arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Imperial College London(帝国理工学院)

共收录 1182
2508.19988 2026-05-26 cs.CL

AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios

AgentCoMa:一个混合常识与数学推理的现实场景组合基准

Lisa Alazraki, Lihu Chen, Ana Brassard, Joe Stacey, Hossein A. Rahmani, Marek Rei

机构 * Imperial College London(帝国理工学院伦敦分校) RIKEN(日本研究机构) University of Sheffield(谢菲尔德大学) University College London(伦敦大学学院)

AI总结 提出AgentCoMa基准,测试大语言模型在组合常识与数学推理任务上的性能,发现模型在单独步骤上准确率高但组合后平均下降近30%。

Comments ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25057 2026-05-26 math.NA cs.LG cs.NA

Random Neural Network Expressivity for Non-Linear Partial Differential Equations

随机神经网络对非线性偏微分方程的表达能力

Muhammed Ali Mehmood, Lukas Gonon

机构 * Department of Mathematics(数学系) Imperial College London(帝国理工学院伦敦分校) School of Computer Science(计算机科学学院) University of St. Gallen(圣加尔登大学)

AI总结 研究随机生成隐藏权重的神经网络(RaNNs)对非线性偏微分方程解的逼近能力,推导了误差界并得到维数无关的逼近率1/2,应用于多孔介质方程和可压缩Navier-Stokes方程。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25020 2026-05-26 cs.AI cs.CL

Privacy-Preserving Local Language Models for Longitudinal Data Retrieval in Chronic Dermatologic Disease: Implementation in Pemphigus Patients

慢性皮肤病纵向数据检索中的隐私保护本地语言模型:在天疱疮患者中的实施

Abdurrahim Yilmaz, Ayşe Esra Koku Aksu, Duygu Yamen, Vefa Asli Erdemir, Mehmet Salih Gurel, Gulsum Gencoglan, Joram M. Posma, Burak Temelkuran

机构 * Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London(系统医学系,代谢、消化与生殖部,帝国理工学院伦敦分校) Department of Dermatology and Venereology, Istanbul Research and Training Hospital(皮肤科与性病科,伊斯坦布尔研究与培训医院) Department of Dermatology and Venereology, Istanbul Medeniyet University(皮肤科与性病科,伊斯坦布尔梅德尼yet大学) Department of Dermatology and Venereology, Istanbul Medicana Atakoy Hospital(皮肤科与性病科,伊斯坦布尔Medicana阿塔科伊医院)

AI总结 本研究评估了本地部署的隐私保护小型语言模型(SLM)在天疱疮患者长期随访记录中检索结构化临床特征并生成纵向摘要的能力,结果显示SLM在特征检索任务中平均准确率达82.25%,且医生对AI生成摘要的质量、临床准确性和实用性评分较高。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.18766 2026-05-26 cs.LG

Enhancing the Parameterization of Reservoir Properties for Data Assimilation Using Deep VAE-GAN

利用深度VAE-GAN增强数据同化中储层属性的参数化

M. A. Sampaio, P. H. Ranazzi, M. J. Blunt

机构 * Departamento de Engenharia de Minas e de Petróleo, Escola Politécnica, Universidade de São Paulo(圣保罗大学采矿与石油工程系,理工学院) Department of Earth Science and Engineering, Imperial College London(伦敦帝国理工学院地球科学与工程系)

AI总结 提出将VAE-GAN与ESMDA结合,以同时实现高质量储层描述和良好历史拟合,克服传统方法在非高斯分布和有限集合大小上的局限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24330 2026-05-26 cs.LG

Interdomain Attention: Beyond Token-Level Key-Value Memory

域间注意力:超越令牌级键值记忆

Naoki Kiyohara, Harrison Bo Hua Zhu, Riccardo El Hassanin, Zhuo Sun, Wenlong Chen, Samir Bhatt, Yingzhen Li

