arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Harvard University(哈佛大学)

共收录 1301
2404.01549 2026-07-21 cs.CL cs.SE 版本更新

Octopus: On-device language model for function calling of software APIs

章鱼:用于软件API函数调用的设备端语言模型

Wei Chen, Zhiyuan Li, Mingyuan Ma

机构 * Stanford University(斯坦福大学) Harvard University(哈佛大学)

AI总结 研究利用设备端大语言模型调用软件API,通过编译数据集微调不同参数模型,提升其API交互能力,提出条件掩码技术和新基准,经微调的Octopus模型在API调用上性能超GPT-4,推动自动化软件开发和API集成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23786 2026-07-20 cs.AI cs.LG 版本更新

FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment

FAIR_XAI: 通过可解释性提升多模态基础模型公平性以用于幸福感评估

Sophie Chiang, Tom Brennan, Fethiye Irmak Dogan, Jiaee Cheong, Hatice Gunes

机构 * Department of Computer Science & Technology, University of Cambridge(计算机科学与技术系,剑桥大学) Harvard University(哈佛大学)

AI总结 本文研究了多模态基础模型在幸福感评估中的公平性问题,通过可解释性干预框架改善诊断可靠性与公平性,发现不同模型在不同数据集上表现差异显著,且存在性别和种族偏见。

Comments 11 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22274 2026-07-20 cs.CV 版本更新

GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure

GeCo:通过运动和结构评估视频生成的几何一致性

Leslie Gu, Junhwa Hur, Charles Herrmann, Fangneng Zhan, Todd Zickler, Deqing Sun, Hanspeter Pfister

机构 * Harvard University(哈佛大学) Google DeepMind(谷歌DeepMind) MIT(麻省理工学院)

AI总结 GeCo通过融合残差运动和深度先验,检测静态场景中的几何变形和遮挡不一致问题,并用于评估视频生成模型的性能与缺陷。

详情

展开后加载摘要…

URL PDF HTML 收藏
2205.04599 2026-07-20 cs.LG cs.AI 版本更新

Perception-Aligned AI Outputs: End-to-End Visual Prediction for Uncertainty Communication in Clinical Decision-Making

感知对齐的人工智能输出:临床决策中用于不确定性通信的端到端视觉预测

Mohammad Eslami, Solale Tabarestani, Saber Kazeminasab, Ehsan Adeli, Glyn Elwyn, Tobias Elze, Mengyu Wang, Nazlee Zebardast, Lucia Sobrin, Nassir Navab, Daniel Shu Wei Ting, Malek Adjouadi

机构 * Harvard Ophthalmology AI Lab(哈佛眼科人工智能实验室) Schepens Eye Research Institute of Massachusetts Eye and Ear(马萨诸塞眼耳医院施佩恩眼科研究所) Harvard Medical School(哈佛医学院) Center for Advanced Technology and Education(先进教育技术中心) Florida International University(佛罗里达国际大学) Dartmouth Institute for Health Policy and Clinical Practice(达特茅斯健康政策与临床实践研究所) Dartmouth College(达特茅斯学院) Computer Aided Medical Procedures(医学辅助程序) Technical University of Munich(慕尼黑技术大学) Singapore Eye Research Institute(新加坡眼科研究所) Singapore National Eye Centre(新加坡国家眼科中心) Department of Ophthalmology, Byers Eye Institute, Stanford University(眼科部门,比尔斯眼科研究所,斯坦福大学)

AI总结 研究针对医疗保健中可解释人工智能的问题,提出以人为本的机器学习可视化学习框架VL4ML,通过直观视觉表示传达模型预测与不确定性,经多临床任务验证及评估,结果显示其能有效支持临床决策,具有广泛可及性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.14946 2026-07-17 cs.CV 新提交

DINE: Distance Is Not Enough -- Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registration

