLMs) in Persian. Existing Persian cultural benchmarks rely predominantly on multiple-choice formats and English-centric metrics that fail to capture Persian's morphological complexity and semantic nuance. Our framework introduces a Persian-specific short-answer evaluation that combines rule-based morphological normalization with a hybrid syntactic and semantic similarity module, enabling robust soft-match scoring beyond exact string overlap. Through systematic evaluation of 15 state-of-the-art open- and closed-source models across three culturally grounded Persian datasets, we demonstrate that our hybrid evaluation improves scoring consistency by +10 compared to exact-match baselines by capturing meaning that surface-level methods cannot detect. Our human evaluation further confirms that the proposed semantic similarity metric achieves higher agreement with human judgments than LLM-based judges. We publicly release our evaluation framework, providing the first standardized benchmark for measuring cultural understanding in Persian and establishing a reproducible foundation for cross-cultural LLM evaluation research. --- ### Hypernetwork-based approach for grid-independent functional data clustering Authors: Anirudh Thatipelli, Ali Siahkoohi Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22823v1 Functional data clustering is concerned with grouping functions that share similar structure, yet most existing methods implicitly operate on sampled grids, causing cluster assignments to depend on resolution, sampling density, or preprocessing choices rather than on the underlying functions themselves. To address this limitation, we introduce a framework that maps discretized function observations -- at arbitrary resolution and on arbitrary grids -- into a fixed-dimensional vector space via an auto-encoding architecture. The encoder is a hypernetwork that maps coordinate-value pairs to the weight space of an implicit neural representation (INR), which serves as the decoder. Because INRs represent functions with very few parameters, this design yields compact representations that are decoupled from the sampling grid, while the hypernetwork amortizes weight prediction across the dataset. Clustering is then performed in this weight space using standard algorithms, making the approach agnostic to both the discretization and the choice of clustering method. By means of synthetic and real-world experiments in high-dimensional settings, we demonstrate competitive clustering performance that is robust to changes in sampling resolution -- including generalization to resolutions not seen during training. --- ### FlexMS: A Unified Public Benchmark for Molecule Tandem Mass Spectrum Prediction Authors: Yunhua Zhong, Yixuan Tang, Yifan Li, Pan Liu, Zhiwen Yang, Zanyi Wang, Jie Yang, Jun Xia Published: 2026-02-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22822v4 Tandem mass spectrometry (MS/MS) is central to small molecule identification, but current deep learning systems for spectrum prediction still remain difficult to evaluate and deploy in practice. While novel architectures constantly claim state-of-the-art performance, inconsistent metadata conditioning and entangled preprocessing pipelines hinder fair architectural comparisons. Besides, existing evaluations are often restricted to curated datasets, failing to capture the heterogeneity and cross-domain shifts of real-world metabolomics. Furthermore, current benchmarks lack difficulty-aware diagnostics and leave blind to how models behave under specific compute or data constraints. To address this, we present FlexMS, a modular public-data benchmark framework that standardizes MS/MS prediction across public resources while keeping molecular encoders, metadata conditioning, predictor heads, and downstream retrieval under one protocol. FlexMS establishes a fair evaluation playground which significantly lowers the barrier for integrating new predictive tools. Rather than solely optimizing for average scores, FlexMS augments aggregate accuracy with difficulty-aware diagnostics, providing actionable guidance on model selection across different compute constraints, data scales, and downstream retrieval objectives. Ultimately, FlexMS provides the community with a reproducible standard to identify which algorithmic conclusions are stable and which operating points are most viable in practice. --- ### CMSA-Net: Causal Multi-scale Aggregation with Adaptive Multi-source Reference for Video Polyp Segmentation Authors: Tong Wang, Yaolei Qi, Siwen Wang, Imran Razzak, Guanyu Yang, Yutong Xie Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22821v1 Video polyp segmentation (VPS) is an important task in computer-aided colonoscopy, as it helps doctors accurately locate and track polyps during examinations. However, VPS remains challenging because polyps often look similar to surrounding mucosa, leading to weak semantic discrimination. In addition, large changes in polyp position and scale across video frames make stable and accurate segmentation difficult. To address these challenges, we propose a robust VPS framework named CMSA-Net. The proposed network introduces a Causal Multi-scale Aggregation (CMA) module to effectively gather semantic information from multiple historical frames at different scales. By using causal attention, CMA ensures that temporal feature propagation follows strict time order, which helps reduce noise and improve feature reliability. Furthermore, we design a Dynamic Multi-source Reference (DMR) strategy that adaptively selects informative and reliable reference frames based on semantic separability and prediction confidence. This strategy provides strong multi-frame guidance while keeping the model efficient for real-time inference. Extensive experiments on the SUN-SEG dataset demonstrate that CMSA-Net achieves state-of-the-art performance, offering a favorable balance between segmentation accuracy and real-time clinical applicability. --- ### Face Time Traveller : Travel Through Ages Without Losing Identity Authors: Purbayan Kar, Ayush Ghadiya, Vishal Chudasama, Pankaj Wasnik, C. V. Jawahar Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22819v1 Face aging, an ill-posed problem shaped by environmental and genetic factors, is vital in entertainment, forensics, and digital archiving, where realistic age transformations must preserve both identity and visual realism. However, existing works relying on numerical age representations overlook the interplay of biological and contextual cues. Despite progress in recent face aging models, they struggle with identity preservation in wide age transformations, also static attention and optimization-heavy inversion in diffusion limit adaptability, fine-grained control and background consistency. To address these challenges, we propose Face Time Traveller (FaceTT), a diffusion-based framework that achieves high-fidelity, identity-consistent age transformation. Here, we introduce a Face-Attribute-Aware Prompt Refinement strategy that encodes intrinsic (biological) and extrinsic (environmental) aging cues for context-aware conditioning. A tuning-free Angular Inversion method is proposed that efficiently maps real faces into the diffusion latent space for fast and accurate reconstruction. Moreover, an Adaptive Attention Control mechanism is introduced that dynamically balances cross-attention for semantic aging cues and self-attention for structural and identity preservation. Extensive experiments on benchmark datasets and in-the-wild testset demonstrate that FaceTT achieves superior identity retention, background preservation and aging realism over state-of-the-art (SOTA) methods. --- ### Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks Authors: Shuo He, Lang Feng, Qi Wei, Xin Cheng, Lei Feng, Bo An Published: 2026-02-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.22817v1 Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy updates, recent research has increasingly shifted toward stepwise group-based policy optimization, which treats each step in a rollout trajectory independently while using a memory module to retain historical context. However, we find a key issue in estimating stepwise relative advantages, namely context inconsistency, where steps within the same group may differ in their historical contexts. Empirically, we reveal that this issue can lead to severely biased advantage estimation, thereby degrading policy optimization significantly. To address the issue, in this paper, we propose Hierarchy-of-Groups Policy Optimization (HGPO) for long-horizon agentic tasks. Specifically, within a group of rollout trajectories, HGPO assigns each step to multiple hierarchical groups according to the consistency of historical contexts. Then, for each step, HGPO computes distinct advantages within each group and aggregates them with an adaptive weighting scheme. In this way, HGPO can achieve a favorable bias-variance trade-off in stepwise advantage estimation, without extra models or rollouts. Evaluations on two challenging agentic tasks, ALFWorld and WebShop with Qwen2.5-1.5B-Instruct