Showing 1–50 of 1,290 results for author: Lu, Z

KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation

Authors: Tongbo Chen, Zhengxi Lu, Zhan Xu, Guocheng Shao, Shaohan Zhao, Fei Tang, Yong Du, Kaitao Song, Yizhou Liu, Yuchen Yan, Wenqi Zhang, Xu Tan, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Abstract: Personalized mobile agents that infer user preferences and calibrate proactive assistance hold great promise as everyday digital assistants, yet existing benchmarks fail to capture what this requires. Prior work evaluates preference recovery from static histories or intent prediction from fixed contexts. Neither tests whether an agent can elicit missing preferences through interaction, nor whether… ▽ More Personalized mobile agents that infer user preferences and calibrate proactive assistance hold great promise as everyday digital assistants, yet existing benchmarks fail to capture what this requires. Prior work evaluates preference recovery from static histories or intent prediction from fixed contexts. Neither tests whether an agent can elicit missing preferences through interaction, nor whether it can decide when to intervene, seek consent, or remain silent in a live GUI environment. We introduce KnowU-Bench, an online benchmark for personalized mobile agents built on a reproducible Android emulation environment, covering 42 general GUI tasks, 86 personalized tasks, and 64 proactive tasks. Unlike prior work that treats user preferences as static context, KnowU-Bench hides the user profile from the agent and exposes only behavioral logs, forcing genuine preference inference rather than context lookup. To support multi-turn preference elicitation, it instantiates an LLM-driven user simulator grounded in structured profiles, enabling realistic clarification dialogues and proactive consent handling. Beyond personalization, KnowU-Bench provides comprehensive evaluation of the complete proactive decision chain, including grounded GUI execution, consent negotiation, and post-rejection restraint, evaluated through a hybrid protocol combining rule-based verification with LLM-as-a-Judge scoring. Our experiments reveal a striking degradation: agents that excel at explicit task execution fall below 50% under vague instructions requiring user preference inference or intervention calibration, even for frontier models like Claude Sonnet 4.6. The core bottlenecks are not GUI navigation but preference acquisition and intervention calibration, exposing a fundamental gap between competent interface operation and trustworthy personal assistance. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration

Authors: Haichang Li, Qinshi Zhang, Piaohong Wang, Zhicong Lu

Abstract: In the human-AI collaboration area, the context formed naturally through multi-turn interactions is typically flattened into a chronological sequence and treated as a fixed whole in subsequent reasoning, with no mechanism for dynamic organization and management along the collaboration workflow. Yet these contexts differ substantially in lifecycle, structural hierarchy, and relevance. For instance,… ▽ More In the human-AI collaboration area, the context formed naturally through multi-turn interactions is typically flattened into a chronological sequence and treated as a fixed whole in subsequent reasoning, with no mechanism for dynamic organization and management along the collaboration workflow. Yet these contexts differ substantially in lifecycle, structural hierarchy, and relevance. For instance, temporary or abandoned exchanges and parallel topic threads persist in the limited context window, causing interference and even conflict. Meanwhile, users are largely limited to influencing context indirectly through input modifications (e.g., corrections, references, or ignoring), leaving their control neither explicit nor verifiable. To address this, we propose Mixed-Initiative Context, which reconceptualizes the context formed across multi-turn interactions as an explicit, structured, and manipulable interactive object. Under this concept, the structure, scope, and content of context can be dynamically organized and adjusted according to task needs, enabling both humans and AI to actively participate in context construction and regulation. To explore this concept, we implement Contextify as a probe system and conduct a user study examining users' context management behaviors, attitudes toward AI initiative, and overall collaboration experience. We conclude by discussing the implications of this concept for the HCI community. △ Less

Submitted 8 April, 2026; originally announced April 2026.

Comments: 19 pages, 3 figures, 1 table. Appendix on pages 13-19 (main text is self-contained)

ACM Class: H.5.2

Semantic-Topological Graph Reasoning for Language-Guided Pulmonary Screening

Authors: Chenyu Xue, Yiran Liu, Mian Zhou, Jionglong Su, Zhixiang Lu

Abstract: Medical image segmentation driven by free-text clinical instructions is a critical frontier in computer-aided diagnosis. However, existing multimodal and foundation models struggle with the semantic ambiguity of clinical reports and fail to disambiguate complex anatomical overlaps in low-contrast scans. Furthermore, fully fine-tuning these massive architectures on limited medical datasets invariab… ▽ More Medical image segmentation driven by free-text clinical instructions is a critical frontier in computer-aided diagnosis. However, existing multimodal and foundation models struggle with the semantic ambiguity of clinical reports and fail to disambiguate complex anatomical overlaps in low-contrast scans. Furthermore, fully fine-tuning these massive architectures on limited medical datasets invariably leads to severe overfitting. To address these challenges, we propose a novel Semantic-Topological Graph Reasoning (STGR) framework for language-guided pulmonary screening. Our approach elegantly synergizes the reasoning capabilities of large language models (LLaMA-3-V) with the zero-shot delineation of vision foundation models (MedSAM). Specifically, we introduce a Text-to-Vision Intent Distillation (TVID) module to extract precise diagnostic guidance. To resolve anatomical ambiguity, we formulate mask selection as a dynamic graph reasoning problem, where candidate lesions are modeled as nodes and edges capture spatial and semantic affinities. To ensure deployment feasibility, we introduce a Selective Asymmetric Fine-Tuning (SAFT) strategy that updates less than 1% of the parameters. Rigorous 5-fold cross-validation on the LIDC-IDRI and LNDb datasets demonstrates that our framework establishes a new state-of-the-art. Notably, it achieves an 81.5% Dice Similarity Coefficient (DSC) on LIDC-IDRI, outperforming leading LLM-based tools like LISA by over 5%. Crucially, our SAFT strategy acts as a powerful regularizer, yielding exceptional cross-fold stability (0.6% DSC variance) and paving the way for robust, context-aware clinical deployment. △ Less

Submitted 7 April, 2026; originally announced April 2026.

From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation

Authors: Ziang Lu, Lei Sang, Lin Mu, Yiwen Zhang

Abstract: Cross-domain Recommendation (CDR) exploits multi-domain correlations to alleviate data sparsity. As a core task within this field, inter-domain recommendation focuses on predicting preferences for users who interact in a source domain but lack behavioral records in a target domain. Existing approaches predominantly rely on overlapping users as anchors for knowledge transfer. In real-world scenario… ▽ More Cross-domain Recommendation (CDR) exploits multi-domain correlations to alleviate data sparsity. As a core task within this field, inter-domain recommendation focuses on predicting preferences for users who interact in a source domain but lack behavioral records in a target domain. Existing approaches predominantly rely on overlapping users as anchors for knowledge transfer. In real-world scenarios, overlapping users are often scarce, leaving the vast majority of users with only single-domain interactions. For these users, the absence of explicit alignment signals makes fine-grained preference transfer intrinsically difficult. To address this challenge, this paper proposes Language-Guided Conditional Diffusion for CDR (LGCD), a novel framework that integrates Large Language Models (LLMs) and diffusion models for inter-domain sequential recommendation. Specifically, we leverage LLM reasoning to bridge the domain gap by inferring potential target preferences for single-domain users and mapping them to real items, thereby constructing pseudo-overlapping data. We distinguish between real and pseudo-interaction pathways and introduce additional supervision constraints to mitigate the semantic noise brought by pseudo-interaction. Furthermore, we design a conditional diffusion architecture to precisely guide the generation of target user representations based on source-domain patterns. Extensive experiments demonstrate that LGCD significantly outperforms state-of-the-art methods in inter-domain recommendation tasks. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Comments: 11 pages, 6 figures

MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation

Authors: Zhixiang Lu, Chong Zhang, Chenyu Xue, Angelos Stefanidis, Chong Li, Jionglong Su, Zhengyong Jiang

Abstract: Neural machine translation (NMT) from Chinese to low-resource Southeast Asian languages remains severely constrained by the extreme scarcity of clean parallel corpora and the pervasive noise in existing mined data. This chronic shortage not only impedes effective model training but also sustains a large performance gap with high-resource directions, leaving millions of speakers of languages such a… ▽ More Neural machine translation (NMT) from Chinese to low-resource Southeast Asian languages remains severely constrained by the extreme scarcity of clean parallel corpora and the pervasive noise in existing mined data. This chronic shortage not only impedes effective model training but also sustains a large performance gap with high-resource directions, leaving millions of speakers of languages such as Lao, Burmese, and Tagalog with persistently low-quality translation systems despite recent advances in large multilingual models. We introduce \textbf{M}ultilingual \textbf{E}xpert-\textbf{R}eward \textbf{I}nformed \textbf{T}uning (\textbf{MERIT}), a unified translation framework that transforms the traditional English-centric ALT benchmark into a Chinese-centric evaluation suite for five Southeast Asian low-resource languages (LRLs). Our framework combines language-specific token prefixing (LTP) with supervised fine-tuning (SFT) and a novel group relative policy optimization (GRPO) guided by the semantic alignment reward (SAR). These results confirm that, in LRL{\textrightarrow}Chinese translation, targeted data curation and reward-guided optimization dramatically outperform mere model scaling. △ Less

Submitted 6 April, 2026; originally announced April 2026.

STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models

Authors: Linfeng Fan, Yuan Tian, Ziwei Li, Zhiwu Lu

Abstract: Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing mitigation methods typically treat hallucination as a uniform decoding failure, applying globally shared correction rules. We instead observe that decoder layers contribute differently to visual grounding and later linguisti… ▽ More Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing mitigation methods typically treat hallucination as a uniform decoding failure, applying globally shared correction rules. We instead observe that decoder layers contribute differently to visual grounding and later linguistic composition, indicating that intervention must be layer-aware. Based on this insight, we propose STEAR, a layer-aware spatiotemporal evidence intervention framework. STEAR identifies high-risk decoding steps and selects token-conditioned visual evidence from grounding-sensitive middle layers. It uses this shared evidence for two coupled purposes: restoring missing local grounding in middle layers, and constructing temporally perturbed patch-level counterfactuals to falsify inconsistent reasoning during late-layer decoding. Consequently, STEAR mitigates both spatial and temporal hallucinations within an efficient single-encode inference framework. Experiments across representative Video-LLM backbones and challenging benchmarks demonstrate that STEAR consistently reduces hallucinations while improving faithfulness, temporal consistency, and robustness. Our results confirm that reliable video decoding relies on intervening on precise evidence at the right layer, rather than enforcing a global penalty. The code is provided in the Supplementary Material. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: Preprint

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Authors: Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Abstract: Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the… ▽ More Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the knowledge it merely follows. We ask whether skills can instead be internalized into model parameters, enabling zero-shot autonomous behavior without any runtime skill retrieval. We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization. SKILL0 introduces a training-time curriculum that begins with full skill context and progressively withdraws it. Skills are grouped offline by category and rendered with interaction history into a compact visual context, teaching he model tool invocation and multi-turn task completion. A Dynamic Curriculum then evaluates each skill file's on-policy helpfulness, retaining only those from which the current policy still benefits within a linearly decaying budget, until the agent operates in a fully zero-shot setting. Extensive agentic experiments demonstrate that SKILL0 achieves substantial improvements over the standard RL baseline (+9.7\% for ALFWorld and +6.6\% for Search-QA), while maintaining a highly efficient context of fewer than 0.5k tokens per step. Our code is available at https://github.com/ZJU-REAL/SkillZero. △ Less

Submitted 2 April, 2026; originally announced April 2026.

RePart: Efficient Hypergraph Partitioning with Logic Replication Optimization for Multi-FPGA System

Authors: Zizhuo Fu, Yifan Zhou, Zhaoxin Lu, Guangyu Sun, Runsheng Wang, Meng Li, Yibo Lin

Abstract: Multi-FPGA systems (MFS) are widely adopted for VLSI emulation and rapid prototyping. In an MFS, FPGAs connect only to a limited number of neighbors through bandwidth-constrained links, so inter-FPGA communication cost depends on network topology. This setting exposes two fundamental limitations of existing MFS-aware partitioning methods: conventional hypergraph partitioners focus solely on cut si… ▽ More Multi-FPGA systems (MFS) are widely adopted for VLSI emulation and rapid prototyping. In an MFS, FPGAs connect only to a limited number of neighbors through bandwidth-constrained links, so inter-FPGA communication cost depends on network topology. This setting exposes two fundamental limitations of existing MFS-aware partitioning methods: conventional hypergraph partitioners focus solely on cut size and ignore topological structure, and they leave substantial FPGA resources unused due to conservative balance margins. We present RePart, a fully customized multilevel hypergraph partitioning framework for MFS that integrates logic replication with topology-aware optimization. RePart introduces three coordinated innovations across the multilevel pipeline: FPGA-aware dynamic coarsening, heat-value guided assignment, and replication-deletion supported refinement. Extensive experiments on the Titan23 and EDA Elite Challenge Contest benchmarks show that RePart reduces total hop distance by 52.3% on average over state-of-the-art hypergraph partitioners with an 11.1x speedup, and outperforms the EDA Elite Challenge winners. Code is available at: https://github.com/Welement-zyf/RePart. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Comments: 2026 International Symposium of Electronics Design Automation (ISEDA)

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems

Authors: Mingming Ha, Guanchen Wang, Linxun Chen, Xuan Rao, Yuexin Shi, Tianbao Ma, Zhaojie Liu, Yunqian Fan, Zilong Lu, Yanan Niu, Han Li, Kun Gai

Abstract: In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there are three mainstream architectures for achieving scaling in recommendation models, namely attention-based, TokenMixer-based, and factorization-machine-based methods, which exhibit fundamental differe… ▽ More In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there are three mainstream architectures for achieving scaling in recommendation models, namely attention-based, TokenMixer-based, and factorization-machine-based methods, which exhibit fundamental differences in both design philosophy and architectural structure. In this paper, we propose a unified scaling architecture for recommendation systems, namely \textbf{UniMixer}, to improve scaling efficiency and establish a unified theoretical framework that unifies the mainstream scaling blocks. By transforming the rule-based TokenMixer to an equivalent parameterized structure, we construct a generalized parameterized feature mixing module that allows the token mixing patterns to be optimized and learned during model training. Meanwhile, the generalized parameterized token mixing removes the constraint in TokenMixer that requires the number of heads to be equal to the number of tokens. Furthermore, we establish a unified scaling module design framework for recommender systems, which bridges the connections among attention-based, TokenMixer-based, and factorization-machine-based methods. To further boost scaling ROI, a lightweight UniMixing module is designed, \textbf{UniMixing-Lite}, which further compresses the model parameters and computational cost while significantly improve the model performance. The scaling curves are shown in the following figure. Extensive offline and online experiments are conducted to verify the superior scaling abilities of \textbf{UniMixer}. △ Less

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

Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning

Authors: Rongjin Li, Zichen Tang, Xianghe Wang, Xinyi Hu, Zhengyu Wang, Zhengyu Lu, Yiling Huang, Jiayuan Chen, Weisheng Tan, Jiacheng Liu, Zhongjun Yang, Haihong E

Abstract: With the rapid progress of multimodal large language models (MLLMs), AI already performs well at literature retrieval and certain reasoning tasks, serving as a capable assistant to human researchers, yet it remains far from autonomous research. The fundamental reason is that current work on academic paper reasoning is largely confined to a search-oriented paradigm centered on pre-specified targets… ▽ More With the rapid progress of multimodal large language models (MLLMs), AI already performs well at literature retrieval and certain reasoning tasks, serving as a capable assistant to human researchers, yet it remains far from autonomous research. The fundamental reason is that current work on academic paper reasoning is largely confined to a search-oriented paradigm centered on pre-specified targets, with reasoning grounded in relevance retrieval, which struggles to support researcher-style full-document understanding, reasoning, and verification. To bridge this gap, we propose \textbf{ScholScan}, a new benchmark for academic paper reasoning. ScholScan introduces a scan-oriented task setting that asks models to read and cross-check entire papers like human researchers, scanning the document to identify consistency issues. The benchmark comprises 1,800 carefully annotated questions drawn from nine error categories across 13 natural-science domains and 715 papers, and provides detailed annotations for evidence localization and reasoning traces, together with a unified evaluation protocol. We assessed 15 models across 24 input configurations and conducted a fine-grained analysis of MLLM capabilities for all error categories. Across the board, retrieval-augmented generation (RAG) methods yield no significant improvements, revealing systematic deficiencies of current MLLMs on scan-oriented tasks and underscoring the challenge posed by ScholScan. We expect ScholScan to be the leading and representative work of the scan-oriented task paradigm. △ Less

Submitted 27 March, 2026; originally announced March 2026.

Comments: Accepted to ICLR 2026

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}

Hybrid Deep Learning with Temporal Data Augmentation for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries

Authors: Yun Tian, Guili Wang, Jian Bi, Kaixin Han, Chenglu Wu, Zhiyi Lu, Chenhao Li, Liangwang Sun, Minyu Zhou, Chenchen Xu

Abstract: Accurate prediction of lithium-ion battery remaining useful life (RUL) is essential for reliable health monitoring and data-driven analysis of battery degradation. However, the robustness and generalization capabilities of existing RUL prediction models are significantly challenged by complex operating conditions and limited data availability. To address these limitations, this study proposes a hy… ▽ More Accurate prediction of lithium-ion battery remaining useful life (RUL) is essential for reliable health monitoring and data-driven analysis of battery degradation. However, the robustness and generalization capabilities of existing RUL prediction models are significantly challenged by complex operating conditions and limited data availability. To address these limitations, this study proposes a hybrid deep learning model, CDFormer, which integrates convolutional neural networks, deep residual shrinkage networks, and Transformer encoders extract multiscale temporal features from battery measurement signals, including voltage, current, and capacity. This architecture enables the joint modeling of local and global degradation dynamics, effectively improving the accuracy of RUL prediction.To enhance predictive reliability, a composite temporal data augmentation strategy is proposed, incorporating Gaussian noise, time warping, and time resampling, explicitly accounting for measurement noise and variability. CDFormer is evaluated on two real-world datasets, with experimental results demonstrating its consistent superiority over conventional recurrent neural network-based and Transformer-based baselines across key metrics. By improving the reliability and predictive performance of RUL prediction from measurement data, CDFormer provides accurate and reliable forecasts, supporting effective battery health monitoring and data-driven maintenance strategies. △ Less

Submitted 28 March, 2026; originally announced March 2026.

