arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Fudan University(复旦大学)

共收录 1920
2602.00491 2026-05-27 cs.CL

From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas

从知识到推理:形式化GlobalHealthAtlas上的专业公共卫生推理

Zhaokun Yan, Shan Xu, Wuzheng Dong, Zhaohan Liu, Lijie Feng, Chengxiao Dai, Chen Tianqi, Binfan Liu, Yunpu Ma, Wenting Wei, Yingting Li, Yi Zhang, Tongning Wu

机构 * China Academy of Information and Communications Technology(中国信息通信技术研究院) CRRC Industrial Academy Co., Ltd.(CRRC工业学院有限公司) The University of Sydney(悉尼大学) Ludwig Maximilian University of Munich(慕尼黑路德维希-马克西米利安大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Beijing University of Posts and Telecommunications(北京邮电大学) Shanghai Institute of Infectious Disease and Biosecurity(上海传染病与生物安全研究院) School of Public Health, Fudan University(复旦大学公共卫生学院)

AI总结 为解决公共卫生推理缺乏结构化监督信号和基准的问题,提出大规模多语言数据集GlobalHealthAtlas(280,210实例,15领域,17语言),并构建LLM辅助的构建与质量控制流水线及领域对齐评估器,支持安全关键型公共卫生推理的LLM训练与评估。

Journal ref ICML 2026 regular

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01833 2026-05-27 cs.AI cs.CL

Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning

先规划后行动:面向LLM推理的高层规划引导强化学习

Zhihao Dou, Qinjian Zhao, Zhongwei Wan, Dinggen Zhang, Weida Wang, Towsif Raiyan, Benteng Chen, Qingtao Pan, Yang Ouyang, Chaoda Song, Zhiqiang Gao, Shufei Zhang, Sumon Biswas

机构 * Case Western Reserve University, Cleveland, OH, USA(凯斯西储大学) Kean University, Union, NJ, USA(凯恩大学) The Ohio State University, Columbus, OH, USA(俄亥俄州立大学) Fudan University, Shanghai, China(复旦大学) Shanghai Artificial Intelligence Laboratory, Shanghai, China(上海人工智能实验室) The University of Hong Kong, Hong Kong, China(香港大学) North Carolina State University, Raleigh, NC, USA(北卡罗来纳州立大学)

AI总结 提出PTA-GRPO两阶段框架,通过高层规划引导与强化学习联合优化,提升LLM在数学和自然科学推理任务中的准确性和泛化能力。

Comments 19 pages and 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11063 2026-05-27 cs.AI cs.CR

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

三思而后行:通过思想修正增强智能体行为安全

Changyue Jiang, Wenqi Zhang, Xudong Pan, Geng Hong, Min Yang

机构 * Fudan University, Shanghai, China(复旦大学,上海,中国) Shanghai Innovation Institute, Shanghai, China(上海创新研究院,上海,中国) Shanghai Pudong Research Institute of Cryptology, Shanghai, China(上海浦东密码研究院,上海,中国)

AI总结 提出Thought-Aligner,一种轻量级插件式安全模型,在动作执行前对不安全思想进行因果修正,无需修改底层智能体,通过两阶段对比学习训练,在多个基准和六种LLM上将行为安全从约50%提升至约90%,超越现有防护约23%,同时提升有用性约5%。

Comments Accepted to ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26003 2026-05-26 cs.CV

Towards 3D heart mesh generation using contactless radar imaging and physics-informed neural network

基于非接触式雷达成像和物理信息神经网络的3D心脏网格生成

Jinye Li, Chenxi Fu, Minghang Zheng, Yang Liu, Xiahai Zhuang, Qingchao Chen

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Fudan University(复旦大学) Peking University(北京大学)

AI总结 提出SAR2Mesh框架,通过粗到细的网格变形过程,结合几何感知特征投影和物理信息雷达损失,从合成孔径雷达图像重建高保真3D心脏几何结构。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23904 2026-05-26 cs.AI cs.CL

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

SkillOpt: 自我进化智能体技能的执行策略

Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, Ziwei Zhou, Zisu Huang, Yan Li, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Yuqing Yang, Dongdong Chen, Xue Yang, Chong Luo