机构 * Imperial College London, UK(伦敦帝国学院) University of Copenhagen, Denmark(哥本哈根大学) Shanghai University of Finance(上海金融学院) Canon Inc., Japan(日本佳能公司) Technical University of Denmark, Denmark(丹麦技术大学)

AI总结 提出域间注意力机制,通过核方法将状态空间模型集成到注意力模块中,实现固定大小状态上的查询条件注意力,在语言建模中优于SSM和标准注意力基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24127 2026-05-26 cs.RO

Investigating the Effect of a Series Elastic Actuation Retrofit to Black-Box Actuators

研究串联弹性驱动改造对黑箱执行器的影响

Ivan Tregear, Ayhan Aktas, Ferdinando Rodriguez y Baena

机构 * Imperial College London, Mechanical Engineering Department(帝国理工学院伦敦校区机械工程系)

AI总结 通过为黑箱执行器加装串联弹性元件,利用有限元分析设计扭转弹性元件,实现了高保真力测量,将开环力控制带宽从10.32 Hz提升至30.32 Hz,提升2.93倍,且性能优于成本更高的商用传感器。

Comments Related GitHub repo available here: https://github.com/ITregear/SeriesElasticActuation-FYP

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15173 2026-05-26 cs.CL cs.AI

Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation

揭示自回归LLM在事件表示中主题适配性的知识

Safeyah Khaled Alshemali, Daniel Bauer, Yuval Marton

机构 * Imperial College London(伦敦帝国学院) Columbia University(哥伦比亚大学) University of Washington(华盛顿大学)

AI总结 通过多种提示设计、输入上下文操作、推理和输出形式,研究自回归大语言模型是否具有一致且可表达的事件参数主题适配性知识,并在基准测试上取得新最优结果。

Comments Significant update with massive changes: all experiments rerun with current LLMs; includes new probability estimate analysis and expanded results in Sections 4 and 5. The paper has been accepted to CoNLL-2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23840 2026-05-25 cs.CV

MuellerPT: Decomposition Driven Pretraining for Dense Learning in Mueller Polarimetry

MuellerPT: 穆勒偏振测量中密集学习的分解驱动预训练

Adam Tlemsani, Yingdian Li, Maxime Giot, Naim Slim, Christopher J. Peters, Abhijeet Ghosh, Daniel S. Elson

机构 * Department of Computing, Imperial College London(帝国理工学院计算机系) Hamlyn Centre for Robotic Surgery, Imperial College London(帝国理工学院机器人外科中心) Department of Surgery and Cancer, Imperial College London(帝国理工学院外科与癌症系) Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences(中国科学院西安光学精密机械研究所) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 提出MuellerPT,一种通过预测Lu-Chipman分解图进行物理引导预训练的方法,在少样本分割和分类任务中显著提升标签效率和跨样本泛化能力。

Comments Accepted to 29th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.24920 2026-05-25 cs.CR cs.AI

SUDP: Secret-Use Delegation Protocol for Agentic Systems

SUDP: 面向智能体系统的秘密使用委托协议

Xiaohang Yu, Hejia Geng, Xinmeng Zeng, William Knottenbelt

机构 * Imperial College London(伦敦帝国学院) University of Oxford(牛津大学) Stanford University(斯坦福大学)

AI总结 针对智能体系统中用户秘密被滥用的问题,提出秘密使用委托协议(SUDP),通过授权、委托和兑现机制实现一次性秘密使用,满足七项安全属性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23629 2026-05-25 cs.CV

DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs

DDX-TRACE: 视觉语言模型中医学诊断轨迹的基准

Jiazhen Pan, Weixiang Shen, Jun Li, Julian Canisius, Felix Bitzer, Paula Roßmüller, Jiancheng Yang, Virginie Kreutzinger, Daniel Rueckert, Benedikt Wiestler

机构 * Technical University of Munich(慕尼黑技术大学) TUM University Hospital(TUM大学医院) Munich Center for Machine Learning(慕尼黑机器学习中心) LMU Munich(慕尼黑大学) Aalto University(阿尔托大学) Imperial College London(伦敦帝国学院)

