arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Johns Hopkins University(约翰斯·霍普金斯大学)

2026-05-26 至 2026-05-26 共收录 10
2509.23975 2026-05-26 eess.SY cs.LG cs.NA cs.SY math.NA math.OC

Equation-Free Coarse Control of Distributed Parameter Systems via Local Neural Operators

基于局部神经算子的分布式参数系统无方程粗粒度控制

Gianluca Fabiani, Constantinos Siettos, Ioannis G. Kevrekidis

机构 * Hopkins Extreme Materials Institute and Department of Chemical and Biomolecular Engineering, Johns Hopkins University(霍普金斯极端材料研究所和化学与生物分子工程系,约翰霍普金斯大学) Dipartimento di Matematica e Applicazioni ”Renato Caccioppoli”, Università degli studi di Napoli Federico II(Renato Caccioppoli数学与应用系,那不勒斯费德里克二世大学) Department of Chemical and Biomolecular Engineering and Department of Applied Mathematics and Statistics, Johns Hopkins University(化学与生物分子工程系和应用数学与统计学系,约翰霍普金斯大学)

AI总结 提出一种数据驱动方法,利用局部神经算子学习短时解算子,结合Krylov子空间方法计算稳态和降阶模型,实现无显式粗粒度方程的高维分布式参数系统控制。

Comments 8 pages, 2 figures

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
2605.24852 2026-05-26 cs.LG cs.SY eess.SY

T2S-MPC: Time-Embedded Online Adaptive Model Predictive Control for Time-Varying Dynamics

T2S-MPC:面向时变动力学的时间嵌入在线自适应模型预测控制

Zeyu Shen, Zhuoyuan Wang, Laixi Shi

机构 * JHU Department of Applied Mathematics and Statistics, Johns Hopkins University, MD, USA(约翰霍普金斯大学应用数学与统计学系) CMU Department of Electrical and Computer Engineering, Carnegie Mellon University, PA, USA(卡内基梅隆大学电气与计算机工程系)

AI总结 提出T2S-MPC框架,通过时间嵌入和双时间尺度更新在线学习残差动力学模型,实现快速时变环境下的自适应模型预测控制,在四旋翼任务中优于经典和神经MPC方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24810 2026-05-26 cs.LG cs.AI cs.RO stat.AP

Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning

跨域能量引导扩散生成用于动态偏移强化学习

Yu Yang, Yihong Guo, Anqi Liu, Pan Xu

机构 * Duke University(杜克大学) Johns Hopkins University(约翰霍普金斯大学)

AI总结 提出CEDGE框架,利用能量引导扩散模型生成目标域轨迹,解决动态偏移下离线强化学习的域适应问题。

Comments 29 pages, 3 figures, and 14 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24789 2026-05-26 cs.CV eess.IV

Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification

自监督对比学习用于心脏磁共振序列分类

Yuli Wang, Hyewon Jung, Dongshen Peng, Yuwei Dai, Jing Wu, Haoyue Guan, Yoko Kato, Zhicheng Jiao, Yu Sun, Ihab Kamel, Joao Lima, Cheng Ting Lin, Harrison Bai

机构 * Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine(放射科与放射科学系,约翰霍普金斯大学医学院) Department of Electrical and Computer Engineering, Johns Hopkins University(电气与计算机工程系,约翰霍普金斯大学) Department of Computer Science, University of North Carolina at Chapel Hill(计算机科学系,北卡罗来纳大学教堂山分校) Department of Radiology, University of Colorado Denver Anschutz Medical Campus(放射科,科罗拉多大学丹佛分校安舒茨医学中心) Department of Radiology, Second Xiangya Hospital, Central South University(放射科,中南大学湘雅医院) Department of Cardiology, Johns Hopkins University School of Medicine(心血管科,约翰霍普金斯大学医学院) Department of Diagnostic Imaging, Brown University Health(诊断影像科,布朗大学健康中心)

AI总结 针对预训练ViT在心脏MR领域迁移效果差的问题,提出基于图像的自监督对比学习适应策略,在内部数据集上优于监督训练,并泛化到外部MR数据集,四个常见序列分类AUC超过0.75。

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
2510.20954 2026-05-26 stat.ML cs.LG eess.SP

A Spectral Framework for Graph Neural Operators: Convergence Guarantees and Tradeoffs

图神经算子的谱框架:收敛保证与权衡

Roxanne Holden, Luana Ruiz

机构 * Applied Mathematics and Statistics(应用数学与统计学) Johns Hopkins University(约翰霍普金斯大学)

AI总结 本文提出统一谱框架,分析图神经算子在无正则性、全局Lipschitz连续和分段Lipschitz连续假设下的收敛率与权衡。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23931 2026-05-26 cs.AI cs.PL cs.SE

BODHI: Precise OS Kernel Specification Inference

BODHI:精确的操作系统内核规范推断

Zhiming Chang, Ziyang Li

机构 * Department of Applied Mathematics and Statistics(应用数学与统计学系) Johns Hopkins University(约翰霍普金斯大学) Department of Computer Science(计算机科学系)

AI总结 提出一种领域知识提示方法BODHI,通过结构化C到Python翻译指南增强少样本提示,在OSV-Bench基准上将Pass@1从55.10%提升至96.73%,缩小了通用代码生成与形式规范合成之间的差距。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22809 2026-05-26 cs.CV

Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving

Sensor2Sensor: 自动驾驶的跨本体传感器转换

Jiahao Wang, Bo Sun, Yijing Bai, Vincent Casser, Songyou Peng, Zehao Zhu, Meng-Li Shih, Xander Masotto, Shih-Yang Su, Kanaad V Parvate, Tiancheng Ge, Linn Bieske, Dragomir Anguelov, Mingxing Tan, Chiyu Max Jiang

机构 * Waymo Johns Hopkins University(约翰霍普金斯大学) Google DeepMind(谷歌DeepMind) University of Washington(华盛顿大学)

AI总结 提出Sensor2Sensor生成模型,将单目行车记录仪视频转换为多模态传感器数据(多视角相机图像和LiDAR点云),通过4D高斯泼溅重建和扩散架构解决无配对数据问题,为自动驾驶开发解锁外部数据源。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12479 2026-05-26 math.OC cs.AI cs.GT cs.MA econ.GN q-fin.EC

EXOTIC: An Exact, Optimistic, Tree-Based Algorithm for Min-Max Optimization

EXOTIC: 一种用于极小极大优化的精确、乐观、基于树的算法

Chinmay Maheshwari, Chinmay Pimpalkhare, Debasish Chatterjee

机构 * Department of Electrical and Computer Engineering, and Data Science and AI Institute at Johns Hopkins University(约翰霍普金斯大学电气与计算机工程系及数据科学与人工智能研究院) Institute for Computational and Mathematical Engineering at Stanford University(斯坦福大学计算与数学工程研究所) Center for Systems and Control, IIT Bombay(印度理工学院班加罗尔系统与控制中心)

AI总结 针对凸-非凹和非凸-凹极小极大优化问题,提出一种基于Sion极小极大定理扩展的重新表述,并设计EXOTIC算法结合迭代凸优化与乐观分层树搜索,以计算全局极小极大值,理论保证最优性间隙上界,实验优于梯度方法,并首次精确求解三人以上博弈的安全策略。

Comments 35 pages, 2 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