机构 * Microsoft(微软公司) Shanghai Jiao Tong University(上海交通大学) Tongji University(同济大学) Fudan University(复旦大学)

AI总结 提出SkillOpt,一种系统性的可控文本空间优化器,通过分离的优化器模型对技能文档进行有界编辑,并仅在严格改善验证分数时接受编辑,从而稳定训练技能,在六个基准测试中全面优于现有方法。

Comments 27 pages, 4 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25964 2026-05-26 cs.AI

LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation

LECTOR: 科学推理图与引言生成的联合优化

Jiabei Xiao, Yizhou Wang, Chen Tang, Pengze Li, Wanli Ouyang, Shixiang Tang

机构 * The Chinese University of Hong Kong(香港中文大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Fudan University(复旦大学)

AI总结 提出LECTOR框架,通过逻辑-表达协同强化学习联合优化科学推理图的结构保真度和引言生成质量,在Nature Communications数据集上实现显著提升。

Comments 25 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25874 2026-05-26 cs.CV

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

WBench:面向交互式视频世界模型评估的综合多轮基准

Kaining Ying, Hengrui Hu, Siyu Ren, Jiamu Li, Fengjiao Chen, Ziwen Wang, Xuezhi Cao, Xunliang Cai, Henghui Ding

机构 * Fudan University(复旦大学) Meituan Longcat Team(美团Longcat团队)

AI总结 提出WBench,一个包含五个维度、289个测试用例和1058轮交互的综合多轮基准,用于系统评估交互式世界模型,并发现现有模型在不同维度上表现不一。

Comments Technical report of WBench. Homepage: https://meituan-longcat.github.io/WBench/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25626 2026-05-26 cs.CL

Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC

超越字面翻译:评估社交媒体用户生成内容中的文化有效性

Linjuan Wu, Ruiqi Zhang, Xinze Lyu, Ye Guo, Daoxin Zhang, Zhe Xu, Yao Hu, Yixin Cao, Yongliang Shen, Weiming Lu

机构 * Zhejiang University(浙江大学) Fudan University(复旦大学) Xiaohongshu Inc.(小红书公司)

AI总结 针对社交媒体用户生成内容翻译中文化传递与情感共鸣不足的问题,提出CULTURE-MT基准,通过构建涵盖14个领域、4种文化负载类型的1002条UGC笔记,并引入文化有效性评估标准,实验表明传统指标无法捕捉文化有效性,且基础LLM的文化有效性与模型规模相关。

Comments Accepted by ICML2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25621 2026-05-26 cs.CV

StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering

StreamOV: 通过证据引导记忆与响应触发的流式全视频理解

Ming Xie, Zizheng Huang, Xudong Tan, Chao Wang, Xiangyu Zeng, Wenxiao Wu, Tao Chen, Limin Wang, Yanwei Fu

机构 * Shanghai Innovation Institute(上海创新研究院) Fudan University(复旦大学) Nanjing University(南京大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Huazhong University of Science and Technology(华中科技大学)

AI总结 提出StreamOV框架,利用多模态证据引导的长短期记忆和隐状态驱动的触发机制,实现流式全视频理解中的在线推理与主动响应,并在新基准SOVBench上取得最优性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25599 2026-05-26 cs.LG cs.CV

Generalized Evidential Deep Learning: From a Bayesian Perspective

广义证据深度学习:从贝叶斯视角

Yuanye Liu, Yibo Gao, Yuanyang Chen, Xiahai Zhuang

机构 * School of Data Science, Fudan University, Shanghai, China(复旦大学数据科学学院,上海,中国)

AI总结 本文从广义贝叶斯框架出发,为证据深度学习建立理论基础,并提出统一可扩展的广义证据深度学习框架,在分类、不确定性估计和OOD检测上取得可比结果。

Comments Submitted to ICML2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25595 2026-05-26 cs.CV

How Far Has AI Come in Liver Fibrosis Staging? A Large-Scale Real-World Dataset and Benchmark

