arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Shanghai Jiao Tong University(上海交通大学)

共收录 246
2603.21876 2026-07-21 cs.CV 版本更新

Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems

热拓扑坍缩:针对红外视觉系统的通用物理贴片攻击

Chengyin Hu, Yikun Guo, Yuxian Dong, Qike Zhang, Kalibinuer Tiliwalidi, Yiwei Wei, Haitao Shi, Jiujiang Guo, Jiahuan Long, Xiang Chen

机构 * China University of Petroleum-Beijing at Karamay(中国石油大学(北京)克拉玛依校区) University of Electronic Science and Technology of China(电子科技大学) College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部) School of Software, Shandong University(山东大学软件学院) Shanghai Jiaotong University(上海交通大学)

AI总结 本文提出通用物理贴片攻击方法UPPA,通过几何约束参数化贝塞尔块建模扰动,利用粒子群优化算法实现全局数据分布统一优化,实现动态变形下的拓扑稳定性,实验表明其在无在线计算开销下具有高攻击成功率和强跨域泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.03061 2026-07-21 cs.LG cs.AI math.ST stat.ME stat.ML stat.TH 版本更新

Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals

评估LLMs在不知道答案时的性能:通过比较信号进行数学推理的统计评估

Zihan Dong, Zhixian Zhang, Yang Zhou, Can Jin, Ruijia Wu, Linjun Zhang

机构 * Rutgers University(罗格斯大学) Shanghai Jiao Tong University(上海交通大学)

AI总结 本文提出一种统计高效的方法,通过结合标准结果与成对比较信号,提升LLM数学推理能力评估的准确性和稳定性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.02402 2026-07-21 cs.RO cs.AI cs.CV physics.app-ph 版本更新

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

SoMA:一种用于机器人软体操作的实-仿真神经模拟器

Mu Huang, Hui Wang, Kerui Ren, Linning Xu, Yunsong Zhou, Mulin Yu, Bo Dai, Jiangmiao Pang

机构 * Fudan University, China(复旦大学) Shanghai Artificial Intelligence Laboratory, China(上海人工智能实验室) Shanghai Jiao Tong University, China(上海交通大学) The Chinese University of Hong Kong, China(香港中文大学) The University of Hong Kong, China(香港大学)

AI总结 SoMA是一种用于机器人软体操作的实-仿真神经模拟器,通过统一的潜在神经空间实现可控、稳定的长周期操作和泛化能力。

Comments Project page: https://city-super.github.io/SoMA/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.24679 2026-07-21 cs.AI eess.SP 版本更新

Multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis under unseen working conditions

用于未知工况下故障诊断的具有双重解缠的多模态跨域混合融合模型

Pengcheng Xia, Yixiang Huang, Chengjin Qin, Chengliang Liu

机构 * State Key Laboratory of Mechanical System and Vibration(机械系统与振动国家重点实验室) Shanghai Jiao Tong University(上海交通大学)

AI总结 针对未知工况下故障诊断问题,提出具有双重解缠的多模态跨域混合融合模型,通过双重解缠框架、跨域混合融合策略和三模态融合机制,实现多模态表示学习与域泛化,实验验证该方法优于先进方法及各组件有效性。

Comments Accepted for publication in Mechanical Systems and Signal Processing

Journal ref Mechanical Systems and Signal Processing, Volume 258, 2026, 114693

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.11436 2026-07-20 cs.AI 版本更新

The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning

多模态焦点的潮起潮落:为基于视觉的语言模型推理调度视觉中继窗口

Wencheng Ye, Yi Bin, Yujuan Ding, Hongye Fang, Zheng Wang, Xing Xu, Jingkuan Song, Yun Zhang, Sirui Da, Heng Tao Shen

机构 * School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院) School of Fashion and Textiles, The Hong Kong Polytechnic University(香港理工大学纺织及制衣学院) School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院)

AI总结 研究视觉语言模型视觉证据不稳定问题,通过剖析其内部多模态注意力焦点的三阶段分布,提出TRACE框架,该框架能自适应控制推理,在多模型和多基准测试中显著提升基于证据的多模态推理能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.29538 2026-07-20 cs.SE cs.AI 版本更新