and Qwen2.5-7B-Instruct, show that HGPO significantly outperforms existing agentic RL methods under the same computational constraints. Code is available at https://github.com/langfengQ/verl-agent/tree/master/recipe/hgpo. --- ### When Should an AI Act? A Human-Centered Model of Scene, Context, and Behavior for Agentic AI Design Authors: Soyoung Jung, Daehoo Yoon, Sung Gyu Koh, Young Hwan Kim, Yehan Ahn, Sung Park Published: 2026-02-26 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.22814v1 Agentic AI increasingly intervenes proactively by inferring users' situations from contextual data yet often fails for lack of principled judgment about when, why, and whether to act. We address this gap by proposing a conceptual model that reframes behavior as an interpretive outcome integrating Scene (observable situation), Context (user-constructed meaning), and Human Behavior Factors (determinants shaping behavioral likelihood). Grounded in multidisciplinary perspectives across the humanities, social sciences, HCI, and engineering, the model separates what is observable from what is meaningful to the user and explains how the same scene can yield different behavioral meanings and outcomes. To translate this lens into design action, we derive five agent design principles (behavioral alignment, contextual sensitivity, temporal appropriateness, motivational calibration, and agency preservation) that guide intervention depth, timing, intensity, and restraint. Together, the model and principles provide a foundation for designing agentic AI systems that act with contextual sensitivity and judgment in interactions. --- ### Accelerating Local LLMs on Resource-Constrained Edge Devices via Distributed Prompt Caching Authors: Hiroki Matsutani, Naoki Matsuda, Naoto Sugiura Published: 2026-02-26 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2602.22812v2 Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states across multiple low-end edge devices. To fully utilize prompt similarity, our distributed caching mechanism also supports partial matching. As this approach introduces communication overhead associated with state sharing over a wireless network, we introduce a Bloom-filter-based data structure, referred to as a catalog, to determine whether a remote server possesses the desired internal states, thereby suppressing unnecessary communication. Experiments using the Gemma-3 270M model and the MMLU dataset on the Raspberry Pi Zero 2W platform demonstrate that the proposed approach reduces TTFT (Time to First Token) and TTLT (Time to Last Token) by 93.12% and 50.07% on average, respectively. --- ### Multi-agent imitation learning with function approximation: Linear Markov games and beyond Authors: Luca Viano, Till Freihaut, Emanuele Nevali, Volkan Cevher, Matthieu Geist, Giorgia Ramponi Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22810v2 In this work, we present the first theoretical analysis of multi-agent imitation learning (MAIL) in linear Markov games where both the transition dynamics and each agent's reward function are linear in some given features. We demonstrate that by leveraging this structure, it is possible to replace the state-action level "all policy deviation concentrability coefficient" (Freihaut et al., arXiv:2510.09325) with a concentrability coefficient defined at the feature level which can be much smaller than the state-action analog when the features are informative about states' similarity. Furthermore, to circumvent the need for any concentrability coefficient, we turn to the interactive setting. We provide the first, computationally efficient, interactive MAIL algorithm for linear Markov games and show that its sample complexity depends only on the dimension of the feature map $d$. Building on these theoretical findings, we propose a deep MAIL interactive algorithm which clearly outperforms BC on games such as Tic-Tac-Toe and Connect4. --- ### PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models Authors: Mingde Yao, Zhiyuan You, King-Man Tam, Menglu Wang, Tianfan Xue Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22809v3 With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality of editing highly depends on carefully designed instructions, placing the burden of task decomposition and sequencing entirely on the user. To achieve autonomous image editing, we present PhotoAgent, a system that advances image editing through explicit aesthetic planning. Specifically, PhotoAgent formulates autonomous image editing as a long-horizon decision-making problem. It reasons over user aesthetic intent, plans multi-step editing actions via tree search, and iteratively refines results through closed-loop execution with memory and visual feedback, without requiring step-by-step user prompts. To support reliable evaluation in real-world scenarios, we introduce UGC-Edit, an aesthetic evaluation benchmark consisting of 7,000 photos and a learned aesthetic reward model. We also construct a test set containing 1,017 photos to systematically assess autonomous photo editing performance. Extensive experiments demonstrate that PhotoAgent consistently improves both instruction adherence and visual quality compared with baseline methods. The project page is https://mdyao.github.io/PhotoAgent/. --- ### MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks Authors: Shiqian Su, Sen Xing, Xuan Dong, Muyan Zhong, Bin Wang, Xizhou Zhu, Yuntao Chen, Wenhai Wang, Yue Deng, Pengxiang Zhu, Ziyuan Liu, Tiantong Li et al. Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22808v1 Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments. Although recent agent frameworks aim to enhance model autonomy through tool integration and external interaction, they still suffer from naive workflows, unstable performance, limited support across diverse benchmarks and tasks, and heavy reliance on costly commercial APIs. In this work, we propose a high-performance and robust open-source agent framework, termed MiroFlow, which incorporates an agent graph for flexible orchestration, an optional deep reasoning mode to enhance performance, and a robust workflow execution to ensure stable and reproducible performance. Extensive experiments demonstrate that MiroFlow consistently achieves state-of-the-art performance across multiple agent benchmarks, including GAIA, BrowseComp-EN/ZH, HLE, xBench-DeepSearch, and notably FutureX. We hope it could serve as an easily accessible, reproducible, and comparable baseline for the deep research community. --- ### Communication-Guided Multi-Mutation Differential Evolution for Crop Model Calibration Authors: Sakshi Aggarwal, Mudasir Ganaie, Mukesh Saini Published: 2026-02-26 Categories: cs.NE arXiv: https://arxiv.org/abs/2602.22804v1 In this paper, we propose a multi-mutation optimization algorithm, Differential Evolution with Multi-Mutation Operator-Guided Communication (DE-MMOGC), implemented to improve the performance and convergence abilities of standard differential evolution in uncertain environments. DE-MMOGC introduces a communication-guided scheme integrated with multiple mutation operators to encourage exploration and avoid premature convergence. Along with this, it includes a dynamic operator selection mechanism to use the best-performing operator over successive generations. To assimilate real-world uncertainties and missing observations into the predictive model, the proposed algorithm is combined with the Ensemble Kalman Filter. To evaluate the efficacy of the proposed DE-MMOGC in uncertain systems, the unified framework is applied to improve the predictive accuracy of crop simulation models. These simulation models are essential to precision agriculture, as they make it easier to estimate crop growth in a variety of unpredictable weather scenarios. Additionally, precisely calibrating these models raises a challenge due to missing observations. Hence, the simplified WOFOST crop simulation model is incorporated in this study for leaf area index (LAI)-based crop yield estimation. DE-MMOGC enhances the WOFOST performance by optimizing crucial weather parameters (temperature and rainfall), since these parameters are highly uncertain across different crop varieties, such as wheat, rice, and cotton. The experimental study shows that DE-MMOGC outperforms the traditional evolutionary optimizers and achieves better correlation with real LAI values. We found that DE-MMOGC is a resilient solution for crop monitoring. --- ### Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving Authors: Yinan Zheng, Tianyi Tan, Bin Huang, Enguang Liu, Ruiming Liang, Jianlin Zhang, Jianwei Cui, Guang Chen, Kun Ma, Hangjun Ye, Long Chen, Ya-Qin Zhang et al. Published: 2026-02-26 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22801v2 Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, their applications and evaluations in autonomous driving remain limited to simulation-based or laboratory settings. The full strength of diffusion models for large-scale, complex real-world settings, such as End-to-End Autonomous Driving (E2E AD), remains underexplored. In this study, we