AI在肝纤维化分期中取得了多大进展?大规模真实世界数据集与基准

Yuanye Liu, Nannan Shi, Zhejia Zhang, Hanxiao Zhang, Boya Wang, Derong Yu, Nao Wang, Yuxin Jin, Yang Zhou, Kunhao Yuan, Siqi Wang, Lida Yang, Xu Qiao, Wentao Liu, Xuelei He, Xin Hong, Guoyan Zheng, Xin Chen, Guang-Zhong Yang, Le Zhang, Lei Li, Yuxin Shi, Xiahai Zhuang

机构 * School of Data Science, Fudan University, Shanghai, China(复旦大学数据科学学院) Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China(复旦大学上海公共卫生临床中心放射科) Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA(西北大学电气与计算机工程系) Shanghai Key Laboratory of Flexible Medical Robotics, Tongren Hospital, Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China(上海柔性医疗机器人重点实验室) School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China(上海交通大学生物医学工程学院) School of Computer Science, University of Nottingham, Nottingham, UK(诺丁汉大学计算机科学学院) Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China(上海交通大学生物医学工程学院医疗机器人研究所) College of Computer Science and Technology, Huaqiao University, Xiamen, China(华侨大学计算机科学与技术学院) School of Electronic Information (School of Artificial Intelligence), Northwest University, Xi'an, China(西北大学电子信息学院(人工智能学院)) Department of Mechanical Engineering, University College London, London, UK(伦敦大学学院机械工程系) Institute of Neuroscience and Cardiovascular Research, University of Edinburgh, Edinburgh, UK(爱丁堡大学神经科学与心血管研究学院) CAS Center for Excellence in Nanoscience, National Center for Nanoscience and Technology, Beijing, China(中国科学院纳米科学卓越中心) School of Control Science and Engineering, Shandong University, Jinan, China(山东大学控制科学与工程学院) School of Engineering, College of Engineering and Physical Sciences, University of Birmingham, Birmingham, UK(伯明翰大学工程学院)

AI总结 基于多中心、多序列MRI的大规模真实世界数据集LiFS,系统评估了9种AI方法在肝纤维化分期中的表现,发现最佳AI与资深放射科医生相当,但跨中心异质性和标签不平衡仍是主要挑战。

Comments Submitted to Medical Image Analysis

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25446 2026-05-26 cs.AI cs.LG

A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography

面向常规心电图广谱心血管评估的信号-语言基础模型

Ziqing Yu, Yuhui Tao, Jiayu Huo, Lei Pan, Zilong Xiao, Juecheng Chen, Xiao Li, Jianxuan Li, You Zhou, Zhixing Li, Cong Wang, Beijian Zhang, Chen Chen, Hongyang Lu, Konstantinos Patlatzoglou, Daniel B. Kramer, Jonathan W. Waks, Yangang Su, Fu Siong Ng, Shuo Wang, Yixiu Liang, Junbo Ge

机构 * Department of Cardiology, Zhongshan Hospital of Fudan University(复旦大学中山医院心内科) Shanghai Institute of Cardiovascular Diseases, National Clinical Research Centre for Interventional Medicine(上海心血管病研究所,国家介入医学临床研究中心) Digital Medical Research Center, School of Basic Medical Sciences, Fudan University(复旦大学基础医学研究院数字医疗研究中心) Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention(上海医学影像计算与计算机辅助手术重点实验室) National Heart and Lung Institute, Imperial College London, Hammersmith Hospital, Du Cane Road(伦敦帝国学院国家心肺研究所,哈马舍姆医院,杜肯路) Department of Cardiology, Shanghai Geriatric Medical Center(上海老年医学中心心内科) Cardiac Rhythm Management, Medtronic Technology Center, Medtronic (Shanghai) Ltd.(美敦力技术中心,美敦力(上海)有限公司,心律管理部) Richard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Beth Israel Deaconess Medical Center, Harvard Medical School(哈佛医学院比尔·德·阿克谢心脏结局研究中心,贝斯以色列·德aconess医疗中心) Harvard-Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Center, Harvard Medical School(哈佛-托尔恩迪克电生理研究所,贝斯以色列·德aconess医疗中心,哈佛医学院) Department of Cardiology, Imperial College Healthcare NHS Trust(伦敦帝国学院医疗信托心内科部) Department of Cardiology, Chelsea and Westminster NHS Foundation Trust(切尔西和温斯洛医院 NHS 基础信托心内科部) Department of Computer Science and Technology, University of Cambridge(剑桥大学计算机科学与技术系)

