arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Cornell University(康奈尔大学)

共收录 950
2607.14367 2026-07-17 cs.LG 新提交

Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning

Dysco:动态子空间增强以减轻联邦学习中的LoRA干扰

Haobo Zhang, Jiankun Wang, Suraj Rajendran, Weishen Pan, Lam Tsoi, Yong Chen, Fei Wang, Jiayu Zhou

机构 * University of Michigan(密歇根大学) Cornell University(康奈尔大学) University of Pennsylvania(宾夕法尼亚大学)

AI总结 研究针对联邦学习中异构客户端使LoRA聚合不稳定的问题,提出动态子空间增强方法Dysco,通过联邦动态分配特定客户端LoRA子空间,经实验验证其能减少干扰、降低训练损失、提升算法性能且开销小。

Comments 33 pages, 10 figures, 11 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.14338 2026-07-17 cs.CV cs.AI cs.LG 新提交

Beyond scalar losses: calibrating segmentation models via gradient vector field surgery

超越标量损失:通过梯度向量场手术校准分割模型

Laurin Lux, Alexander H. Berger, Moritz Knolle, Daniel Rückert, Johannes C. Paetzold

机构 * School of Computation, Information and Technology, TUM(慕尼黑工业大学计算、信息与技术学院) Munich Center for Machine Learning(慕尼黑机器学习中心) Department of Radiology, Weill Cornell Medicine(威尔康乃尔医学院放射科) School of Medicine and Health, TUM University Hospital(慕尼黑工业大学医院医学与健康学院) Cornell Tech(康奈尔科技学院) Department of Computing, Imperial College London(伦敦帝国理工学院计算系)

AI总结 研究针对基于区域损失函数训练的分割模型校准不佳问题,提出对梯度向量场进行“手术”,即给损失偏导数添加因子,依预测误差线性缩放梯度大小,经2D和3D医学分割任务验证该方法有效且能保持高预测准确性。

Comments MIDL 2026. Published version: https://proceedings.mlr.press/v315/lux26a.html

Journal ref Proceedings of Machine Learning Research 315:3397-3423, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.05050 2026-07-17 cs.AI econ.GN q-fin.EC 版本更新

Large language models can effectively convince people to believe conspiracies

大语言模型能够有效地说服人们相信阴谋论

Thomas H. Costello, Kellin Pelrine, Matthew Kowal, Jasper Timm, Antonio A. Arechar, Jean-François Godbout, Adam Gleave, David Rand, Gordon Pennycook

机构 * Carnegie Mellon University(卡内基梅隆大学) York University(约克大学) Center for Research and Teaching in Economics(经济研究中心) MIT(麻省理工学院) Université de Montréal(蒙特利尔大学) Mila Cornell University(康奈尔大学) University of Regina(Regina大学)

AI总结 研究大语言模型能否有效说服人们相信阴谋论,通过四项实验发现其既能增加也能降低阴谋信念,反驳效果更佳,特定提示可降低支持阴谋论有效性,还存在信息分享上的真理不对称,有潜在技术方案减轻风险。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13241 2026-07-16 cs.LG cs.AI 新提交

EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting

EMAGN:基于学习聚类的高效多注意力图网络用于可扩展交通流量预测

Mingxing Xu, Rakesh Chowdary Machineni, Ke Liu, Xi Cheng, Chengqi Lu, Xin Hu, Lyuhao Chen, Xiangyu Li, Junwei You, Oliver Gao

机构 * Shanghai Jiao Tong University(上海交通大学) University of Michigan, Ann Arbor(密歇根大学安娜堡分校) University of California, Berkeley(加利福尼亚大学伯克利分校) Cornell University(康奈尔大学) Technische Universität Dresden(德累斯顿工业大学) Carnegie Mellon University(卡内基梅隆大学) The University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

AI总结 针对交通流量预测中自注意力机制扩展性有限的问题,提出EMAGN,通过学习聚类矩阵将空间注意力机制线性化,降低复杂度,实验表明其在准确性和效率上优于其他模型,扩展了可行模型配置。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13239 2026-07-16 cs.AI 新提交

Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management

用于交通管理的成本最优基础模型部署组合

Xi Cheng, Ke Liu, Siyuan Feng, Jane Lin, H. Oliver Gao

机构 * Cornell University(康奈尔大学) University of California, Berkeley(加州大学伯克利分校) The Hong Kong Polytechnic University(香港理工大学) University of Illinois Chicago(伊利诺伊大学芝加哥分校)

AI总结 研究交通管理中基础模型部署组合问题,提出FMDP混合整数规划,证明其NP难,给出多项式时间贪婪启发式算法,通过案例研究确定低成本组合,经盈亏平衡分析得出本地GPU投资合理的条件。

Comments Accepted at IEEE ITSC 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13058 2026-07-16 cs.RO cs.ET 新提交

Power from Potential: A Survey of Electrostatic Actuators for Haptics

源于电势的动力:用于触觉的静电致动器综述

Ahad M. Rauf, Ran Zhou, Eric Acome, Madeline Balaam, Sean Follmer, Teng Han, Craig Shultz, Daniel Leithinger

机构 * Stanford University(斯坦福大学) KTH Royal Institute of Technology(瑞典皇家理工学院) Artimus Robotics(阿蒂姆斯机器人公司) Chinese Academy of Science(中国科学院) Fluid Reality, Inc.(流体现实公司) Cornell University(康奈尔大学)

AI总结 该文综述用于触觉的高压静电致动器,考察静电可切换粘合剂等四类,描述其触觉输出机制、表征相关性能,通过跨技术分析确定设计限制与新兴策略,指出其在推动触觉交互上的独特定位及关键研究方向。

Comments Copyright 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13174 2026-07-16 physics.comp-ph cs.CE cs.RO 新提交

Towards end-to-end optimization in multimaterial 3D printing

迈向多材料3D打印中的端到端优化

Xue-Ling Luo, Steven Yang, Jingye Tan, Robert F. Shepherd, Noy Cohen, Nikolaos Bouklas

机构 * addressline= Sibley School of Mechanical Aerospace Engineering, Cornell University , city= Ithaca , state= NY , country= USA addressline= Department of Aerospace \& Mechanical Engineering, University of Southern California , city= Los Angeles , state= CA , country= USA addressline= Department of Materials Science Engineering, Technion - Israel Institute of Technology , city= Haifa , country= Israel addressline= Pasteur Labs , city= Brooklyn , state= NY , country= USA

AI总结 针对多材料3D打印中优化空间材料分布与结构拓扑的难题,提出将稀疏物理增强神经网络与有限元拓扑优化集成的端到端框架,通过提取本构定律实现精确微分,应用于软机器人抓手,可取代经验原型制作,建立实用的机器学习设计模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.03525 2026-07-16 cs.SE cs.CL 版本更新

GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments

GameEngineBench:在真实C++运行时环境中评估编码智能体

Brian La, Sejoon Chang, Ben Kim, Junyoung Bae, Aamish Ahmad Beg, Sei Chang, Gonzalo Gonzalez-Pumariega, Kanav Goyal

机构 * Nitrode Nexon Intelligence Labs Dartmouth University(达特茅斯大学) Columbia University(哥伦比亚大学) Cornell University(康奈尔大学)

AI总结 研究利用GameEngineBench在虚幻引擎5项目中评估编码智能体,核心方法是构建来自九个真实游戏仓库的基准测试集,主要贡献是揭示智能体在实时交互软件的C++开发中面临挑战,凸显游戏引擎基准测试的价值。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.12443 2026-07-15 cs.CL cs.DS cs.LG 新提交

Language Identification with Succinct Machine-Independent Traces

基于简洁的与机器无关的迹进行语言识别

Moses Charikar, Jon Kleinberg, Chirag Pabbaraju

机构 * Stanford University(斯坦福大学) Cornell University(康奈尔大学)