conducted a systematic and large-scale investigation to unleash the potential of the diffusion models as planners for E2E AD, based on a tremendous amount of real-vehicle data and road testing. Through comprehensive and carefully controlled studies, we identify key insights into the diffusion loss space, trajectory representation, and data scaling that significantly impact E2E planning performance. Moreover, we also provide an effective reinforcement learning post-training strategy to further enhance the safety and robustness of the learned planner. The resulting diffusion-based learning framework, Hyper Diffusion Planner (HDP), is deployed on a real-vehicle platform and evaluated across 6 urban driving scenarios and 200 km of real-world testing, achieving a notable 10x performance improvement over the base model. Our work demonstrates that diffusion models, when properly designed and trained, can serve as effective and scalable E2E AD planners for complex, real-world autonomous driving tasks. --- ### GSTurb: Gaussian Splatting for Atmospheric Turbulence Mitigation Authors: Hanliang Du, Zhangji Lu, Zewei Cai, Qijian Tang, Qifeng Yu, Xiaoli Liu Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22800v1 Atmospheric turbulence causes significant image degradation due to pixel displacement (tilt) and blur, particularly in long-range imaging applications. In this paper, we propose a novel framework for atmospheric turbulence mitigation, GSTurb, which integrates optical flow-guided tilt correction and Gaussian splatting for modeling non-isoplanatic blur. The framework employs Gaussian parameters to represent tilt and blur, and optimizes them across multiple frames to enhance restoration. Experimental results on the ATSyn-static dataset demonstrate the effectiveness of our method, achieving a peak PSNR of 27.67 dB and SSIM of 0.8735. Compared to the state-of-the-art method, GSTurb improves PSNR by 1.3 dB (a 4.5% increase) and SSIM by 0.048 (a 5.8% increase). Additionally, on real datasets, including the TSRWGAN Real-World and CLEAR datasets, GSTurb outperforms existing methods, showing significant improvements in both qualitative and quantitative performance. These results highlight that combining optical flow-guided tilt correction with Gaussian splatting effectively enhances image restoration under both synthetic and real-world turbulence conditions. The code for this method will be available at https://github.com/DuhlLiamz/3DGS_turbulence/tree/main. --- ### Doubly Adaptive Channel and Spatial Attention for Semantic Image Communication by IoT Devices Authors: Soroosh Miri, Sepehr Abolhasani, Shahrokh Farahmand, S. Mohammad Razavizadeh, Jiguang He Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22794v2 Internet of Things (IoT) networks face significant challenges such as limited communication bandwidth, constrained computational and energy resources, and highly dynamic wireless channel conditions. Utilization of deep neural networks (DNNs) combined with semantic communication has emerged as a promising paradigm to address these limitations. Deep joint source-channel coding (DJSCC) has recently been proposed to enable semantic communication of images. Building upon the original DJSCC formulation, low-complexity attention-style architectures has been added to the DNNs for further performance enhancement. As a main hurdle, training these DNNs separately for various signal-to-noise ratios (SNRs) will amount to excessive storage or communication overhead, which can not be maintained by small IoT devices. SNR Adaptive DJSCC (ADJSCC), has been proposed to train the DNNs once but feed the current SNR as part of the data to the channel-wise attention mechanism. We improve upon ADJSCC by a simultaneous utilization of doubly adaptive channel-wise and spatial attention modules at both transmitter and receiver. These modules dynamically adjust to varying channel conditions and spatial feature importance, enabling robust and efficient feature extraction and semantic information recovery. Simulation results corroborate that our proposed doubly adaptive DJSCC (DA-DJSCC) significantly improves upon ADJSCC in several performance criteria, while incurring a mild increase in complexity. These facts render DA-DJSCC a desirable choice for semantic communication in performance demanding but low-complexity IoT networks. --- ### Doubly Adaptive Channel and Spatial Attention for Semantic Image Communication by IoT Devices Authors: Soroosh Miri, Sepehr Abolhasani, Shahrokh Farahmand, S. Mohammad Razavizadeh Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22794v1 Internet of Things (IoT) networks face significant challenges such as limited communication bandwidth, constrained computational and energy resources, and highly dynamic wireless channel conditions. Utilization of deep neural networks (DNNs) combined with semantic communication has emerged as a promising paradigm to address these limitations. Deep joint source-channel coding (DJSCC) has recently been proposed to enable semantic communication of images. Building upon the original DJSCC formulation, low-complexity attention-style architectures has been added to the DNNs for further performance enhancement. As a main hurdle, training these DNNs separately for various signal-to-noise ratios (SNRs) will amount to excessive storage or communication overhead, which can not be maintained by small IoT devices. SNR Adaptive DJSCC (ADJSCC), has been proposed to train the DNNs once but feed the current SNR as part of the data to the channel-wise attention mechanism. We improve upon ADJSCC by a simultaneous utilization of doubly adaptive channel-wise and spatial attention modules at both transmitter and receiver. These modules dynamically adjust to varying channel conditions and spatial feature importance, enabling robust and efficient feature extraction and semantic information recovery. Simulation results corroborate that our proposed doubly adaptive DJSCC (DA-DJSCC) significantly improves upon ADJSCC in several performance criteria, while incurring a mild increase in complexity. These facts render DA-DJSCC a desirable choice for semantic communication in performance demanding but low-complexity IoT networks. --- ### Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning Authors: Taishu Arashima, Hiroshi Kera, Kazuhiko Kawamoto Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22791v1 Human trajectory prediction plays a crucial role in applications such as autonomous navigation and video surveillance. While recent works have explored the integration of human skeleton sequences to complement trajectory information, skeleton data in real-world environments often suffer from missing joints caused by occlusions. These disturbances significantly degrade prediction accuracy, indicating the need for more robust skeleton representations. We propose a robust trajectory prediction method that incorporates a self-supervised skeleton representation model pretrained with masked autoencoding. Experimental results in occlusion-prone scenarios show that our method improves robustness to missing skeletal data without sacrificing prediction accuracy, and consistently outperforms baseline models in clean-to-moderate missingness regimes. --- ### Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift Authors: Hyunwoo Kim, Hanau Yi, Jaehee Bae, Yumin Kim Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22790v1 The rapid evolution of large language models (LLMs) has transformed prompt engineering from a localized craft into a systems-level governance challenge. As models scale and update across generations, prompt behavior becomes sensitive to shifts in instruction-following policies, alignment regimes, and decoding strategies, a phenomenon we characterize as GPT-scale model drift. Under such conditions, surface-level formatting conventions and ad hoc refinement are insufficient to ensure stable, interpretable control. This paper reconceptualizes Natural Language Declarative Prompting (NLD-P) as a declarative governance method rather than a rigid field template. NLD-P is formalized as a modular control abstraction that separates provenance, constraint logic, task content, and post-generation evaluation, encoded directly in natural language without reliance on external orchestration code. We define minimal compliance criteria, analyze model-dependent schema receptivity, and position NLD-P as an accessible governance framework for non-developer practitioners operating within evolving LLM ecosystems. Portions of drafting and editorial refinement employed a schema-bound LLM assistant configured under NLD-P. All conceptual framing, methodological claims, and final revisions were directed, reviewed, and approved by the human author under a documented human-in-the-loop protocol. The paper concludes by outlining implications for declarative control under ongoing model evolution and identifying directions for future empirical validation. --- ### Probing for Knowledge Attribution in Large Language Models Authors: Ivo Brink, Alexander Boer, Dennis Ulmer Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22787v3 