AI总结 提出ECGCLIP信号-语言对比学习框架,通过大规模心电图-报告预训练,在89项下游任务中超越基线,实现对常见心律失常、超声心动图靶标及罕见心脏病的广谱评估。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25421 2026-05-26 cs.CL

HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol

HyLaT: 通过混合潜在-文本协议实现高效多智能体通信

Xinyi Mou, Siyuan Wang, Zejun Li, Yulan He, Zhongyu Wei

机构 * Fudan University(复旦大学) The Chinese University of Hong Kong(香港中文大学) King’s College London(伦敦国王学院) The Alan Turing Institute(艾伦·图灵研究所) Shanghai Innovation Institute(上海创新研究院)

AI总结 针对多智能体通信中的三元困境,提出混合潜在-文本协议HyLaT,通过潜在通道传输认知信号提升效率,自然语言表达关键信号保证可解释性,并设计两阶段训练框架,显著降低通信开销同时保持任务性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25388 2026-05-26 cs.LG q-bio.QM

ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks

ViroBench:病毒基因组学任务中的核苷酸基础模型基准测试

Dongxin Ye, Fang Hu, Han Hu, Shu Hu, Yang Tan, Wanli Ouyang, Stan Z. Li, Jie Cui, Nanqing Dong

机构 * Shanghai Innovation Institute Shanghai China(深圳河套学院) University of Electronic Science Fudan University Shanghai China Shanghai Artificial Intelligence Laboratory Shanghai China Institute of Infection Health Fudan University Shanghai China Shanghai Sci-Tech Inno Center for Infection \& Immunity Shanghai China Shanghai Jiao Tong University Shanghai China Shenzhen Loop Area Institute Shenzhen China Chinese University of Hong Kong Hong Kong China Westlake University Hangzhou China Shanghai Innovation Institute Fudan University Shanghai Artificial Intelligence Laboratory Shanghai Sci-Tech Inno Center for Infection \& Immunity Shanghai Jiao Tong University Shenzhen Loop Area Institute Chinese University of Hong Kong Westlake University

AI总结 提出首个针对病毒基因组学的综合基准ViroBench,评估66个核苷酸基础模型在生物学理解和潜在生物安全风险上的表现,发现模型在系统发育和时间偏移下性能下降,生成任务中统计似然与生物功能有效性脱钩,且预训练数据的分类多样性比参数规模更重要。

Comments 42 pages,15 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25377 2026-05-26 cs.CV cs.AI

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation

对抗正交解缠用于LVLM幻觉缓解

Ruoxi Cheng, Haoxuan Ma, Zhengfei Hai, Yiyan Huang, Ranjie Duan, Tianle Zhang, Xu Yang, Ziyi Ye, Xingjun Ma

机构 * Fudan University(复旦大学) Tencent(腾讯) Nanjing University(南京大学) Southeast University(东南大学) Great Bay University(大坝大学) TeleAI, China Telecom(TeleAI,中国电信)

AI总结 提出对抗正交解缠(AOD)框架,通过最小最大目标学习幻觉相关方向,并利用双前向对比解码策略,在不需额外训练的情况下缓解大型视觉语言模型(LVLM)的幻觉问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16953 2026-05-26 cs.AI cs.CL

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

人类如何处理AI生成的幻觉内容:一项神经影像学研究

Shuqi Zhu, Yi Zhong, Ziyi Ye, Bangde Du, Yujia Zhou, Qingyao Ai, Yiqun Liu

机构 * Department of Computer Science and Technology, Tsinghua University, Beijing, China(清华大学计算机科学与技术系) Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China(复旦大学可信具身人工智能研究院)