DINE:距离并不够——学习用于鲁棒软组织点云配准的全局变形先验

Sara Monji-Azad, Rohit Beer, Marvin Kinz, Claudia Scherl, Jürgen Hesser

机构 * Mannheim Institute for Intelligent Systems in Medicine (MIISM), Medical Faculty Mannheim, Heidelberg University(曼海姆医学智能系统研究所(MIISM),海德堡大学曼海姆医学院) Department of Radiation Oncology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School(布莱根妇女医院放射肿瘤学系,达纳-法伯癌症研究所,哈佛医学院) Department of Otorhinolaryngology, Head and Neck Surgery, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University(海德堡大学曼海姆医学院曼海姆大学医学中心耳鼻咽喉头颈外科) Department of Otolaryngology, Head and Neck Surgery, Campus Klinikum Bielefeld Mitte, University Hospital OWL of Bielefeld University(比勒费尔德大学OWL大学医院比勒费尔德市中心校区耳鼻咽喉头颈外科) Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University(海德堡大学跨学科科学计算中心(IWR)) Central Institute for Computer Engineering (ZITI), Heidelberg University(海德堡大学中央计算机工程研究所(ZITI)) CZS Heidelberg Center for Model-Based AI, Heidelberg University(海德堡大学CZS基于模型的人工智能中心)

AI总结 研究针对软组织点云配准中对应估计难题,提出DINE框架,通过学习统计先验增强基于距离的配准,应用于两个主干并采用两阶段策略,实验表明其能降低平均倒角距离,提高对变形和噪声的鲁棒性,凸显全局变形合理性的重要性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.15948 2026-07-17 cs.AI q-bio.NC 版本更新

Subjective functions

主观函数

Samuel J. Gershman

机构 * Harvard University(哈佛大学) Department of Psychology(心理学系) Center for Brain Science(脑科学中心) Kempner Institute for the Study of Natural and Artificial Intelligence(自然与人工智能研究学院)

AI总结 本文探讨了主观函数的概念,通过预期预测误差作为例子,提出了一种赋予人工系统自主设定目标能力的方法,连接了心理学、神经科学和机器学习。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00923 2026-07-17 cs.LG 版本更新

Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming

超越基准:动态、自动和系统化的红队代理用于可信的医疗语言模型

Jiazhen Pan, Bailiang Jian, Paul Hager, Yundi Zhang, Che Liu, Friederike Jungmann, Hongwei Bran Li, Julian Canisius, Chenyu You, Junde Wu, Jiayuan Zhu, Fenglin Liu, Yuyuan Liu, Niklas Bubeck, Moritz Knolle, Chen, Chen, Christian Wachinger, Zhenyu Gong, Cheng Ouyang, Georgios Kaissis, Benedikt Wiestler, Daniel Rueckert

机构 * Technical University of Munich (TUM)(慕尼黑技术大学) University of Oxford(牛津大学) TUM University Hospital(慕尼黑技术大学医院) Imperial College London(伦敦帝国理工学院) Harvard Medical School(哈佛医学院) Stony Brook University(史泰兹布鲁克大学) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心) University of Sheffield(谢菲尔德大学)

AI总结 本文提出DAS红队框架,通过动态压力测试揭示医疗语言模型在鲁棒性、隐私、偏见和幻觉方面的潜在风险,发现高静态基准性能与低动态可靠性之间的'基准差距'。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01680 2026-07-16 econ.EM cs.LG 版本更新

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach

从非结构化数据中做出可解释的发现:一种高维多重假设检验方法

Jacob Carlson

机构 * Harvard University(哈佛大学)

AI总结 本文针对社会科学家利用非结构化数据获取实证见解的需求,提出通用灵活框架。借AI可解释性方法映射数据到概念嵌入,计算统计量检验假设,经选择性推断得出发现,并生成评估自然语言描述,具有低自由度、鲁棒性等优点。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.12631 2026-07-15 cs.CL cs.AI 新提交

Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?

诱导情绪会影响大语言模型在序列决策中的行为吗?