"Law at Your Fingertips": Understanding Legal Information Seeking on Video-Sharing Platforms in China

Authors: Zhiyang Wu, Junliang Chen, Qian Wan, Qing Xiao, Piaohong Wang, Ge Gao, Zhicong Lu

Abstract: Equipping laypeople with the capabilities to seek legal information has been an important goal for Legal Empowerment in modern society. However, unlike general information-seeking behaviors, legal information seeking is characterized by high stakes, urgency, and a critical need for emotional support, which traditional text-based searching platforms struggle to satisfy. In recent years, people have… ▽ More Equipping laypeople with the capabilities to seek legal information has been an important goal for Legal Empowerment in modern society. However, unlike general information-seeking behaviors, legal information seeking is characterized by high stakes, urgency, and a critical need for emotional support, which traditional text-based searching platforms struggle to satisfy. In recent years, people have been increasingly turning to Video-Sharing Platforms (VSPs) for access to legal information and to fulfill their legal needs. Despite the importance of this shift, such VSP-mediated legal information-seeking practices remain underexplored. Through an observational analysis of legal content on two VSPs (Douyin and Bilibili) and interviews with 20 Chinese information seekers, this study examined the practices and challenges associated with seeking, comprehending, and evaluating legal information on VSPs. We further revealed the formation of trust and engagement on the VSP-based legal knowledge-sharing community, highlighting how VSP affordances helped mitigate seekers' epistemic discomfort and satisfy their needs for emotional support. In the discussion, we provided insights on balancing heuristic and systematic processing to encourage information cross-validation, and offered implications for designing trustworthy civic information systems and fostering an accessible, safe, and efficient information-seeking environment in digital space. △ Less

Submitted 27 March, 2026; originally announced March 2026.

Comments: 25 pages, 1 figure; Accepted by ACM CSCW 2026. To appear in Proceedings of the ACM on Human-Computer Interaction (CSCW)

ACM Class: H.5.m; K.4.0

EcoThink: A Green Adaptive Inference Framework for Sustainable and Accessible Agents

Authors: Linxiao Li, Zhixiang Lu

Abstract: As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint of Large Language Models (LLMs) presents a critical sustainability challenge. Current paradigms indiscriminately apply computation-intensive strategies like Chain-of-Thought (CoT) to billions of daily queries, causing LLM overthinking, a redundancy that amplifies carbon emissions and oper… ▽ More As the Web transitions from static retrieval to generative interaction, the escalating environmental footprint of Large Language Models (LLMs) presents a critical sustainability challenge. Current paradigms indiscriminately apply computation-intensive strategies like Chain-of-Thought (CoT) to billions of daily queries, causing LLM overthinking, a redundancy that amplifies carbon emissions and operational barriers. This inefficiency directly undermines UN Sustainable Development Goals 13 (Climate Action) and 10 (Reduced Inequalities) by hindering equitable AI access in resource-constrained regions. To address this, we introduce EcoThink, an energy-aware adaptive inference framework designed to reconcile high-performance AI intelligence with environmental responsibility. EcoThink employs a lightweight, distillation-based router to dynamically assess query complexity, skipping unnecessary reasoning for factoid retrieval while reserving deep computation for complex logic. Extensive evaluations across 9 diverse benchmarks demonstrate that EcoThink reduces inference energy by 40.4% on average (up to 81.9% for web knowledge retrieval) without statistically significant performance loss. By mitigating algorithmic waste, EcoThink offers a scalable path toward a sustainable, inclusive, and energy-efficient generative AI Agent. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Comments: Accepted by WWW 2026

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience

Authors: Zichuan Lin, Feiyu Liu, Yijun Yang, Jiafei Lyu, Yiming Gao, Yicheng Liu, Zhicong Lu, Yangbin Yu, Mingyu Yang, Junyou Li, Deheng Ye, Jie Jiang

Abstract: Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the… ▽ More Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation. △ Less

Submitted 25 March, 2026; originally announced March 2026.

Comments: Code and models are available at https://github.com/ui-voyager/UI-Voyager

VOLMO: Versatile and Open Large Models for Ophthalmology

Authors: Zhenyue Qin, Younjoon Chung, Elijah Lee, Wanyue Feng, Xuguang Ai, Serina Applebaum, Minjie Zou, Yang Liu, Pan Xiao, Mac Singer, Amisha Dave, Aidan Gilson, Tiarnan D. L. Keenan, Emily Y. Chew, Zhiyong Lu, Yih-Chung Tham, Ron Adelman, Luciano V. Del Priore, Qingyu Chen

Abstract: Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structured clinical data, and free-text notes to determine disease severity and management, which is time-consuming and burdensome. Recent multimodal large language models (MLLMs) show promise, but existing gene… ▽ More Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structured clinical data, and free-text notes to determine disease severity and management, which is time-consuming and burdensome. Recent multimodal large language models (MLLMs) show promise, but existing general and medical MLLMs perform poorly in ophthalmology, and few ophthalmology-specific MLLMs are openly available. We present VOLMO (Versatile and Open Large Models for Ophthalmology), a model-agnostic, data-open framework for developing ophthalmology-specific MLLMs. VOLMO includes three stages: ophthalmology knowledge pretraining on 86,965 image-text pairs from 26,569 articles across 82 journals; domain task fine-tuning on 26,929 annotated instances spanning 12 eye conditions for disease screening and severity classification; and multi-step clinical reasoning on 913 patient case reports for assessment, planning, and follow-up care. Using this framework, we trained a compact 2B-parameter MLLM and compared it with strong baselines, including InternVL-2B, LLaVA-Med-7B, MedGemma-4B, MedGemma-27B, and RETFound. We evaluated these models on image description generation, disease screening and staging classification, and assessment-and-management generation, with additional manual review by two healthcare professionals and external validation on three independent cohorts for age-related macular degeneration and diabetic retinopathy. Across settings, VOLMO-2B consistently outperformed baselines, achieving stronger image description performance, an average F1 of 87.4% across 12 eye conditions, and higher scores in external validation. △ Less

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

Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors

Authors: Chuanqing Zhuang, Xin Lu, Zehui Deng, Zhengda Lu, Yiqun Wang, Junqi Diao, Jun Xiao

Abstract: Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and sparse points priors. In this work, we propose a pose-free omnidirectional 3DGS method, named PFGS360, that reconstructs 3D Gaussians from unposed omnidirectional videos. To achieve accurate camera pose estimation, we first… ▽ More Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and sparse points priors. In this work, we propose a pose-free omnidirectional 3DGS method, named PFGS360, that reconstructs 3D Gaussians from unposed omnidirectional videos. To achieve accurate camera pose estimation, we first construct a spherical consistency-aware pose estimation module, which recovers poses by establishing consistent 2D-3D correspondences between the reconstructed Gaussians and the unposed images using Gaussians' internal depth priors. Besides, to enhance the fidelity of novel view synthesis, we introduce a depth-inlier-aware densification module to extract depth inliers and Gaussian outliers with consistent monocular depth priors, enabling efficient Gaussian densification and achieving photorealistic novel view synthesis. The experiments show significant outperformance over existing pose-free and pose-aware 3DGS methods on both real-world and synthetic 360-degree videos. Code is available at https://github.com/zcq15/PFGS360. △ Less

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

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents

Authors: Yutao Luo, Haotian Zhu, Shuchao Pang, Zhigang Lu, Tian Dong, Yongbin Zhou, Minhui Xue

Abstract: The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI models rely on environmental injection or deceptive pop-ups to mislead the agent operation. However, these techniques do not work on screenshots-based mobile GUI… ▽ More The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI models rely on environmental injection or deceptive pop-ups to mislead the agent operation. However, these techniques do not work on screenshots-based mobile GUI agents due to the challenges of restricted trigger design spaces, OS background interference, and conflicts in multiple trigger-action mappings. We propose AgentRAE, a novel backdoor attack capable of inducing Remote Action Execution in mobile GUI agents using visually natural triggers (e.g., benign app icons in notifications). To address the underfitting caused by natural triggers and achieve accurate multi-target action redirection, we design a novel two-stage pipeline that first enhances the agent's sensitivity to subtle iconographic differences via contrastive learning, and then associates each trigger with a specific mobile GUI agent action through a backdoor post-training. Our extensive evaluation reveals that the proposed backdoor preserves clean performance with an attack success rate of over 90% across ten mobile operations. Furthermore, it is hard to visibly detect the benign-looking triggers and circumvents eight representative state-of-the-art defenses. These results expose an overlooked backdoor vector in mobile GUI agents, underscoring the need for defenses that scrutinize notification-conditioned behaviors and internal agent representations. △ Less

Submitted 24 March, 2026; originally announced March 2026.

Knowledge Boundary Discovery for Large Language Models

Authors: Ziquan Wang, Zhongqi Lu

Abstract: We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer (within-knowledge boundary) and (ii) those it cannot (beyond-knowledge boundary). Iteratively exploring and explo… ▽ More We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer (within-knowledge boundary) and (ii) those it cannot (beyond-knowledge boundary). Iteratively exploring and exploiting the LLM's responses to find its knowledge boundaries is challenging because of the hallucination phenomenon. To find the knowledge boundaries of an LLM, the agent interacts with the LLM under the modeling of exploring a partially observable environment. The agent generates a progressive question as the action, adopts an entropy reduction as the reward, receives the LLM's response as the observation and updates its belief states. We demonstrate that the KBD detects knowledge boundaries of LLMs by automatically finding a set of non-trivial answerable and unanswerable questions. We validate the KBD by comparing its generated knowledge boundaries with manually crafted LLM benchmark datasets. Experiments show that our KBD-generated question set is comparable to the human-generated datasets. Our approach paves a new way to evaluate LLMs. △ Less

Submitted 13 January, 2026; originally announced March 2026.