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

RESOURCE2SKILL: 从人类创建的多模态资源中提取可执行智能体技能

Yijia Fan, Zonglin Di, Zimo Wen, Yifan Yang, Mingxi Cheng, Qi Dai, Bei Liu, Kai Qiu, Yue Dong, Ji Li, Chong Luo

机构 * University of California, Santa Cruz(加州大学圣克鲁兹分校) Shanghai Jiao Tong University(上海交通大学) Microsoft(微软)

AI总结 提出RESOURCE2SKILL框架,从教程视频、代码库、文章等人类多模态资源中提取可执行技能,构建分层多模态技能维基,提升智能体在七个领域的任务表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.00898 2026-07-20 cs.LG cs.RO 版本更新

Dichotomous Diffusion Policy Optimization

二元扩散策略优化

Ruiming Liang, Yinan Zheng, Kexin Zheng, Tianyi Tan, Jianxiong Li, Liyuan Mao, Zhihao Wang, Guang Chen, Hangjun Ye, Jingjing Liu, Jinqiao Wang, Xianyuan Zhan

机构 * Fundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(基础模型研究中心,自动化研究所,中国科学院) School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学) Institute for AI Industry Research (AIR), Tsinghua University(人工智能产业研究院(AIR),清华大学) The Chinese University of Hong Kong(香港中文大学) Shanghai Jiao Tong University(上海交通大学) Peking University(北京大学) Xiaomi EV(小米电动车)

AI总结 DIPOLE是一种新的RL算法,通过二元策略分解实现稳定可控的扩散策略优化,适用于复杂现实应用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.15356 2026-07-20 cs.AI 版本更新

RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

RAD:检索高质量示范以增强决策

Lu Guo, Yixiang Shan, Zhengbang Zhu, Qifan Liang, Lichang Song, Ting Long, Weinan Zhang, Yi Chang

机构 * School of Artificial Intelligence, Jilin University, Changchun, China(吉林大学人工智能学院) School of Computer Science, Shanghai Jiao Tong University, Shanghai, China(上海交通大学计算机学院)

AI总结 研究针对离线强化学习泛化能力受限问题,提出RAD方法,通过引入检索机制,从离线数据集检索高回报可达状态作目标,利用生成模型生成子轨迹规划,经实验验证该方法在多基准测试中性能优越。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.01211 2026-07-17 cs.SE cs.AI 版本更新

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

性能优化基准测试是否可靠地衡量编码智能体?

Zhi Chen, Zhensu Sun, Yuling Shi, David Lo, Lingxiao Jiang

机构 * Singapore Management University(新加坡管理大学) Shanghai Jiao Tong University(上海交通大学)

AI总结 本研究审计了三个仓库级性能优化基准(GSO、SWE-Perf、SWE-fficiency),发现参考补丁的可复现性差、评分规则导致排名不一致,且多数任务已被公开提交解决,揭示了聚合排名掩盖的性能差距。

Comments 12 pages, 7 figures. Public data: https://github.com/chenzhi-cz/performance-optimization-benchmark-reliability

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12936 2026-07-17 cs.RO cs.AI 版本更新

Pipette: An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics

面向湿实验室机器人的具身仿真平台、基准测试及数据高效增强框架

Zhe Liu, Huanbo Jin, Zhaohui Du, Zhe Wang, Dongzhan Zhou, Minting Pan, He Xu, Peijia Li, Jiaming Gu, Quan Lu, Qi Wang, Bin Ji, Ting Xiao

机构 * Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education(能源化工过程智能制造国家重点实验室) Department of Computer Science and Engineering(计算机科学与工程系) Department of Laboratory Medicine(实验室医学系) Shanghai Jiao Tong University School of Medicine(上海交通大学医学院)

AI总结 提出Pipette平台,包含可编辑资产、仿真数据增强管道和11任务基准测试,将30次演示的VLA成功率从44.1%提升至74.7%。

Comments 19 pages, 19figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30060 2026-07-17 cs.CV 版本更新