Minh Khoi Ho, Zihao Zhu, Runchuan Zhu, Levina Li, Zhiwen Fan, Zhangyang Wang, Junyuan Hong

机构 * MBZUAI(穆罕默德·本·扎耶德人工智能大学) Texas A&M University(德州农工大学) National University of Singapore(新加坡国立大学) UCLA(加州大学洛杉矶分校) University of Texas at Austin(德克萨斯大学奥斯汀分校) Mass General Hospital(麻省总医院) Harvard Medical School(哈佛医学院)

AI总结 研究探讨诱导情绪对大语言模型在序列决策中行为的影响,采用爱荷华赌博任务结合情绪诱导程序,发现诱导情绪平均不显著影响其决策动态,但愤怒有条件地影响决策,揭示了与人类行为的差异,为相关研究提供工具。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12346 2026-07-15 cs.CV cs.AI cs.LG 版本更新

Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy

Atlas H&E-TME:基于AI的可扩展组织分析,达到专家病理学家级别的准确性

Kai Standvoss, Miriam Hägele, Rosemarie Krupar, Julika Ribbat-Idel, Jennifer Altschüler, Gerrit Erdmann, Hans Pinckaers, Evelyn Ramberger, Madleen Drinkwitz, Ádám Nárai, Alexander Möllers, Katja Lingelbach, Sebastian Kons, Lukas Hönig, Recepcan Adigüzel, Joana Baião, Alberto Megina Gonzalo, Marius Teodorescu, Marie-Lisa Eich, Paolo Chetta, Shakil Merchant, Verena Aumiller, Simon Schallenberg, Andrew Norgan, Klaus-Robert Müller, Lukas Ruff, Maximilian Alber, Frederick Klauschen

机构 * Aignostics, Germany(Aignostics,德国) Institute of Pathology, Charité – Universitätsmedizin Berlin, Germany(柏林夏里特医学院病理学研究所) Berlin Institute of Health, Charité – Universitätsmedizin Berlin, Germany(柏林夏里特医学院柏林健康研究所) Massachusetts General Hospital, Department of Pathology, Harvard Medical School, Boston, MA, US(哈佛医学院麻省总医院病理学系) Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, US(梅奥诊所检验医学与病理学系) Machine Learning Group, Technische Universität Berlin, Germany(柏林工业大学机器学习组) BIFOLD – Berlin Institute for the Foundations of Learning and Data, Germany(柏林学习与数据基础研究所) Department of Artificial Intelligence, Korea University, Republic of Korea(高丽大学人工智能系) Max-Planck Institute for Informatics, Germany(马克斯·普朗克信息学研究所) German Cancer Research Center (DKFZ) & German Cancer Consortium (DKTK), Berlin & Munich Partner Sites, Germany(德国癌症研究中心及德国癌症联盟柏林和慕尼黑合作站点) Institute of Pathology, Ludwig-Maximilians-Universität München, Germany(慕尼黑大学病理学研究所) Bavarian Cancer Research Center (BZKF), Germany(巴伐利亚癌症研究中心)

AI总结 提出Atlas H&E-TME系统,利用病理基础模型预测组织质量、区域和细胞类型,通过IHC共识验证和20万+注释基准,在多种癌症中达到或超越病理学家水平。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12765 2026-07-15 cs.LG 版本更新

Inference-Time Machine Unlearning via Gated Activation Redirection

推理时的机器去学习 via 门控激活重定向

Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinskü

机构 * MALTA, Machine Learning Theory and Applications Lab, PUCRS, Porto Alegre, Brazil(MALTA机器学习理论与应用实验室,PUCRS,波士顿-阿尔格雷,巴西) Harvard University(哈佛大学) Kunumi Institute, Brazil(库努米研究所,巴西)