AI总结 通过EEG实验,研究人类在处理多模态大语言模型生成的幻觉与非幻觉内容时的神经动力学差异,揭示误判的幻觉内容未能触发标准神经认知事实验证通路。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.08426 2026-05-26 cs.CL cs.AI cs.CV

Prism: Spectral-Aware Block-Sparse Attention

Prism: 频谱感知的块稀疏注意力

Xinghao Wang, Pengyu Wang, Xiaoran Liu, Fangxu Liu, Jason Chu, Kai Song, Xipeng Qiu

机构 * Fudan University(复旦大学) Shanghai Innovation Institute(上海创新研究院) ByteDance Inc.(字节跳动公司) OpenMOSS Team(OpenMOSS团队)

AI总结 针对长上下文LLM预填充中块稀疏注意力的块选择效率瓶颈,提出无训练频谱感知方法Prism,通过高低频分支分解和能量温度校准恢复位置信号,实现纯块级重要性估计,在保持精度同时实现高达5.1倍加速。

Comments ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14249 2026-05-26 cs.CL

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

哪种推理轨迹能更好地教会学生推理?一个信息对齐的简单度量

Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * Fudan University(复旦大学) Shanghai AI Laboratory(上海人工智能实验室) University of Toronto(多伦多大学) University of Sydney(悉尼大学)

AI总结 提出Rank-Surprisal Ratio (RSR)度量,通过结合对齐性和信息性评估推理轨迹对学生模型的适用性,在轨迹选择和教师选择中显著优于现有方法。

Comments Accepted to ACL 2026 (Main Conference). 31 pages. Project page: https://github.com/UmeanNever/RankSurprisalRatio

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17629 2026-05-26 cs.CV cs.AI cs.CL

CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning

CLiViS: 通过语言-视觉协同释放认知地图用于具身视觉推理

Kailing Li, Qi'ao Xu, Tianwen Qian, Yuqian Fu, Yang Jiao, Xiaoling Wang

机构 * School of Computer Science and Technology, East China Normal University(东华大学计算机科学与技术学院) King Abdullah University of Science and Technology(科廷大学) Fudan University(复旦大学)

AI总结 提出CLiViS框架,通过LLM进行高层任务规划并协调VLM驱动的开放世界视觉感知,构建动态认知地图以迭代更新场景上下文,实现无需训练的具身视觉推理。

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.10947 2026-05-26 cs.CV

Residual Connections Harm Generative Representation Learning

残差连接损害生成式表示学习

Xiao Zhang, Ruoxi Jiang, William Gao, Rebecca Willett, Michael Maire

机构 * University of Chicago(芝加哥大学) Fudan University(复旦大学) Tencent(腾讯) Shanghai Academy of AI for Science(上海人工智能科学研究院)

AI总结 通过减少残差网络中恒等捷径的权重,显著提升掩码自编码器和扩散模型等生成式表示学习框架中的语义特征学习质量。

Comments accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25024 2026-05-26 cs.CV

DA-UCT: Self-Supervised Domain-Adaptive Ultrasound Computed Tomography for Rapid Musculoskeletal Sound Speed Reconstruction

DA-UCT:用于快速肌肉骨骼声速重建的自监督域自适应超声计算机断层扫描

Tianyu Liu, Heyu Ma, Aiduo Wang, Peiwen Li, Boyi Li, Ying Li, Dan Li, Chengcheng Liu, Dean Ta

机构 * College of Biomedical Engineering, Fudan University(复旦大学生物医学工程学院)

AI总结 提出SDA-UCT框架,通过自监督域自适应和注意力增强网络,实现快速高分辨率肌肉骨骼超声计算机断层扫描重建,显著提升速度并保持高质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24932 2026-05-26 cs.CV

X-Edit: Exact, Explicit, and Explainable Null-Space Editing for Medical Vision Transformers

X-Edit: 面向医学视觉Transformer的精确、显式且可解释的零空间编辑

Yuanye Liu, Siyuan Zhou, Ke Zhang, Lei Li, Wei Chen, Xiahai Zhuang

机构 * Fudan University(复旦大学) Johns Hopkins University(约翰霍普金斯大学) National University of Singapore(新加坡国立大学) University of Sydney(悉尼大学)