Large language model (LLM) hallucinations, meaning fluent but factually incorrect generations, fall into two types: faithfulness violations, where the model misuses provided context, and factuality violations, where answers reflect errors in internal knowledge. Proper mitigation depends on knowing which source drives each answer. We study contributive attribution, i.e. the classification of the dominant knowledge source behind each output, and show that a simple linear probe trained on hidden representations can reliably identify it. We introduce AttriWiki, a self-supervised pipeline that automatically generates labelled training data by prompting models to recall withheld entities from memory or read them from context without relying on knowledge conflicts. Probes trained on AttriWiki achieve up to 0.96 Macro-$F_1$ on Llama-3.1-8B, Mistral-7B, and Qwen-7B, transfer to SQuAD and WebQuestions with 0.94-0.99 Macro-$F_1$, and generalise zero-shot to Tighidet et al. (2024)'s benchmark, outperforming their probe on conflicting settings without retraining. Furthermore, attribution mismatches raise error rates by up to 70%, though correct attribution does not guarantee correct answers, pointing to the need for broader detection frameworks. --- ### Probing for Knowledge Attribution in Large Language Models Authors: Ivo Brink, Alexander Boer, Dennis Ulmer Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22787v2 Large language model (LLM) hallucinations, meaning fluent but factually incorrect generations, fall into two types: faithfulness violations, where the model misuses provided context, and factuality violations, where answers reflect errors in internal knowledge. Proper mitigation depends on knowing which source drives each answer. We study contributive attribution, i.e. the classification of the dominant knowledge source behind each output, and show that a simple linear probe trained on hidden representations can reliably identify it. We introduce AttriWiki, a self-supervised pipeline that automatically generates labelled training data by prompting models to recall withheld entities from memory or read them from context without relying on knowledge conflicts. Probes trained on AttriWiki achieve up to 0.96 Macro-$F_1$ on Llama-3.1-8B, Mistral-7B, and Qwen-7B, transfer to SQuAD and WebQuestions with 0.94-0.99 Macro-$F_1$, and generalise zero-shot to Tighidet et al. (2024)'s benchmark, outperforming their probe on conflicting settings without retraining. Furthermore, attribution mismatches raise error rates by up to 70%, though correct attribution does not guarantee correct answers, pointing to the need for broader detection frameworks. --- ### QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning Authors: Yuanjun Li, Bin Zhang, Hao Chen, Zhouyang Jiang, Dapeng Li, Zhiwei Xu Published: 2026-02-26 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22786v1 Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic Q-value overestimation. This issue is particularly severe in MARL due to the combinatorial explosion of the joint action space, which often results in unstable learning and suboptimal policies. To address this problem, we propose QSIM, a similarity weighted Q-learning framework that reconstructs the TD target using action similarity. Instead of using the greedy joint action directly, QSIM forms a similarity weighted expectation over a structured near-greedy joint action space. This formulation allows the target to integrate Q-values from diverse yet behaviorally related actions while assigning greater influence to those that are more similar to the greedy choice. By smoothing the target with structurally relevant alternatives, QSIM effectively mitigates overestimation and improves learning stability. Extensive experiments demonstrate that QSIM can be seamlessly integrated with various VD methods, consistently yielding superior performance and stability compared to the original algorithms. Furthermore, empirical analysis confirms that QSIM significantly mitigates the systematic value overestimation in MARL. Code is available at https://github.com/MaoMaoLYJ/pymarl-qsim. --- ### SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation Authors: Ling Wang, Hao-Xiang Guo, Xinzhou Wang, Fuchun Sun, Kai Sun, Pengkun Liu, Hang Xiao, Zhong Wang, Guangyuan Fu, Eric Li, Yang Liu, Yikai Wang Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22785v1 We introduce SceneTransporter, an end-to-end framework for structured 3D scene generation from a single image. While existing methods generate part-level 3D objects, they often fail to organize these parts into distinct instances in open-world scenes. Through a debiased clustering probe, we reveal a critical insight: this failure stems from the lack of structural constraints within the model's internal assignment mechanism. Based on this finding, we reframe the task of structured 3D scene generation as a global correlation assignment problem. To solve this, SceneTransporter formulates and solves an entropic Optimal Transport (OT) objective within the denoising loop of the compositional DiT model. This formulation imposes two powerful structural constraints. First, the resulting transport plan gates cross-attention to enforce an exclusive, one-to-one routing of image patches to part-level 3D latents, preventing entanglement. Second, the competitive nature of the transport encourages the grouping of similar patches, a process that is further regularized by an edge-based cost, to form coherent objects and prevent fragmentation. Extensive experiments show that SceneTransporter outperforms existing methods on open-world scene generation, significantly improving instance-level coherence and geometric fidelity. Code and models will be publicly available at https://2019epwl.github.io/SceneTransporter/. --- ### TrajTok: Learning Trajectory Tokens enables better Video Understanding Authors: Chenhao Zheng, Jieyu Zhang, Jianing Zhang, Weikai Huang, Ashutosh Kumar, Quan Kong, Oncel Tuzel, Chun-Liang Li, Ranjay Krishna Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22779v3 Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and task-agnostic. We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective, dynamically adapting its token granularity to semantic complexity, independent of video duration. TrajTok contains a unified segmenter that performs implicit clustering over pixels in both space and time to directly produce object trajectories in a single forward pass. By prioritizing downstream adaptability over pixel-perfect segmentation fidelity, TrajTok is lightweight and efficient, yet empirically improves video understanding performance. With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods. TrajTok also proves to be a versatile component beyond its role as a tokenizer. We show that it can be seamlessly integrated as either a probing head for pretrained visual features (TrajAdapter) or an alignment connector in vision-language models (TrajVLM) with especially strong performance in long-video reasoning. --- ### KMLP: A Scalable Hybrid Architecture for Web-Scale Tabular Data Modeling Authors: Mingming Zhang, Pengfei Shi, Zhiqing Xiao, Feng Zhao, Guandong Sun, Yulin Kang, Ruizhe Gao, Ningtao Wang, Xing Fu, Weiqiang Wang, Junbo Zhao Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22777v1 Predictive modeling on web-scale tabular data with billions of instances and hundreds of heterogeneous numerical features faces significant scalability challenges. These features exhibit anisotropy, heavy-tailed distributions, and non-stationarity, creating bottlenecks for models like Gradient Boosting Decision Trees and requiring laborious manual feature engineering. We introduce KMLP, a hybrid deep architecture integrating a shallow Kolmogorov-Arnold Network (KAN) front-end with a Gated Multilayer Perceptron (gMLP) backbone. The KAN front-end uses learnable activation functions to automatically model complex non-linear transformations for each feature, while the gMLP backbone captures high-order interactions. Experiments on public benchmarks and an industrial dataset with billions of samples show KMLP achieves state-of-the-art performance, with advantages over baselines like GBDTs increasing at larger scales, validating KMLP as a scalable deep learning paradigm for large-scale web tabular data. --- ### TherapyProbe: Generating Design Knowledge for Relational Safety in Mental Health Chatbots Through Adversarial Simulation Authors: Joydeep Chandra, Satyam Kumar Navneet, Yong Zhang Published: 2026-02-26 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.22775v1 As mental health chatbots proliferate to address the global treatment gap, a critical question emerges: How do we design for relational safety the quality of interaction patterns that unfold across conversations rather than the correctness of individual responses? Current safety evaluations assess single-turn crisis responses, missing the therapeutic dynamics that determine whether chatbots help or harm over time. We introduce TherapyProbe, a design probe methodology that generates