Comments: 9 pages,4 figures

SkinCLIP-VL: Consistency-Aware Vision-Language Learning for Multimodal Skin Cancer Diagnosis

Authors: Zhixiang Lu, Shijie Xu, Kaicheng Yan, Xuyue Cai, Chong Zhang, Yulong Li, Angelos Stefanidis, Anh Nguyen, Jionglong Su

Abstract: The deployment of vision-language models (VLMs) in dermatology is hindered by the trilemma of high computational costs, extreme data scarcity, and the black-box nature of deep learning. To address these challenges, we present SkinCLIP-VL, a resource-efficient framework that adapts foundation models for trustworthy skin cancer diagnosis. Adopting a frozen perception, adaptive reasoning paradigm, we… ▽ More The deployment of vision-language models (VLMs) in dermatology is hindered by the trilemma of high computational costs, extreme data scarcity, and the black-box nature of deep learning. To address these challenges, we present SkinCLIP-VL, a resource-efficient framework that adapts foundation models for trustworthy skin cancer diagnosis. Adopting a frozen perception, adaptive reasoning paradigm, we integrate a frozen CLIP encoder with a lightweight, quantized Qwen2.5-VL via low-rank adaptation (LoRA). To strictly align visual regions with clinical semantics under long-tailed distributions, we propose the Consistency-aware Focal Alignment (CFA) Loss. This objective synergizes focal re-weighting, semantic alignment, and calibration. On ISIC and Derm7pt benchmarks, SkinCLIP-VL surpasses 13B-parameter baselines by 4.3-6.2% in accuracy with 43% fewer parameters. Crucially, blinded expert evaluation and out-of-distribution testing confirm that our visually grounded rationales significantly enhance clinical trust compared to traditional saliency maps. △ Less

Submitted 21 March, 2026; originally announced March 2026.

Comments: Accepted by 2026 IEEE International Conference on Multimedia and Expo (ICME 2026)

ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents

Authors: Zijian Lu, Yiping Zuo, Yupeng Nie, Xin He, Weibei Fan, Lianyong Qi, Shi Jin

Abstract: Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and therefore cannot be checked or locally repaired. To address this, we present ContractSkill, a framework that converts a draft skill into an executable artifact with ex… ▽ More Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and therefore cannot be checked or locally repaired. To address this, we present ContractSkill, a framework that converts a draft skill into an executable artifact with explicit procedural structure, enabling deterministic verifica tion, fault localization, and minimal local repair. This turns skill refinement from full rewriting into localized editing of a single skill artifact. Experiments on VisualWebArena show that Contract Skill is effective in realistic web environments, while MiniWoB provides a controlled test of the mechanism behind the gain. Under matched transfer layers, repaired artifacts also remain reusable after removing the source model from the loop, providing evi dence of portability within the same benchmark family rather than full-benchmark generalization. These results suggest that the central challenge is not merely generating skills, but mak ing them explicit, executable, and repairable. Code is available at https://github.com/underfitting-lu/contractskill.git. △ Less

Submitted 31 March, 2026; v1 submitted 20 March, 2026; originally announced March 2026.

Comments: 10 pages, 4 figures, 6 tables

SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia

Authors: Zhixiang Lu, Chong Zhang, Yulong Li, Angelos Stefanidis, Anh Nguyen, Imran Razzak, Jionglong Su, Zhengyong Jiang

Abstract: The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language models (LLMs) offer a potential solution for translation, their deployment in data-poor contexts faces a dual challenge: the scarcity of high-quality, culturally relevant data and the prohibitive energy costs of training on… ▽ More The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language models (LLMs) offer a potential solution for translation, their deployment in data-poor contexts faces a dual challenge: the scarcity of high-quality, culturally relevant data and the prohibitive energy costs of training on massive, noisy web corpora. To resolve the tension between digital inclusion and environmental sustainability, we introduce Sustainable Agent-Guided Expert-tuning (SAGE). This framework pioneers an energy-aware paradigm that prioritizes the "right data" over "big data". Instead of carbon-intensive training on unfiltered datasets, SAGE employs a reinforcement learning (RL) agent, optimized via Group Relative Policy Optimization (GRPO), to autonomously curate a compact training set. The agent utilizes a semantic reward signal derived from a small, expert-constructed set of community dialogues to filter out noise and cultural misalignment. We then efficiently fine-tune open-source LLMs on this curated data using Low-Rank Adaptation (LoRA). We applied SAGE to translation tasks between English and seven low-resource languages (LRLs) in Southeast Asia. Our approach establishes new state-of-the-art performance on BLEU-4 and COMET-22 metrics, effectively capturing local linguistic nuances. Crucially, SAGE surpasses baselines trained on full datasets while reducing data usage by 97.1% and training energy consumption by 95.2%. By delivering high-performance models with a minimal environmental footprint, SAGE offers a scalable and responsible pathway to bridge the digital divide in the Global South. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Comments: Accepted by WWW 2026

From Plausibility to Verifiability: Risk-Controlled Generative OCR for Vision-Language Models

Authors: Weile Gong, Yiping Zuo, Zijian Lu, Xin He, Weibei Fan, Lianyong Qi, Shi Jin

Abstract: Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-gene… ▽ More Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-generation and unsupported substitutions, creating deployment risk even when benchmark accuracy remains high. We therefore formulate frozen VLM OCR as a selective accept/abstain problem and propose a model-agnostic Geometric Risk Controller. The controller probes multiple structured views of the same input, applies lightweight structural screening, and accepts a transcription only when cross-view consensus and stability satisfy predefined criteria, yielding a small family of operating points. Experiments on frozen VLM backbones and standard OCR benchmarks show consistent reductions in extreme-error risk and catastrophic over-generation at predictable coverage costs. Reliable deployment of generative OCR with frozen VLMs benefits from explicit system-level risk control rather than unconstrained generation. △ Less

Submitted 31 March, 2026; v1 submitted 20 March, 2026; originally announced March 2026.

Comments: 10 pages, 5 figures, 5 tables

Post-Quantum Cryptography from Quantum Stabilizer Decoding

Authors: Jonathan Z. Lu, Alexander Poremba, Yihui Quek, Akshar Ramkumar

Abstract: Post-quantum cryptography currently rests on a small number of hardness assumptions, posing significant risks should any one of them be compromised. This vulnerability motivates the search for new and cryptographically versatile assumptions that make a convincing case for quantum hardness. In this work, we argue that decoding random quantum stabilizer codes -- a quantum analog of the well-studied… ▽ More Post-quantum cryptography currently rests on a small number of hardness assumptions, posing significant risks should any one of them be compromised. This vulnerability motivates the search for new and cryptographically versatile assumptions that make a convincing case for quantum hardness. In this work, we argue that decoding random quantum stabilizer codes -- a quantum analog of the well-studied LPN problem -- is an excellent candidate. This task occupies a unique middle ground: it is inherently native to quantum computation, yet admits an equivalent formulation with purely classical input and output, as recently shown by Khesin et al. (STOC '26). We prove that the average-case hardness of quantum stabilizer decoding implies the core primitives of classical Cryptomania, including public-key encryption (PKE) and oblivious transfer (OT), as well as one-way functions. Our constructions are moreover practical: our PKE scheme achieves essentially the same efficiency as state-of-the-art LPN-based PKE, and our OT is round-optimal. We also provide substantial evidence that stabilizer decoding does not reduce to LPN, suggesting that the former problem constitutes a genuinely new post-quantum assumption. Our primary technical contributions are twofold. First, we give a reduction from random quantum stabilizer decoding to an average-case problem closely resembling LPN, but which is equipped with additional symplectic algebraic structure. While this structure is essential to the quantum nature of the problem, it raises significant barriers to cryptographic security reductions. Second, we develop a new suit of scrambling techniques for such structured linear spaces, and use them to produce rigorous security proofs for all of our constructions. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: 49 pages

HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning

Authors: Zhicong Lu, Zichuan Lin, Wei Jia, Changyuan Tian, Deheng Ye, Peiguang Li, Li Jin, Nayu Liu, Guangluan Xu, Wei Feng

Abstract: While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance performance via multi-turn reinforcement learning. However, they suffer from delayed propagation in sparse outcome rewards and unreliable credit assignment with potential… ▽ More While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance performance via multi-turn reinforcement learning. However, they suffer from delayed propagation in sparse outcome rewards and unreliable credit assignment with potentially overly fine-grained and unfocused turnlevel process rewards. In this paper, we propose (HISR) exploiting Hindsight Information to modulate Segmental process Rewards, which closely aligns rewards with sub-goals and underscores significant segments to enhance the reliability of credit assignment. Specifically, a segment-level process RM is presented to assign rewards for each sub-goal in the task, avoiding excessively granular allocation to turns. To emphasize significant segments in the trajectory, a hindsight model is devised to reflect the preference of performing a certain action after knowing the trajectory outcome. With this characteristic, we design the ratios of sequence likelihoods between hindsight and policy model to measure action importance. The ratios are subsequently employed to aggregate segment importance scores, which in turn modulate segmental process rewards, enhancing credit assignment reliability. Extensive experimental results on three publicly benchmarks demonstrate the validity of our method. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: Submitted to ACL 2026 on Jan 5, 2026

OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data

Authors: Bin Cao, Sipeng Zheng, Hao Luo, Boyuan Li, Jing Liu, Zongqing Lu

Abstract: Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, a million-level, high-quality, and open-… ▽ More Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, a million-level, high-quality, and open-source motion dataset containing over 2800 hours of human motion. Each sequence undergoes rigorous quality control through physical feasibility validation and multi-granularity filtering, with detailed second-wise text annotations. We also develop an automated pipeline for creating long-horizon sequences, enabling complex motion generation. Building upon OpenT2M, we introduce MonoFrill, a pretrained motion model that achieves compelling T2M results without complicated designs or technique tricks as "frills". Its core component is 2D-PRQ, a novel motion tokenizer that captures spatiotemporal dependencies by dividing the human body into biology parts. Experiments show that OpenT2M significantly improves generalization of existing T2M models, while 2D-PRQ achieves superior reconstruction and strong zero-shot performance. We expect OpenT2M and MonoFrill will advance the T2M field by addressing longstanding data quality and benchmarking challenges. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting

Authors: Wanpeng Zhang, Hao Luo, Sipeng Zheng, Yicheng Feng, Haiweng Xu, Ziheng Xi, Chaoyi Xu, Haoqi Yuan, Zongqing Lu

Abstract: Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying quality, so many trajectories reflect recovery behavior, inconsistent operator skill, or weakly informative supervision. Uniform post-training gives equal credit to… ▽ More Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying quality, so many trajectories reflect recovery behavior, inconsistent operator skill, or weakly informative supervision. Uniform post-training gives equal credit to all samples and can therefore average over conflicting or low-attribution data. We propose Posterior-Transition Reweighting (PTR), a reward-free and conservative post-training method that decides how much each training sample should influence the supervised update. For each sample, PTR encodes the observed post-action consequence as a latent target, inserts it into a candidate pool of mismatched targets, and uses a separate transition scorer to estimate a softmax identification posterior over target indices. The posterior-to-uniform ratio defines the PTR score, which is converted into a clipped-and-mixed weight and applied to the original action objective through self-normalized weighted regression. This construction requires no tractable policy likelihood and is compatible with both diffusion and flow-matching action heads. Rather than uniformly trusting all recorded supervision, PTR reallocates credit according to how attributable each sample's post-action consequence is under the current representation, improving conservative offline adaptation to heterogeneous robot data. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline

Authors: Xingyu Liu, Zewei He, Yu Chen, Chunyu Zhu, Zixuan Chen, Xing Luo, Zhe-Ming Lu

Abstract: When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define t… ▽ More When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR$^3$) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR$^3$) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR$^3$ successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images. The RDRF dataset and the codes will be made public upon acceptance. △ Less

Submitted 6 April, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Comments: 25 pages, 22 figures

OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding

Authors: Siting Zhu, Ziyun Lu, Guangming Wang, Chenguang Huang, Yongbo Chen, I-Ming Chen, Wolfram Burgard, Hesheng Wang

Abstract: Open-vocabulary scene understanding is crucial for robotic applications, enabling robots to comprehend complex 3D environmental contexts and supporting various downstream tasks such as navigation and manipulation. However, existing methods require pre-built complete 3D semantic maps to construct scene graphs for scene understanding, which limits their applicability in robotic scenarios where envir… ▽ More Open-vocabulary scene understanding is crucial for robotic applications, enabling robots to comprehend complex 3D environmental contexts and supporting various downstream tasks such as navigation and manipulation. However, existing methods require pre-built complete 3D semantic maps to construct scene graphs for scene understanding, which limits their applicability in robotic scenarios where environments are explored incrementally. To address this challenge, we propose OGScene3D, an open-vocabulary scene understanding system that achieves accurate 3D semantic mapping and scene graph construction incrementally. Our system employs a confidence-based Gaussian semantic representation that jointly models semantic predictions and their reliability, enabling robust scene modeling. Building on this representation, we introduce a hierarchical 3D semantic optimization strategy that achieves semantic consistency through local correspondence establishment and global refinement, thereby constructing globally consistent semantic maps. Moreover, we design a long-term global optimization method that leverages temporal memory of historical observations to enhance semantic predictions. By integrating 2D-3D semantic consistency with Gaussian rendering contribution, this method continuously refines the semantic understanding of the entire scene. Furthermore, we develop a progressive graph construction approach that dynamically creates and updates both nodes and semantic relationships, allowing continuous updating of the 3D scene graphs. Extensive experiments on widely used datasets and real-world scenes demonstrate the effectiveness of our OGScene3D on open-vocabulary scene understanding. △ Less

Submitted 17 March, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning

Authors: Aozhe Wang, Yuchen Yan, Nan Zhou, Zhengxi Lu, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Abstract: Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent self-play methods unify code and test generation in a single model, but face a inherent dilemma: white-box access leads to self-collusion where the model produ… ▽ More Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent self-play methods unify code and test generation in a single model, but face a inherent dilemma: white-box access leads to self-collusion where the model produces trivial tests for easy rewards, yet black-box restriction yields generic tests that miss implementation-specific bugs. We introduce Code-A1, an adversarial co-evolution framework that jointly optimizes a Code LLM and a Test LLM with opposing objectives. The Code LLM is rewarded for passing more tests, while the Test LLM is rewarded for exposing more defects. This architectural separation eliminates self-collusion risks and safely enables white-box test generation, where the Test LLM can inspect candidate code to craft targeted adversarial tests. We further introduce a Mistake Book mechanism for experience replay and a composite reward balancing test validity with adversarial difficulty. Experiments on Qwen2.5-Coder models demonstrate that Code-A1 achieves code generation performance matching or exceeding models trained on human-annotated tests, while significantly improving test generation capability. △ Less

Submitted 16 March, 2026; originally announced March 2026.

Comments: Project Page: https://zju-real.github.io/Code-A1 Code: https://github.com/ZJU-REAL/Code-A1

One CT Unified Model Training Framework to Rule All Scanning Protocols

Authors: Fengzhi Xu, Ziyuan Yang, Zexin Lu, Yingyu Chen, Fenglei Fan, Hongming Shan, Yi Zhang

Abstract: Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data, which is an impractical demand due to inevitable organ motion. Unsupervised approaches attempt to overcome this limitation, but their assumption of homogeneous no… ▽ More Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data, which is an impractical demand due to inevitable organ motion. Unsupervised approaches attempt to overcome this limitation, but their assumption of homogeneous noise neglects the variability of scanning protocols, leading to poor generalization and potential model collapse. We further observe that distinct scanning protocols, which correspond to different physical imaging processes, produce discrete sub-manifolds in the feature space, contradicting these assumptions and limiting their effectiveness. To address this, we propose an Uncertainty-Guided Manifold Smoothing (UMS) framework to bridge the gaps between sub-manifolds. A classifier in UMS identifies sub-manifolds and predicts uncertainty scores, which guide the generation of diverse samples across the entire manifold. By leveraging the classifier's capability, UMS effectively fills the gaps between discrete sub-manifolds, and promotes a continuous and dense feature space. Due to the complexity of the global manifold, it's hard to directly model it. Therefore, we propose to dynamically incorporate the global- and sub-manifold-specific features. Specifically, we design a global- and sub-manifold-driven architecture guided by the classifier, which enables dynamic adaptation to subdomain variations. This dynamic mechanism improves the network's capacity to capture both shared and domain-specific features, thereby improving reconstruction performance. Extensive experiments on public datasets are conducted to validate the effectiveness of our method across different generation paradigms. △ Less

Submitted 16 March, 2026; originally announced March 2026.

Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality

Authors: Wenrui Cai, Zhenyi Lu, Yuzhe Li, Yongchao Feng, Jinqing Zhang, Qingjie Liu, Yunhong Wang

Abstract: With the advent of Transformer-based one-stream trackers that possess strong capability in inter-frame relation modeling, recent research has increasingly focused on how to introduce spatio-temporal context. However, most existing methods rely on a limited number of historical frames, which not only leads to insufficient utilization of the context, but also inevitably increases the length of input… ▽ More With the advent of Transformer-based one-stream trackers that possess strong capability in inter-frame relation modeling, recent research has increasingly focused on how to introduce spatio-temporal context. However, most existing methods rely on a limited number of historical frames, which not only leads to insufficient utilization of the context, but also inevitably increases the length of input and incurs prohibitive computational overhead. Methods that query an external memory bank, on the other hand, suffer from inadequate fusion between the retrieved spatio-temporal features and the backbone. Moreover, using discrete historical frames as context overlooks the rich dynamics of the target. To address the issues, we propose Uni-MDTrack, which consists of two core components: Memory-Aware Compression Prompt (MCP) module and Dynamic State Fusion (DSF) module. MCP effectively compresses rich memory features into memory-aware prompt tokens, which deeply interact with the input throughout the entire backbone, significantly enhancing the performance while maintaining a stable computational load. DSF complements the discrete memory by capturing the continuous dynamic, progressively introducing the updated dynamic state features from shallow to deep layers, while also preserving high efficiency. Uni-MDTrack also supports unified tracking across RGB, RGB-D/T/E, and RGB-Language modalities. Experiments show that in Uni-MDTrack, training only the MCP, DSF, and prediction head, keeping the proportion of trainable parameters around 30%, yields substantial performance gains, achieves state-of-the-art results on 10 datasets spanning five modalities. Furthermore, both MCP and DSF exhibit excellent generality, functioning as plug-and-play components that can boost the performance of various baseline trackers, while significantly outperforming existing parameter-efficient training approaches. △ Less

Submitted 15 March, 2026; originally announced March 2026.