AI总结 提出DDX-TRACE基准,通过隐藏证据的多轮诊断轨迹评估VLM在神经放射学中的工作流质量,揭示最终诊断分数无法反映的推理缺陷。

Comments 41 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11679 2026-05-25 cs.CV

Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

面向临床的大脑MRI基础模型:来自FOMO25挑战赛的发现

Asbjørn Munk, Stefano Cerri, Vardan Nersesjan, Christian Hedeager Krag, Jakob Ambsdorf, Pablo Rocamora García, Julia Machnio, Peirong Liu, Suhyun Ahn, Nasrin Akbari, Yasmina Al Khalil, Kimberly Amador, Sina Amirrajab, Tal Arbel, Meritxell Bach Cuadra, Ujjwal Baid, Bhakti Baheti, Jaume Banus, Kamil Barbierik, Christoph Brune, Yansong Bu, Baptiste Callard, Yuhan Chen, Cornelius Crijnen, Corentin Dancette, Peter Drotar, Prasad Dutande, Nils D. Forkert, Saurabh Garg, Jakub Gazda, Matej Gazda, Benoît Gérin, Partha Ghosh, Weikang Gong, Pedro M. Gordaliza, Sam Hashemi, Tobias Heimann, Fucang Jia, Jiexin Jiang, Emily Kaczmarek, Chris Kang, Seung Kwan Kang, Mohammad Khazaei, Julien Khlaut, Petros Koutsouvelis, Jae Sung Lee, Yuchong Li, Mengye Lyu, Mingchen Ma, Anant Madabhushi, Klaus H. Maier-Hein, Pierre Manceron, Andrés Martínez Mora, Moona Mazher, Felix Meister, Nataliia Molchanova, Steven A. Niederer, Leonard Nürnberg, Jinah Park, Abdul Qayyum, Jonas Richiardi, Antoine Saporta, Branislav Setlak, Ning Shen, Justin Szeto, Constantin Ulrich, Puru Vaish, Vibujithan Vigneshwaran, Leroy Volmer, Zihao Wang, Siqi Wei, Anthony Winder, Jelmer M. Wolterink, Maxence Wynen, Chang Yang, Si Young Yie, Mostafa Mehdipour Ghazi, Akshay Pai, Espen Jimenez Solem, Sebastian Nørgaard Llambias, Mikael Boesen, Michael Eriksen Benros, Juan Eugenio Iglesias, Mads Nielsen