Towards Consistent Video Geometry Estimation

Towards Consistent Video Geometry Estimation

Zhu Yu, Jingnan Gao, Runmin Zhang, Lingteng Qiu, Zhengyi Zhao, Rui Peng, Yichao Yan, Kejie Qiu, Siyu Zhu, Zilong Dong, Si-Yuan Cao, Hui-Liang Shen

机构 * Zhejiang University(浙江大学) Tongyi Lab, Alibaba Group(阿里云实验室) Shanghai Jiao Tong University(上海交通大学) Fudan University(复旦大学)

AI总结 提出ViGeo,一种基于纯Transformer架构的前馈基础模型,通过动态分块注意力机制和基于补全的数据精炼框架,实现视频序列中空间密集且时间一致的几何(深度、法线、点图)估计,在在线、离线及长视频任务中达到最先进性能。

Comments Project webpage: https://pkqbajng.github.io/ViGeo/

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.12785 2026-07-16 cs.CV 版本更新

ExtraGS: Enhancing Endoscopic View Extrapolation via Diffusion-Guided 3D Gaussian Splatting

ExtraGS:通过扩散引导的3D高斯点渲染增强内窥镜视图外推

Cheng-Tai Hsieh, Jiwei Shan, Han Fang, Jianshu Hu, Tao Ni, Lijun Han, Yutong Ban, Shing Shin Cheng, Hesheng Wang

机构 * The School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, and the Shanghai Key Laboratory of Navigation and Location-Based Services(上海交通大学自动化与智能感知学院以及上海市导航与位置服务重点实验室) Global College, Shanghai Jiao Tong University(上海交通大学密西根学院) Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属第九人民医院)

AI总结 研究针对传统内窥镜视野局限及神经渲染外推有伪影问题,提出ExtraGS框架,通过不确定性引导虚拟相机采样、扩散模型细化视图及置信加权微调策略,增强内窥镜视图外推,在新视图合成中达先进性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.12252 2026-07-16 cs.CL 版本更新

FinResearchBench II: A Deep Research Benchmark with Consensus-Derived Gold Rubrics for Distinguishing Financial Report Quality

金融研究基准II:一个具有共识衍生黄金标准的深度研究基准,用于区分财务报告质量

Beidi Luan, Rui Sun, Sinuo Wang, Yan Gu, Chao Li, Zhenliang Xiong, Jing Li, Zuo Bai

机构 * StepFun(步趣) FinStep(鳍步) University of Adelaide(阿德莱德大学) Shanghai Jiao Tong University(上海交通大学)

AI总结 该研究针对深度研究代理生成财务报告的大规模评估瓶颈,提出可扩展管道生成高质量标准。通过构建基准、合成候选标准、比较大语言模型与人类评估,经两个过滤器得出黄金标准集,用于评估10个深度研究系统,实现可扩展的基准评估等研究。

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.10581 2026-07-16 cs.CV 版本更新

Multi-view Hand Reconstruction with a Point-Embedded Transformer

基于点嵌入变换器的多视图手部重建

Lixin Yang, Licheng Zhong, Pengxiang Zhu, Xinyu Zhan, Junxiao Kong, Jian Xu, Cewu Lu

机构 * School of Artificial Intelligence (SAI), Shanghai Jiao Tong University(人工智能学院(SAI),上海交通大学) School of Mechanical Engineering, Shanghai Jiao Tong University(机械工程学院,上海交通大学) School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(电子信息与电气工程学院,上海交通大学) Institute of Automation Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所(CASIA))

AI总结 研究提出POEM模型用于多视图手部重建,通过在多视图立体空间嵌入基点表示手部网格,并结合多数据集及相机参数随机化训练,实现了通用、实用且经济高效的双手运动捕捉。

Comments TPAMI 2025, Extension of CVPR 2023, correction on Table 4: HO3D results

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.06978 2026-07-15 cs.RO 版本更新

SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization

SPECTRA:用于机器人技能泛化的上下文条件频谱运动基元

Boxuan Zhang, Sheng Liu, Chenlin Ming, Ahmed Abdelrahman

机构 * Technical University of Munich(慕尼黑工业大学) Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院) Shanghai Jiao Tong University(上海交通大学)

AI总结 研究机器人操作模仿学习中如何保留任务几何形状与动态可允许运动,提出频谱运动基元框架,结合任务空间与关节空间调节,经实验验证该方法在多方面表现良好,能有效实现技能泛化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.31946 2026-07-15 cs.CV 版本更新

World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration

世界叙事模型:从像素采样到物理世界编排的高度可控视频生成范式转变

Ye Chen, Xuanhong Chen, Yupeng Zhu, Liming Tan, Zhewen Wan, Yuxuan Xiong, Tielong Wang, Jinfan Liu, Wuze Zhang, Xiongzhen Zhang, Feifei Li, Xianglin Luo, Zhehan Zhao, Zhifan Zhang, Laisheng Kou, Zhujin Liang, Yugang Chen, Muchun Chen, Xu Miao, Yijing Zhang, Xiaojie Sheng, Qiang Hu, Jialiang Chen, Weimin Zhang, Wenjun Zhang, Bingbing Ni

机构 * Shanghai Jiao Tong University(上海交通大学)

AI总结 提出世界叙事模型(WNM),将视频生成解耦为结构化物理叙事与像素渲染,通过协同代理将多模态输入转化为可编辑的4D世界表示,驱动基础模型生成符合创作者意图的视频,大幅提升可控性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.31437 2026-07-15 cs.CV 版本更新

Astra: a generalizable report generation foundation model for 3D computed tomography

Astra:一种用于三维计算机断层扫描的通用报告生成基础模型

Zhuhao Wang, Fang Chen, Chaohui Yu, Zihan Li, Yuchao Zheng, Jing Wang, Xuan Yang, Jia Guo, Zhenlu Yang, Xingju Zheng, Yihua Sun, Haojie Han, Xiaoxiao Qin, Zhan Feng, Wenbo Xiao, Chao Zhu, Yuehua Li, Shipeng Zhang, Hao Luo, Yunsong Peng, Fan Wang, Hongen Liao

机构 * School of Biomedical Engineering, Tsinghua University(清华大学生物医学工程学院) School of Biomedical Engineering, Shanghai Jiao Tong University(上海交通大学生物医学工程学院) DAMO Academy, Alibaba Group(阿里云达摩院) Hupan Laboratory(壶辰实验室) Department of Biomedical Engineering, National University of Singapore(新加坡国立大学生物医学工程系) Department of Radiology, Guizhou Provincial People’s Hospital(贵州省级人民医院放射科) Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine(浙江大学医学院附属第一医院放射科) Department of Radiology, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属第六人民医院放射科) College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)

AI总结 提出Astra模型,通过风格统一和强化学习,在8个器官系统的CT报告生成中实现高精度,平均细粒度诊断指标提升44.1%,并加速临床工作流。

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.17670 2026-07-15 cs.CV cs.LG q-bio.QM q-bio.TO 版本更新

