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 3178
2512.21924 2025-12-29 cs.CV cs.AI

Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learning

通过解耦解剖学习在脑部MRI中进行无监督异常检测

Tao Yang, Xiuying Wang, Hao Liu, Guanzhong Gong, Lian-Ming Wu, Yu-Ping Wang, Lisheng Wang

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,中国) School of Computer Science, The University of Sydney, Sydney, Australia.(计算机科学学院,悉尼大学,澳大利亚) Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.(放射科,仁济医院,医学院,上海交通大学,中国) Biomedical Engineering Department, Tulane University, New Orleans, USA.(生物医学工程系, Tulane 大学,美国新奥尔良)

AI总结 本文提出了解耦解剖学习框架,通过解耦MRI成像信息与解剖结构,提升多模态MRI的异常检测性能,实验表明在九个数据集上优于17种现有方法。

Comments Accepted by Medical Image Analysis (2025)

Journal ref Medical Image Analysis (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21883 2025-12-29 cs.CV

Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer

Reloc-VGGT: 基于几何基础的变换器视觉重定位

Tianchen Deng, Wenhua Wu, Kunzhen Wu, Guangming Wang, Siting Zhu, Shenghai Yuan, Xun Chen, Guole Shen, Zhe Liu, Hesheng Wang

机构 * Shanghai Jiao Tong University(上海交通大学) Nanyang Technological University(南洋理工大学) Cambridge University(剑桥大学)

AI总结 Reloc-VGGT通过早期融合机制和稀疏掩码注意力策略,实现高效多视图空间整合,提升复杂环境下的视觉定位准确性和实时性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21711 2025-12-29 cs.CL cs.AI

Do Latent Tokens Think? A Causal and Adversarial Analysis of Chain-of-Continuous-Thought

潜在标记是否思考?对连续思维链的因果和对抗分析

Yuyi Zhang, Boyu Tang, Tianjie Ju, Sufeng Duan, Gongshen Liu

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

AI总结 本文通过因果和对抗分析揭示COCONUT作为伪推理机制的问题,指出其依赖捷径而非真实推理。

Comments 13 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16509 2025-12-29 cs.CV

SlowFast-SCI: Slow-Fast Deep Unfolding Learning for Spectral Compressive Imaging

SlowFast-SCI: 慢-快深度展开学习用于光谱压缩成像

Haijin Zeng, Xuan Lu, Yurong Zhang, Qiangqiang Shen, Guoqing Chao, Li Jiang, Yongyong Chen

机构 * Harvard University(哈佛大学) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) Shanghai Jiaotong University(上海交通大学) City University of Hong Kong(香港城市大学) Harbin Institute of Technology, Weihai(哈尔滨工业大学(威海)) The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

AI总结 SlowFast-SCI是一种双速深度展开框架,通过预训练和自适应模块实现高效自适应的光谱重建,显著提升参数效率和适应速度。

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.05607 2025-12-29 cs.CL

CC-GSEO-Bench: A Content-Centric Benchmark for Measuring Source Influence in Generative Search Engines

CC-GSEO-Bench: 一种以内容为中心的基准,用于衡量生成搜索引擎中源影响力

Qiyuan Chen, Jiahe Chen, Hongsen Huang, Qian Shao, Jintai Chen, Renjie Hua, Hongxia Xu, Ruijia Wu, Ren Chuan, Jian Wu

机构 * Zhejiang University(浙江大学) Soochow Securities(苏州证券) HKUST(GZ)(香港科技大学(广州)) Shanghai Jiaotong University(上海交通大学)

AI总结 CC-GSEO-Bench通过大规模数据集和创作者导向的评估框架,量化生成搜索引擎中源文章的影响,涵盖曝光、忠实信用、因果影响等核心维度。

Comments Technical Report

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11781 2025-12-29 cs.CV cs.AI cs.LG

ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model

ACMamba: 通过非对称共识状态空间模型实现快速无监督异常检测

Guanchun Wang, Xiangrong Zhang, Yifei Zhang, Zelin Peng, Tianyang Zhang, Xu Tang, Licheng Jiao