Comments: 15 pages, 9 figures, 16 tables

Walking Further: Semantic-aware Multimodal Gait Recognition Under Long-Range Conditions

Authors: Zhiyang Lu, Wen Jiang, Tianren Wu, Zhichao Wang, Changwang Zhang, Siqi Shen, Ming Cheng

Abstract: Gait recognition is an emerging biometric technology that enables non-intrusive and hard-to-spoof human identification. However, most existing methods are confined to short-range, unimodal settings and fail to generalize to long-range and cross-distance scenarios under real-world conditions. To address this gap, we present \textbf{LRGait}, the first LiDAR-Camera multimodal benchmark designed for r… ▽ More Gait recognition is an emerging biometric technology that enables non-intrusive and hard-to-spoof human identification. However, most existing methods are confined to short-range, unimodal settings and fail to generalize to long-range and cross-distance scenarios under real-world conditions. To address this gap, we present \textbf{LRGait}, the first LiDAR-Camera multimodal benchmark designed for robust long-range gait recognition across diverse outdoor distances and environments. We further propose \textbf{EMGaitNet}, an end-to-end framework tailored for long-range multimodal gait recognition. To bridge the modality gap between RGB images and point clouds, we introduce a semantic-guided fusion pipeline. A CLIP-based Semantic Mining (SeMi) module first extracts human body-part-aware semantic cues, which are then employed to align 2D and 3D features via a Semantic-Guided Alignment (SGA) module within a unified embedding space. A Symmetric Cross-Attention Fusion (SCAF) module hierarchically integrates visual contours and 3D geometric features, and a Spatio-Temporal (ST) module captures global gait dynamics. Extensive experiments on various gait datasets validate the effectiveness of our method. △ Less

Submitted 14 March, 2026; originally announced March 2026.

Comments: Accepted by AAAI 2026

Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis

Authors: Dayou Li, Lulin Liu, Bangya Liu, Shijie Zhou, Jiu Feng, Ziqi Lu, Minghui Zheng, Chenyu You, Zhiwen Fan

Abstract: To serve as a scalable data source for embodied AI, world models should act as true simulators that infer interaction dynamics strictly from user actions, rather than mere conditional video generators relying on privileged future object states. In this context, egocentric Human-Object Interaction (HOI) world models are critical for predicting physically grounded first-person rollouts. However, bui… ▽ More To serve as a scalable data source for embodied AI, world models should act as true simulators that infer interaction dynamics strictly from user actions, rather than mere conditional video generators relying on privileged future object states. In this context, egocentric Human-Object Interaction (HOI) world models are critical for predicting physically grounded first-person rollouts. However, building such models is profoundly challenging due to rapid head motions, severe occlusions, and high-DoF hand articulations that abruptly alter contact topologies. Consequently, existing approaches often circumvent these physics challenges by resorting to conditional video generation with access to known future object trajectories. We introduce EgoHOI, an egocentric HOI world model that breaks away from this shortcut to simulate photorealistic, contact-consistent interactions from action signals alone. To ensure physical accuracy without future-state inputs, EgoHOI distills geometric and kinematic priors from 3D estimates into physics-informed embeddings. These embeddings regularize the egocentric rollouts toward physically valid dynamics. Experiments on the HOT3D dataset demonstrate consistent gains over strong baselines, and ablations validate the effectiveness of our physics-informed design. △ Less

Submitted 13 March, 2026; originally announced March 2026.

TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking

Authors: Jiale Meng, Jie Zhang, Runyi Hu, Zhe-Ming Lu, Tianwei Zhang, Yiming Li

Abstract: We propose TRACE, a structure-aware framework leveraging diffusion models for localized character encoding to embed data. Unlike existing methods that rely on edge features or pre-defined codebooks, TRACE exploits character structures that provide inherent resistance to noise interference due to their stability and unified representation across diverse characters. Our framework comprises three key… ▽ More We propose TRACE, a structure-aware framework leveraging diffusion models for localized character encoding to embed data. Unlike existing methods that rely on edge features or pre-defined codebooks, TRACE exploits character structures that provide inherent resistance to noise interference due to their stability and unified representation across diverse characters. Our framework comprises three key components: (1) adaptive diffusion initialization that automatically identifies handle points, target points, and editing regions through specialized algorithms including movement probability estimator (MPE), target point estimation (TPE) and mask drawing model (MDM), (2) guided diffusion encoding for precise movement of selected point, and (3) masked region replacement with a specialized loss function to minimize feature alterations after the diffusion process. Comprehensive experiments demonstrate \name{}'s superior performance over state-of-the-art methods, achieving more than 5 dB improvement in PSNR and 5\% higher extraction accuracy following cross-media transmission. \name{} achieves broad generalizability across multiple languages and fonts, making it particularly suitable for practical document security applications. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design

Authors: Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu, Yicheng Zou, Qipeng Guo

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk inducing reward hacking, where models shortcut reasoning via random guessing or simple elimination. Current approaches often mitigate this by converting MCQs to op… ▽ More Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk inducing reward hacking, where models shortcut reasoning via random guessing or simple elimination. Current approaches often mitigate this by converting MCQs to open-ended formats, thereby discarding the contrastive signal provided by expert-designed distractors. In this work, we systematically investigate the impact of option design on RLVR. Our analysis highlights two primary insights: (1) Mismatches in option counts between training and testing degrade performance. (2) Strong distractors effectively mitigate random guessing, enabling effective RLVR training even with 2-way questions. Motivated by these findings, we propose Iterative Distractor Curation (IDC), a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning. Experiments on various benchmarks demonstrate that our method effectively enhances distractor quality and yields significant gains in RLVR training compared to the original data. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning

Authors: Yuehao Song, Shaoyu Chen, Hao Gao, Yifan Zhu, Weixiang Yue, Jialv Zou, Bo Jiang, Zihao Lu, Yu Wang, Qian Zhang, Xinggang Wang

Abstract: Vision-language models (VLMs) enhance the planning capability of end-to-end (E2E) driving policy by leveraging high-level semantic reasoning. However, existing approaches often overlook the dual-system consistency between VLM's high-level decision and E2E's low-level planning. As a result, the generated trajectories may misalign with the intended driving decisions, leading to weakened top-down gui… ▽ More Vision-language models (VLMs) enhance the planning capability of end-to-end (E2E) driving policy by leveraging high-level semantic reasoning. However, existing approaches often overlook the dual-system consistency between VLM's high-level decision and E2E's low-level planning. As a result, the generated trajectories may misalign with the intended driving decisions, leading to weakened top-down guidance and decision-following ability of the system. To address this issue, we propose Senna-2, an advanced VLM-E2E driving policy that explicitly aligns the two systems for consistent decision-making and planning. Our method follows a consistency-oriented three-stage training paradigm. In the first stage, we conduct driving pre-training to achieve preliminary decision-making and planning, with a decision adapter transmitting VLM decisions to E2E policy in the form of implicit embeddings. In the second stage, we align the VLM and the E2E policy in an open-loop setting. In the third stage, we perform closed-loop alignment via bottom-up Hierarchical Reinforcement Learning in 3DGS environments to reinforce the safety and efficiency. Extensive experiments demonstrate that Senna-2 achieves superior dual-system consistency (19.3% F1 score improvement) and significantly enhances driving safety in both open-loop (5.7% FDE reduction) and closed-loop settings (30.6% AF-CR reduction). △ Less

Submitted 11 March, 2026; originally announced March 2026.

Comments: 15 pages, 8 figures. Project page: https://ambitious-idiot.github.io/senna2-project

Landmark Guided 4D Facial Expression Generation

Authors: Xin Lu, Zhengda Lu, Yiqun Wang, Jun Xiao

Abstract: In this paper, we proposed a generative model that learns to synthesize the 4D facial expression with the neutral landmark. Existing works mainly focus on the generation of sequences guided by expression labels, speech, etc, while they are not robust to the change of different identities. Our LM-4DGAN utilizes neutral landmarks to guide the facial expression generation while adding an identity dis… ▽ More In this paper, we proposed a generative model that learns to synthesize the 4D facial expression with the neutral landmark. Existing works mainly focus on the generation of sequences guided by expression labels, speech, etc, while they are not robust to the change of different identities. Our LM-4DGAN utilizes neutral landmarks to guide the facial expression generation while adding an identity discriminator and a landmark autoencoder to the basic WGAN for achieving better identity robustness. Furthermore, we add a cross-attention mechanism to the existing displacement decoder which is suitable for the given identity. △ Less

Submitted 10 March, 2026; originally announced March 2026.

FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing

Authors: Xin Lu, Chuanqing Zhuang. Zhengda Lu, Yiqun Wang, Jun Xiao

Abstract: 4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-frame motion of expression sequences. In this paper, we propose a frequency-controlled 4D facial expression synthesizing method, FC-4DFS. Specifically, we introduce a frequency-controlled LSTM network to generate 4D facial… ▽ More 4D facial expression synthesizing is a critical problem in the fields of computer vision and graphics. Current methods lack flexibility and smoothness when simulating the inter-frame motion of expression sequences. In this paper, we propose a frequency-controlled 4D facial expression synthesizing method, FC-4DFS. Specifically, we introduce a frequency-controlled LSTM network to generate 4D facial expression sequences frame by frame from a given neutral landmark with a given length. Meanwhile, we propose a temporal coherence loss to enhance the perception of temporal sequence motion and improve the accuracy of relative displacements. Furthermore, we designed a Multi-level Identity-Aware Displacement Network based on a cross-attention mechanism to reconstruct the 4D facial expression sequences from landmark sequences. Finally, our FC-4DFS achieves flexible and SOTA generation results of 4D facial expression sequences with different lengths on CoMA and Florence4D datasets. The code will be available on GitHub. △ Less

Submitted 10 March, 2026; originally announced March 2026.