AI总结 本文提出了一种无需训练和梯度的机器去学习方法GUARD-IT,通过在推理时依赖输入的激活引导来消除特定数据集的影响,同时保持模型性能,且在量化部署下仍有效。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01568 2026-07-15 cs.LG cs.CV cs.IT math.IT q-bio.NC 版本更新

Same Compression Principle, Different Geometry: Rate-Distortion Signatures Dissociate Biological and Artificial Visual Systems

泛化与信息权衡的率-失真签名

Leyla Roksan Caglar, Pedro A. M. Mediano, Baihan Lin

机构 * Windreich Department of AI Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA Department of Computing, Imperial College London, London, UK Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA Berkman Klein Center for Internet \& Society, Harvard University, Cambridge, MA, USA

AI总结 本文提出率-失真理论框架,通过斜率和曲率签名分析系统泛化与鲁棒性权衡,揭示生物与人工系统在RD空间中的不同表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01241 2026-07-15 cs.CY cs.AI 版本更新

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

首先,不伤害:迈向临床安全的大语言模型

David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj, Priyank Jain, Jessica Tran, Matthew Gwiazdon, Arjun Rustagi, Jenelle Jindal, Jacob M. Koshy, Vinay Kadiyala, Anup Agarwal, Bassman Tappuni, Brianna French, Sirus Jesudasen, Christopher V. Cosgriff, Rebanta Chakraborty, Jillian Caldwell, Susan Ziolkowski, David J. Iberri, Robert Diep, Rahul S. Dalal, Kira L. Newman, Kristin Galetta, J. Carl Pallais, Nancy Wei, Kathleen M. Buchheit, David I. Hong, Vartan Pahalyants, Ernest Y. Lee, Allen Shih, Tamara B. Kaplan, Vishnu Ravi, Sarita Khemani, Thomas A. Buckley, April S. Liang, Daniel Shirvani, Advait Patil, Nicholas Marshall, Kanav Chopra, Joel Koh, Adi Badhwar, Anastasia Perez, Austin J. Schoeffler, Mahbuba Tusty, Chase M. Walton, Liam G. McCoy, David J. H. Wu, Yingjie Weng, Sumant Ranji, Kevin Schulman, Nigam H. Shah, Jason Hom, Arnold Milstein, Arjun K. Manrai, Adam Rodman, Jonathan H. Chen, Ethan Goh

机构 * Harvard Combined Dermatology Program(哈佛联合皮肤科项目) Department of Dermatology, Mass General Brigham(麻省总医院皮肤科) Harvard Medical School(哈佛医学院) Stanford Center for Biomedical Informatics Research(斯坦福生物医学信息学研究中心) Stanford University(斯坦福大学) Division of Hospital Medicine, Department of Medicine, Stanford University School of Medicine(斯坦福大学医学院医院医学科) Department of Medicine, Cambridge Health Alliance(剑桥健康联盟医学科) Beth Israel Deaconess Hospital–Plymouth(贝塞斯达德acons医院-普利茅斯) Department of Medicine, University of California, San Francisco(加州大学旧金山分校医学科) Department of Neurology, Stanford University School of Medicine(斯坦福大学医学院神经科) Department of Medicine, Beth Israel Deaconess Medical Center(贝塞斯达德acons医学中心医学科) Division of Cardiology, Department of Medicine, Cambridge Health Alliance(剑桥健康联盟心脏病科) Department of Cardiovascular Medicine, Summa Health System(Summa健康系统心血管医学科) Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, University of Wisconsin-Madison(威斯康星大学麦迪逊分校医学科过敏、呼吸科和危重医学科) Division of Pulmonary and Critical Care Medicine, Department of Medicine, Massachusetts General Hospital(麻省总医院呼吸科和危重医学科) Center for Immunology and Inflammatory Diseases, Department of Medicine, Massachusetts General Hospital(麻省总医院免疫和炎症疾病中心) Broad Institute of MIT and Harvard(MIT和哈佛Broad研究所) Division of Pulmonary, Critical Care, and Sleep Medicine, Cambridge Health Alliance(剑桥健康联盟呼吸科、危重医学科和睡眠医学科)