actionable design knowledge by systematically exploring chatbot conversation trajectories through adversarial multi-agent simulation. Using open-source models, TherapyProbe surfaces relational safety failures interaction patterns like "validation spirals" where chatbots progressively reinforce hopelessness, or "empathy fatigue" where responses become mechanical over turns. Our contribution is translating these failures into a Safety Pattern Library of 23 failure archetypes with corresponding design recommendations. We contribute: (1) a replicable methodology requiring no API costs, (2) a clinically-grounded failure taxonomy, and (3) design implications for developers, clinicians, and policymakers. --- ### ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making Authors: Yusuke Watanabe, Yohei Kobashi, Takeshi Kojima, Yusuke Iwasawa, Yasushi Okuno, Yutaka Matsuo Published: 2026-02-26 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2602.22771v1 Clinical decisions are often required under incomplete information. Clinical experts must identify whether available information is sufficient for judgment, as both premature conclusion and unnecessary abstention can compromise patient safety. To evaluate this capability of large language models (LLMs), we developed ClinDet-Bench, a benchmark based on clinical scoring systems that decomposes incomplete-information scenarios into determinable and undeterminable conditions. Identifying determinability requires considering all hypotheses about missing information, including unlikely ones, and verifying whether the conclusion holds across them. We find that recent LLMs fail to identify determinability under incomplete information, producing both premature judgments and excessive abstention, despite correctly explaining the underlying scoring knowledge and performing well under complete information. These findings suggest that existing benchmarks are insufficient to evaluate the safety of LLMs in clinical settings. ClinDet-Bench provides a framework for evaluating determinability recognition, leading to appropriate abstention, with potential applicability to medicine and other high-stakes domains, and is publicly available. --- ### AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications Authors: Yujie Zhao, Boqin Yuan, Junbo Huang, Haocheng Yuan, Zhongming Yu, Haozhou Xu, Lanxiang Hu, Abhilash Shankarampeta, Zimeng Huang, Wentao Ni, Yuandong Tian, Jishen Zhao Published: 2026-02-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22769v4 Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet existing memory benchmarks are largely dialogue-centric, while real agent memory consists of continuous agent-environment interaction trajectories composed of states, actions, observations, and tool outputs. To address this gap, we introduce **AMA-Bench** (**A**gent **M**emory with **A**ny length), a benchmark for evaluating long-horizon memory in realistic agentic settings. AMA-Bench combines real-world agent trajectories from representative applications with expert-curated QA, as well as synthetic trajectories that scale to arbitrary horizons with rule-based QA. Our study shows that existing memory systems underperform because they fail to capture causal and objective information and rely heavily on lossy similarity-based retrieval. We further propose **AMA-Agent**, a memory system based on causality-graph construction and tool-augmented retrieval. AMA-Agent achieves **57.22%** accuracy on AMA-Bench, outperforming the strongest baseline by **11.16%**. Resources are available at: (https://ama-bench.github.io/)(https://ama-bench.github.io/). --- ### Imagination Helps Visual Reasoning, But Not Yet in Latent Space Authors: You Li, Chi Chen, Yanghao Li, Fanhu Zeng, Kaiyu Huang, Jinan Xu, Maosong Sun Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22766v3 Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its effectiveness remain unclear. Motivated to demystify the true source of its efficacy, we investigate the validity of latent reasoning using Causal Mediation Analysis. We model the process as a causal chain: the input as the treatment, the latent tokens as the mediator, and the final answer as the outcome. Our findings uncover two critical disconnections: (a) Input-Latent Disconnect: dramatic perturbations on the input result in negligible changes to the latent tokens, suggesting that latent tokens do not effectively attend to the input sequence. (b) Latent-Answer Disconnect: perturbations on the latent tokens yield minimal impact on the final answer, indicating the limited causal effect latent tokens imposing on the outcome. Furthermore, extensive probing analysis reveals that latent tokens encode limited visual information and exhibit high similarity. Consequently, we challenge the necessity of latent reasoning and propose a straightforward alternative named CapImagine, which teaches the model to explicitly imagine using text. Experiments on vision-centric benchmarks show that CapImagine significantly outperforms complex latent-space baselines, highlighting the superior potential of visual reasoning through explicit imagination. --- ### Imagination Helps Visual Reasoning, But Not Yet in Latent Space Authors: You Li, Chi Chen, Yanghao Li, Fanhu Zeng, Kaiyu Huang, Jinan Xu, Maosong Sun Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22766v2 Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its effectiveness remain unclear. Motivated to demystify the true source of its efficacy, we investigate the validity of latent reasoning using Causal Mediation Analysis. We model the process as a causal chain: the input as the treatment, the latent tokens as the mediator, and the final answer as the outcome. Our findings uncover two critical disconnections: (a) Input-Latent Disconnect: dramatic perturbations on the input result in negligible changes to the latent tokens, suggesting that latent tokens do not effectively attend to the input sequence. (b) Latent-Answer Disconnect: perturbations on the latent tokens yield minimal impact on the final answer, indicating the limited causal effect latent tokens imposing on the outcome. Furthermore, extensive probing analysis reveals that latent tokens encode limited visual information and exhibit high similarity. Consequently, we challenge the necessity of latent reasoning and propose a straightforward alternative named CapImagine, which teaches the model to explicitly imagine using text. Experiments on vision-centric benchmarks show that CapImagine significantly outperforms complex latent-space baselines, highlighting the superior potential of visual reasoning through explicit imagination. --- ### Towards Better RL Training Data Utilization via Second-Order Rollout Authors: Zhe Yang, Yudong Wang, Rang Li, Zhifang Sui Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22765v1 Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by training with only first-order rollout (generating multiple responses for a question), and we argue that this approach fails to fully exploit the potential of training data because of the neglect of critique capability training. To tackle this problem, we further introduce the concept of second-order rollout (generating multiple critiques for a response) and propose a unified framework for jointly training generation and critique capabilities. Extensive experiments across various models and datasets demonstrate that our approach can utilize training data more effectively than vanilla RL and achieve better performance under the same training data. Additionally, we uncover several insightful findings regarding second-order rollout and critique training, such as the importance of label balance in critique training and the noise problem of outcome-based rewards, which can be mitigated through sampling techniques. Our work offers a preliminary exploration of dynamic data augmentation and joint generation-critique training in RL, providing meaningful inspiration for the further advancement of RL training --- ### Distributed LLM Pretraining During Renewable Curtailment Windows: A Feasibility Study Authors: Philipp Wiesner, Soeren Becker, Brett Cornick, Dominik Scheinert, Alexander Acker, Odej Kao Published: 2026-02-26 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2602.22760v1 Training large language models (LLMs) requires substantial compute and energy. At the same time, renewable energy sources regularly produce more electricity than the grid can absorb, leading to curtailment, the deliberate reduction of clean generation that would otherwise go to waste. These periods represent an opportunity: if training is aligned with curtailment windows, LLMs can be pretrained using electricity that is both clean and cheap. This technical report presents a system that performs full-parameter LLM training across geo-distributed GPU clusters during regional curtailment windows, elastically switching between local single-site training and federated multi-site synchronization as sites become available or unavailable. Our prototype trains a 561M-parameter transformer model across three clusters