AI总结 本文受大语言模型启发,针对语言识别的Gold-Angluin模型相关问题,解决能否用小字母表迹及能否直接从语言定义迹的问题,给出肯定答案,展示了如何定义计算迹实现极限识别,所用字母表与语言定义字母表大小成线性关系且与语言其他属性无关。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03529 2026-07-15 cs.RO 版本更新

LapSurgie: Humanoid Robots Performing Surgery via Teleoperated Handheld Laparoscopy

LapSurgie: 人形机器人通过远程操控手持腹腔镜进行手术

Zekai Liang, Xiao Liang, Soofiyan Atar, Sreyan Das, Zoe Chiu, Peihan Zhang, Calvin Joyce, Florian Richter, Shanglei Liu, Michael C. Yip

机构 * Department of Electrical and Computer Engineering, University of California San Diego(加州大学圣地亚哥分校电气与计算机工程系) School of Electrical and Computer Engineering, Cornell University(康奈尔大学电气与计算机工程学院) UC San Diego Health(加州大学圣地亚哥医学中心)

AI总结 LapSurgie是一种基于人形机器人的腹腔镜远程操控框架,通过逆映射策略实现精准手到工具控制,并通过用户研究验证了其在微创手术中的可行性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18315 2026-07-15 cs.LG cs.AI 版本更新

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task

更高的嵌入维度为简单排序任务创建更强的世界模型

Brady Bhalla, Honglu Fan, Nancy Chen, Tony Yue YU

机构 * California Institute of Technology(加利福尼亚理工学院) Google DeepMind(谷歌DeepMind) Cornell University(康奈尔大学)

AI总结 研究在强化学习训练的变压器中嵌入维度对内部“世界模型”的影响,发现更高维度能产生更好的内部表示,经数百实验观察到两种机制,结果证明变压器构建结构化内部世界模型且模型大小可提升表示质量。

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
2506.12339 2026-07-15 cs.HC cs.AI 版本更新

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation

SheetMind:一个由端到端大语言模型驱动的用于电子表格自动化的多智能体框架

Xi Cheng, Ruiyan Zhu, Ke Liu, Rakesh Chowdary Machineni, Lyuhao Chen, Brian Zhu, Daniel Jin, Zheng Qi, Neeraj Parihar, Zhoutian Xu, Oliver Gao

机构 * Cornell University(康奈尔大学) University of California, Berkeley(加州大学伯克利分校) University of Michigan(密歇根大学) Carnegie Mellon University(卡内基梅隆大学) Hong Kong University of Science and Technology (GZ)(香港科学与技术大学)

AI总结 介绍由大语言模型驱动的多智能体框架SheetMind用于电子表格自动化,其分层系统含三个智能体,经评估在SheetCopilot基准测试中执行成功率达100%、功能正确性54.8%超对手,消融研究验证配置优势,还集成到谷歌表格。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.11885 2026-07-14 cs.CV cs.GR 新提交

Latent-Identity Tuning in Text-to-Image Personalization Models

文本到图像个性化模型中的潜在身份调整

Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor, Daniel Cohen-Or, Or Patashnik

机构 * Tel Aviv University(特拉维夫大学) Cornell University(康奈尔大学)

AI总结 研究文本到图像个性化模型中细粒度身份调整问题,利用预训练冻结编码器潜在空间,无需额外训练,通过揭示潜在语义方向实现局部、细粒度且语义连贯的面部编辑,经实验验证有效。

Comments Project page at: https://garibida.github.io/IdentityTuning/

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.11874 2026-07-14 cs.RO cs.AI cs.LG 新提交

A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation

一种用于灵巧操作的极简重定向引导强化学习方法

Yunhai Feng, Natalie Leung, Jiaxuan Wang, Lujie Yang, Haozhi Qi, Preston Culbertson

机构 * Cornell University(康奈尔大学) Amazon FAR(亚马逊FAR)

AI总结 研究如何将重定向引导强化学习用于灵巧操作,提出REGRIND方法,从单人演示学习策略,经重定向、模拟训练、零样本转移到硬件,在丰富接触任务中产生类人行为,还分析了模拟到现实转移的关键因素。

