Showing 1–50 of 2,032 results for author: Lin, J

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning

Authors: Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang

Abstract: Conventional Retrieval-Augmented Generation (RAG) systems often struggle with complex multi-hop queries over long documents due to their single-pass retrieval. We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. To incentivize the information seeking capabi… ▽ More Conventional Retrieval-Augmented Generation (RAG) systems often struggle with complex multi-hop queries over long documents due to their single-pass retrieval. We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. To incentivize the information seeking capabilities of our agents, we propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO. Our core insight is that in multi-turn RL, the more semantically similar two trajectories are, the more accurate their shared baseline estimation becomes. Leveraging this, SPO calculates a more precise baseline by similarity-weighted averaging of rewards across multiple trajectories, unlike GRPO which inappropriately applies the initial state's baseline to all intermediate states. This provides a more stable and accurate learning signal for our agents, leading to superior training performance that surpasses GRPO. Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%. Furthermore, SPO demonstrates superior performance over GRPO, boosting results by 5.0% with Qwen3-8B and 6.1% with Qwen3-4B. These results highlight the effectiveness of our integrated framework and novel training algorithm in advancing the state-of-the-art for complex, long-document visual question answering. △ Less

Submitted 15 April, 2026; originally announced April 2026.

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

Authors: Donghao Zhou, Guisheng Liu, Hao Yang, Jiatong Li, Jingyu Lin, Xiaohu Huang, Yichen Liu, Xin Gao, Cunjian Chen, Shilei Wen, Chi-Wing Fu, Pheng-Ann Heng

Abstract: In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditioned on text, reference images, audio, and pose. This task holds significant practical value for automating content creation in real-world applications, such as e-commerce demonstrations, short video production, and interactive entertainment. Howeve… ▽ More In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditioned on text, reference images, audio, and pose. This task holds significant practical value for automating content creation in real-world applications, such as e-commerce demonstrations, short video production, and interactive entertainment. However, existing approaches fail to accommodate all these requisite conditions. We present OmniShow, an end-to-end framework tailored for this practical yet challenging task, capable of harmonizing multimodal conditions and delivering industry-grade performance. To overcome the trade-off between controllability and quality, we introduce Unified Channel-wise Conditioning for efficient image and pose injection, and Gated Local-Context Attention to ensure precise audio-visual synchronization. To effectively address data scarcity, we develop a Decoupled-Then-Joint Training strategy that leverages a multi-stage training process with model merging to efficiently harness heterogeneous sub-task datasets. Furthermore, to fill the evaluation gap in this field, we establish HOIVG-Bench, a dedicated and comprehensive benchmark for HOIVG. Extensive experiments demonstrate that OmniShow achieves overall state-of-the-art performance across various multimodal conditioning settings, setting a solid standard for the emerging HOIVG task. △ Less

Submitted 13 April, 2026; originally announced April 2026.

Comments: Project page: https://correr-zhou.github.io/OmniShow/

LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation

Authors: Yuqian Yuan, Wenqiao Zhang, Juekai Lin, Yu Zhong, Mingjian Gao, Binhe Yu, Yunqi Cao, Wentong Li, Yueting Zhuang, Beng Chin Ooi

Abstract: Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring precise object-level grounding, fine-grained spatial reasoning, and controllable visual manipulation. In particular, existing systems often struggle to identify the correct instance, preserve object identity across interactions, and localize… ▽ More Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring precise object-level grounding, fine-grained spatial reasoning, and controllable visual manipulation. In particular, existing systems often struggle to identify the correct instance, preserve object identity across interactions, and localize or modify designated regions with high precision. Object-centric vision provides a principled framework for addressing these challenges by promoting explicit representations and operations over visual entities, thereby extending multimodal systems from global scene understanding to object-level understanding, segmentation, editing, and generation. This paper presents a comprehensive review of recent advances at the convergence of LMMs and object-centric vision. We organize the literature into four major themes: object-centric visual understanding, object-centric referring segmentation, object-centric visual editing, and object-centric visual generation. We further summarize the key modeling paradigms, learning strategies, and evaluation protocols that support these capabilities. Finally, we discuss open challenges and future directions, including robust instance permanence, fine-grained spatial control, consistent multi-step interaction, unified cross-task modeling, and reliable benchmarking under distribution shift. We hope this paper provides a structured perspective on the development of scalable, precise, and trustworthy object-centric multimodal systems. △ Less

Submitted 13 April, 2026; originally announced April 2026.

Comments: 38 pages, 6 figures

STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation

Authors: Jierun Lin, Jiacong Chen, Qingyu Mao, Shuai Liu, Xiandong Meng, Fanyang Meng, Yongsheng Liang

Abstract: 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inac… ▽ More 2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inaccurate predictions for spatio-temporal deformations and unsatisfactory representation quality. To address these problems, this paper proposes a Spatio-Temporal hash encoding framework for Gaussian-based Video representation (STGV). By decomposing video features into learnable 2D spatial and 3D temporal hash encodings, STGV effectively facilitates the learning of motion patterns for dynamic components while maintaining background details for static elements. In addition, we construct a more stable and consistent initial canonical Gaussian representation through a key frame canonical initialization strategy, preventing from feature overlapping and a structurally incoherent geometry representation. Experimental results demonstrate that our method attains better video representation quality (+0.98 PSNR) against other Gaussian-based methods and achieves competitive performance in downstream video tasks. △ Less

Submitted 13 April, 2026; v1 submitted 12 April, 2026; originally announced April 2026.

MMRareBench: A Rare-Disease Multimodal and Multi-Image Medical Benchmark

Authors: Junzhi Ning, Jiashi Lin, Yingying Fang, Wei Li, Jiyao Liu, Cheng Tang, Chenglong Ma, Wenhao Tang, Tianbin Li, Ziyan Huang, Guang Yang, Junjun He

Abstract: Multimodal large language models (MLLMs) have advanced clinical tasks for common conditions, but their performance on rare diseases remains largely untested. In rare-disease scenarios, clinicians often lack prior clinical knowledge, forcing them to rely strictly on case-level evidence for clinical judgments. Existing benchmarks predominantly evaluate common-condition, single-image settings, leavin… ▽ More Multimodal large language models (MLLMs) have advanced clinical tasks for common conditions, but their performance on rare diseases remains largely untested. In rare-disease scenarios, clinicians often lack prior clinical knowledge, forcing them to rely strictly on case-level evidence for clinical judgments. Existing benchmarks predominantly evaluate common-condition, single-image settings, leaving multimodal and multi-image evidence integration under rare-disease data scarcity systematically unevaluated. We introduce MMRareBench, to our knowledge the first rare-disease benchmark jointly evaluating multimodal and multi-image clinical capability across four workflow-aligned tracks: diagnosis, treatment planning, cross-image evidence alignment, and examination suggestion. The benchmark comprises 1,756 question-answer pairs with 7,958 associated medical images curated from PMC case reports, with Orphanet-anchored ontology alignment, track-specific leakage control, evidence-grounded annotations, and a two-level evaluation protocol. A systematic evaluation of 23 MLLMs reveals fragmented capability profiles and universally low treatment-planning performance, with medical-domain models trailing general-purpose MLLMs substantially on multi-image tracks despite competitive diagnostic scores. These patterns are consistent with a capacity dilution effect: medical fine-tuning can narrow the diagnostic gap but may erode the compositional multi-image capability that rare-disease evidence integration demands. △ Less

Submitted 12 April, 2026; originally announced April 2026.

Expect the Unexpected? Testing the Surprisal of Salient Entities

Authors: Jessica Lin, Amir Zeldes

Abstract: Previous work examining the Uniform Information Density (UID) hypothesis has shown that while information as measured by surprisal metrics is distributed more or less evenly across documents overall, local discrepancies can arise due to functional pressures corresponding to syntactic and discourse structural constraints. However, work thus far has largely disregarded the relative salience of disco… ▽ More Previous work examining the Uniform Information Density (UID) hypothesis has shown that while information as measured by surprisal metrics is distributed more or less evenly across documents overall, local discrepancies can arise due to functional pressures corresponding to syntactic and discourse structural constraints. However, work thus far has largely disregarded the relative salience of discourse participants. We fill this gap by studying how overall salience of entities in discourse relates to surprisal using 70K manually annotated mentions across 16 genres of English and a novel minimal-pair prompting method. Our results show that globally salient entities exhibit significantly higher surprisal than non-salient ones, even controlling for position, length, and nesting confounds. Moreover, salient entities systematically reduce surprisal for surrounding content when used as prompts, enhancing document-level predictability. This effect varies by genre, appearing strongest in topic-coherent texts and weakest in conversational contexts. Our findings refine the UID competing pressures framework by identifying global entity salience as a mechanism shaping information distribution in discourse. △ Less

Submitted 12 April, 2026; originally announced April 2026.