ReTac-ACT: A State-Gated Vision-Tactile Fusion Transformer for Precision Assembly

Authors: Minchi Ruan, LiangQing Zhou, Hongtong Li, Zongtao Wang, ZhaoMing Lu, Jianwei Zhang, Bin Fang

Abstract: Precision assembly requires sub-millimeter corrections in contact-rich "last-millimeter" regions where visual feedback fails due to occlusion from the end-effector and workpiece. We present ReTac-ACT (Reconstruction-enhanced Tactile ACT), a vision-tactile imitation learning policy that addresses this challenge through three synergistic mechanisms: (i) bidirectional cross-attention enabling recipro… ▽ More Precision assembly requires sub-millimeter corrections in contact-rich "last-millimeter" regions where visual feedback fails due to occlusion from the end-effector and workpiece. We present ReTac-ACT (Reconstruction-enhanced Tactile ACT), a vision-tactile imitation learning policy that addresses this challenge through three synergistic mechanisms: (i) bidirectional cross-attention enabling reciprocal visuo-tactile feature enhancement before fusion, (ii) a proprioception-conditioned gating network that dynamically elevates tactile reliance when visual occlusion occurs, and (iii) a tactile reconstruction objective enforcing learning of manipulation-relevant contact information rather than generic visual textures. Evaluated on the standardized NIST Assembly Task Board M1 benchmark, ReTac-ACT achieves 90% peg-in-hole success, substantially outperforming vision-only and generalist baseline methods, and maintains 80% success at industrial-grade 0.1mm clearance. Ablation studies validate that each architectural component is indispensable. The ReTac-ACT codebase and a vision-tactile demonstration dataset covering various clearance levels with both visual and tactile features will be released to support reproducible research. △ Less

Submitted 18 March, 2026; v1 submitted 10 March, 2026; originally announced March 2026.

Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA

Authors: Xin Lu, Rui Li, Xun Huang, Weixin Li, Chuanqing Zhuang, Jiayuan Li, Zhengda Lu, Jun Xiao, Yunhong Wang

Abstract: Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-populated scenes, human activities and occlusions introduce significant perceptual non-stationarity: task-relevant cues are transient and view-dependent, while a store-then-retrieve strategy over-accumulates redundant evi… ▽ More Embodied Question Answering (EQA) has traditionally been evaluated in temporally stable environments where visual evidence can be accumulated reliably. However, in dynamic, human-populated scenes, human activities and occlusions introduce significant perceptual non-stationarity: task-relevant cues are transient and view-dependent, while a store-then-retrieve strategy over-accumulates redundant evidence and increases inference cost. This setting exposes two practical challenges for EQA agents: resolving ambiguity caused by viewpoint-dependent occlusions, and maintaining compact yet up-to-date evidence for efficient inference. To enable systematic study of this setting, we introduce DynHiL-EQA, a human-in-the-loop EQA dataset with two subsets: a Dynamic subset featuring human activities and temporal changes, and a Static subset with temporally stable observations. To address the above challenges, we present DIVRR (Dynamic-Informed View Refinement and Relevance-guided Adaptive Memory Selection), a training-free framework that couples relevance-guided view refinement with selective memory admission. By verifying ambiguous observations before committing them and retaining only informative evidence, DIVRR improves robustness under occlusions while preserving fast inference with compact memory. Extensive experiments on DynHiL-EQA and the established HM-EQA dataset demonstrate that DIVRR consistently improves over existing baselines in both dynamic and static settings while maintaining high inference efficiency. △ Less

Submitted 10 March, 2026; originally announced March 2026.

ProvAgent: Threat Detection Based on Identity-Behavior Binding and Multi-Agent Collaborative Attack Investigation

Authors: Wenhao Yan, Ning An, Linxu Li, Bingsheng Bi, Bo Jiang, Zhigang Lu, Baoxu Liu, Junrong Liu, Cong Dong

Abstract: Advanced Persistent Threats (APTs) pose critical challenges to modern cybersecurity due to their multi-stage and stealthy nature. While provenance-based detection approaches show promise in capturing causal attack semantics, current threat provenance practices face two paradoxical issues: (1) expert skepticism, where human analysts doubt the capability of traditional detection models to identify c… ▽ More Advanced Persistent Threats (APTs) pose critical challenges to modern cybersecurity due to their multi-stage and stealthy nature. While provenance-based detection approaches show promise in capturing causal attack semantics, current threat provenance practices face two paradoxical issues: (1) expert skepticism, where human analysts doubt the capability of traditional detection models to identify complex attacks; and (2) expert dependence, as analysts cannot manually process large-scale raw logs to detect threats without these models. Consequently, collaboration between humans and traditional models remains the prevailing paradigm. However, this renders investigation quality contingent upon human expertise and frequently results in alert fatigue. To address these challenges, we present ProvAgent, a framework that evolves the threat provenance paradigm from human-model collaboration to a novel collaboration between multi-agent systems and traditional models. ProvAgent leverages the speed and cost-efficiency of traditional models for initial anomaly screening over large-scale logs. By enforcing fine-grained identity-behavior consistency via graph contrastive learning, it profiles entities based on specific attributes to generate high-fidelity alerts. With these alerts serving as investigation entry points, ProvAgent achieves in-depth autonomous investigation through a hypothesis-verification multi-agent framework. Evaluations with real-world datasets demonstrate that ProvAgent outperforms six state-of-the-art (SOTA) baselines in anomaly detection. Through automated investigation, ProvAgent reconstructs near-complete attack processes at a minimum cost of \$0.06 per day. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Comments: The code of ProvAgent is publicly available at \url{https://github.com/Win7ery/ProvAgent}

VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model

Authors: Jinxiang Lai, Wenzhe Zhao, Zexin Lu, Hualei Zhang, Qinyu Yang, Rongwei Quan, Zhimin Li, Shuai Shao, Song Guo, Qinglin Lu

Abstract: Visual content generation has advanced from single-image to multi-image workflows, yet existing agents remain largely plan-driven and lack systematic reflection mechanisms to correct mid-trajectory visual errors. To address this limitation, we propose VisionCreator-R1, a native visual generation agent with explicit reflection, together with a Reflection-Plan Co-Optimization (RPCO) training methodo… ▽ More Visual content generation has advanced from single-image to multi-image workflows, yet existing agents remain largely plan-driven and lack systematic reflection mechanisms to correct mid-trajectory visual errors. To address this limitation, we propose VisionCreator-R1, a native visual generation agent with explicit reflection, together with a Reflection-Plan Co-Optimization (RPCO) training methodology. Through extensive experiments and trajectory-level analysis, we uncover reflection-plan optimization asymmetry in reinforcement learning (RL): planning can be reliably optimized via plan rewards, while reflection learning is hindered by noisy credit assignment. Guided by this insight, our RPCO first trains on the self-constructed VCR-SFT dataset with reflection-strong single-image trajectories and planning-strong multi-image trajectories, then co-optimization on VCR-RL dataset via RL. This yields our unified VisionCreator-R1 agent, which consistently outperforms Gemini2.5Pro on existing benchmarks and our VCR-bench covering single-image and multi-image tasks. △ Less

Submitted 9 March, 2026; originally announced March 2026.

U6G XL-MIMO Radiomap Prediction: Multi-Config Dataset and Beam Map Approach

Authors: Xiaojie Li, Yu Han, Zhizheng Lu, Shi Jin, Chao-Kai Wen

Abstract: The upper 6 GHz (U6G) band with XL-MIMO is a key enabler for sixth-generation wireless systems, yet intelligent radiomap prediction for such systems remains challenging. Existing datasets support only small-scale arrays (up to 8x8) with predominantly isotropic antennas, far from the 1024-element directional arrays envisioned for 6G. Moreover, current methods encode array configurations as scalar p… ▽ More The upper 6 GHz (U6G) band with XL-MIMO is a key enabler for sixth-generation wireless systems, yet intelligent radiomap prediction for such systems remains challenging. Existing datasets support only small-scale arrays (up to 8x8) with predominantly isotropic antennas, far from the 1024-element directional arrays envisioned for 6G. Moreover, current methods encode array configurations as scalar parameters, forcing neural networks to extrapolate array-specific radiation patterns, which fails when predicting radiomaps for configurations absent from training data. To jointly address data scarcity and generalization limitations, this paper advances XL-MIMO radiomap prediction from three aspects. To overcome data limitations, we construct the first XL-MIMO radiomap dataset containing 78400 radiomaps across 800 urban scenes, five frequency bands (1.8-6.7 GHz), and nine array configurations up to 32x32 uniform planar arrays with directional elements. To enable systematic evaluation, we establish a comprehensive benchmark framework covering practical scenarios from coverage estimation without field measurements to generalization across unseen configurations and environments. To enable generalization to arbitrary beam configurations without retraining, we propose the beam map, a physics-informed spatial feature that analytically computes array-specific coverage patterns. By decoupling deterministic array radiation from data learned multipath propagation, beam maps shift generalization from neural network extrapolation to physics-based computation. Integrating beam maps into existing architectures reduces mean absolute error by up to 60.0% when generalizing to unseen configurations and up to 50.5% when transferring to unseen environments. The complete dataset and code are publicly available at https://lxj321.github.io/MulticonfigRadiomapDataset/. △ Less

Submitted 6 March, 2026; originally announced March 2026.