Comments Website: https://yunhaifeng.com/REGRIND

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.11606 2026-07-14 cs.CL cs.DS cs.LG 新提交

Globally Consistent Coloring Schemes for Language Identification

用于语言识别的全局一致着色方案

Moses Charikar, Jon Kleinberg, Chirag Pabbaraju

机构 * Stanford University(斯坦福大学) Cornell University(康奈尔大学)

AI总结 研究对抗性语言学习所需额外信息,探讨终端着色能否替代整个颜色序列用于语言识别,证明每个字符串只需一个终端位,全局构造用超限递归,还表明有限颜色的博雷尔映射终端着色不能识别所有可数子集合。

Comments Abstract shortened to fit arxiv limit

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.11570 2026-07-14 cs.RO cs.HC 新提交

ERR@HRI 3.0 Challenge: Multimodal Detection of Errors and Anticipation in Human-Robot Interactions

ERR@HRI 3.0 挑战赛:人机交互中错误与预期的多模态检测

Maria Teresa Parreira, Micol Spitale, Maia Stiber, Shiye Cao, Amama Mahmood, Chien-Ming Huang, Hatice Gunes, Wendy Ju

机构 * Cornell University(康奈尔大学) Microsoft Research(微软研究院) Johns Hopkins University(约翰霍普金斯大学) University of Cambridge(剑桥大学)

AI总结 ERR@HRI 3.0 挑战赛提供自然场景视频数据集,供研究者开发多模态机器学习模型检测人机交互错误与预期,三个团队提交的有效模型超卷积神经网络基线,为构建相关检测系统提供了数据、任务、基线及结果等参考。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10682 2026-07-14 cs.RO 新提交

SensorPerch: Sense Wherever and Whenever it Matters

SensorPerch:随时随地感知重要之处

Zhanxin Wu, Ruofei Tong, Tapomayukh Bhattacharjee

机构 * Cornell University(康奈尔大学)

AI总结 针对机器人感知视角受限问题,提出SensorPerch,通过将传感器视为独立实体实现主动感知。它由可重构传感器平台和视角选择框架组成,能按需构建与任务相关的视角。在对象耦合和策略耦合感知任务中验证了该范式的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10608 2026-07-14 cs.AI 新提交

The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory

合规陷阱:诊断人工智能代理如何处理冲突记忆

Yixiong Chen, Xinyi Bai, Alan Yuille

机构 * Johns Hopkins University(约翰·霍普金斯大学) Cornell University(康奈尔大学)

AI总结 研究人工智能代理处理冲突记忆的问题,提出E-P-R框架,通过在WebArena和MemTrapBench上实例化发现主要失败始于入口,冲突记忆导致合规陷阱,强调评估记忆增强型代理应考虑其处理记忆的全过程。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.09884 2026-07-14 cs.CV cs.LG 新提交

ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning

ShapKO:用于稳健多模态学习的Shapley自适应模态剔除

Nusrat Binta Nizam, Fengbei Liu, Sunwoo Kwak, Minh Nguyen, Ruining Deng, Mert R. Sabuncu

机构 * Cornell University(康奈尔大学) Cornell Tech(康奈尔科技学院) Weill Cornell Medicine(威尔康乃尔医学院)

AI总结 针对多模态医学模型在输入缺失或模态主导时性能不佳的问题,提出ShapKO动态训练策略,基于验证效用学习特定模态剔除概率,通过评估性能、估计重要性和更新概率促进互补表示,在多数据集上提升了模型性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.09734 2026-07-14 cs.HC cs.RO 新提交

The Individual-Targeting Assumption: A Systematic Review of Proactive Robots in Human Group Settings

个体目标假设:对人类群体环境中主动机器人的系统综述

Tauhid Tanjim, Tasmia Mayen, Malte F. Jung, Susan R. Fussell

机构 * Department of Information Science at Cornell University(康奈尔大学信息科学系) School of Education, Louisiana State University(路易斯安那州立大学教育学院)