Comments: Accepted to ACL 2026 (main, long); camera-ready version

Building Regulation Capacity in Human-AI Collaborative Learning: A Human-Centred GenAI System

Authors: Yujing Zhang, Jionghao Lin

Abstract: Collaborative learning works when groups regulate together by setting shared goals, coordinating participation, monitoring progress, and responding to breakdowns through co-regulation (CoRL) and socially shared regulation (SSRL). As generative AI (GenAI) enters group work, however, it remains unclear whether and how it supports these socially distributed regulation processes. This doctoral project… ▽ More Collaborative learning works when groups regulate together by setting shared goals, coordinating participation, monitoring progress, and responding to breakdowns through co-regulation (CoRL) and socially shared regulation (SSRL). As generative AI (GenAI) enters group work, however, it remains unclear whether and how it supports these socially distributed regulation processes. This doctoral project proposes a GenAI-supported collaborative learning system grounded in CoRL and SSRL to strengthen groups' socially distributed regulation capacity. The system links three components: (1) group activity generation; (2) an in-group support agent that provides process-focused prompts without giving solutions; and (3) an embedded learning analytics dashboard that turns interaction traces into timely summaries for monitoring and decision making. The project progresses from mechanism to design to impact: it first identifies how GenAI reshapes regulation patterns and which patterns indicate more effective Human-AI collaboration, then builds an integrated GenAI system that targets these patterns, and finally evaluates whether the GenAI system improves regulation capacity and group performance across varying levels of GenAI involvement. Expected contributions include a teacher-in-the-loop system for Human-AI collaboration and process-level evidence on how GenAI reconfigures CoRL and SSRL in group work. △ Less

Submitted 11 April, 2026; originally announced April 2026.

Comments: 7 pages, 2 figures. Accepted at AIED 2026

The Double-Edged Sword of Open-Ended Interaction: How LLM-Driven NPCs Affect Players' Cognitive Load and Gaming Experience

Authors: Ting-Chen Hsu, Wenran Chen, Jiangxu Lin, Fei Qin, Zheyuan Zhang

Abstract: This study examines how large language model-driven non-player characters (LLM-NPCs) affect players' cognitive load and gaming experience, with a particular focus on the underlying psychological mechanisms, differences across task scenarios, and the role of individual traits. Conducting a randomized between-subject experiment (N=130) in a self-developed game prototype "Campus Culture Week", we com… ▽ More This study examines how large language model-driven non-player characters (LLM-NPCs) affect players' cognitive load and gaming experience, with a particular focus on the underlying psychological mechanisms, differences across task scenarios, and the role of individual traits. Conducting a randomized between-subject experiment (N=130) in a self-developed game prototype "Campus Culture Week", we compared player interactions with LLM-NPCs and traditional pre-scripted NPCs across multiple interactive modules. The results showed that LLM-NPCs significantly increased players' cognitive load (p < .001), an effect mediated by factors such as expressive effort and response uncertainty. However, LLM-NPCs did not yield a statistically significant improvement in overall gaming experience (p = .195); while they positively influenced players' perceived autonomy, they exerted a negative influence on system usability and trust. The effects of LLM-NPCs also significantly varied across task scenarios (p < .001), with stronger increases in cognitive load in more open-ended modules such as content creation and relationship building. The influence of individual differences was generally limited, although the personality traits of extraversion (p = .031) and neuroticism (p = .047) demonstrated some predictive power regarding cognitive load. This study provides empirical evidence for understanding the "double-edged sword" effect of LLM-NPCs on player experience, and highlight the importance of scenario-sensitive and user-sensitive design in intelligent NPC systems. △ Less

Submitted 11 April, 2026; originally announced April 2026.

Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization

Authors: Jiachen Zhu, Lingyu Yang, Rong Shan, Congmin Zheng, Zeyu Zheng, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin

Abstract: The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive in human-centric ecosystems, they must evolve Humanization capabilities. We introduce the ``Turing Test on Screen,'' formally modeling the interaction as a MinM… ▽ More The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive in human-centric ecosystems, they must evolve Humanization capabilities. We introduce the ``Turing Test on Screen,'' formally modeling the interaction as a MinMax optimization problem between a detector and an agent aiming to minimize behavioral divergence. We then collect a new high-fidelity dataset of mobile touch dynamics, and conduct our analysis that vanilla LMM-based agents are easily detectable due to unnatural kinematics. Consequently, we establish the Agent Humanization Benchmark (AHB) and detection metrics to quantify the trade-off between imitability and utility. Finally, we propose methods ranging from heuristic noise to data-driven behavioral matching, demonstrating that agents can achieve high imitability theoretically and empirically without sacrificing performance. This work shifts the paradigm from whether an agent can perform a task to how it performs it within a human-centric ecosystem, laying the groundwork for seamless coexistence in adversarial digital environments. △ Less

Submitted 23 February, 2026; originally announced April 2026.

SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos

Authors: Xiyang Huang, Jiawei Lin, Keying Wu, Jiaxin Huang, Kailai Yang, Renxiong Wei, Cheng zeng, Jiayi Xiang, Ziyan Kuang, Min Peng, Qianqian Xie, Sophia Ananiadou

Abstract: Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing interactions update the procedural state and thereby determine the correctness of later actions. We introduce SiMing-Bench, the first benchmark for evaluating this… ▽ More Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing interactions update the procedural state and thereby determine the correctness of later actions. We introduce SiMing-Bench, the first benchmark for evaluating this capability from full-length clinical skill videos. It targets rubric-grounded process-level judgment of whether interaction-driven state updates preserve procedural correctness across an entire workflow. SiMing-Bench is instantiated with SiMing-Score, a physician-annotated dataset of real clinical skill examination videos spanning cardiopulmonary resuscitation, automated external defibrillator operation, and bag-mask ventilation, each paired with a standardized step-wise rubric and dual-expert labels. Across diverse open- and closed-source MLLMs, we observe consistently weak agreement with physician judgments. Moreover, weak performance on rubric-defined intermediate steps persists even when overall procedure-level correlation appears acceptable, suggesting that coarse global assessment substantially overestimates current models' procedural judgment ability. Additional analyses with binary step judgment and step-aligned clips indicate that the bottleneck is not merely fine-grained scoring or temporal localization, but modeling how continuous interactions update procedural state over time. △ Less

Submitted 10 April, 2026; originally announced April 2026.

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)

Authors: Lishen Qu, Yao Liu, Jie Liang, Hui Zeng, Wen Dai, Guanyi Qin, Ya-nan Guan, Shihao Zhou, Jufeng Yang, Lei Zhang, Radu Timofte, Xiyuan Yuan, Wanjie Sun, Shihang Li, Bo Zhang, Bin Chen, Jiannan Lin, Yuxu Chen, Qinquan Gao, Tong Tong, Song Gao, Jiacong Tang, Tao Hu, Xiaowen Ma, Qingsen Yan , et al. (10 additional authors not shown)

Abstract: This paper presents NTIRE 2026, the 3rd Restore Any Image Model (RAIM) challenge on multi-exposure image fusion in dynamic scenes. We introduce a benchmark that targets a practical yet difficult HDR imaging setting, where exposure bracketing must be fused under scene motion, illumination variation, and handheld camera jitter. The challenge data contains 100 training sequences with 7 exposure level… ▽ More This paper presents NTIRE 2026, the 3rd Restore Any Image Model (RAIM) challenge on multi-exposure image fusion in dynamic scenes. We introduce a benchmark that targets a practical yet difficult HDR imaging setting, where exposure bracketing must be fused under scene motion, illumination variation, and handheld camera jitter. The challenge data contains 100 training sequences with 7 exposure levels and 100 test sequences with 5 exposure levels, reflecting real-world scenarios that frequently cause misalignment and ghosting artefacts. We evaluate submissions with a leaderboard score derived from PSNR, SSIM, and LPIPS, while also considering perceptual quality, efficiency, and reproducibility during the final review. This track attracted 114 participating teams and received 987 submissions. The winning methods significantly improved the ability to remove artifacts from multi-exposure fusion and recover fine details. The dataset and the code of each team can be found at the repository: https://github.com/qulishen/RAIM-HDR. △ Less

Submitted 10 April, 2026; originally announced April 2026.

Comments: Accepted by CVPRW 2026

BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields

Authors: Fan Yang, Wenrui Chen, Guorun Yan, Ruize Liao, Wanjun Jia, Dongsheng Luo, Jiacheng Lin, Kailun Yang, Zhiyong Li, Yaonan Wang

Abstract: In unstructured environments, functional dexterous grasping calls for the tight integration of semantic understanding, precise 3D functional localization, and physically interpretable execution. Modular hierarchical methods are more controllable and interpretable than end-to-end VLA approaches, but existing ones still rely on predefined affordance labels and lack the tight semantic--pose coupling… ▽ More In unstructured environments, functional dexterous grasping calls for the tight integration of semantic understanding, precise 3D functional localization, and physically interpretable execution. Modular hierarchical methods are more controllable and interpretable than end-to-end VLA approaches, but existing ones still rely on predefined affordance labels and lack the tight semantic--pose coupling needed for functional dexterous manipulation. To address this, we propose BLaDA (Bridging Language to Dexterous Actions in 3DGS fields), an interpretable zero-shot framework that grounds open-vocabulary instructions as perceptual and control constraints for functional dexterous manipulation. BLaDA establishes an interpretable reasoning chain by first parsing natural language into a structured sextuple of manipulation constraints via a Knowledge-guided Language Parsing (KLP) module. To achieve pose-consistent spatial reasoning, we introduce the Triangular Functional Point Localization (TriLocation) module, which utilizes 3D Gaussian Splatting as a continuous scene representation and identifies functional regions under triangular geometric constraints. Finally, the 3D Keypoint Grasp Matrix Transformation Execution (KGT3D+) module decodes these semantic-geometric constraints into physically plausible wrist poses and finger-level commands. Extensive experiments on complex benchmarks demonstrate that BLaDA significantly outperforms existing methods in both affordance grounding precision and the success rate of functional manipulation across diverse categories and tasks. Code will be publicly available at https://github.com/PopeyePxx/BLaDA. △ Less

Submitted 14 April, 2026; v1 submitted 9 April, 2026; originally announced April 2026.