机构 * School of Artificial Intelligence, Xidian University(西安电子科技大学人工智能学院) MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(上海交通大学人工智能研究院)

AI总结 ACMamba通过非对称共识状态空间模型实现快速无监督异常检测,利用区域级实例替代密集像素样本,降低计算成本并提升性能。

Comments 15 pages, 9 figures

Journal ref Proceedings of the 33rd ACM International Conference on Multimedia, ACM MM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.09990 2025-12-29 cs.CR cs.AI cs.CL cs.CV cs.LG

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability

X-Boundary:建立精确的安全边界以在不损害可用性的情况下保护LLM免受多轮劫持攻击

Xiaoya Lu, Dongrui Liu, Yi Yu, Luxin Xu, Jing Shao

机构 * School of Electronic Information and Electric Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

AI总结 X-Boundary通过建立精确的安全边界,有效防御多轮劫持攻击,同时减少过度拒绝率并保持模型通用能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21691 2025-12-29 cs.CV

Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective

从动力学角度分析VGGT中注意力崩溃的机制

Huan Li, Longjun Luo, Yuling Shi, Xiaodong Gu

机构 * Huazhong University of Science and Technology(华中科技大学) Guangdong University of Technology(广东工业大学) Shanghai Jiao Tong University(上海交通大学)

AI总结 VGGT中注意力崩溃现象从动力学角度进行数学解释,揭示token特征流收敛规律及token合并方法对延迟崩溃的作用。

Comments 8 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21675 2025-12-29 cs.CV

UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

UniPercept:迈向跨美学、质量、结构和纹理的统一感知级图像理解

Shuo Cao, Jiayang Li, Xiaohui Li, Yuandong Pu, Kaiwen Zhu, Yuanting Gao, Siqi Luo, Yi Xin, Qi Qin, Yu Zhou, Xiangyu Chen, Wenlong Zhang, Bin Fu, Yu Qiao, Yihao Liu

机构 * University of Science and Technology of China(中国科学技术大学) Shanghai AI Laboratory(上海人工智能实验室) Peking University(北京大学) Shanghai Jiao Tong University(上海交通大学) Tsinghua University(清华大学) Nanjing University(南京大学) Sun Yat-sen University(中山大学) Tele-AI Website(Tele-AI网站)

AI总结 UniPercept通过领域自适应预训练和任务对齐强化学习,实现跨美学、质量、结构和纹理的统一感知级图像理解,优于现有多模态大语言模型。

Comments 27 pages, 14 figures, 17 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21476 2025-12-29 cs.CV cs.AI

GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification

GPF-Net:门控渐进融合学习用于息肉重识别

Suncheng Xiang, Xiaoyang Wang, Junjie Jiang, Hejia Wang, Dahong Qian

机构 * Shanghai Jiao Tong University(上海交通大学) Peking University(北京大学) Shanghai Fifth People's Hospital(上海第五人民医院)

AI总结 GPF-Net通过门控渐进融合学习提升息肉重识别性能,结合多模态融合策略优于现有单模态模型。

Comments Work in progress

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20355 2025-12-29 cs.RO

FAR-AVIO: Fast and Robust Schur-Complement Based Acoustic-Visual-Inertial Fusion Odometry with Sensor Calibration

FAR-AVIO:基于Schur补的快速且稳健的声学-视觉-惯性融合里程计

Hao Wei, Peiji Wang, Qianhao Wang, Tong Qin, Fei Gao, Yulin Si

机构 * Zhejiang University(浙江大学) Global Institute of Future Technology(未来技术全球研究院) Shanghai Jiao Tong University(上海交通大学)

AI总结 FAR-AVIO通过基于Schur补的EKF实现快速且稳健的水下声学-视觉-惯性融合里程计,结合自适应权重调整和在线校准,提升定位精度与计算效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21332 2025-12-25 cs.CL cs.AI