AI总结 提出NOHARM基准,包含1100个初级到专科咨询案例,评估28个LLM的医疗建议安全性,发现高达22.6%的案例存在严重危害风险,其中遗漏错误占80%以上。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04144 2026-07-15 cs.AI 版本更新

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories

RippleBench: 利用现有知识库捕捉涟漪效应

Roy Rinberg, Usha Bhalla, Igor Shilov, Flavio P. Calmon, Rohit Gandikota

机构 * Harvard University(哈佛大学) Imperial College London(伦敦帝国学院) Northeastern University(东北大学)

AI总结 提出RippleBench-Maker自动管道,从知识库检索语义邻居生成选择题,评估八种遗忘方法在Llama3-8B-Instruct上的涟漪效应,发现准确率下降随语义距离衰减且跨模型一致。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.15131 2026-07-15 math.ST cs.LG stat.ME stat.ML stat.TH 版本更新

Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling

高维二分类中的最优且可证明的校准:角度校准与Platt缩放

Yufan Li, Pragya Sur

机构 * Harvard University(哈佛大学)

AI总结 针对高维高斯特征下的线性二分类器,提出基于估计权重与真实权重夹角的角度校准方法,证明其可校准且唯一Bregman最优,并揭示Platt缩放在高维下收敛于该最优解。

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
2607.11052 2026-07-14 cs.LG cs.CL 新提交

Domain-Aware Scaling Laws Uncover Data Synergy

领域感知缩放定律揭示数据协同效应

Kimia Hamidieh, Lester Mackey, David Alvarez-Melis

机构 * MIT CSAIL(麻省理工学院计算机科学与人工智能实验室) Microsoft Research(微软研究院) Harvard University(哈佛大学)

AI总结 研究语言模型预训练中的数据协同效应,利用开放权重语言模型的观测变化估计领域间协同效应,其框架提高预测精度,恢复稳定估计,经训练模型验证能正确预测性能排名。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10892 2026-07-14 cs.RO 新提交

A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer

用于多任务块推的单扩散策略控制器,具有零样本模拟到现实转移

Haitong Ma, Haldun Balim, Yang Hu, Bo Dai, Na Li

机构 * Harvard University(哈佛大学) Georgia Institute of Technology(佐治亚理工学院)

AI总结 研究旨在用强化学习从零训练单扩散策略用于多任务块推,提出含简单策略损失函数的框架,结合反向课程生成等应对探索挑战,评估其在不同条件下零样本从模拟到现实的转移能力,证明该流程有效。

Comments 8 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10792 2026-07-14 cs.CV 新提交

MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction

MAC-Splat:用于高保真稀疏视图重建的多属性一致性

Jinqian Yang, Yichen Wu, Wanhua Li, Haokun Lin, Renzhen Wang, Xiangchu Feng, Xixi Jia

机构 * Xidian University(西安电子科技大学) Harvard University(哈佛大学) Nanyang Technological University(南洋理工大学) City University of Hong Kong(香港城市大学) Xi’an Jiaotong University(西安交通大学)

AI总结 针对稀疏视图重建中现有方法存在几何伪影的问题,提出MAC-Splat训练框架,利用MASt3R和DINOv3获取2D对应关系并定义MAC损失,联合正则化3D属性,实验证明该方法能有效解决不适定的稀疏视图重建问题,性能优于基线。

Comments Accepted to the European Conference on Computer Vision (ECCV 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10787 2026-07-14 cs.CV cs.CL 新提交

Detecting AI-Generated Video: A Vision-Language Dual-View Survey

检测人工智能生成的视频:视觉-语言双视角综述

Dylan Xinming Hou, Juntian Zhang, Xu Gu, Yichen Wu, Nils Lukas, Gus Xia, Xiuying Chen, Yuhan Liu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学中关村人工智能学院) Harvard University(哈佛大学)