Comments: Code will be publicly available at https://github.com/PopeyePxx/BLaDA

Human-AI Collaboration Reconfigures Group Regulation from Socially Shared to Hybrid Co-Regulation

Authors: Yujing Zhang, Xianghui Meng, Shihui Feng, Jionghao Lin

Abstract: Generative AI (GenAI) is increasingly used in collaborative learning, yet its effects on how groups regulate collaboration remain unclear. Effective collaboration depends not only on what groups discuss, but on how they jointly manage goals, participation, strategy use, monitoring, and repair through co-regulation and socially shared regulation. We compared collaborative regulation between Human-A… ▽ More Generative AI (GenAI) is increasingly used in collaborative learning, yet its effects on how groups regulate collaboration remain unclear. Effective collaboration depends not only on what groups discuss, but on how they jointly manage goals, participation, strategy use, monitoring, and repair through co-regulation and socially shared regulation. We compared collaborative regulation between Human-AI and Human-Human groups in a parallel-group randomised experiment with 71 university students completing the same collaborative tasks with GenAI either available or unavailable. Focusing on human discourse, we used statistical analyses to examine differences in the distribution of collaborative regulation across regulatory modes, regulatory processes, and participatory focuses. Results showed that GenAI availability shifted regulation away from predominantly socially shared forms towards more hybrid co-regulatory forms, with selective increases in directive, obstacle-oriented, and affective regulatory processes. Participatory-focus distributions, however, were broadly similar across conditions. These findings suggest that GenAI reshapes the distribution of regulatory responsibility in collaboration and offer implications for the human-centred design of AI-supported collaborative learning. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Comments: 9 pages, 2 figures. Accepted at AIED 2026. Camera-ready version with updated references

EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment

Authors: Qiance Tang, Ziqi Wang, Jieyu Lin, Ziyun Li, Barbara De Salvo, Sai Qian Zhang

Abstract: Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of its most important application domains. Nevertheless, the task remains highly challenging due to the need for reasoning over extended temporal contexts and diverse, unstructured activities. Although several benchmarks exist, most egocentric datasets r… ▽ More Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of its most important application domains. Nevertheless, the task remains highly challenging due to the need for reasoning over extended temporal contexts and diverse, unstructured activities. Although several benchmarks exist, most egocentric datasets rely on human worn cameras and focus mainly on visual content, with limited consideration of underlying user behavior when forming video-related queries. EgoEverything is a benchmark that explicitly considers human behavior by leveraging human attention signals, abstracted from gaze data, when generating questions. It comprises over 5,000 multiple choice question answer pairs, spanning more than 100 hours of video. By integrating human attention signals during question generation, it more faithfully captures natural human behavior and offers a realistic evaluation setting for long-context egocentric video understanding in AR. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

Authors: Chenyu Zhou, Huacan Chai, Wenteng Chen, Zihan Guo, Rong Shan, Yuanyi Song, Tianyi Xu, Yingxuan Yang, Aofan Yu, Weiming Zhang, Congming Zheng, Jiachen Zhu, Zeyu Zheng, Zhuosheng Zhang, Xingyu Lou, Changwang Zhang, Zhihui Fu, Jun Wang, Weiwen Liu, Jianghao Lin, Weinan Zhang

Abstract: Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the model to recover internally are now externalized into memory stores, reusable skills, interaction protocols, and the surrounding harness that makes these modules reliable in practice. This paper reviews that shift throu… ▽ More Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the model to recover internally are now externalized into memory stores, reusable skills, interaction protocols, and the surrounding harness that makes these modules reliable in practice. This paper reviews that shift through the lens of externalization. Drawing on the idea of cognitive artifacts, we argue that agent infrastructure matters not merely because it adds auxiliary components, but because it transforms hard cognitive burdens into forms that the model can solve more reliably. Under this view, memory externalizes state across time, skills externalize procedural expertise, protocols externalize interaction structure, and harness engineering serves as the unification layer that coordinates them into governed execution. We trace a historical progression from weights to context to harness, analyze memory, skills, and protocols as three distinct but coupled forms of externalization, and examine how they interact inside a larger agent system. We further discuss the trade-off between parametric and externalized capability, identify emerging directions such as self-evolving harnesses and shared agent infrastructure, and discuss open challenges in evaluation, governance, and the long-term co-evolution of models and external infrastructure. The result is a systems-level framework for explaining why practical agent progress increasingly depends not only on stronger models, but on better external cognitive infrastructure. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Comments: 54 pages, tech report on Externalization in LLM Agents

IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling

Authors: Zhaomeng Zhou, Lan Zhang, Junyang Wang, Mu Yuan, Junda Lin, Jinke Song

Abstract: Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap. While large language models (LLMs) excel at semantic understanding, existing perception-centric pipelines operate retrospectively, overlooking the fundamental decision of what to sense and when. We formalize this proac… ▽ More Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap. While large language models (LLMs) excel at semantic understanding, existing perception-centric pipelines operate retrospectively, overlooking the fundamental decision of what to sense and when. We formalize this proactive decision as Semantic-Spatial Sensor Scheduling (S3) and demonstrate that direct LLM planning is unreliable due to inherent gaps in representation, reasoning, and optimization. To bridge these gaps, we introduce the Spatial Trajectory Graph (STG), a neuro-symbolic paradigm governed by a verify-before-commit discipline that transforms open-ended planning into a verifiable graph optimization problem. Based on STG, we implement IoT-Brain, a concrete system embodiment, and construct TopoSense-Bench, a campus-scale benchmark with 5,250 natural-language queries across 2,510 cameras. Evaluations show that IoT-Brain boosts task success rate by 37.6% over the strongest search-intensive methods while running nearly 2 times faster and using 6.6 times fewer prompt tokens. In real-world deployment, it approaches the reliability upper bound while reducing 4.1 times network bandwidth, providing a foundational framework for LLMs to interact with the physical world with unprecedented reliability and efficiency. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Comments: To appear in ACM MobiCom 2026; 13 pages, 12 figures

Assessing the Impact and Underlying Pathways of Sequenced AI feedback on Student Learning

Authors: Jie Cao, Chloe Qianhui Zhao, Christian Schunn, Elizabeth A. McLaughlin, Jionghao Lin, Kenneth R. Koedinger

Abstract: Feedback is essential for learning, but its effectiveness relies heavily on how well it engages students in the educational process. Generative AI offers novel opportunities to efficiently produce rich, formative feedback, ranging from direct explanations to incrementally sequenced scaffolding designed to promote learner autonomy. Despite these capabilities, it is still unclear whether sequenced (… ▽ More Feedback is essential for learning, but its effectiveness relies heavily on how well it engages students in the educational process. Generative AI offers novel opportunities to efficiently produce rich, formative feedback, ranging from direct explanations to incrementally sequenced scaffolding designed to promote learner autonomy. Despite these capabilities, it is still unclear whether sequenced (layered) AI feedback -- which provides encouragement and hints before revealing the correct answer -- genuinely enhances engagement and learning outcomes. To investigate this, we randomly assigned 199 participants to receive either sequenced or non-sequenced AI-generated feedback. We evaluated its impact on learning performance, cognitive and behavioral engagement, and affective perceptions to understand how these factors mediate overall learning outcomes. Results show that sequenced feedback elicited slightly higher behavioral engagement and, as anticipated, was perceived as more encouraging and supportive of student independence. Concurrently, however, it induced a higher level of mental effort. Mediation analyses identified a positive affective pathway driven by perceived encouragement, which was completely counteracted by a negative behavioral pathway associated with the average number of tasks requiring three or more submissions; the cognitive pathway (mental effort) remained non-significant. Overall, sequenced feedback led to significantly poorer learning outcomes when compared to direct, non-sequenced feedback. These findings highlight a crucial trade-off: although sequenced AI scaffolding boosts engagement and positive user perceptions, it can have a detrimental effect on actual learning performance. By integrating analyses of outcomes, perceptions, and underlying mechanisms, this study provides nuanced insights for designing automated, AI-driven feedback systems. △ Less

Submitted 14 April, 2026; v1 submitted 8 April, 2026; originally announced April 2026.

Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training

Authors: Jinhong Lin, Pan Wang, Zitong Zhan, Lin Zhang, Pedro Morgado

Abstract: A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a curriculum strategy that schedules training images from simple to complex without modifying the model or loss. Each image is scored offline by a semantic-aware co… ▽ More A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a curriculum strategy that schedules training images from simple to complex without modifying the model or loss. Each image is scored offline by a semantic-aware complexity metric combining foreground dominance (how much of the image salient objects occupy) and foreground typicality (how closely the salient content matches learned visual prototypes). A temperature-controlled sampler then prioritizes low-complexity images early and anneals toward uniform sampling. On ImageNet 256x256 with SiT backbones (S/2 to XL/2), Data Warmup improves IS by up to 6.11 and FID by up to 3.41, reaching baseline quality tens of thousands of iterations earlier. Reversing the curriculum (exposing hard images first) degrades performance below the uniform baseline, confirming that the simple-to-complex ordering itself drives the gains. The method combines with orthogonal accelerators such as REPA and requires only ~10 minutes of one-time preprocessing with zero per-iteration overhead. △ Less

Submitted 8 April, 2026; originally announced April 2026.