C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling

C2LLM技术报告:通过自适应跨注意力池化实现代码检索的新前沿

Jin Qin, Zihan Liao, Ziyin Zhang, Hang Yu, Peng Di, Rui Wang

机构 * Ant Group(蚂蚁集团) Shanghai Jiao Tong University(上海交通大学)

AI总结 C2LLM通过自适应跨注意力池化技术,实现更高效的代码检索,其模型在代码嵌入任务中取得新突破。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20943 2025-12-25 cs.GR cs.DC cs.LG cs.MM cs.NI eess.IV

AirGS: Real-Time 4D Gaussian Streaming for Free-Viewpoint Video Experiences

AirGS: 实时4D高斯流式处理以实现自由视角视频体验

Zhe Wang, Jinghang Li, Yifei Zhu

机构 * Global College, Shanghai Jiao Tong University(上海交通大学全球学院)

AI总结 AirGS通过优化4DGS框架,实现高质量低延迟的自由视角视频体验,减少质量退化并提升传输效率。

Comments This paper is accepted by IEEE International Conference on Computer Communications (INFOCOM), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20135 2025-12-25 cs.AI

MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization

MolAct:一种用于分子编辑和性质优化的代理强化学习框架

Zhuo Yang, Yeyun Chen, Jiaqing Xie, Ben Gao, Shuaike Shen, Wanhao Liu, Liujia Yang, Beilun Wang, Tianfan Fu, Yuqiang Li

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Xidian University(西安电子科技大学) Shanghai Innovation Institute(上海创新研究院) Wuhan University(武汉大学) Shanghai Jiao Tong University(上海交通大学) Southeast University(东南大学) Nanjing University(南京大学) Carnegie Mellon University(卡内基梅隆大学)

AI总结 MolAct框架通过代理强化学习方法,实现了分子编辑和性质优化的多步骤、工具增强过程,提升了分子设计的可靠性和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.11005 2025-12-25 cs.LG

AdaMuon: Adaptive Muon Optimizer

AdaMuon:自适应穆斯优化器

Chongjie Si, Debing Zhang, Wei Shen

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University(人工智能微电子实验室、人工智能学院、计算机科学学院、上海交通大学) Xiaohongshu Inc.(小红书公司)

AI总结 AdaMuon通过结合元素级适应性和正交更新,实现了大规模神经网络训练中的高效稳定优化,训练效率超过Adam达40%。

Comments Codes are available at https://github.com/Chongjie-Si/AdaMuon

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12491 2025-12-25 cs.CL

CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences

CAKE:基于层优先级的级联和自适应KV缓存淘汰

Ziran Qin, Yuchen Cao, Mingbao Lin, Wen Hu, Shixuan Fan, Ke Cheng, Weiyao Lin, Jianguo Li

机构 * Shanghai Jiao Tong University(上海交通大学) Ant Group(蚂蚁集团)

AI总结 CAKE通过级联和自适应机制优化KV缓存淘汰,提升低内存下的模型性能和解码效率。

Comments Accepted by ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20635 2025-12-25 cs.LG

SHRP: Specialized Head Routing and Pruning for Efficient Encoder Compression

SHRP:用于高效编码器压缩的专用头部路由和剪枝

Zeli Su, Ziyin Zhang, Wenzheng Zhang, Zhou Liu, Guixian Xu, Wentao Zhang

机构 * Minzu University of China(民族大学) Shanghai Jiao Tong University(上海交通大学) Peking University(北京大学)

AI总结 SHRP通过专用头部路由和剪枝技术,实现高效编码器压缩,减少参数并提升计算效率,适用于大规模和低延迟网络部署。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20469 2025-12-24 cs.AI

Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale

Bohrium + SciMaster: 构建大规模智能科学的基础设施和生态系统

Linfeng Zhang, Siheng Chen, Yuzhu Cai, Jingyi Chai, Junhan Chang, Kun Chen, Zhi X. Chen, Zhaohan Ding, Yuwen Du, Yuanpeng Gao, Yuan Gao, Jing Gao, Zhifeng Gao, Qiangqiang Gu, Yanhui Hong, Yuan Huang, Xi Fang, Xiaohong Ji, Guolin Ke, Zixing Lei, Xinyu Li, Yongge Li, Ruoxue Liao, Hang Lin, Xiaolu Lin, Yuxiang Liu, Xinzijian Liu, Zexi Liu, Jintan Lu, Tingjia Miao, Haohui Que, Weijie Sun, Yanfeng Wang, Bingyang Wu, Tianju Xue, Rui Ye, Jinzhe Zeng, Duo Zhang, Jiahui Zhang, Linfeng Zhang, Tianhan Zhang, Wenchang Zhang, Yuzhi Zhang, Zezhong Zhang, Hang Zheng, Hui Zhou, Tong Zhu, Xinyu Zhu, Qingguo Zhou, Weinan E

机构 * DP Technology Beijing China(北京DP技术有限公司) AI for Science Institute Beijing China(北京AI for Science研究院) Shanghai Jiao Tong University Shanghai China(上海交通大学) Beihang University Beijing China(北京航空航天大学) Peking University Beijing China(北京大学) Institute of Theoretical Physics Chinese Academy of Sciences Beijing China(中国科学院理论物理研究所) Shanghai Innovation Institute Shanghai China(上海创新研究院) East China Normal University Shanghai China(华东师范大学) Zhongguancun Academy Beijing China(中关村学院) University of Science and Technology of China Hefei China(中国科学技术大学) Tongji University Shanghai China(同济大学) The Hong Kong University of Science and Technology Hong Kong China(香港科技大学)

AI总结 Bohrium+SciMaster通过构建基础设施和生态系统,实现大规模智能科学的高效工作流编排与执行,显著提升科学产出效率和可追溯性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20217 2025-12-24 cs.CV

LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptation

LiteFusion: 从基于视觉到多模态的3D目标检测器的最小适应

Xiangxuan Ren, Zhongdao Wang, Pin Tang, Guoqing Wang, Jilai Zheng, Chao Ma

机构 * China Ministry of Education (MOE) Key Laboratory of Artificial Intelligence(中国教育部人工智能重点实验室) Artificial Intelligence Institute, Shanghai Jiao Tong University(上海交通大学人工智能学院) Huawei Noah’s Ark Lab(华为诺亚实验室)

AI总结 LiteFusion通过将LiDAR数据作为补充几何信息源,无需专用LiDAR编码器,显著提升多模态3D目标检测性能。

Comments 13 pages, 9 figures, 8 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18279 2025-12-24 cs.CV

UniMPR: A Unified Framework for Multimodal Place Recognition with Heterogeneous Sensor Configurations

UniMPR: 一种用于异构传感器配置的多模态地点识别统一框架

Zhangshuo Qi, Jingyi Xu, Luqi Cheng, Shichen Wen, Yiming Ma, Guangming Xiong

机构 * Beijing Institute of Technology(北京理工大学) Shanghai Jiao Tong University(上海交通大学) The University of New South Wales(新南威尔士大学)

AI总结 UniMPR提出了一种统一框架,能够适应多种异构传感器配置,通过极坐标BEV特征空间和多分支网络实现多模态地点识别的高效与鲁棒性。

Comments 14 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08674 2025-12-24 cs.AI cs.MA

Multi-Agent Intelligence for Multidisciplinary Decision-Making in Gastrointestinal Oncology

多智能体智能在胃肠肿瘤多学科决策中的应用

Rongzhao Zhang, Junqiao Wang, Shuyun Yang, Mouxiao Bian, Chihao Zhang, Dongyang Wang, Qiujuan Yan, Yun Zhong, Yuwei Bai, Guanxu Zhu, Kangkun Mao, Miao Wang, Chao Ding, Renjie Lu, Lei Wang, Lei Zheng, Tao Zheng, Xi Wang, Zhuo Fan, Bing Han, Meiling Liu, Luyi Jiang, Dongming Shan, Wenzhong Jin, Jiwei Yu, Zheng Wang, Jie Xu, Meng Luo