机构 * organization= Department of Computer Science, University of Copenhagen , city= Copenhagen , country= Denmark organization= Pioneer Centre for AI , city= Copenhagen , country= Denmark organization= Copenhagen Research Centre for Biological Precision Psychiatry, Mental Health Centre Copenhagen, Copenhagen University Hospital , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital Harvard Medical School , city= Boston , state= Massachusetts , country= USA Artificial Intelligence Laboratory, Massachusetts Institute of Technology , city= Boston , state= Massachusetts , country= USA organization= Johns Hopkins University , city= Baltimore , state= Maryland , country= USA organization= Radiological AI Testcenter (RAIT) , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Copenhagen University Hospital, Rigshospitalet , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Copenhagen University Hospital, Bispebjerg \& Frederiksberg Hospital , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Department of Clinical Medicine, Faculty of Health Medical Sciences, University of Copenhagen , city= Copenhagen , country= Denmark organization= Division of Medical Image Computing, German Cancer Research Center (DKFZ) , city= Heidelberg , country= Germany organization= University of British Columbia , city= Vancouver , state= British Columbia , country= Canada organization= Hawkes Institute, Department of Computer Science, University College London , city= London , country= United Kingdom Lung Institute, Faculty of Medicine, Imperial College London , city= London , country= United Kingdom organization= Department of Applied Mathematics, Technical Medical Centre, University of Twente , city= Enschede , country= Netherlands organization= IISLAB, Technical University of Košice , city= Košice , country= Slovakia organization= 2nd Department of Internal Medicine, Pavol Jozef Safarik University L Pasteur University Hospital , city= Košice , country= Slovakia organization= Fudan University , city= Shanghai , country= China organization= Shenzhen Technology University , city= Shenzhen , country= China organization= Department of Radiology, Lausanne University Hospital University of Lausanne , city= Lausanne , country= Switzerland organization= Louvain Neuroinflammation Imaging Lab (NIL), Université Catholique de Louvain , city= Brussels , country= Belgium organization= University of Applied Sciences organization= CIBM Center for Biomedical Imaging , city= Lausanne , country= Switzerland organization= Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology Reproduction, Maastricht University Medical Centre+ , city= Maastricht , country= The Netherlands organization= Department of Biomedical Engineering, Medical Image Analysis, Eindhoven University of Technology , city= Eindhoven , country= The Netherlands organization= Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , city= Shenzhen , country= China organization= McGill University Mila - Quebec AI Institute , city= Montreal , country= Canada organization= Hotchkiss Brain Institute Department of Radiology, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= Department of Radiology, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= Alberta Children's Hospital Research Institute, Department of Clinical Neuroscience, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= The Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech Emory University , city= Atlanta , state= Georgia , country= USA organization= SGGS College of Engineering organization= Seoul National University , city= Seoul , country= South Korea organization= The D-Lab, Department of Precision Medicine, GROW Research Institute for Oncology Reproduction, Maastricht University , city= Maastricht , country= The Netherlands organization= Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School , city= Boston , state= Massachusetts , country= USA Nuclear Medicine, CARIM \& GROW, Maastricht University , city= Maastricht , country= The Netherlands organization= Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham Women’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA Learning Group, Heidelberg University Hospital , city= Heidelberg , country= Germany

AI总结 针对临床脑MRI数据异质且标注成本高的问题,FOMO25挑战赛通过自监督预训练(FOMO60K数据集)评估了16个团队的基础模型,发现自监督预训练能提升域迁移泛化性,但不同任务需不同预训练目标,且模型规模扩展收益有限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06610 2026-05-25 cs.LG

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

CapTrack: 大语言模型后训练中遗忘的多方面评估

Lukas Thede, Stefan Winzeck, Zeynep Akata, Jonathan Richard Schwarz

机构 * Thomson Reuters Foundational Research(汤姆森路透基础研究) Tübingen AI Center, University of Tübingen(图宾根人工智能中心,图宾根大学) Munich Center for Machine Learning (MCML), Technical University Munich(慕尼黑机器学习中心(MCML),慕尼黑技术大学) Imperial College London(伦敦帝国理工学院)

AI总结 提出CapTrack框架,通过行为分类和评估套件系统分析LLM后训练中的遗忘现象,发现遗忘不仅限于参数知识,还涉及鲁棒性和默认行为的显著漂移。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14311 2026-05-25 cs.LG cs.AI

Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback

通过图结构反馈进行多重公平正则化器的在线学习

Quan Zhou, Jakub Marecek, Robert Shorten

机构 * Department of Mathematics, National University of Singapore(新加坡国立大学数学系) Department of Computer Science, Czech Technical University(捷克技术大学计算机科学系) Dyson School of Design Engineering, Imperial College London(伦敦帝国理工学院设计工程戴森学院) Imperial College London(伦敦帝国理工学院)

AI总结 本文针对在线决策中多重公平约束的权重自适应问题,提出了一种基于图结构反馈的赌博机算法,能够在不预先知道权重的情况下在线学习并平衡多个公平性目标。

Comments Published in Transactions on Machine Learning Research (TMLR), 2026. OpenReview: https://openreview.net/forum?id=y8iWuDZtEw

Journal ref Transactions on Machine Learning Research (TMLR), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22622 2026-05-22 cs.LG math.OC

A note on convergence of Wasserstein policy optimization

关于Wasserstein策略优化收敛性的注记

David Šiška, Yufei Zhang

机构 * School of Mathematics, University of Edinburgh(爱丁堡大学数学学院) Department of Mathematics, Imperial College London(伦敦帝国理工学院数学系)