Comments: CVPRW in the proceedings of CVPR 2026

A comparative analysis of machine learning models in SHAP analysis

Authors: Justin Lin, Julia Fukuyama

Abstract: In this growing age of data and technology, large black-box models are becoming the norm due to their ability to handle vast amounts of data and learn incredibly complex data patterns. The deficiency of these methods, however, is their inability to explain the prediction process, making them untrustworthy and their use precarious in high-stakes situations. SHapley Additive exPlanations (SHAP) anal… ▽ More In this growing age of data and technology, large black-box models are becoming the norm due to their ability to handle vast amounts of data and learn incredibly complex data patterns. The deficiency of these methods, however, is their inability to explain the prediction process, making them untrustworthy and their use precarious in high-stakes situations. SHapley Additive exPlanations (SHAP) analysis is an explainable AI method growing in popularity for its ability to explain model predictions in terms of the original features. For each sample and feature in the data set, an associated SHAP value quantifies the contribution of that feature to the prediction of that sample. Analysis of these SHAP values provides valuable insight into the model's decision-making process, which can be leveraged to create data-driven solutions. The interpretation of these SHAP values, however, is model-dependent, so there does not exist a universal analysis procedure. To aid in these efforts, we present a detailed investigation of SHAP analysis across various machine learning models and data sets. In uncovering the details and nuance behind SHAP analysis, we hope to empower analysts in this less-explored territory. We also present a novel generalization of the waterfall plot to the multi-classification problem. △ Less

Submitted 8 April, 2026; originally announced April 2026.

Comments: 17 pages, 16 figures, 4 tables

On Emotion-Sensitive Decision Making of Small Language Model Agents

Authors: Jiaju Lin, Xingjian Du, Qingyun Wu, Ellen Wenting Zou, Jindong Wang

Abstract: Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations ignore emotion as a causal factor influencing behavior. We study emotion-sensitive decision making by combining representation-level emotion induction with a structured game-theoretic evaluation. Emotional states are induced using activation steering derived from crowd-va… ▽ More Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations ignore emotion as a causal factor influencing behavior. We study emotion-sensitive decision making by combining representation-level emotion induction with a structured game-theoretic evaluation. Emotional states are induced using activation steering derived from crowd-validated, real-world emotion-eliciting texts, enabling controlled and transferable interventions beyond prompt-based methods. We introduce a benchmark built around canonical decision templates that span cooperative and competitive incentives under both complete and incomplete information. These templates are instantiated using strategic scenarios from \textsc{Diplomacy}, \textsc{StarCraft II}, and diverse real-world personas. Experiments across multiple model families in various architecture and modalities, show that emotional perturbations systematically affect strategic choices, but the resulting behaviors are often unstable and not fully aligned with human expectations. Finally, we outline an approach to improve robustness to emotion-driven perturbations. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning

Authors: Juekai Lin, Yun Zhu, Honglin Lin, Sijing Li, Tianwei Lin, Zheng Liu, Xiaoyang Wang, Wenqiao Zhang, Lijun Wu

Abstract: Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is… ▽ More Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Precise Aggressive Aerial Maneuvers with Sensorimotor Policies

Authors: Tianyue Wu, Guangtong Xu, Zihan Wang, Junxiao Lin, Tianyang Chen, Yuze Wu, Zhichao Han, Zhiyang Liu, Fei Gao

Abstract: Precise aggressive maneuvers with lightweight onboard sensors remains a key bottleneck in fully exploiting the maneuverability of drones. Such maneuvers are critical for expanding the systems' accessible area by navigating through narrow openings in the environment. Among the most relevant problems, a representative one is aggressive traversal through narrow gaps with quadrotors under SE(3) constr… ▽ More Precise aggressive maneuvers with lightweight onboard sensors remains a key bottleneck in fully exploiting the maneuverability of drones. Such maneuvers are critical for expanding the systems' accessible area by navigating through narrow openings in the environment. Among the most relevant problems, a representative one is aggressive traversal through narrow gaps with quadrotors under SE(3) constraints, which require the quadrotors to leverage a momentary tilted attitude and the asymmetry of the airframe to navigate through gaps. In this paper, we achieve such maneuvers by developing sensorimotor policies directly mapping onboard vision and proprioception into low-level control commands. The policies are trained using reinforcement learning (RL) with end-to-end policy distillation in simulation. We mitigate the fundamental hardness of model-free RL's exploration on the restricted solution space with an initialization strategy leveraging trajectories generated by a model-based planner. Careful sim-to-real design allows the policy to control a quadrotor through narrow gaps with low clearances and high repeatability. For instance, the proposed method enables a quadrotor to navigate a rectangular gap at a 5 cm clearance, tilted at up to 90-degree orientation, without knowledge of the gap's position or orientation. Without training on dynamic gaps, the policy can reactively servo the quadrotor to traverse through a moving gap. The proposed method is also validated by training and deploying policies on challenging tracks of narrow gaps placed closely. The flexibility of the policy learning method is demonstrated by developing policies for geometrically diverse gaps, without relying on manually defined traversal poses and visual features. △ Less

Submitted 7 April, 2026; v1 submitted 7 April, 2026; originally announced April 2026.

Comments: This manuscript was submitted in June 2025. The first revision was submitted in November 2025. The second revision was submitted in February 2026. The first two authors contributed equally to this work

Primitive-based Truncated Diffusion for Efficient Trajectory Generation of Differential Drive Mobile Manipulators

Authors: Long Xu, Choilam Wong, Yuhang Zhong, Junxiao Lin, Jialiang Hou, Fei Gao

Abstract: We present a learning-enhanced motion planner for differential drive mobile manipulators to improve efficiency, success rate, and optimality. For task representation encoder, we propose a keypoint sequence extraction module that maps boundary states to 3D space via differentiable forward kinematics. Point clouds and keypoints are encoded separately and fused with attention, enabling effective inte… ▽ More We present a learning-enhanced motion planner for differential drive mobile manipulators to improve efficiency, success rate, and optimality. For task representation encoder, we propose a keypoint sequence extraction module that maps boundary states to 3D space via differentiable forward kinematics. Point clouds and keypoints are encoded separately and fused with attention, enabling effective integration of environment and boundary states information. We also propose a primitive-based truncated diffusion model that samples from a biased distribution. Compared with vanilla diffusion model, this framework improves the efficiency and diversity of the solution. Denoised paths are refined by trajectory optimization to ensure dynamic feasibility and task-specific optimality. In cluttered 3D simulations, our method achieves higher success rate, improved trajectory diversity, and competitive runtime compared to vanilla diffusion and classical baselines. The source code is released at https://github.com/nmoma/nmoma . △ Less

Submitted 5 April, 2026; originally announced April 2026.

Comments: 9 pages, 6 figures

MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers

Authors: Zhihan Guo, Rundong Xue, Yuting Lu, Jionghao Lin

Abstract: Novice math teachers often encounter students' mistakes that are difficult to diagnose and remediate. Misconceptions are especially challenging because teachers must explain what went wrong and how to solve them. Although many existing large language model (LLM) platforms can assist in generating instructional feedback, these LLMs loosely connect pedagogical knowledge and student mistakes, which m… ▽ More Novice math teachers often encounter students' mistakes that are difficult to diagnose and remediate. Misconceptions are especially challenging because teachers must explain what went wrong and how to solve them. Although many existing large language model (LLM) platforms can assist in generating instructional feedback, these LLMs loosely connect pedagogical knowledge and student mistakes, which might make the guidance less actionable for teachers. To address this gap, we propose MisEdu-RAG, a dual-hypergraph-based retrieval-augmented generation (RAG) framework that organizes pedagogical knowledge as a concept hypergraph and real student mistake cases as an instance hypergraph. Given a query, MisEdu-RAG performs a two-stage retrieval to gather connected evidence from both layers and generates a response grounded in the retrieved cases and pedagogical principles. We evaluate on \textit{MisstepMath}, a dataset of math mistakes paired with teacher solutions, as a benchmark for misconception-aware retrieval and response generation across topics and error types. Evaluation results on \textit{MisstepMath} show that, compared with baseline models, MisEdu-RAG improves token-F1 by 10.95\% and yields up to 15.3\% higher five-dimension response quality, with the largest gains on \textit{Diversity} and \textit{Empowerment}. To verify its applicability in practical use, we further conduct a pilot study through a questionnaire survey of 221 teachers and interviews with 6 novices. The findings suggest that MisEdu-RAG provides diagnosis results and concrete teaching moves for high-demand misconception scenarios. Overall, MisEdu-RAG demonstrates strong potential for scalable teacher training and AI-assisted instruction for misconception handling. Our code is available on GitHub: https://github.com/GEMLab-HKU/MisEdu-RAG. △ Less

Submitted 5 April, 2026; originally announced April 2026.