AI总结 综述人工智能生成视频检测,将任务重定义为事实保真度验证,提出视觉-语言双视角分类法,基于对221篇论文回顾,综合生成范式、审视检测方法、回顾评估指标,讨论挑战并指出未来方向。

Comments 51 pages, accepted by ACL 2026

Journal ref Association for Computational Linguistics 2026 pages 32221 to 32255

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10389 2026-07-14 cs.DC cs.LG 新提交

Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models

有状态世界,无状态弹性:交互式世界模型的精确状态服务

Jin Li, Jiawei Chen

机构 * Harvard University(哈佛大学) Independent Researcher(独立研究者)

AI总结 研究交互式世界模型精确状态服务中的调度问题,提出 WorldMove 方法,能快速迁移缓存且保证位相同,通过可接受性条件等解决调度难题,实现跨传输和验证的联合调度,提升集群可调度性。

Comments 20 pages. Extended version

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10039 2026-07-14 physics.data-an cs.LG hep-ph 新提交

Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough

我们准备好迎接人工智能驱动的发现了吗?在下一次基础物理学突破之前进行人工智能验证

Gaia Grosso, Vinicius Mikuni, Lukas Heinrich

机构 * NSF AI Institute for Artificial Intelligence and Fundamental Interactions(NSF人工智能与基本相互作用研究院) MIT Laboratory for Nuclear Science(MIT核科学实验室) School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院) Nagoya University(名古屋大学) Technical University Munich(慕尼黑技术大学) Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心)

AI总结 探讨在基础物理学中,随着机器学习日益自主,确保其可靠性至关重要。通过VERaiPHY计划框架,结合统计发现工作流程确定验证时机,强调归纳偏差等局限,思考物理学家角色,以实现机器学习在物理学中负责任的整合。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.27537 2026-07-14 cs.CV 版本更新

MemoBench: Benchmarking World Modeling in Dynamically Changing Environments

MemoBench: 动态变化环境中的世界建模基准测试

Haoyu Chen, Kaichen Zhou, Hang Hua, Kaile Zhang, Jingwen Qian, Wufei Ma, Haonan Chen, Chunjiang Liu, Yizhou Zhao, Xiaoyuan Wang, Weiyue Li, Alan Yuille, Paul Pu Liang, Yilun Du

机构 * Harvard University(哈佛大学) MIT(麻省理工学院) MIT-IBM Watson AI Lab(MIT-IBM沃森人工智能实验室) Boston University(波士顿大学) Google(谷歌) JHU(约翰霍普金斯大学) CMU(卡内基梅隆大学) Kempner Institute(肯普纳研究所)

AI总结 提出MemoBench基准,通过目标消失-重现范式评估视频生成模型在动态环境中的记忆一致性,涵盖合成与真实场景,揭示现有模型的关键挑战。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01331 2026-07-14 cs.CL cs.AI cs.LG 版本更新

MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models

MetaState: 持久工作记忆增强离散扩散语言模型的推理能力

Kejing Xia, Mingzhe Li, Lixuan Wei, Zhenbang Du, Xiangchi Yuan, Dachuan Shi, Qirui Jin, Wenke Lee

机构 * Georgia Institute of Technology(佐治亚理工学院) University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) Harvard University(哈佛大学)

AI总结 MetaState通过引入轻量级循环增强模块,为冻结的离散扩散语言模型提供持久固定大小的工作记忆,提升推理性能,平均提升4.5%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15353 2026-07-14 stat.AP cs.LG stat.ML 版本更新

Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions

现实世界中的强化学习:统计挑战与未来方向综述

Asim H. Gazi, Yongyi Guo, Daiqi Gao, Ziping Xu, Kelly W. Zhang, Susan A. Murphy

机构 * Department of Computer Science, Harvard University(哈佛大学计算机科学系) Department of Statistics, University of Wisconsin–Madison(威斯康星大学麦迪逊分校统计学系) Department of Statistics, Harvard University(哈佛大学统计学系) School of Data Science and Society, University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校数据科学与社会学院) Department of Mathematics, Imperial College London(伦敦帝国理工学院数学系)