using the Flower federated learning framework, with curtailment periods derived from real-world marginal carbon intensity traces. Preliminary results show that curtailment-aware scheduling preserves training quality while reducing operational emissions to 5-12% of single-site baselines. --- ### Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval Authors: Yuan-Chih Chen, Chun-Shien Lu Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22759v1 Recent advances in image authenticity have primarily focused on deepfake detection and localization, leaving recovery of tampered contents for factual retrieval relatively underexplored. We propose a unified hidden-code recovery framework that enables both retrieval and restoration from post-hoc and in-generation watermarking paradigms. Our method encodes semantic and perceptual information into a compact hidden-code representation, refined through multi-scale vector quantization, and enhances contextual reasoning via conditional Transformer modules. To enable systematic evaluation for natural images, we construct ImageNet-S, a benchmark that provides paired image-label factual retrieval tasks. Extensive experiments on ImageNet-S demonstrate that our method exhibits promising retrieval and reconstruction performance while remaining fully compatible with diverse watermarking pipelines. This framework establishes a foundation for general-purpose image recovery beyond detection and localization. --- ### Decomposing Physician Disagreement in HealthBench Authors: Satya Borgohain, Roy Mariathas Published: 2026-02-26 Categories: cs.AI, stat.AP arXiv: https://arxiv.org/abs/2602.22758v2 We decompose physician disagreement in the HealthBench medical AI evaluation dataset to understand where variance resides and what observable features can explain it. Rubric identity accounts for 15.8% of met/not-met label variance but only 3.6-6.9% of disagreement variance; physician identity accounts for just 2.4%. The dominant 81.8% case-level residual is not reduced by HealthBench's metadata labels (z = -0.22, p = 0.83), normative rubric language (pseudo R^2 = 1.2%), medical specialty (0/300 Tukey pairs significant), surface-feature triage (AUC = 0.58), or embeddings (AUC = 0.485). Disagreement follows an inverted-U with completion quality (AUC = 0.689), confirming physicians agree on clearly good or bad outputs but split on borderline cases. Physician-validated uncertainty categories reveal that reducible uncertainty (missing context, ambiguous phrasing) more than doubles disagreement odds (OR = 2.55, p < 10^(-24)), while irreducible uncertainty (genuine medical ambiguity) has no effect (OR = 1.01, p = 0.90), though even the former explains only ~3% of total variance. The agreement ceiling in medical AI evaluation is thus largely structural, but the reducible/irreducible dissociation suggests that closing information gaps in evaluation scenarios could lower disagreement where inherent clinical ambiguity does not, pointing toward actionable evaluation design improvements. --- ### AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors Authors: Abhay Sheshadri, Aidan Ewart, Kai Fronsdal, Isha Gupta, Samuel R. Bowman, Sara Price, Samuel Marks, Rowan Wang Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22755v3 We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation, or secret geopolitical loyalties--which it does not confess to when directly asked. AuditBench models are highly diverse--some are subtle, while others are overt, and we use varying training techniques both for implanting behaviors and training models not to confess. To demonstrate AuditBench's utility, we develop an investigator agent that autonomously employs a configurable set of auditing tools. By measuring investigator agent success using different tools, we can evaluate their efficacy. Notably, we observe a tool-to-agent gap, where tools that perform well in standalone non-agentic evaluations fail to translate into improved performance when used with our investigator agent. We find that our most effective tools involve scaffolded calls to auxiliary models that generate diverse prompts for the target. White-box interpretability tools can be helpful, but the agent performs best with black-box tools. We also find that audit success varies greatly across training techniques: models trained on synthetic documents are easier to audit than models trained on demonstrations, with better adversarial training further increasing auditing difficulty. We release our models, agent, and evaluation framework to support future quantitative, iterative science on alignment auditing. --- ### Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction Authors: Nils Schwager, Simon Münker, Alistair Plum, Achim Rettinger Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.22752v1 The transition of Large Language Models (LLMs) from exploratory tools to active "silicon subjects" in social science lacks extensive validation of operational validity. This study introduces Conditioned Comment Prediction (CCP), a task in which a model predicts how a user would comment on a given stimulus by comparing generated outputs with authentic digital traces. This framework enables a rigorous evaluation of current LLM capabilities with respect to the simulation of social media user behavior. We evaluated open-weight 8B models (Llama3.1, Qwen3, Ministral) in English, German, and Luxembourgish language scenarios. By systematically comparing prompting strategies (explicit vs. implicit) and the impact of Supervised Fine-Tuning (SFT), we identify a critical form vs. content decoupling in low-resource settings: while SFT aligns the surface structure of the text output (length and syntax), it degrades semantic grounding. Furthermore, we demonstrate that explicit conditioning (generated biographies) becomes redundant under fine-tuning, as models successfully perform latent inference directly from behavioral histories. Our findings challenge current "naive prompting" paradigms and offer operational guidelines prioritizing authentic behavioral traces over descriptive personas for high-fidelity simulation. --- ### Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning Authors: Qiannian Zhao, Chen Yang, Jinhao Jing, Yunke Zhang, Xuhui Ren, Lu Yu, Shijie Zhang, Hongzhi Yin Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22751v1 Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learning with Verifiable Rewards (RLVR), yet most existing outcome-only RLVR pipelines rely almost exclusively on a binary correctness signal and largely ignore the model's intrinsic uncertainty. We term this discrepancy the uncertainty-reward mismatch, under which high- and low-uncertainty solutions are treated equivalently, preventing the policy from "Know What You Know" and impeding the shift from optimizing for correct answers to optimizing effective reasoning paths. This limitation is especially critical in reasoning-centric tasks such as mathematics and question answering, where performance hinges on the quality of the model's internal reasoning process rather than mere memorization of final answers. To address this, we propose EGPO, a metacognitive entropy calibration framework that explicitly integrates intrinsic uncertainty into RLVR for enhancing LRMs. EGPO estimates per-sample uncertainty using a zero-overhead entropy proxy derived from token-level likelihoods and aligns it with extrinsic correctness through an asymmetric calibration mechanism that preserves correct reasoning while selectively regulating overconfident failures, thereby enabling stable and uncertainty-aware policy optimization. Moreover, EGPO recovers informative learning signals from otherwise degenerate group-based rollouts without modifying the verifier or reward definition. Extensive experiments across multiple benchmarks demonstrate that the proposed EGPO leads to substantial and consistent improvements in reasoning performance, establishing a principled path for advancing LRMs through metacognitive entropy calibration. --- ### Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study Authors: Kaizheng Wang, Yunjia Wang, Fabio Cuzzolin, David Moens, Hans Hallez, Siu Lun Chau Published: 2026-02-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.22747v2 Epistemic uncertainty in neural networks is commonly modeled using two second-order paradigms: distribution-based representations, which rely on posterior parameter distributions, and set-based representations based on credal sets (convex sets of probability distributions). These frameworks are often regarded as fundamentally non-comparable due to differing semantics, assumptions, and evaluation practices, leaving their relative merits unclear. Empirical comparisons are further confounded by variations in the underlying predictive models. To clarify this issue, we present a controlled comparative study enabling principled, like-for-like evaluation of the two paradigms. Both representations are constructed from the same finite collection of predictive distributions generated by a shared neural network, isolating representational effects from