The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography

TopCoW挑战——用于CT和MR血管造影的拓扑感知Willis环分割

Kaiyuan Yang, Fabio Musio, Yihui Ma, Norman Juchler, Johannes C. Paetzold, Rami Al-Maskari, Luciano Höher, Hongwei Bran Li, Ibrahim Ethem Hamamci, Anjany Sekuboyina, Suprosanna Shit, Houjing Huang, Chinmay Prabhakar, Ezequiel de la Rosa, Bastian Wittmann, Diana Waldmannstetter, Florian Kofler, Fernando Navarro, Martin J. Menten, Ivan Ezhov, Daniel Rueckert, Iris N. Vos, Ynte M. Ruigrok, Birgitta K. Velthuis, Hugo J. Kuijf, Pengcheng Shi, Wei Liu, Ting Ma, Maximilian R. Rokuss, Yannick Kirchhoff, Fabian Isensee, Klaus Maier-Hein, Chengcheng Zhu, Huilin Zhao, Philippe Bijlenga, Julien Hämmerli, Catherine Wurster, Laura Westphal, Jeroen Bisschop, Elisa Colombo, Hakim Baazaoui, Hannah-Lea Handelsmann, Andrew Makmur, James Hallinan, Amrish Soundararajan, Benedikt Wiestler, Jan S. Kirschke, Evamaria O. Riedel, Roland Wiest, Emmanuel Montagnon, Laurent Letourneau-Guillon, Kwanseok Oh, Dahye Lee, Orhun Utku Aydin, Adam Hilbert, Jana Rieger, Dimitrios Rallios, Satoru Tanioka, Alexander Koch, Dietmar Frey, Abdul Qayyum, Moona Mazher, Steven Niederer, Nico Disch, Julius C. Holzschuh, Dominic LaBella, Francesco Galati, Daniele Falcetta, Maria A. Zuluaga, Chaolong Lin, Haoran Zhao, Zehan Zhang, Minghui Zhang, Xin You, Hanxiao Zhang, Guang-Zhong Yang, Yun Gu, Sinyoung Ra, Jongyun Hwang, Hyunjin Park, Junqiang Chen, Marek Wodzinski, Henning Müller, Nesrin Mansouri, Florent Autrusseau, Cansu Yalcin, Rachika E. Hamadache, Clara Lisazo, Joaquim Salvi, Adrià Casamitjana, Xavier Lladó, Uma Maria Lal-Trehan Estrada, Valeriia Abramova, Luca Giancardo, Arnau Oliver, Paula Casademunt, Adrian Galdran, Matteo Delucchi, Oscar Camara, Jialu Liu, Haibin Huang, Yue Cui, Zehang Lin, Yusheng Liu, Shunzhi Zhu, Tatsat R. Patel, Adnan H. Siddiqui, Vincent M. Tutino, Maysam Orouskhani, Huayu Wang, Mahmud Mossa-Basha, Yuki Sato, Sven Hirsch, Susanne Wegener, Bjoern Menze

机构 * Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland Institute of Computational Life Sciences, Zurich University of Applied Sciences (ZHAW), Waedenswil, Switzerland Department of Neuroradiology, University Hospital of Zurich, Zurich, Switzerland Department of Neurosurgery, Zhongnan Hospital of Wuhan University, Wuhan, China Department of Radiology at Weill Cornell Medicine, Cornell University, New York, USA Institute for Tissue Engineering School of Computation, Information Technology, Technical University of Munich, Germany Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School, Boston, USA School of Medicine Health, TUM Klinikum, Technical University of Munich, Germany Munich Center for Machine Learning, Munich, Germany Department of Computing, Imperial College London, London, UK Image Sciences Institute, UMC Utrecht, Utrecht, The Netherlands Department of Neurology Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands Department of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands Electronic \& Information Engineering School, Harbin Institute of Technology (Shenzhen), China Peng Cheng Laboratory, Shenzhen, China Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany Faculty of Mathematics Computer Science, Heidelberg University, Germany Helmholtz Imaging, German Cancer Research Center, Heidelberg, Germany Data Science School for Health, Karlsruhe/Heidelberg, Germany Learning Group, Department of Radiation Oncology, Heidelberg University Hospital Department of Radiology, University of Washington, Seattle, WA, USA Department of Radiology, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China Department of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, Switzerland Department of Neurology, University Hospital of Zurich, Zurich, Switzerland Department of Physiology, University of Toronto, Canada Department of Neurosurgery, University Hospital of Zurich, Zurich, Switzerland Department of Diagnostic Imaging, National University Hospital, Singapore University of Chicago, USA Department of Diagnostic Interventional Neuroradiology, University Hospital Berne University of Berne, Berne, Switzerland Centre de Recherche du Centre Hospitalier de l’Université de Montréal (CRCHUM), Montréal, Québec, Canada DEEPNOID Inc., Seoul, South Korea Department of Artificial Intelligence, Korea University, Seoul, South Korea Charité Lab for AI in Medicine (CLAIM), Charité Universitätsmedizin Berlin, Berlin, Germany Lung Institute, Faculty of Medicine, Imperial College London, London, UK Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK Department of Radiation Oncology, Duke University Medical Center, Durham, NC, USA Institute of Medical Technology, Peking University Health Science Center, Beijing, China Hangzhou Genlight MedTech Co., Ltd., China Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China Department of Automation, Shanghai Jiao Tong University, Shanghai, China Department of Artificial Intelligence, Sungkyunkwan University, Seoul, South Korea Department of Electrical Computer Engineering, Sungkyunkwan University, Seoul, South Korea Shanghai MediWorks Precision Instruments Co., Ltd., China Institute of Informatics, HES-SO Valais-Wallis, Switzerland Department of Measurement Electronics, AGH University of Krakow, Poland Laboratoire de Thermique et Energie de Nantes (LTeN), Université Nantes, Polytech’Nantes, Nantes, France Research Institute of Computer Vision Center for Precision Health, McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, USA Physense, BCN-Medtech, Department of Communication Information Technologies, Universitat Pompeu Fabra, Barcelona, Spain Department of Mathematical Modeling Machine Learning, University of Zurich, Zurich, Switzerland Laboratory of Brain Atlas Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China School of Computer Information Engineering, Xiamen University of Technology, Xiamen, China Vascular Research Center, University at Buffalo, NY, USA Department of Pathology Anatomical Sciences, University at Buffalo, NY, USA Department of Neurosurgery, University at Buffalo, NY, USA LPIXEL Inc., Tokyo, Japan