AI总结 提出X-Edit框架,通过因果定位和零空间投影实现医学图像分类中ViT模型的精确错误修正,避免灾难性遗忘。

Comments Early accepted by MICCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24931 2026-05-26 cs.RO

Learning High-Frequency Continuous Action Chunks in Latent Space

在潜在空间中学习高频连续动作块

Kunyun Wang, Yuhang Zheng, Yupeng Zheng, Jieru Zhao, Wenchao Ding

机构 * School of Computer Science, Shanghai Jiao Tong University, Shanghai, China(上海交通大学计算机科学学院) National University of Singapore, Singapore(新加坡国立大学) Institute of Automation, Chinese Academy of Sciences, Beijing, China(中国科学院自动化研究所) Fudan University, Shanghai, China(复旦大学)

AI总结 本文提出通过变分自编码器将高频动作学习从动作空间转移到潜在空间,并引入Reuse-then-Refine块级精炼策略,以提升高频控制的时间与空间一致性,实现复杂接触任务的平滑执行。

Comments 17 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24598 2026-05-26 cs.AI cs.MA

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

Hera: 面向设备-云协作LLM智能体的长时程协调学习

Yuxin Zhang, Mengxue Hu, Zheng Lin, Xiaoyi Fan, Fan Xie, Zihan Fang, Jing Yang, Wenjun Zhu, Zhiwen Chen, Chengfei Lv, Zhe Chen

机构 * Fudan University(复旦大学) Alibaba Group(阿里巴巴集团) The University of Hong Kong(香港大学) Shenzhen MSU-BIT University(深圳MSU-BIT大学) New York University(纽约大学) Universiti Malaya(马来亚大学) SpaceAIC Co., Ltd.(SpaceAIC公司)

AI总结 提出Hera,一种步骤级设备-云LLM智能体协调器,通过两阶段训练(模仿学习+强化学习)优化长时程任务的性能-成本帕累托前沿。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24532 2026-05-26 cs.CV

Image-Conditioned Instance Prompt Network for Referring Remote Sensing Image Segmentation

图像条件实例提示网络用于遥感图像指代分割

Biaoyu Ren, Qingsheng Wang, Cun Xu, Dingkang Yang, Wenxuan Wang

机构 * School of Computer Science, Northwestern Polytechnical University, Xi'an, China(西北工业大学计算机科学学院,西安,中国) College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China(复旦大学智能机器人与先进制造学院,上海,中国) Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, China(西北工业大学深圳研究院,深圳,中国)

AI总结 提出图像条件实例提示网络(ICIPNet),通过自适应视觉语义表示和双边信息融合模块,缓解跨模态特征融合瓶颈,提升遥感图像指代分割性能。

Comments 6 pages, 3 figures. Equal contribution: Biaoyu Ren and Qingsheng Wang. Corresponding authors: Dingkang Yang and Wenxuan Wang

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21652 2026-05-26 cs.CV cs.AI

Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming

Look-Closer-Then-Diagnose: 通过主动缩放实现置信度感知的超声VQA

Yue Zhou, Erxuan Wu, Yikang Sun, Hongjoo Lee, Yuan Bi, Huixiong Xu, Nassir Navab, Zhongliang Jiang

机构 * Computer Aided Medical Procedures (CAMP)(计算机辅助医疗程序) TU Munich, Germany(慕尼黑工业大学,德国) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心) Munich, Germany(慕尼黑,德国) Zhongshan Hospital, Fudan University, China(复旦大学中山医院) The University of Hong Kong, Hongkong, China(香港大学,香港,中国)

AI总结 提出一个模拟超声医师认知流程的框架,通过“缩放-诊断”范式和基于组相对策略优化的不确定性感知奖励,提升超声视觉问答中病灶定位和诊断性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.02900 2026-05-26 cs.CR cs.AI cs.CV cs.RO