ACM Class: I.2.4; H.3.3; K.3.1

TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables

Authors: Xiaoyu Chen, Lu Dai, Hanqing Wang, Zhuoyu Li, Wenbin Dai, Yanzong Zheng, Zhenggang Xia, Junyong Lin, Hui Xiong

Abstract: Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance remains limited for complex tables with hierarchical layouts. In this paper, we identify a critical Perception Bottleneck through quantitative analysis. We find th… ▽ More Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance remains limited for complex tables with hierarchical layouts. In this paper, we identify a critical Perception Bottleneck through quantitative analysis. We find that as task complexity scales, the number of involved discrete visual regions increases disproportionately. This processing density leads to an internal "Perceptual Overload," where MLLMs struggle to maintain accurate spatial attention during implicit generation. To address this bottleneck, we introduce TableVision, a large-scale, trajectory-aware benchmark designed for spatially grounded reasoning. TableVision stratifies tabular tasks into three cognitive levels (Perception, Reasoning, and Analysis) across 13 sub-categories. By utilizing a rendering-based deterministic grounding pipeline, the dataset explicitly couples multi-step logical deductions with pixel-perfect spatial ground truths, comprising 6,799 high-fidelity reasoning trajectories. Our empirical results, supported by diagnostic probing, demonstrate that explicit spatial constraints significantly recover the reasoning potential of MLLMs. Furthermore, our two-stage decoupled framework achieves a robust 12.3% overall accuracy improvement on the test set. TableVision provides a rigorous testbed and a fresh perspective on the synergy between perception and logic in document understanding. △ Less

Submitted 4 April, 2026; originally announced April 2026.

ExpressEdit: Fast Editing of Stylized Facial Expressions with Diffusion Models in Photoshop

Authors: Kenan Tang, Jiasheng Guo, Jeffrey Lin, Yao Qin

Abstract: Facial expressions of characters are a vital component of visual storytelling. While current AI image editing models hold promise for assisting artists in the task of stylized expression editing, these models introduce global noise and pixel drift into the edited image, preventing the integration of these models into professional image editing software and workflows. To bridge this gap, we introdu… ▽ More Facial expressions of characters are a vital component of visual storytelling. While current AI image editing models hold promise for assisting artists in the task of stylized expression editing, these models introduce global noise and pixel drift into the edited image, preventing the integration of these models into professional image editing software and workflows. To bridge this gap, we introduce ExpressEdit, a fully open-source Photoshop plugin that is free from common artifacts of proprietary image editing models and robustly synergizes with native Photoshop operations such as Liquify. ExpressEdit seamlessly edits an expression within 3 seconds on a single consumer-grade GPU, significantly faster than popular proprietary models. Moreover, to support the generation of diverse expressions according to different narrative needs, we compile a comprehensive expression database of 135 expression tags enriched with example stories and images designed for retrieval-augmented generation. We open source the code and dataset to facilitate future research and artistic exploration. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: Accepted to CVPR 2026 Workshop on Generative AI for Storytelling (AISTORY)

Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots

Authors: Junyang Liang, Yuxuan Liu, Yabin Chang, Junfan Lin, Junkai Ji, Hui Li, Changxin Huang, Jianqiang Li

Abstract: Achieving quadruped robot locomotion across diverse and dynamic terrains presents significant challenges, primarily due to the discrepancies between simulation environments and real-world conditions. Traditional sim-to-real transfer methods often rely on manual feature design or costly real-world fine-tuning. To address these limitations, this paper proposes the DreamTIP framework, which incorpora… ▽ More Achieving quadruped robot locomotion across diverse and dynamic terrains presents significant challenges, primarily due to the discrepancies between simulation environments and real-world conditions. Traditional sim-to-real transfer methods often rely on manual feature design or costly real-world fine-tuning. To address these limitations, this paper proposes the DreamTIP framework, which incorporates Task-Invariant Properties learning within the Dreamer world model architecture to enhance sim-to-real transfer capabilities. Guided by large language models, DreamTIP identifies and leverages Task-Invariant Properties, such as contact stability and terrain clearance, which exhibit robustness to dynamic variations and strong transferability across tasks. These properties are integrated into the world model as auxiliary prediction targets, enabling the policy to learn representations that are insensitive to underlying dynamic changes. Furthermore, an efficient adaptation strategy is designed, employing a mixed replay buffer and regularization constraints to rapidly calibrate to real-world dynamics while effectively mitigating representation collapse and catastrophic forgetting. Extensive experiments on complex terrains, including Stair, Climb, Tilt, and Crawl, demonstrate that DreamTIP significantly outperforms state-of-the-art baselines in both simulated and real-world environments. Our method achieves an average performance improvement of 28.1% across eight distinct simulated transfer tasks. In the real-world Climb task, the baseline method achieved only a 10\ success rate, whereas our method attained a 100% success rate. These results indicate that incorporating Task-Invariant Properties into Dreamer learning offers a novel solution for achieving robust and transferable robot locomotion. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: Accepted by IEEE International Conference on Robotics and Automation (ICRA) 2026

Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

Authors: Xiaohang Nie, Zihan Guo, Zicai Cui, Jiachi Yang, Zeyi Chen, Leheyi De, Yu Zhang, Junwei Liao, Bo Huang, Yingxuan Yang, Zhi Han, Zimian Peng, Linyao Chen, Wenzheng Tom Tang, Zongkai Liu, Tao Zhou, Botao Amber Hu, Shuyang Tang, Jianghao Lin, Weiwen Liu, Muning Wen, Yuanjian Zhou, Weinan Zhang

Abstract: As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward Artificial General Intelligence (AGI). However, LLM-based multi-agent systems (LaMAS) are hindered by open-world issues such as scaling friction,… ▽ More As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward Artificial General Intelligence (AGI). However, LLM-based multi-agent systems (LaMAS) are hindered by open-world issues such as scaling friction, coordination breakdown, and value dissipation. To address these challenges, we introduce Holos, a web-scale LaMAS architected for long-term ecological persistence. Holos adopts a five-layer architecture, with core modules primarily featuring the Nuwa engine for high-efficiency agent generation and hosting, a market-driven Orchestrator for resilient coordination, and an endogenous value cycle to achieve incentive compatibility. By bridging the gap between micro-level collaboration and macro-scale emergence, Holos hopes to lay the foundation for the next generation of the self-organizing and continuously evolving Agentic Web. We have publicly released Holos (accessible at https://holosai.io), providing a resource for the community and a testbed for future research in large-scale agentic ecosystems. △ Less

Submitted 18 January, 2026; originally announced April 2026.

Comments: 38 pages, 8 figures, and 4 tables

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models

Authors: Yansong Guo, Chaoyang Zhu, Jiayi Ji, Jianghang Lin, Liujuan Cao

Abstract: Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune video tokens at input level while neglecting the inherent information structure embedded in videos and large language models (LLMs). To address this, we propose… ▽ More Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune video tokens at input level while neglecting the inherent information structure embedded in videos and large language models (LLMs). To address this, we propose HieraVid, a hierarchical pruning framework that progressively and dynamically reduces visual redundancy. Based on two observations that videos possess the segment-frame structure and LLMs internally propagate multi-modal information unidirectionally, we decompose pruning into three levels: 1) segment-level, where video tokens are first temporally segmented and spatially merged; 2) frame-level, where similar frames within the same segment are jointly pruned to preserve diversity; 3) layer-level, redundancy gradually shrinks as LLM layer increases w/o compromising performance. We conduct extensive experiments on four widely used video understanding benchmarks to comprehensively evaluate the effectiveness of HieraVid. Remarkably, with only 30% of tokens retained, HieraVid achieves new state-of-the-art performance, while maintaining over 98% and 99% of the performance of LLaVA-Video-7B and LLaVA-OneVision-7B, respectively. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Universal computational thermal imaging overcoming the ghosting effect

Authors: Hongyi Xu, Du Wang, Chenjun Zhao, Jiashuo Chen, Jiale Lin, Liqin Cao, Yanfei Zhong, Yiyuan She, Fanglin Bao

Abstract: Thermal imaging is crucial for night vision but fundamentally hampered by the ghosting effect, a loss of detailed texture in cluttered photon streams. While conventional ghosting mitigation has relied on data post-processing, the recent breakthrough in heat-assisted detection and ranging (HADAR) opens a promising frontier for hyperspectral computational thermal imaging that produces night vision w… ▽ More Thermal imaging is crucial for night vision but fundamentally hampered by the ghosting effect, a loss of detailed texture in cluttered photon streams. While conventional ghosting mitigation has relied on data post-processing, the recent breakthrough in heat-assisted detection and ranging (HADAR) opens a promising frontier for hyperspectral computational thermal imaging that produces night vision with day-like visibility. However, universal anti-ghosting imaging remains elusive, as state-of-the-art HADAR applies only to limited scenes with uniform materials, whereas material non-uniformity is ubiquitous in the real world. Here, we propose a universal computational thermal imaging framework, TAG (thermal anti-ghosting), to address material non-uniformity and overcome ghosting for high-fidelity night vision. TAG takes hyperspectral photon streams for nonparametric texture recovery, enabling our experimental demonstration of unprecedented expression recovery in thus-far-elusive ghostly human faces -- the archetypal, long-recognized ghosting phenomenon. Strikingly, TAG not only universally outperforms HADAR across various scenes, but also reveals the influence of material non-uniformity, shedding light on HADAR's effectiveness boundary. We extensively test facial texture and expression recovery across day and night, and demonstrate, for the first time, thermal 3D topological alignment and mood detection. This work establishes a universal foundation for high-fidelity computational night vision, with potential applications in autonomous navigation, reconnaissance, healthcare, and wildlife monitoring. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Comments: 9 pages, 6 figures

ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget

Authors: Nandan Thakur, Zijian Chen, Xueguang Ma, Jimmy Lin

Abstract: Search agents, which integrate language models (LMs) with web search, are becoming crucial for answering complex user queries. Constructing training datasets for deep research tasks, involving multi-step retrieval and reasoning, remains challenging due to expensive human annotation, or cumbersome prerequisites. In this work, we introduce ORBIT, a training dataset with 20K reasoning-intensive queri… ▽ More Search agents, which integrate language models (LMs) with web search, are becoming crucial for answering complex user queries. Constructing training datasets for deep research tasks, involving multi-step retrieval and reasoning, remains challenging due to expensive human annotation, or cumbersome prerequisites. In this work, we introduce ORBIT, a training dataset with 20K reasoning-intensive queries with short verifiable answers, generated using a frugal framework without relying on paid API services. The modular framework relies on four stages: seed creation, question-answer pair generation, and two stages of verification: self and external. ORBIT spans 15 domains and each training pair requires 4-5 reasoning steps, with external search verification required from the complete web. We train Qwen3-4B as the base model on ORBIT using GRPO and evaluate it on Wikipedia question answering tasks. Extensive experiment results demonstrate that ORBIT-4B achieves strong performance among sub-4B LLMs as search agents, proving the utility of synthetic datasets. Our framework, code and datasets are open-sourced and available publicly. △ Less

Submitted 2 April, 2026; v1 submitted 1 April, 2026; originally announced April 2026.