AI总结 组织TopCoW基准挑战,发布含125对MRA和CTA扫描的注释数据集,参与者提交CoW分割和变体分类算法,经评估,最佳算法在多任务中表现出色,证明CoW分割算法对下游临床应用有可解释性效用。

Comments Summary paper for the TopCoW Challenge: 4 figures, 1 table, and supplementary material in appendix. Accepted for publication in NEJM AI. Datasets and best-performing algorithm Dockers are available at https://zenodo.org/records/15692630 and https://zenodo.org/records/15665435

Journal ref NEJM AI 2026;3(8)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15284 2026-07-15 cs.LG cs.CV 版本更新

Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation

用于分布外检测的核主成分分析:非线性核选择与近似

Kun Fang, Qinghua Tao, Mingzhen He, Kexin Lv, Runze Yang, Haibo Hu, Xiaolin Huang, Jie Yang, Longbing Cao

机构 * Department of Automation, Shanghai Jiao Tong University(上海交通大学自动化系) Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电子与电气工程系) School of Automation, Beijing Institute of Technology(北京理工大学自动化学院) China Mobile (Shanghai) Information and Communication Technology Co., Ltd.(中国移动(上海)信息技术有限公司) School of Computing, Macquarie University(麦考瑞大学计算机学院)

AI总结 研究针对深度神经网络分布外检测问题,利用核主成分分析框架,通过选择余弦 - 高斯核及近似技术,有效刻画分布外与分布内数据差异,提高检测功效和效率,为非线性特征子空间检测提供新见解与方法。

Comments This study is an extension of its conference version published in NeurIPS'24, see https://proceedings.neurips.cc/paper_files/paper/2024/hash/f2543511e5f4d4764857f9ad833a977d-Abstract-Conference.html

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.10094 2026-07-15 cs.CV cs.LG 版本更新

Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model

超越感知距离:基于扩散模型的分布外检测深度表示差异评估

Kun Fang, Zuopeng Yang, Haibo Hu, Xiaolin Huang, Jie Yang, Qinghua Tao

机构 * Department of Automation, Shanghai Jiao Tong University(上海交通大学自动化系) Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电子与电气工程系) The Intsig Information Co., Ltd., Shanghai, China(上海Intsig信息有限公司) School of Automation, Beijing Institute of Technology(北京理工大学自动化学院)

AI总结 研究基于扩散模型的分布外检测差异评估,提出以分类器相关方式评估,利用其表示空间量化特征级和logit级差异,设计优化策略构成DDR框架,实验表明DDR在ImageNet-1K数据集上检测性能优于其他方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24956 2026-07-14 cs.CL 版本更新