Comments: This work has been submitted to the IEEE for possible publication

GazeMoE: Perception of Gaze Target with Mixture-of-Experts

Authors: Zhuangzhuang Dai, Zhongxi Lu, Vincent G. Zakka, Luis J. Manso, Jose M Alcaraz Calero, Chen Li

Abstract: Estimating human gaze target from visible images is a critical task for robots to understand human attention, yet the development of generalizable neural architectures and training paradigms remains challenging. While recent advances in pre-trained vision foundation models offer promising avenues for locating gaze targets, the integration of multi-modal cues -- including eyes, head poses, gestures… ▽ More Estimating human gaze target from visible images is a critical task for robots to understand human attention, yet the development of generalizable neural architectures and training paradigms remains challenging. While recent advances in pre-trained vision foundation models offer promising avenues for locating gaze targets, the integration of multi-modal cues -- including eyes, head poses, gestures, and contextual features -- demands adaptive and efficient decoding mechanisms. Inspired by Mixture-of-Experts (MoE) for adaptive domain expertise in large vision-language models, we propose GazeMoE, a novel end-to-end framework that selectively leverages gaze-target-related cues from a frozen foundation model through MoE modules. To address class imbalance in gaze target classification (in-frame vs. out-of-frame) and enhance robustness, GazeMoE incorporates a class-balancing auxiliary loss alongside strategic data augmentations, including region-specific cropping and photometric transformations. Extensive experiments on benchmark datasets demonstrate that our GazeMoE achieves state-of-the-art performance, outperforming existing methods on challenging gaze estimation tasks. The code and pre-trained models are released at https://huggingface.co/zdai257/GazeMoE △ Less

Submitted 6 March, 2026; originally announced March 2026.

Comments: 8 pages, 3 figures, ICRA 2026

Accelerating Sampling-Based Control via Learned Linear Koopman Dynamics

Authors: Wenjian Hao, Yuxuan Fang, Zehui Lu, Shaoshuai Mou

Abstract: This paper presents an efficient model predictive path integral (MPPI) control framework for systems with complex nonlinear dynamics. To improve the computational efficiency of classic MPPI while preserving control performance, we replace the nonlinear dynamics used for trajectory propagation with a learned linear deep Koopman operator (DKO) model, enabling faster rollout and more efficient trajec… ▽ More This paper presents an efficient model predictive path integral (MPPI) control framework for systems with complex nonlinear dynamics. To improve the computational efficiency of classic MPPI while preserving control performance, we replace the nonlinear dynamics used for trajectory propagation with a learned linear deep Koopman operator (DKO) model, enabling faster rollout and more efficient trajectory sampling. The DKO dynamics are learned directly from interaction data, eliminating the need for analytical system models. The resulting controller, termed MPPI-DK, is evaluated in simulation on pendulum balancing and surface vehicle navigation tasks, and validated on hardware through reference-tracking experiments on a quadruped robot. Experimental results demonstrate that MPPI-DK achieves control performance close to MPPI with true dynamics while substantially reducing computational cost, enabling efficient real-time control on robotic platforms. △ Less

Submitted 5 March, 2026; originally announced March 2026.

Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution

Authors: Qiao Jin, Yin Fang, Lauren He, Yifan Yang, Guangzhi Xiong, Zhizheng Wang, Nicholas Wan, Joey Chan, Donald C. Comeau, Robert Leaman, Charalampos S. Floudas, Aidong Zhang, Michael F. Chiang, Yifan Peng, Zhiyong Lu

Abstract: Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of… ▽ More Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To efficiently perform biomedical evidence attribution, we present Med-V1, a family of small language models with only three billion parameters. Trained on high-quality synthetic data newly developed in this study, Med-V1 substantially outperforms (+27.0% to +71.3%) its base models on five biomedical benchmarks unified into a verification format. Despite its smaller size, Med-V1 performs comparably to frontier LLMs such as GPT-5, along with high-quality explanations for its predictions. We use Med-V1 to conduct a first-of-its-kind use case study that quantifies hallucinations in LLM-generated answers under different citation instructions. Results show that the format instruction strongly affects citation validity and hallucination, with GPT-5 generating more claims but exhibiting hallucination rates similar to GPT-4o. Additionally, we present a second use case showing that Med-V1 can automatically identify high-stakes evidence misattributions in clinical practice guidelines, revealing potentially negative public health impacts that are otherwise challenging to identify at scale. Overall, Med-V1 provides an efficient and accurate lightweight alternative to frontier LLMs for practical and real-world applications in biomedical evidence attribution and verification tasks. Med-V1 is available at https://github.com/ncbi-nlp/Med-V1. △ Less

Submitted 5 March, 2026; originally announced March 2026.

The Company You Keep: How LLMs Respond to Dark Triad Traits

Authors: Zeyi Lu, Angelica Henestrosa, Pavel Chizhov, Ivan P. Yamshchikov

Abstract: Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this behavior is encouraged, it may become problematic when interacting with user prompts that reflect negative social tendencies. Such responses risk amplifying harmful behavior rather than mitigating it. In this study, we examine how LLMs respond to user prompt… ▽ More Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this behavior is encouraged, it may become problematic when interacting with user prompts that reflect negative social tendencies. Such responses risk amplifying harmful behavior rather than mitigating it. In this study, we examine how LLMs respond to user prompts expressing varying degrees of Dark Triad traits (Machiavellianism, Narcissism, and Psychopathy) using a curated dataset. Our analysis reveals differences across models, whereby all models predominantly exhibit corrective behavior, while showing reinforcing output in certain cases. Model behavior also depends on the severity level and differs in the sentiment of the response. Our findings raise implications for designing safer conversational systems that can detect and respond appropriately when users escalate from benign to harmful requests. △ Less

Submitted 7 April, 2026; v1 submitted 4 March, 2026; originally announced March 2026.

ACM Class: J.4; K.4.1; K.4.2; I.2.7; I.2.0

Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation

Authors: Zilin Lu, Ruifeng Yuan, Weiwei Cao, Wanxing Chang, Zhongyu Wei, Sinuo Wang, Yong Xia, Ling Zhang, Jianpeng Zhang

Abstract: Radiologists highly desire fully automated AI for radiology report generation (R2G), yet existing approaches fall short in clinical utility. Reinforcement learning (RL) holds potential to address these shortcomings, but its adoption in this task remains underexplored. In this paper, we revisit RL in terms of data efficiency and optimization effectiveness for R2G tasks. First, we explore the impact… ▽ More Radiologists highly desire fully automated AI for radiology report generation (R2G), yet existing approaches fall short in clinical utility. Reinforcement learning (RL) holds potential to address these shortcomings, but its adoption in this task remains underexplored. In this paper, we revisit RL in terms of data efficiency and optimization effectiveness for R2G tasks. First, we explore the impact of data quantity and quality on the performance of RL in medical contexts, revealing that data quality plays a more critical role than quantity. To this end, we propose a diagnostic diversity-based data sampling strategy that enables comparable performance with fewer samples. Second, we observe that the majority of tokens in radiology reports are template-like and diagnostically uninformative, whereas the low frequency of clinically critical tokens heightens the risk of being overlooked during optimization. To tackle this, we introduce Diagnostic Token-weighted Policy Optimization (DiTPO), which directly optimizes for clinical accuracy by using a diagnostic F1 score as the reward signal. Unlike standard RL approaches that treat all tokens equally, DiTPO explicitly models the varying importance of different tokens through rule- or gradient-based mechanisms to prioritize clinically relevant content. Extensive experiments on the MIMIC-CXR, IU-Xray, and CheXpert Plus datasets demonstrate that our framework achieves state-of-the-art (SOTA) performance while requiring substantially fewer training samples in RL. Notably, on MIMIC-CXR, our framework attains an F1 score of 0.516 using only 20% of the RL training samples. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attention

Authors: Wensheng Wu, Zheming Lu, Ziqian Lu, Zewei He, Xuecheng Sun, Zhao Wang, Jungong Han, Yunlong Yu

Abstract: Industrial anomaly detection faces significant challenges due to the scarcity of anomalous samples and the complexity of real-world anomalies. In this paper, we propose a foundation model-based anomaly synthesis pipeline (FMAS) that generates highly realistic anomalous samples without fine-tuning or class-specific training. Motivated by the distinct frequency-domain characteristics of anomalies, w… ▽ More Industrial anomaly detection faces significant challenges due to the scarcity of anomalous samples and the complexity of real-world anomalies. In this paper, we propose a foundation model-based anomaly synthesis pipeline (FMAS) that generates highly realistic anomalous samples without fine-tuning or class-specific training. Motivated by the distinct frequency-domain characteristics of anomalies, we introduce aWavelet Domain Attention Module (WDAM), which exploits adaptive sub-band processing to enhance anomaly feature extraction. The combination of FMAS and WDAM significantly improves anomaly detection sensitivity while maintaining computational efficiency. Comprehensive experiments on MVTec AD and VisA datasets demonstrate that WDAM, as a plug-and-play module, achieves substantial performance gains against existing baselines. △ Less

Submitted 3 March, 2026; originally announced March 2026.