predictive accuracy. Our study evaluates each representation through the lens of 3 uncertainty measures across 8 benchmarks, including selective prediction and out-of-distribution detection, spanning 6 underlying predictive models and 10 independent runs per configuration. Our results show that meaningful comparison between these seemingly non-comparable frameworks is both feasible and informative, providing insights into how second-order representation choices impact practical uncertainty-aware performance. --- ### SPATIALALIGN: Aligning Dynamic Spatial Relationships in Video Generation Authors: Fengming Liu, Tat-Jen Cham, Chuanxia Zheng Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22745v2 Most text-to-video (T2V) generators prioritize aesthetic quality, but often ignoring the spatial constraints in the generated videos. In this work, we present SPATIALALIGN, a self-improvement framework that enhances T2V models capabilities to depict Dynamic Spatial Relationships (DSR) specified in text prompts. We present a zeroth-order regularized Direct Preference Optimization (DPO) to fine-tune T2V models towards better alignment with DSR. Specifically, we design DSR-SCORE, a geometry-based metric that quantitatively measures the alignment between generated videos and the specified DSRs in prompts, which is a step forward from prior works that rely on VLM for evaluation. We also conduct a dataset of text-video pairs with diverse DSRs to facilitate the study. Extensive experiments demonstrate that our fine-tuned model significantly out performs the baseline in spatial relationships. The code will be released in Link. Project page: https://fengming001ntu.github.io/SpatialAlign/ --- ### Generative Data Transformation: From Mixed to Unified Data Authors: Jiaqing Zhang, Mingjia Yin, Hao Wang, Yuxin Tian, Yuyang Ye, Yawen Li, Wei Guo, Yong Liu, Enhong Chen Published: 2026-02-26 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.22743v2 Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start, recent researchs have leveraged data from multiple auxiliary domains to enrich information within the target domain. However, inherent domain gaps can degrade the quality of mixed-domain data, leading to negative transfer and diminished model performance. Existing prevailing \emph{model-centric} paradigm -- which relies on complex, customized architectures -- struggles to capture the subtle, non-structural sequence dependencies across domains, leading to poor generalization and high demands on computational resources. To address these shortcomings, we propose \textsc{Taesar}, a \emph{data-centric} framework for \textbf{t}arget-\textbf{a}lign\textbf{e}d \textbf{s}equenti\textbf{a}l \textbf{r}egeneration, which employs a contrastive decoding mechanism to adaptively encode cross-domain context into target-domain sequences. It employs contrastive decoding to encode cross-domain context into target sequences, enabling standard models to learn intricate dependencies without complex fusion architectures. Experiments show \textsc{Taesar} outperforms model-centric solutions and generalizes to various sequential models. By generating enriched datasets, \textsc{Taesar} effectively combines the strengths of data- and model-centric paradigms. The code accompanying this paper is available at~ \textcolor{blue}{https://github.com/USTC-StarTeam/Taesar}. --- ### ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control Authors: Akihisa Watanabe, Qing Yu, Edgar Simo-Serra, Kent Fujiwara Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22742v1 Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion naturalness. Building on the observation that many animation tasks can be formulated as a linear inverse problem, we introduce ProjFlow, a training-free sampler that achieves zero-shot, exact satisfaction of linear spatial constraints while preserving motion realism. Our key advance is a novel kinematics-aware metric that encodes skeletal topology. This metric allows the sampler to enforce hard constraints by distributing corrections coherently across the entire skeleton, avoiding the unnatural artifacts of naive projection. Furthermore, for sparse inputs, such as filling in long gaps between a few keyframes, we introduce a time-varying formulation using pseudo-observations that fade during sampling. Extensive experiments on representative applications, motion inpainting, and 2D-to-3D lifting, demonstrate that ProjFlow achieves exact constraint satisfaction and matches or improves realism over zero-shot baselines, while remaining competitive with training-based controllers. --- ### AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation Authors: Tongfei Chen, Shuo Yang, Yuguang Yang, Linlin Yang, Runtang Guo, Changbai Li, He Long, Chunyu Xie, Dawei Leng, Baochang Zhang Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.22740v2 Referring Image Segmentation (RIS) aims to segment the object in an image uniquely referred to by a natural language expression. However, RIS training often contains hard-to-align and instance-specific visual signals; optimizing on such pixels injects misleading gradients and drives the model in the wrong direction. By explicitly estimating pixel-level vision-language alignment, the learner can suppress low-alignment regions, concentrate on reliable cues, and acquire more generalizable alignment features. In this paper, we propose Alignment-Aware Masked Learning (AML), a simple yet effective training strategy that quantifies region-referent alignment (PMME) and filters out unreliable pixels during optimization (AFM). Specifically, each sample first computes a similarity map between visual and textual features, and then masks out pixels falling below an adaptive similarity threshold, thereby excluding poorly aligned regions from the training process. AML does not require architectural changes and incurs no inference overhead, directing attention to the areas aligned with the textual description. Experiments on the RefCOCO (vanilla/+/g) datasets show that AML achieves state-of-the-art results across all 8 splits, and beyond improving RIS performance, AML also enhances the model's robustness to diverse descriptions and scenarios. Code is available at https://github.com/pipashu1/AMLRIS. --- ### Simulation-based Optimization for Augmented Reading Authors: Yunpeng Bai, Shengdong Zhao, Antti Oulasvirta Published: 2026-02-26 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.22735v1 Augmented reading systems aim to adapt text presentation to improve comprehension and task performance, yet existing approaches rely heavily on heuristics, opaque data-driven models, or repeated human involvement in the design loop. We propose framing augmented reading as a simulation-based optimization problem grounded in resource-rational models of human reading. These models instantiate a simulated reader that allocates limited cognitive resources, such as attention, memory, and time under task demands, enabling systematic evaluation of text user interfaces. We introduce two complementary optimization pipelines: an offline approach that explores design alternatives using simulated readers, and an online approach that personalizes reading interfaces in real time using ongoing interaction data. Together, this perspective enables adaptive, explainable, and scalable augmented reading design without relying solely on human testing. --- ### Asymmetric Idiosyncrasies in Multimodal Models Authors: Muzi Tao, Chufan Shi, Huijuan Wang, Shengbang Tong, Xuezhe Ma Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22734v1 In this work, we study idiosyncrasies in the caption models and their downstream impact on text-to-image models. We design a systematic analysis: given either a generated caption or the corresponding image, we train neural networks to predict the originating caption model. Our results show that text classification yields very high accuracy (99.70\%), indicating that captioning models embed distinctive stylistic signatures. In contrast, these signatures largely disappear in the generated images, with classification accuracy dropping to at most 50\% even for the state-of-the-art Flux model. To better understand this cross-modal discrepancy, we further analyze the data and find that the generated images fail to preserve key variations present in captions, such as differences in the level of detail, emphasis on color and texture, and the distribution of objects within a scene. Overall, our classification-based framework provides a novel methodology for quantifying both the stylistic idiosyncrasies of caption models and the prompt-following ability of text-to-image systems. --- ### Generative Recommendation for Large-Scale Advertising Authors: Ben Xue, Dan Liu, Lixiang Wang, Mingjie Sun, Peng Wang, Pengfei Zhang, Shaoyun Shi, Tianyu Xu, Yunhao Sha, Zhiqiang Liu, Bo Kong, Bo Wang et al. Published: 2026-02-26 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.22732v3 Generative recommendation has recently attracted widespread attention in industry due to its potential for scaling and stronger model capacity. However, deploying