NITP: Next Implicit Token Prediction for LLM Pre-training

NITP:面向LLM预训练的下一隐式令牌预测

Xiangdong Zhang, Debing Zhang, Shaofeng Zhang, Xiaohan Qin, Yu Cheng, Junchi Yan

机构 * School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院) Xiaohongshu Inc.(小红书公司) The Chinese University of Hong Kong(香港中文大学) University of Science and Technology of China(中国科学技术大学)

AI总结 提出NITP方法,通过在表示空间中添加密集连续监督来增强离散令牌预测,以解决标准下一令牌预测中潜在表示空间约束不足的问题,并在0.5B至9B参数模型上取得一致性能提升。

Comments Accepted at ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23568 2026-07-14 cs.RO cs.SY eess.SY 版本更新

TactileReflex: Noise-Statistics-Driven Vision-Tactile Reflex Control for Force-Sensitive Manipulation

TactileReflex:基于噪声统计的视觉-触觉反射控制用于力敏感操作

Ziyan Feng, Yulong Fu, Zheng Li, Yuxin He, Jieji Ren, Yudong Zhong, Lujia Wang, Jinni Zhou, Qiang Nie

机构 * Thrust of Robotics and Autonomous Systems, The Hong Kong University of Science and Technology (Guangzhou)(机器人与自主系统研究所,香港科学与技术大学(广州)) School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院)

AI总结 针对易变形容器操作中的力控制难题,提出基于噪声统计的标定驱动反射控制范式,利用视觉触觉传感器提取图像级代理并实现约12Hz的优先反射通道,无需外部标定或手动调参。

Comments 8 pages, 4 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.18601 2026-07-14 cs.CV 版本更新

Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models

Incantation: 自然语言作为多实体视频世界模型的动作接口

Shangwen Zhu, Qianyu Peng, Zhao Pu, Zhilei Shu, Xiangrui Ke, Zhaohu Xing, Zizhao Tong, Zeqing Wang, Xinyu Cui, Zian Zheng, Huangji Wang, Jian Zhao, Yeying Jin, Fan Cheng, Ruili Feng

机构 * SJTU(上海交通大学) NVIDIA Research(英伟达研究) USTC(中国科学技术大学) UCAS(乌兹别克斯坦科学院) NUS(新加坡国立大学) UWaterloo(滑铁卢大学) HKUST(香港理工大学) HKU(香港大学) ZGCA(浙江大学)

AI总结 本研究提出了一种基于自然语言的动作接口,用于多实体视频世界模型,解决了传统接口在细粒度多实体控制和跨实体、跨世界泛化能力上的不足,通过引入自然语言条件化实现了更强大的表达能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09633 2026-07-14 cs.RO cs.SY eess.SY 版本更新

Minimizing Worst-Case Weighted Latency for Multi-Robot Persistent Monitoring: Theory and RL-Based Solutions

最小化多机器人持续监控的最坏情况加权延迟:理论与基于强化学习的解决方案

Weizhen Wang, Ziheng Wang, Jianping He, Xinping Guan, Xiaoming Duan

机构 * School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China(自动化与智能感知学院,上海交通大学,上海,中国) Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China(系统控制与信息处理重点实验室,中华人民共和国教育部,上海,中国)

AI总结 本文研究多机器人在加权图上的持续监控问题,提出尾性能目标以改进传统最坏情况延迟评估,并基于强化学习构建TWLO-MDP模型,通过实验验证方法在合成和现实场景中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09149 2026-07-14 cs.LG cs.AI cs.MA 版本更新

Enabling Agents to Communicate Entirely in Latent Space

使智能体能够在潜在空间中完全交流

Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying

机构 * State Key Lab of CAD&CG(CAD与CG国家重点实验室) Future Living Lab of Alibaba(阿里巴巴未来生活实验室) Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence(浙江医学影像人工智能重点实验室) Shanghai Jiao Tong University(上海交通大学)