Comments: Preprint

Learning Shared Representations for Multi-Task Linear Bandits

Authors: Jiabin Lin, Shana Moothedath

Abstract: Multi-task representation learning is an approach that learns shared latent representations across related tasks, facilitating knowledge transfer and improving sample efficiency. This paper introduces a novel approach to multi-task representation learning in linear bandits. We consider a setting with T concurrent linear bandit tasks, each with feature dimension d, that share a common latent repres… ▽ More Multi-task representation learning is an approach that learns shared latent representations across related tasks, facilitating knowledge transfer and improving sample efficiency. This paper introduces a novel approach to multi-task representation learning in linear bandits. We consider a setting with T concurrent linear bandit tasks, each with feature dimension d, that share a common latent representation of dimension r \ll min{d,T}$, capturing their underlying relatedness. We propose a new Optimism in the Face of Uncertainty Linear (OFUL) algorithm that leverages shared low-rank representations to enhance decision-making in a sample-efficient manner. Our algorithm first collects data through an exploration phase, estimates the shared model via spectral initialization, and then conducts OFUL based learning over a newly constructed confidence set. We provide theoretical guarantees for the confidence set and prove that the unknown reward vectors lie within the confidence set with high probability. We derive cumulative regret bounds and show that the proposed approach achieves \tilde{O}(\sqrt{drNT}), a significant improvement over solving the T tasks independently, resulting in a regret of \tilde{O}(dT\sqrt{N}). We performed numerical simulations to validate the performance of our algorithm for different problem sizes. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Practice Less, Explain More: LLM-Supported Self-Explanation Improves Explanation Quality on Transfer Problems in Calculus

Authors: Eason Chen, Xinyi Tang, Yvonne Zhao, Meiyi Chen, Meryam Elmir, Elizabeth McLaughlin, Mingyu Yuan, Yumo Wang, Shyam Agarwal, Jared Cochrane, Jionghao Lin, Tongshuang Wu, Ken Koedinger

Abstract: We conducted a between-subjects experiment (N=92) comparing three conditions in a calculus learning environment: no self-explanation (control), menu-based self-explanation, and open-ended self-explanation with LLM-generated feedback. All conditions showed positive learning gains within a fixed 60-minute practice session, with no significant between-condition differences in post-test performance. O… ▽ More We conducted a between-subjects experiment (N=92) comparing three conditions in a calculus learning environment: no self-explanation (control), menu-based self-explanation, and open-ended self-explanation with LLM-generated feedback. All conditions showed positive learning gains within a fixed 60-minute practice session, with no significant between-condition differences in post-test performance. On transfer questions, the open-ended condition produced significantly higher-quality explanations than control on "Not Enough Information" (NEI) problems ($β$=+11.9 percentage points, $p$=.030), though the corresponding NEI multiple-choice accuracy advantage was not significant ($p$=.183). Moreover, across all post-test open-ended explanations, the open-ended condition showed a marginally significant advantage ($β$=+7.3%, $p$=.057). These findings suggest that LLM-supported open-ended self-explanation can improve explanation quality on NEI transfer problems, with weaker evidence across broader transfer explanation measures. Notably, these effects emerged even though learners in the open-ended condition completed substantially fewer practice problems within the same practice time. △ Less

Submitted 31 March, 2026; originally announced April 2026.

Comments: 9 pages, 2 figures. Accepted at AIED 2026. Camera-ready version with updated references

Scalable AI-assisted Workflow Management for Detector Design Optimization Using Distributed Computing

Authors: Derek Anderson, Amit Bashyal, Markus Diefenthaler, Cristiano Fanelli, Wen Guan, Tanja Horn, Alex Jentsch Meifeng Lin, Tadashi Maeno, Kei Nagai, Hemalata Nayak, Connor Pecar, Karthik Suresh, Fang-Ying Tsai, Anselm Vossen, Tianle Wang, Torre Wenaus

Abstract: The Production and Distributed Analysis (PanDA) system, originally developed for the ATLAS experiment at the CERN Large Hadron Collider (LHC), has evolved into a robust platform for orchestrating large-scale workflows across distributed computing resources. Coupled with its intelligent Distributed Dispatch and Scheduling (iDDS) component, PanDA supports AI/ML-driven workflows through a scalable an… ▽ More The Production and Distributed Analysis (PanDA) system, originally developed for the ATLAS experiment at the CERN Large Hadron Collider (LHC), has evolved into a robust platform for orchestrating large-scale workflows across distributed computing resources. Coupled with its intelligent Distributed Dispatch and Scheduling (iDDS) component, PanDA supports AI/ML-driven workflows through a scalable and flexible workflow engine. We present an AI-assisted framework for detector design optimization that integrates multi-objective Bayesian optimization with the PanDA--iDDS workflow engine to coordinate iterative simulations across heterogeneous resources. The framework addresses the challenge of exploring high-dimensional parameter spaces inherent in modern detector design. We demonstrate the framework using benchmark problems and realistic studies of the ePIC and dRICH detectors for the Electron-Ion Collider (EIC). Results show improved automation, scalability, and efficiency in multi-objective optimization. This work establishes a flexible and extensible paradigm for AI-driven detector design and other computationally intensive scientific applications. △ Less

Submitted 31 March, 2026; originally announced March 2026.

$AutoDrive\text{-}P^3$: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning

Authors: Yuqi Ye, Zijian Zhang, Junhong Lin, Shangkun Sun, Changhao Peng, Wei Gao

Abstract: Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However, current VLM-based approaches suffer from two major limitations: 1) Some VLMs directly output planning results without chain-of-thought (CoT) reasoning, bypassing crucial perception and prediction stages which creates a… ▽ More Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However, current VLM-based approaches suffer from two major limitations: 1) Some VLMs directly output planning results without chain-of-thought (CoT) reasoning, bypassing crucial perception and prediction stages which creates a significant domain gap and compromises decision-making capability; 2) Other VLMs can generate outputs for perception, prediction, and planning tasks but employ a fragmented decision-making approach where these modules operate separately, leading to a significant lack of synergy that undermines true planning performance. To address these limitations, we propose ${AutoDrive\text{-}P^3}$, a novel framework that seamlessly integrates $\textbf{P}$erception, $\textbf{P}$rediction, and $\textbf{P}$lanning through structured reasoning. We introduce the ${P^3\text{-}CoT}$ dataset to facilitate coherent reasoning and propose ${P^3\text{-}GRPO}$, a hierarchical reinforcement learning algorithm that provides progressive supervision across all three tasks. Specifically, ${AutoDrive\text{-}P^3}$ progressively generates CoT reasoning and answers for perception, prediction, and planning, where perception provides essential information for subsequent prediction and planning, while both perception and prediction collectively contribute to the final planning decisions, enabling safer and more interpretable autonomous driving. Additionally, to balance inference efficiency with performance, we introduce dual thinking modes: detailed thinking and fast thinking. Extensive experiments on both open-loop (nuScenes) and closed-loop (NAVSIMv1/v2) benchmarks demonstrate that our approach achieves state-of-the-art performance in planning tasks. Code is available at https://github.com/haha-yuki-haha/AutoDrive-P3. △ Less

Submitted 30 March, 2026; originally announced March 2026.

Comments: Accepted at ICLR 2026 (International Conference on Learning Representations)

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Authors: Meituan LongCat Team, Bin Xiao, Chao Wang, Chengjiang Li, Chi Zhang, Chong Peng, Hang Yu, Hao Yang, Haonan Yan, Haoze Sun, Haozhe Zhao, Hong Liu, Hui Su, Jiaqi Zhang, Jiawei Wang, Jing Li, Kefeng Zhang, Manyuan Zhang, Minhao Jing, Peng Pei, Quan Chen, Taofeng Xue, Tongxin Pan, Xiaotong Li, Xiaoyang Li , et al. (64 additional authors not shown)

Abstract: The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Aut… ▽ More The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next △ Less

Submitted 29 March, 2026; originally announced March 2026.

Comments: LongCat-Next Technical Report

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Authors: Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu, Wei Li, Yinghao Zhu, Shujian Gao, Yanyan Huang, Sibo Ju, Yanzhou Su, Pengcheng Chen, Wenhao Tang, Tianbin Li, Haoyu Wang, Yuanfeng Ji, Hui Sun, Shaobo Min, Liang Peng, Feilong Tang, Haochen Xue, Rulin Zhou , et al. (102 additional authors not shown)

Abstract: Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of… ▽ More Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models. △ Less

Submitted 28 March, 2026; originally announced March 2026.