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine(上海第九人民医院,上海交通大学医学院) Renji Hospital, Shanghai Jiao Tong University School of Medicine(仁济医院,上海交通大学医学院) Shanghai Institute of Infectious Disease and Biosecurity, Fudan University(上海市传染病防治研究所暨生物安全研究所,复旦大学) Shanghai Health Development Research Center (Shanghai Medical Information Center)(上海市卫生健康发展研究中心(上海市医疗信息中心)) Shanghai Kupas Technology Co., Ltd.(上海库帕斯科技有限公司)

AI总结 本文提出基于多智能体的框架,用于提升胃肠肿瘤多学科决策的自动化支持,通过模拟多学科团队协作,提高推理逻辑和医疗准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16193 2025-12-24 cs.DC cs.AI

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation

快速LLM后训练通过解耦和最快-N推测

Rongxin Cheng, Kai Zhou, Xingda Wei, Siyuan Liu, Mingcong Han, Mingjing Ai, Yeju Zhou, Baoquan Zhong, Wencong Xiao, Rong Chen, Haibo Chen

机构 * Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University(并行与分布式系统研究所,上海交通大学) ByteDance Seed(字节跳动种子)

AI总结 SpecActor通过解耦和最快-N推测方法提升LLM后训练效率,实现2.0-2.7倍的rollout加速和1.4-2.3倍的端到端训练时间提升。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05671 2025-12-24 eess.AS cs.CL

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning

通过文本仅微调实现语音大模型的低资源领域适应

Yangui Fang, Jing Peng, Xu Li, Yu Xi, Chengwei Zhang, Guohui Zhong, Kai Yu

机构 * Huazhong University of Science and Technology, School of Electronic Information and Communications(华中科技大学电子信息与通信学院) MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China(人工智能MoE重点实验室、AI研究院、X-LANCE实验室、上海交通大学、上海,中国) Jiangsu Key Lab of Language Computing, Suzhou, China(江苏省语言计算重点实验室、苏州,中国) AISpeech Co., Ltd., Suzhou, China(AISpeech公司、苏州,中国)

AI总结 本文提出通过文本仅微调实现语音大模型在低资源环境下的领域适应,有效提升识别性能并减少领域迁移中的性能下降。

Comments This paper has been ACCEPTED for publication in ASRU

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24347 2025-12-24 cs.CL eess.AS

Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction

更少的幻觉,更多的验证:一种基于LLM的三阶段框架用于语音识别错误纠正

Yangui Fang, Baixu Chen, Jing Peng, Xu Li, Yu Xi, Chengwei Zhang, Guohui Zhong

机构 * Huazhong University of Science and Technology, School of Electronic Information and Communications(华中科技大学电子信息与通信学院) MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China(人工智能联合实验室、AI研究院、X-LANCE实验室、上海交通大学) AISpeech Ltd, Suzhou, China(上海苏州AISpeech有限公司)

AI总结 本文提出一种基于LLM的三阶段框架,用于减少语音识别错误纠正中的幻觉问题,通过预检测、链式思维修正和推理验证提高纠正准确性。

Comments This paper has been ACCEPTED for publication in ASRU

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.06050 2025-12-24 cs.CV cs.RO

Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes

单目相机在大规模场景中增量联合学习深度、姿态和隐式场景表示

Tianchen Deng, Nailin Wang, Chongdi Wang, Shenghai Yuan, Jingchuan Wang, Hesheng Wang, Danwei Wang, Weidong Chen

机构 * Institute of Medical Robotics and Department of Automation, Shanghai Jiao Tong University(上海交通大学医学机器人研究所和自动化系) Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai(系统控制与信息处理重点实验室,教育部,上海) School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电子与电气工程学院)

AI总结 本文提出了一种增量联合学习框架,通过视觉Transformer提升大规模场景的深度、姿态估计和隐式场景表示能力。

Journal ref IEEE Transactions on Automation Science and Engineering, vol. 22, pp. 22541-22552, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.19583 2025-12-23 cs.RO cs.GR

Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations

从合成演示中学习通用的手-物体跟踪

Yinhuai Wang, Runyi Yu, Hok Wai Tsui, Xiaoyi Lin, Hui Zhang, Qihan Zhao, Ke Fan, Miao Li, Jie Song, Jingbo Wang, Qifeng Chen, Ping Tan

机构 * Wuhan University(武汉大学) ETH Zurich(苏黎世联邦理工学院) Shanghai Jiao Tong University(上海交通大学) Shanghai AI Lab(上海人工智能实验室)

AI总结 本文提出了一种从合成数据中学习通用手-物体跟踪控制器的方法,通过HOP和HOT实现从合成到物理的迁移,展示了在复杂任务中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.19320 2025-12-23 cs.LG cs.AI cs.CL cs.CV

MAGIC: Achieving Superior Model Merging via Magnitude Calibration

MAGIC: 通过幅度校准实现卓越的模型合并

Yayuan Li, Jian Zhang, Jintao Guo, Zihan Cheng, Lei Qi, Yinghuan Shi, Yang Gao

机构 * State Key Laboratory for Novel Software Technology(新型软件技术国家重点实验室) National Institute of Healthcare Data Science(医疗数据科学国家研究院) Nanjing University(南京大学) Shanghai Jiao Tong University Medical School Affiliated Ruijin Hospital(上海交通大学附属瑞金医院医学院) School of Computer Science and Engineering(计算机科学与工程学院) Key Lab of Computer Network and Information Integration(计算机网络与信息集成重点实验室) Southeast University(东南大学)

AI总结 MAGIC通过校正特征和权重空间的幅度,提升模型合并性能,无需额外训练。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.19280 2025-12-23 cs.LG cs.AI

Digital Twin-Driven Zero-Shot Fault Diagnosis of Axial Piston Pumps Using Fluid-Borne Noise Signals

基于数字孪生的轴向柱塞泵流体 borne噪声信号零样本故障诊断

Chang Dong, Jianfeng Tao, 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) Shanghai Platform for Smart Manufacturing Co.,Ltd(上海智能制造平台有限公司)

AI总结 本文提出基于数字孪生的轴向柱塞泵零样本故障诊断方法,利用流体 borne噪声信号训练深度学习模型,通过物理指导神经网络和Grad-CAM可视化提升诊断准确率,实验显示其在数据稀缺情况下表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.19213 2025-12-23 cs.CV

InvCoSS: Inversion-driven Continual Self-supervised Learning in Medical Multi-modal Image Pre-training

InvCoSS: 基于反向驱动的医学多模态图像预训练中的连续自监督学习

Zihao Luo, Shaohao Rui, Zhenyu Tang, Guotai Wang, Xiaosong Wang

机构 * University of Electronic Science and Technology of China(电子科技大学) Shanghai Innovation Institute(上海创新研究院) Shanghai Jiao Tong University(上海交通大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Brain-Computer Interface & Brain-Inspired Intelligence Key Laboratory of Sichuan Province(四川省脑机接口与脑启发智能重点实验室)

AI总结 InvCoSS通过反向生成合成图像和多尺度融合网络,实现连续自监督学习,减少存储需求并保护数据隐私。

Comments 16 pages, 10 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18747 2025-12-23 cs.CV cs.AI

IPCV: Information-Preserving Compression for MLLM Visual Encoders

IPCV:信息保留的多模态大语言模型视觉编码器压缩

Yuan Chen, Zichen Wen, Yuzhou Wu, Xuyang Liu, Shuang Chen, Junpeng Ma, Weijia Li, Conghui He, Linfeng Zhang

机构 * EPIC Lab, SJTU(上海交通大学EPIC实验室) CityU(城市大学) Shanghai AI Laboratory(上海人工智能实验室) University of Sheffield(谢菲尔德大学) SCU(上海科技大学) FDU(福建大学) SYSU(南方科技大学)

AI总结 IPCV通过邻居引导重建和注意力稳定化技术,实现无需训练的多模态大语言模型视觉编码器高效压缩,有效降低计算成本并提升性能。

Comments 13 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