AI总结 本文提出Interlat方法,通过利用LLM的连续隐藏状态实现智能体间的潜在空间通信,实验表明其在跨异构模型中表现优异,提升了推理速度并保持性能。

Comments Accepted to ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16112 2026-07-14 cs.CV 版本更新

AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs

AutoV:面向视觉提示检索的损失导向排名用于大视觉-语言模型

Yuan Zhang, Chun-Kai Fan, Sicheng Yu, Junwen Pan, Tao Huang, Ming Lu, Kuan Cheng, Qi She, Shanghang Zhang

机构 * School of Computer Science, Peking University(北京大学计算机学院) ByteDance Inc.(字节跳动公司) Shanghai Jiao Tong University(上海交通大学)

AI总结 AutoV通过损失导向的提示检索提升大视觉-语言模型在图像理解等任务中的性能。

Comments Accepted by ECCV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24653 2026-07-14 cs.LG cs.AI 版本更新

Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge

通过身份桥揭示Transformer中多跳推理的机制

Pengxiao Lin, Zheng-An Chen, Zhi-Qin John Xu

机构 * School of Mathematical Sciences, Shanghai Jiao Tong University(上海交通大学数学科学学院) Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University(上海交通大学自然科学研究院) Shanghai Seres Information Technology Co., Ltd, Shanghai 200040, China(上海塞瑞斯信息技术有限公司)

AI总结 研究大型语言模型多跳推理中两跳推理诅咒现象,引入身份桥进行最小监督,使单层Transformer能实现分布外两跳泛化,通过理论和实证分析揭示其机制及效果,并扩展到主流LLMs的实际设置。

Comments Accepted by COLM 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18610 2026-07-14 cs.CL 版本更新

PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs

PM-KVQ:用于长思维链语言模型的渐进式混合精度键值缓存量化

Tengxuan Liu, Shiyao Li, Jiayi Yang, Tianchen Zhao, Feng Zhou, Xiaohui Song, Guohao Dai, Shengen Yan, Huazhong Yang, Yu Wang

机构 * Tsinghua University(清华大学) Infinigence-AI Columbia University(哥伦比亚大学) OPPO AI Center(OPPO人工智能中心) Shanghai Jiaotong University(上海交通大学)

AI总结 针对长思维链语言模型因键值缓存内存开销大导致性能下降的问题,提出渐进式混合精度KV缓存量化(PM-KVQ),通过渐进量化策略和逐块内存分配减少累积误差,用带位置插值的校准策略增加校准长度,提升了推理性能和吞吐量。

Comments Accepted by ICLR 2026. Code available at https://github.com/thu-nics/PM-KVQ

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.29858 2026-07-13 cs.CL 版本更新

Smooth Scaling Laws Hide Stepwise Token Learning

平滑缩放定律隐藏了逐步的令牌学习

Pingjie Wang, Zechen Hu, Peiru Yang, Fu Guo, Debing Zhang

机构 * Dots Studio, Xiaohongshu Inc.(dots studio,小红书公司) Shanghai Jiao Tong University(上海交通大学) Tsinghua university(清华大学)

AI总结 本文提出令牌级框架,将缩放定律分解为上下文令牌的局部学习事件,通过拟合S形曲线发现令牌学习集中在局部转换中,并利用学习时间谱定量重建验证损失导数,进而通过重塑训练分布实现11%的验证损失加速降低。

Comments 21 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.04600 2026-07-13 cs.RO 版本更新

Act, Sense, Act: Learning Active Perception from Large-Scale Egocentric Human Data

行动、感知、行动:从大规模自我中心人类数据中学习主动感知

Jialiang Li, Yi Qiao, Yunhan Guo, Changwen Chen, Wenzhao Lian

机构 * School of Artificial Intelligence, Shanghai Jiao Tong University(人工智能学院,上海交通大学)

AI总结 研究如何让机器人在无约束环境中实现可泛化操作,提出CoMe - VLA框架,利用大规模人类自我中心数据学习主动感知,集成认知辅助头和双轨记忆系统,经三个阶段训练模型,实验证明该方法在多场景长期任务中有强鲁棒性和适应性。

详情

展开后加载摘要…

URL PDF HTML 收藏