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

具身人工智能的安全性:风险、攻击与防御综述

Xiao Li, Xiang Zheng, Yifeng Gao, Xinyu Xia, Yixu Wang, Xin Wang, Ye Sun, Yunhan Zhao, Ming Wen, Jiayu Li, Zixing Chen, Xun Gong, Yi Liu, Yige Li, Yutao Wu, Cong Wang, Jun Sun, Yixin Cao, Zhineng Chen, Jingjing Chen, Tao Gui, Qi Zhang, Zuxuan Wu, Xipeng Qiu, Xuanjing Huang, Tiehua Zhang, Zhipeng Wei, Kun Wang, Xinfeng Li, Hanxun Huang, Sarah Erfani, James Bailey, Jianping Wang, Chaowei Xiao, Ran He, Bo Li, Xingjun Ma, Yu-Gang Jiang

机构 * Fudan University(复旦大学) Shanghai Innovation Institute(上海创新研究院) City University of Hong Kong(香港城市大学) Jilin University(吉林大学) Singapore Management University(新加坡管理大学) Deakin University(德肯大学) Tongji University(同济大学) Nanyang Technological University(南洋理工大学) Chinese Academy of Sciences(中国科学院) The University of Melbourne(墨尔本大学) Johns Hopkins University(约翰霍普金斯大学)

AI总结 本文综述了具身AI在感知、认知、规划、行动及交互全流程中的安全风险、攻击与防御方法,提出了多层次分类体系,并指出了多模态感知融合脆弱性、规划不稳定及人机交互可信度等关键挑战。

Comments Survey paper; 75 pages, 4 figures, 18 tables; v2 expands embodied-specific coverage of agentic threats, World Action Model threats, and contextual risk mitigation, with over 100 new references added. Project page: https://x-zheng16.github.io/Awesome-Embodied-AI-Safety/

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08988 2026-05-26 cs.AI

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

SEA-Eval: 超越情景评估的自进化智能体基准

Sihang Jiang, Lipeng Ma, Zhonghua Hong, Keyi Wang, Zhiyu Lu, Tengfei Wang, Shisong Chen, Jinghao Zhang, Tianjun Pan, Weijia Li, Jiaqing Liang, Yanghua Xiao

机构 * Fudan University(复旦大学)

AI总结 本文提出自进化智能体(SEA)的形式化定义及其最小充分架构进化飞轮,并构建首个专门评估SEA的基准SEA-Eval,通过顺序任务流设计量化进化增益、稳定性和隐式对齐收敛。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24203 2026-05-26 cs.RO

Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance

Afford-VLA:通过内化可操作性实现动作对齐的视觉规划

Runze Wang, Yuqian Fu, Yu Li, Tao Lin, Tianwen Qian, Mohamed Elhoseiny, Bo Zhao, Yanwei Fu, Yu-Gang Jiang, Xiangyang Xue

机构 * Fudan University(复旦大学) KAUST(康斯坦丁·亚历山大科研大学) SJTU(上海交通大学) East China Normal University(华东师范大学)

AI总结 提出Afford-VLA框架,通过内化任务条件可操作性作为显式视觉规划接口,利用可学习<AFF>令牌查询交互区域并解码为紧凑嵌入以直接条件化动作生成,在多个模拟基准上取得最先进性能。

Comments 20 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23989 2026-05-26 cs.AI cs.CL cs.CR

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security

迈向可信的自主AI:安全性、鲁棒性、隐私与系统安全的全面综述

Jinhu Qi, Muzhi Li, Jiahong Liu, Yuqin Shu, Dianzhi Yu, Shicheng Ma, Wenqian Cui, Yiyang Zhao, Yiyi Chen, Ruoxi Jiang, Irwin King, Zenglin Xu

机构 * Faculty of Engineering, Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学工程学院、计算机科学与工程系) Artificial Intelligence Innovation and Incubation Institute, Fudan University(复旦大学人工智能创新与孵化院) Shanghai Academy of AI for Science(上海人工智能科学研究院)

AI总结 本文综述了自主AI系统在安全鲁棒性与隐私系统安全两个核心维度的风险来源、阶段缓解策略及统一评估指标,并讨论了开放挑战。

Comments 36 pages, 4 figures. Survey/review article on trustworthy agentic AI. Published in Academia AI and Applications, 2026

Journal ref Academia AI and Applications, vol. 2, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