AI总结 本文综述现实世界强化学习应用,指出其研究与部署存在差距及两大挑战。将应用框架化为三部分过程,回顾应对统计挑战的进展,涵盖在线、离线方法及持续改进设计,还概述受应用启发的未来研究方向。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.05972 2026-07-14 cs.CC cs.CR cs.LG 版本更新

Generalized and Unified Equivalences between Hardness and Pseudoentropy

硬度与伪熵之间的广义统一等价关系

Lunjia Hu, Salil Vadhan

机构 * Northeastern University(东北大学) Harvard University(哈佛大学)

AI总结 研究计算硬度与计算随机性的关系,证明统一伪熵刻画,适用于一般熵概念族,由单个通用函数见证。通过权重受限校准等技术,证明增强引理,相比前人刻画在字母表大小依赖上有指数级改进且此依赖不可避免。

Comments Accepted to TCC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.09089 2026-07-13 cs.CV 新提交

DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshes

DETRAM:人类网格的端到端检测、跟踪与恢复

Chunggi Lee, Seonwook Park, Wanhua Li, Umar Iqbal, Hanspeter Pfister

机构 * Harvard University(哈佛大学) NVIDIA(英伟达) Nanyang Technological University(南洋理工大学)

AI总结 研究针对多人场景下人类网格恢复难题,提出DETRAM统一框架,利用单个变压器解码器及可学习查询嵌入,能自动和依用户提示检测、重建与跟踪人类,在多数据集上取得领先跟踪结果及有竞争力的重建精度,实现端到端可训练的用户导向人体分析。

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.14926 2026-07-13 stat.ML cs.LG 版本更新

Contrastive Learning on Multimodal Analysis of Electronic Health Records

电子健康记录多模态分析中的对比学习

Tianxi Cai, Feiqing Huang, Ryumei Nakada, Linjun Zhang, Doudou Zhou

机构 * Harvard T.H. Chan School of Public Health(哈佛T.H. 柏林公共卫生学院) Harvard Medical School(哈佛医学院) Rutgers University(罗格斯大学) National University of Singapore(新加坡国立大学)

AI总结 研究针对电子健康记录多模态数据传统分析方法不足,提出多模态特征嵌入生成模型及对比损失来学习特征表示,经理论分析、模拟研究和真实数据验证,该方法有效且具隐私保护特性,展现了多模态学习优势。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.08397 2026-07-10 cs.CV 新提交

Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation

用于开放词汇量内镜组合式指称分割的属性检索

Shun Liu, Nan Xi, Yang Liu, Tianyu Luan, Xuan Gong, David Doermann

机构 * Virginia Commonwealth University(弗吉尼亚联邦大学) King’s College London(伦敦国王学院) University at Buffalo(纽约州立大学布法罗分校) Harvard Medical School(哈佛医学院)

AI总结 该研究针对内镜图像指称分割面临的挑战,引入ReferEndoscopy基准,提出AR-ERIS框架,利用属性检索进行开放词汇量内镜组合式指称分割,在模拟和真实内镜数据上实现最优性能且泛化能力强。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.08170 2026-07-10 cs.LG 新提交

Understanding Layer Patching in Model Size Interpolation

理解模型大小插值中的层修补

Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak, Marco Fumero, Francesco Locatello, David Alvarez-Melis

机构 * Harvard University(哈佛大学) Kempner Institute(肯普纳研究所) IST Austria(奥地利科学技术研究所)

AI总结 研究零样本模型大小插值中如何选择学生层,将其转化为优化问题并证明可看作无环图最短路径问题。通过实验揭示修补对插值行为的影响,介绍KLPatch算法,为模型大小插值提供理解与实用指导。

Comments 10 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