Comments: 157 pages, 19 figures, 26 tables. Project repo: \url{https://github.com/uni-medical/Project-Imaging-X}

Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models

Authors: Jiajia Song, Zhihan Guo, Jionghao Lin

Abstract: Student simulation can support learning-by-teaching pedagogy where human students (as tutors) teach AI-simulated novice students (as tutees). Recent research often relies on prompt engineering with large language models (LLMs) to simulate novice student behaviour, but it is difficult to keep the AI-simulated student at a stable novice knowledge level. A key reason is that many LLMs are trained to… ▽ More Student simulation can support learning-by-teaching pedagogy where human students (as tutors) teach AI-simulated novice students (as tutees). Recent research often relies on prompt engineering with large language models (LLMs) to simulate novice student behaviour, but it is difficult to keep the AI-simulated student at a stable novice knowledge level. A key reason is that many LLMs are trained to be broadly capable, so even when prompted to "act like a novice," the LLMs can still produce expert-level explanations during the learning-by-teaching interaction process. As a result, the AI-simulated student may drift beyond the intended knowledge level, reducing the credibility of the simulation for studying learning-by-teaching processes. Thus, we propose a knowledge-level simulation approach based on machine unlearning. We investigate this approach using a dataset of multiple-choice questions on Python programming concepts. We apply machine unlearning to transform a knowledgeable LLM into a novice-level AI student (i.e., teachable agent), then evaluate whether the teachable agent can relearn targeted knowledge components through learning-by-teaching dialogue interactions. Finally, we analyse the dialogue logs to characterise how the agent's behaviour changes over time, including its question asking, error patterns, and responsiveness to instruction. The results show that (1) unlearning produces simulated student agents with more novice-like responses than prompt-only baselines, (2) the agents recover a measurable portion of the unlearned knowledge under structured exposure, and (3) dialogue analyses reveal identifiable trajectories of conceptual change and teaching moves that predict learning recovery. △ Less

Submitted 30 March, 2026; v1 submitted 27 March, 2026; originally announced March 2026.

Large Language Model as Token Compressor and Decompressor

Authors: Wenbing Li, Zikai Song, Jielei Zhang, Tianhao Zhao, Junkai Lin, Yiran Wang, Wei Yang

Abstract: In this paper, we establish the novel insight that an off-the-shelf LLM can function as an excellent token compressor and decompressor. To demonstrate, we design a self-expressive autoencoding learning framework fine-tunes a pretrained LLM to translate long texts into a compact internal language of discrete, variable-length latent codes, termed Z-tokens, and to reconstruct the original text exactl… ▽ More In this paper, we establish the novel insight that an off-the-shelf LLM can function as an excellent token compressor and decompressor. To demonstrate, we design a self-expressive autoencoding learning framework fine-tunes a pretrained LLM to translate long texts into a compact internal language of discrete, variable-length latent codes, termed Z-tokens, and to reconstruct the original text exactly from them. The resulting representation is content-adaptive: semantically dense segments receive more Z-tokens, while redundant or predictable regions are aggressively compressed, via lightweight LoRA-based adapter heads. Empirically, our method achieves up to 18 times token reduction on Wikipedia, CNN/DailyMail, HotpotQA, and Qulac-style long-query datasets, while preserving reconstruction fidelity and downstream performance. This simple yet effective design supports applications including prompt compression and autoregressive generation directly in the Z-token space, offering a potential pathway toward token-efficient long-context reasoning. △ Less

Submitted 26 March, 2026; originally announced March 2026.

AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization

Authors: Jiawei Lin, Wanrong Zhu, Vlad I Morariu, Christopher Tensmeyer

Abstract: Document generation has gained growing attention in the field of AI-driven content creation. In this work, we push its boundaries by introducing AnyDoc, a framework capable of handling multiple generation tasks across a wide spectrum of document categories, all represented in a unified HTML/CSS format. To overcome the limited coverage and scale of existing human-crafted document datasets, AnyDoc f… ▽ More Document generation has gained growing attention in the field of AI-driven content creation. In this work, we push its boundaries by introducing AnyDoc, a framework capable of handling multiple generation tasks across a wide spectrum of document categories, all represented in a unified HTML/CSS format. To overcome the limited coverage and scale of existing human-crafted document datasets, AnyDoc first establishes a scalable data synthesis pipeline to automatically generate documents in HTML/CSS form. This pipeline yields DocHTML, a large-scale dataset containing 265,206 document samples, while spanning 111 categories and 32 distinct styles. Additionally, all documents are equipped with comprehensive metadata, including design intentions, HTML/CSS source code, visual assets, and rendered screenshots. Building on the curated dataset, AnyDoc fine-tunes multi-modal large language models (MLLMs) to achieve three practical document generation tasks: intention-to-document, document derendering, and element-to-document. To address the content overflow issue observed during fine-tuning, AnyDoc further incorporates a height-aware reinforcement learning (HARL) post-training procedure. By defining a reward function based on the difference between predicted and target document heights, overflow is penalized and gradually mitigated during HARL, thereby enhancing overall performance. Qualitative and quantitative experiments demonstrate that AnyDoc outperforms both general-purpose MLLMs and task-specific baselines across all three tasks. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Comments: CVPR 2026 Main Conference

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Authors: Yicheng Zou, Dongsheng Zhu, Lin Zhu, Tong Zhu, Yunhua Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou, Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhuo Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang , et al. (152 additional authors not shown)

Abstract: We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertis… ▽ More We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks. △ Less

Submitted 2 April, 2026; v1 submitted 26 March, 2026; originally announced March 2026.

TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification

Authors: Guan Luo, Xiu Li, Rui Chen, Xuanyu Yi, Jing Lin, Chia-Hao Chen, Jiahang Liu, Song-Hai Zhang, Jianfeng Zhang

Abstract: The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the representation mismatch between ground-truth meshes and network predictions: GT meshes have arbitrary, variable topology, while VAEs typically predict fixed-structure… ▽ More The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the representation mismatch between ground-truth meshes and network predictions: GT meshes have arbitrary, variable topology, while VAEs typically predict fixed-structure implicit fields (\eg, SDF on regular grids). This inherent misalignment prevents establishing explicit mesh-level correspondences, forcing prior work to rely on indirect supervision signals such as SDF or rendering losses. Consequently, fine geometric details, particularly sharp features, are poorly preserved during reconstruction. To address this, we introduce TopoMesh, a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes (DMC) topological framework. Specifically, we convert arbitrary input meshes into DMC-compliant representations via a remeshing algorithm that preserves sharp edges using an L$\infty$ distance metric. Our decoder outputs meshes in the same DMC format, ensuring that both predicted and target meshes share identical topological structures. This establishes explicit correspondences at the vertex and face level, allowing us to derive explicit mesh-level supervision signals for topology, vertex positions, and face orientations with clear gradients. Our sparse VAE architecture employs this unified framework and is trained with Teacher Forcing and progressive resolution training for stable and efficient convergence. Extensive experiments demonstrate that TopoMesh significantly outperforms existing VAEs in reconstruction fidelity, achieving superior preservation of sharp features and geometric details. △ Less

Submitted 26 March, 2026; v1 submitted 25 March, 2026; originally announced March 2026.

Comments: Accepted to CVPR 2026. Project page: https://logan0601.github.io/projects/topomesh/index.html

GenMask: Adapting DiT for Segmentation via Direct Mask Generation

Authors: Yuhuan Yang, Xianwei Zhuang, Yuxuan Cai, Chaofan Ma, Shuai Bai, Jiangchao Yao, Ya Zhang, Junyang Lin, Yanfeng Wang

Abstract: Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental misalignment in representation. It also depends heavily on indirect feature extraction pipelines, which complicate the workflow and limit adaptation. In this paper, we… ▽ More Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental misalignment in representation. It also depends heavily on indirect feature extraction pipelines, which complicate the workflow and limit adaptation. In this paper, we argue that instead of indirect adaptation, segmentation tasks should be trained directly in a generative manner. We identify a key obstacle to this unified formulation: VAE latents of binary masks are sharply distributed, noise robust, and linearly separable, distinct from natural image latents. To bridge this gap, we introduce timesteps sampling strategy for binary masks that emphasizes extreme noise levels for segmentation and moderate noise for image generation, enabling harmonious joint training. We present GenMask, a DiT trains to generate black-and-white segmentation masks as well as colorful images in RGB space under the original generative objective. GenMask preserves the original DiT architecture while removing the need of feature extraction pipelines tailored for segmentation tasks. Empirically, GenMask attains state-of-the-art performance on referring and reasoning segmentation benchmarks and ablations quantify the contribution of each component. △ Less

Submitted 26 March, 2026; v1 submitted 24 March, 2026; originally announced March 2026.