real-time generative recommendation in large-scale advertising requires designs beyond large-language-model (LLM)-style training and serving recipes. We present a production-oriented generative recommender co-designed across architecture, learning, and serving, named GR4AD (Generative Recommendation for ADdvertising). As for tokenization, GR4AD proposes UA-SID (Unified Advertisement Semantic ID) to capture complicated business information. Furthermore, GR4AD introduces LazyAR, a lazy autoregressive decoder that relaxes layer-wise dependencies for short, multi-candidate generation, preserving effectiveness while reducing inference cost, which facilitates scaling under fixed serving budgets. To align optimization with business value, GR4AD employs VSL (Value-Aware Supervised Learning) and proposes RSPO (Ranking-Guided Softmax Preference Optimization), a ranking-aware, list-wise reinforcement learning algorithm that optimizes value-based rewards under list-level metrics for continual online updates. For online inference, we further propose dynamic beam serving, which adapts beam width across generation levels and online load to control compute. Large-scale online A/B tests show up to 4.2% ad revenue improvement over an existing DLRM-based stack, with consistent gains from both model scaling and inference-time scaling. GR4AD has been fully deployed in Kuaishou advertising system with over 400 million users and achieves high-throughput real-time serving. --- ### Sapling-NeRF: Geo-Localised Sapling Reconstruction in Forests for Ecological Monitoring Authors: Miguel Ángel Muñoz-Bañón, Nived Chebrolu, Sruthi M. Krishna Moorthy, Yifu Tao, Fernando Torres, Roberto Salguero-Gómez, Maurice Fallon Published: 2026-02-26 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.22731v1 Saplings are key indicators of forest regeneration and overall forest health. However, their fine-scale architectural traits are difficult to capture with existing 3D sensing methods, which make quantitative evaluation difficult. Terrestrial Laser Scanners (TLS), Mobile Laser Scanners (MLS), or traditional photogrammetry approaches poorly reconstruct thin branches, dense foliage, and lack the scale consistency needed for long-term monitoring. Implicit 3D reconstruction methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) are promising alternatives, but cannot recover the true scale of a scene and lack any means to be accurately geo-localised. In this paper, we present a pipeline which fuses NeRF, LiDAR SLAM, and GNSS to enable repeatable, geo-localised ecological monitoring of saplings. Our system proposes a three-level representation: (i) coarse Earth-frame localisation using GNSS, (ii) LiDAR-based SLAM for centimetre-accurate localisation and reconstruction, and (iii) NeRF-derived object-centric dense reconstruction of individual saplings. This approach enables repeatable quantitative evaluation and long-term monitoring of sapling traits. Our experiments in forest plots in Wytham Woods (Oxford, UK) and Evo (Finland) show that stem height, branching patterns, and leaf-to-wood ratios can be captured with increased accuracy as compared to TLS. We demonstrate that accurate stem skeletons and leaf distributions can be measured for saplings with heights between 0.5m and 2m in situ, giving ecologists access to richer structural and quantitative data for analysing forest dynamics. --- ### Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks Authors: Jakub Šmíd, Pavel Přibáň, Pavel Král Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22730v2 This paper introduces a novel Czech dataset in the restaurant domain for aspect-based sentiment analysis (ABSA), enriched with annotations of opinion terms. The dataset supports three distinct ABSA tasks involving opinion terms, accommodating varying levels of complexity. Leveraging this dataset, we conduct extensive experiments using modern Transformer-based models, including large language models (LLMs), in monolingual, cross-lingual, and multilingual settings. To address cross-lingual challenges, we propose a translation and label alignment methodology leveraging LLMs, which yields consistent improvements. Our results highlight the strengths and limitations of state-of-the-art models, especially when handling the linguistic intricacies of low-resource languages like Czech. A detailed error analysis reveals key challenges, including the detection of subtle opinion terms and nuanced sentiment expressions. The dataset establishes a new benchmark for Czech ABSA, and our proposed translation-alignment approach offers a scalable solution for adapting ABSA resources to other low-resource languages. --- ### HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models Authors: Yangguang Lin, Quan Fang, Yufei Li, Jiachen Sun, Junyu Gao, Jitao Sang Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22727v1 Object hallucination in Large Vision-Language Models (LVLMs) significantly hinders their reliable deployment. Existing methods struggle to balance efficiency and accuracy: they often require expensive reference models and multiple forward passes, or apply static edits that risk suppressing genuine visual evidence. To address this, we introduce HulluEdit, a single-pass, reference-free intervention framework. Our core innovation is orthogonal subspace editing: we decompose the hidden states of the model into orthogonal subspaces - visual evidence, conflicting priors, and residual uncertainty - enabling selective suppression of hallucinatory patterns without interfering with visual grounding. This approach mathematically guarantees that edits applied to the prior subspace leave the visual component entirely unaffected. Extensive experiments show that HulluEdit achieves state-of-the-art hallucination reduction on benchmarks including POPE and CHAIR across diverse architectures, while preserving general capabilities on MME and maintaining efficient inference. Our method consistently outperforms contrastive decoding and static subspace editing baselines, offering a new pathway toward more trustworthy LVLMs. --- ### AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification Authors: Tian Zhang, Yiwei Xu, Juan Wang, Keyan Guo, Xiaoyang Xu, Bowen Xiao, Quanlong Guan, Jinlin Fan, Jiawei Liu, Zhiquan Liu, Hongxin Hu Published: 2026-02-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.22724v1 Large language model (LLM) agents increasingly rely on external tools and retrieval systems to autonomously complete complex tasks. However, this design exposes agents to indirect prompt injection (IPI), where attacker-controlled context embedded in tool outputs or retrieved content silently steers agent actions away from user intent. Unlike prompt-based attacks, IPI unfolds over multi-turn trajectories, making malicious control difficult to disentangle from legitimate task execution. Existing inference-time defenses primarily rely on heuristic detection and conservative blocking of high-risk actions, which can prematurely terminate workflows or broadly suppress tool usage under ambiguous multi-turn scenarios. We propose AgentSentry, a novel inference-time detection and mitigation framework for tool-augmented LLM agents. To the best of our knowledge, AgentSentry is the first inference-time defense to model multi-turn IPI as a temporal causal takeover. It localizes takeover points via controlled counterfactual re-executions at tool-return boundaries and enables safe continuation through causally guided context purification that removes attack-induced deviations while preserving task-relevant evidence. We evaluate AgentSentry on the \textsc{AgentDojo} benchmark across four task suites, three IPI attack families, and multiple black-box LLMs. AgentSentry eliminates successful attacks and maintains strong utility under attack, achieving an average Utility Under Attack (UA) of 74.55 %, improving UA by 20.8 to 33.6 percentage points over the strongest baselines without degrading benign performance. --- ### Human Label Variation in Implicit Discourse Relation Recognition Authors: Frances Yung, Daniil Ignatev, Merel Scholman, Vera Demberg, Massimo Poesio Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.22723v1 There is growing recognition that many NLP tasks lack a single ground truth, as human judgments reflect diverse perspectives. To capture this variation, models have been developed to predict full annotation distributions rather than majority labels, while perspectivist models aim to reproduce the interpretations of individual annotators. In this work, we compare these approaches on Implicit Discourse Relation Recognition (IDRR), a highly ambiguous task where disagreement often arises from cognitive complexity rather than ideological bias. Our experiments show that existing annotator-specific models perform poorly in IDRR unless ambiguity is reduced, whereas models trained on label distributions yield more stable predictions. Further analysis indicates that frequent cognitively demanding cases drive inconsistency in human interpretation, posing challenges for perspectivist modeling in IDRR. ---