AI总结 通过对63项群体环境中主动人机交互研究的系统综述,发现个体目标假设(ITA)普遍存在,群体感知方法滞后,未解决机器人进入预先形成群体的问题,还出现三种失败模式,重新定义主动HRI为独特设计问题,确定进入阶段为关键挑战。

Comments 8 pages, 3 figures, 4 tables. Accepted at the 2026 IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.09218 2026-07-14 cs.RO cs.AI 版本更新

TACTIC: Tactile and Vision Conditioned Contact-Centric Control for Whole-Arm Manipulation

用于全臂操作的触觉和视觉条件下的以接触为中心的控制

Rishabh Madan, Angchen Xie, Samantha Saak, Andres Blanco, Dohyeok Lee, Sarah Grace Brown, Yunting Yan, Mark Zolotas, Jose Barreiros, Tapomayukh Bhattacharjee

机构 * Cornell University(康奈尔大学) Carnegie Mellon University(卡内基梅隆大学) Toyota Research Institute(丰田研究机构)

AI总结 研究全臂操作问题,提出TACTIC控制器,它采用以接触为中心的混合预测模型,结合多种传感,通过接触雅可比矩阵耦合动力学与运动学,集成到MPC规划器,在模拟和实际任务中表现出色,优于其他方法。

Comments RSS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.26795 2026-07-14 cs.CV cs.AI cs.MM 版本更新

NaviCache: Test-Time Self-Calibration Caching for Video Generation

NaviCache: 视频生成的测试时自校准缓存

Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang, Zhengyu Chen, Chengxi Zang, Zhou Zhao, Fei Wu

机构 * Zhejiang University(浙江大学) Cornell University(康奈尔大学) Tencent Hunyuan(腾讯文生视频)

AI总结 针对视频扩散模型计算成本高的问题,提出NaviCache方法,将特征演化重构思为惯性导航系统问题,通过双状态估计架构自适应跟踪特征变化比和潜在漂移,实现有界误差的计算跳过,在多个模型上取得优异性能。

Comments Published at ICML 2026: Proceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16536 2026-07-14 cs.SE cs.AI cs.LG

Towards Reliable Testing of Machine Unlearning

迈向可靠的机器无学习测试

Anna Mazhar, Sainyam Galhotra

机构 * Cornell University(康奈尔大学)

AI总结 本文提出了一种基于因果的路径中心视角,通过因果模糊测试生成预算干预,以估计残留直接和间接影响并生成可操作的泄漏报告,解决机器无学习测试中的覆盖路径、调试诊断、回归执行和黑盒适用性问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13213 2026-07-14 stat.ML cs.LG math.OC physics.chem-ph 版本更新

Rare Event Analysis via Stochastic Optimal Control

基于随机最优控制的稀有事件分析

Yuanqi Du, Jiajun He, Dinghuai Zhang, Eric Vanden-Eijnden, Carles Domingo-Enrich

机构 * Microsoft Research New England(微软研究院新英格兰分部) Cornell University(康奈尔大学) University of Cambridge(剑桥大学) Courant Institute of Mathematical Sciences, NYU(纽约大学Courant数学科学研究所)

AI总结 提出将稀有事件分析中的committor函数估计转化为随机最优控制问题,通过反馈控制引导轨迹采样,并开发两种损失函数及处理亚稳态的方法,在基准系统上获得更准确的结果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.07643 2026-07-14 cs.HC cs.CL 交叉投稿

Narrix: Remixing Narrative Strategies from Examples for Story Writing

Narrix:从示例中 remix 叙事策略以进行故事写作

Chao Zhang, Shunan Guo, Abe Davis, Eunyee Koh

机构 * Cornell University(康奈尔大学) Adobe Research(Adobe研究)

AI总结 Narrix 通过可视化叙事策略帮助新手作家提高叙事能力,通过交互式故事弧和颜色编码提示,使作家能有效复用策略,提升创作信心和适应能力。

Comments 24 pages, 10 figures. To appear in CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, April 13-17, 2026, Barcelona, Spain. DOI: https://doi.org/10.1145/3772318.3790813