Comments: Accepted by cvpr 2026

UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Functionality Segmentation

Authors: Jiaying Lin, Dan Xu

Abstract: Functionality segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interactive elements. Existing methods rely on fragmented pipelines that suffer from visual blindness during initial task parsing. We observe that these methods are limited by single-scale, passive and heuristic frame selection. We present UniFunc3D, a unifi… ▽ More Functionality segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interactive elements. Existing methods rely on fragmented pipelines that suffer from visual blindness during initial task parsing. We observe that these methods are limited by single-scale, passive and heuristic frame selection. We present UniFunc3D, a unified and training-free framework that treats the multimodal large language model as an active observer. By consolidating semantic, temporal, and spatial reasoning into a single forward pass, UniFunc3D performs joint reasoning to ground task decomposition in direct visual evidence. Our approach introduces active spatial-temporal grounding with a coarse-to-fine strategy. This allows the model to select correct video frames adaptively and focus on high-detail interactive parts while preserving the global context necessary for disambiguation. On SceneFun3D, UniFunc3D achieves state-of-the-art performance, surpassing both training-free and training-based methods by a large margin with a relative 59.9\% mIoU improvement, without any task-specific training. Code will be released on our project page: https://jiaying.link/unifunc3d. △ Less

Submitted 24 March, 2026; originally announced March 2026.

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

Authors: Shuochen Liu, Junyi Zhu, Long Shu, Junda Lin, Yuhao Chen, Haotian Zhang, Chao Zhang, Derong Xu, Jia Li, Bo Tang, Zhiyu Li, Feiyu Xiong, Enhong Chen, Tong Xu

Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However, prior evaluations typically interleave preference-related dialogues with irrelevant conversations, reducing the task to needle-in-a-haystack retrieval while ignoring relationships between events that drive the evolution of user preferences. Such settings overlook a fu… ▽ More Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However, prior evaluations typically interleave preference-related dialogues with irrelevant conversations, reducing the task to needle-in-a-haystack retrieval while ignoring relationships between events that drive the evolution of user preferences. Such settings overlook a fundamental characteristic of real-world personalization: preferences emerge gradually and accumulate across interactions within noisy contexts. To bridge this gap, we introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall. Additionally, we incorporate (1) text variability and (2) linguistic alignment to simulate erratic user inputs and individual idiolects in real-world data. PERMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time. We design both multiple-choice and interactive tasks to probe the model's understanding of persona along the interaction timeline. Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption, outperforming traditional semantic retrieval of raw dialogues. Nevertheless, they still struggle to maintain a coherent persona across temporal depth and cross-domain interference, highlighting the need for more robust personalized memory management in agents. Our code and data are open-sourced at https://github.com/PolarisLiu1/PERMA. △ Less

Submitted 24 March, 2026; originally announced March 2026.

MedCausalX: Adaptive Causal Reasoning with Self-Reflection for Trustworthy Medical Vision-Language Models

Authors: Jianxin Lin, Chunzheng Zhu, Peter J. Kneuertz, Yunfei Bai, Yuan Xue

Abstract: Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability. We pinpoint three core challenges in medical CoT reason… ▽ More Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability. We pinpoint three core challenges in medical CoT reasoning: how to adaptively trigger causal correction, construct high-quality causal-spurious contrastive samples, and maintain causal consistency across reasoning trajectories. To address these challenges, we propose MedCausalX, an end-to-end framework explicitly models causal reasoning chains in medical VLMs. We first introduce the CRMed dataset providing fine-grained anatomical annotations, structured causal reasoning chains, and counterfactual variants that guide the learning of causal relationships beyond superficial correlations. Building upon CRMed, MedCausalX employs a two-stage adaptive reflection architecture equipped with $\langle$causal$\rangle$ and $\langle$verify$\rangle$ tokens, enabling the model to autonomously determine when and how to perform causal analysis and verification. Finally, a trajectory-level causal correction objective optimized through error-attributed reinforcement learning refines the reasoning chain, allowing the model to distinguish genuine causal dependencies from shortcut associations. Extensive experiments on multiple benchmarks show that MedCausalX consistently outperforms state-of-the-art methods, improving diagnostic consistency by +5.4 points, reducing hallucination by over 10 points, and attaining top spatial grounding IoU, thereby setting a new standard for causally grounded medical reasoning. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Multi-User Multi-Key Image Steganography with Key Isolation

Authors: Tzu-Ti Wei, Yu-Han Tseng, Jun-Yi Lin, Yu-Chee Tseng, Jen-Jee Chen

Abstract: Steganography conceals secret information within innocuous carriers while preserving visual fidelity and enabling reliable recovery. Recent unified networks operate normally under untriggered conditions but switch to hidden steganographic tasks when triggered. PUSNet follows this paradigm by performing image purification during normal operation and steganographic embedding when activated. However,… ▽ More Steganography conceals secret information within innocuous carriers while preserving visual fidelity and enabling reliable recovery. Recent unified networks operate normally under untriggered conditions but switch to hidden steganographic tasks when triggered. PUSNet follows this paradigm by performing image purification during normal operation and steganographic embedding when activated. However, it supports only a single user with one key pair, limiting its applicability in multi-user settings. We propose PUSNet-MK, a multi-key extension that enforces strict key isolation via a mismatched-key isolation loss, effectively preventing cross-key decoding when a wrong key is applied. This design preserves the intended steganographic behavior while addressing a critical security limitation of PUSNet. Extensive experiments demonstrate that PUSNet-MK produces high-quality stego images and accurate secret recovery, while preventing unintended information leakage. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Comments: 6 pages, 5 figures

MSC Class: 68U10; 94A62 ACM Class: I.4.9; K.6.5

AnyPro: Preference-Preserving Anycast Optimization based on Strategic AS-Path Prepending

Authors: Minyuan Zhou, Yuning Chen, Jiaqi Zheng, Yifei Xu, Pan Hu, Yongping Tang, Wendong Yin, Jie Lin, Qingyan Yu, Yuanchao Su, Guihai Chen, Wanchun Dou, Songwu Lu, Wan Du

Abstract: Operating large-scale anycast networks is challenging because client-to-site mappings often misalign with operator's expectation due to opaque inter-domain routing. We present AnyPro, the first system to unlock the full potential of AS-path prepending (ASPP), efficiently deriving globally optimal configurations to steer clients toward performance-optimal sites at scale. AnyPro first employs an eff… ▽ More Operating large-scale anycast networks is challenging because client-to-site mappings often misalign with operator's expectation due to opaque inter-domain routing. We present AnyPro, the first system to unlock the full potential of AS-path prepending (ASPP), efficiently deriving globally optimal configurations to steer clients toward performance-optimal sites at scale. AnyPro first employs an efficient polling mechanism to identify all clients sensitive to ASPP. By analyzing the routing changes during the process, the system derives a set of ASPP constraints that guide client traffic toward the desired sites. We then formulate the anycast optimization problem as a constraint-based program and compute optimal ASPP configurations. Extensive evaluation on a global testbed with 20 PoPs demonstrates the effectiveness of AnyPro: it reduces the 90th percentile latency by 37.7% compared to baseline configurations without ASPP. Furthermore, we show that AnyPro can be integrated with PoP-level anycast optimization techniques to achieve additional performance gains. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Comments: NSDI 2026

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration

Authors: Zihan Guo, Zhiyu Chen, Xiaohang Nie, Jianghao Lin, Yuanjian Zhou, Weinan Zhang

Abstract: With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security challenges, primarily stemming from semantic-behavioral inconsistency and inter-skill combinatorial risks, where individually benign skills induce malicious behaviors… ▽ More With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security challenges, primarily stemming from semantic-behavioral inconsistency and inter-skill combinatorial risks, where individually benign skills induce malicious behaviors during collaborative invocation. To address these vulnerabilities, we propose SkillProbe, a multi-stage security auditing framework driven by multi-agent collaboration. SkillProbe introduces a "Skills-for-Skills" design paradigm, encapsulating auditing processes into standardized skill modules to drive specialized agents through a rigorous pipeline, including admission filtering, semantic-behavioral alignment detection, and combinatorial risk simulation. We conducted a large-scale evaluation using 8 mainstream LLM series across 2,500 real-world skills from ClawHub. Our results reveal a striking popularity-security paradox, where download volume is not a reliable proxy for security quality, as over 90% of high-popularity skills failed to pass rigorous auditing. Crucially, we discovered that high-risk skills form a single giant connected component within the risk-link dimension, demonstrating that cascaded risks are systemic rather than isolated occurrences. We hope that SkillProbe will inspire researchers to provide a scalable governance infrastructure for constructing a trustworthy Agentic Web. SkillProbe is accessible for public experience at skillhub.holosai.io. △ Less

Submitted 21 March, 2026; originally announced March 2026.

Comments: 16 pages, 6 figures

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking

Authors: Jingyang Lin, Jialian Wu, Jiang Liu, Ximeng Sun, Ze Wang, Xiaodong Yu, Jiebo Luo, Zicheng Liu, Emad Barsoum

Abstract: Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a long-horizon video agent that leverages video logic flow to actively seek answer-critical evidence instead of exhaustively parsing the full video. This insight allo… ▽ More Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a long-horizon video agent that leverages video logic flow to actively seek answer-critical evidence instead of exhaustively parsing the full video. This insight allows the model to use far fewer frames while maintaining, or even improving, its video understanding capability. VideoSeek operates in a think-act-observe loop with a well-designed toolkit for collecting multi-granular video observations. This design enables query-aware exploration over accumulated observations and supports practical video understanding and reasoning. Experiments on four challenging video understanding and reasoning benchmarks demonstrate that VideoSeek achieves strong accuracy while using far fewer frames than prior video agents and standalone LMMs. Notably, VideoSeek achieves a 10.2 absolute points improvement on LVBench over its base model, GPT-5, while using 93% fewer frames. Further analysis highlights the significance of leveraging video logic flow, strong reasoning capability, and the complementary roles of toolkit design. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Comments: Accepted at CVPR 2026