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06587 2026-07-14 cs.AI q-fin.CP q-fin.RM

Autonomous AI Agents for Option Hedging: Enhancing Financial Stability through Shortfall Aware Reinforcement Learning

自主AI代理用于期权对冲:通过意识短缺的强化学习增强金融稳定性

Minxuan Hu, Ziheng Chen, Jiayu Yi, Wenxi Sun

机构 * Cornell Ann S. Bowers College of Computing and Information Science, Cornell University(康奈尔大学安·索斯·博尔斯计算与信息科学学院) Department of Mathematics, University of Texas at Austin(德克萨斯大学奥斯汀分校数学系) School of Social Sciences, Nanyang Technological University(南洋理工大学社会科学学院) Krieger School of Arts and Sciences, Johns Hopkins University(约翰霍普金斯大学克里eger艺术与科学学院)

AI总结 本文提出RLOP和QLBS两种强化学习框架,通过意识短缺的方法优化期权对冲,提升金融稳定性并改进风险预测。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.02905 2026-07-14 cs.AI 版本更新

FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights

FIRE-Bench:评估人工智能代理在科学见解重新发现方面的表现

Zhen Wang, Fan Bai, Zhongyan Luo, Jinyan Su, Kaiser Sun, Xinle Yu, Jieyuan Liu, Kun Zhou, Claire Cardie, Mark Dredze, Zhiting Hu, Eric P. Xing

机构 * Johns Hopkins University(约翰霍普金斯大学) Cornell University(康奈尔大学)

AI总结 研究旨在评估大语言模型驱动的人工智能代理在科学见解重新发现上的能力。核心方法是引入FIRE-Bench基准,让代理基于高层次研究问题进行全周期探索。主要贡献是为衡量代理驱动的科学发现进展提供了严格诊断框架,揭示当前代理系统在全周期科研上的挑战。

Comments 34 pages, 3 figures, 16 tables; ICML 2026 Camera-ready Version

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.03979 2026-07-13 cs.LG cs.AI 版本更新

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories

语言模型需要睡眠:学习自我修改和巩固记忆

Ali Behrouz, Farnoosh Hashemi, Adel Javanmard, Vahab Mirrokni

机构 * Google(谷歌) Cornell University(康奈尔大学)

AI总结 受人类学习过程启发,提出“睡眠”范式,通过记忆巩固(知识播种)和梦境(自我改进)两阶段,使模型持续学习、将短期记忆转化为长期知识并自我提升。

Comments A version of this work has been publicly available from September 2025 on OpenReview

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.08233 2026-07-10 cs.AI cs.CV 新提交

Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction

玩禅道世界:在主动视觉概念归纳中挑战人工智能代理

Sophia Koehler, Antonia Wüst, Inga Ibs, Wasu Top Piriyakulkij, Wolfgang Stammer, Constantin Rothkopf, Kevin Ellis, Kristian Kersting

机构 * AIML Lab, TU Darmstadt(人工智能机器学习实验室,达姆施塔特工业大学) Hessian Center for AI (hessian.AI)(黑森州人工智能中心) Psychology of Information Processing, TU Darmstadt(信息处理心理学,达姆施塔特工业大学) Centre for Cognitive Science, TU Darmstadt(认知科学中心,达姆施塔特工业大学) Cornell University(康奈尔大学) Max Planck Institute for Informatics, SIC(马克斯·普朗克信息学研究所,SIC组) German Center for AI (DFKI)(德国人工智能研究中心)

AI总结 研究构建智能系统时代理感知、假设形成及实验设计问题,提出禅道世界环境,评估多种代理方法,发现预测标签精度与恢复潜在规则无关,感知和归纳是不同瓶颈,基于视觉语言模型的代理实验无信息,还收集人类数据揭示差距及改进途径。

详情

展开后加载摘要…

URL PDF HTML 收藏