AI总结 本文探讨了Wasserstein策略优化在连续状态和动作空间中的收敛性问题,通过利用均场分析和log-Sobole不等式,证明了在熵正则化的马尔可夫决策过程框架下,WPO算法能够线性收敛到全局最优解。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22549 2026-05-22 stat.ML cs.LG

A Martingale Kernel Independence Test

一个鞅核独立性检验

Felix Laumann, Zhaolu Liu, Mauricio Barahona

机构 * Imperial College London(伦敦帝国学院)

AI总结 本文提出两种学生化统计量,通过自归一化和半样本分割,实现了无需排列校准的独立性检验,显著提升了计算效率和测试性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10085 2026-05-22 cs.AI

CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs

CODE-SHARP: 连续开放发现和演化的技能作为层次奖励程序

Richard Bornemann, Pierluigi Vito Amadori, Antoine Cully

机构 * Imperial College London(帝国理工学院伦敦分校) Sony Interactive Entertainment(索尼互动娱乐)

AI总结 该研究提出CODE-SHARP框架,通过基础模型自主发现和演化技能作为层次奖励程序,实现通用智能体政策的从零开始强化学习,无需预定义奖励,有效学习长周期技能。

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21502 2026-05-22 q-bio.MN cs.AI cs.LG

Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks

图神经网络解释揭示了生物网络中与疾病相关的枢纽的拓扑特征

Kyle Higgins, Ivan Laponogov, Dennis Veselkov, Kirill Veselkov

机构 * Division of Cancer, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London(癌症部、外科与癌症部门、医学学院、伦敦帝国学院) Department of Computing, Imperial College London(计算部门、伦敦帝国学院) Department of Environmental Health Sciences, Yale University(环境健康科学部门、耶鲁大学)

AI总结 本文研究了图神经网络在生物网络中识别疾病相关结构的方法,发现不同解释方法在稀疏单节点驱动和分布式路径信号中有不同的表现,并提出了一种结合壳层枢纽评分和解释器共识排名的框架,提升了对癌症基因的优先级排序和生物学相关分子的恢复能力。

Comments 25 pages (excluding supplement), 7 figures, 7 supplementary tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02193 2026-05-22 cs.AI

From monoliths to modules: Decomposing transducers for efficient world modelling

从整体到模块:分解转换器以实现高效的world建模

Alexander Boyd, Franz Nowak, David Hyland, Manuel Baltieri, Fernando E. Rosas

机构 * Department of Informatics, University of Sussex(Sussex大学信息学院) Beyond Institute for Theoretical Science (BITS)(理论科学研究所) ETH Zürich(苏黎世联邦理工学院) Principles of Intelligent Behaviour in Biological and Social Systems (PIBBSS)(生物和社会系统智能行为原理研究所) Department of Computer Science, University of Oxford(牛津大学计算机科学系) Araya Inc.(Araya公司) Sussex AI and Sussex Centre for Consciousness Science, University of Sussex(Sussex大学人工智能与意识科学中心) Centre for Complexity Science and Center for Psychedelic Research, Department of Brain Sciences, Imperial College London(复杂科学中心和迷幻研究中心,伦敦帝国理工学院脑科学系) Center for Eudaimonia and Human Flourishing, University of Oxford(幸福与人类繁荣中心,牛津大学)

AI总结 本文提出了一种分解复杂world建模的方法,通过转换器框架将世界模型分解为多个模块,从而提高计算效率并支持分布式推理,为AI安全和现实应用提供基础。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21454 2026-05-21 cs.CV q-bio.QM q-bio.TO

ProtoPathway: Biologically Structured Prototype-Pathway Fusion for Multimodal Cancer Survival Prediction

ProtoPathway: 为多模态癌症生存预测设计的生物结构化原型-路径融合

Amaya Gallagher-Syed, Costantino Pitzalis, Myles J. Lewis, Michael R. Barnes, Gregory Slabaugh

机构 * Queen Mary University of London(伦敦女王学院) Imperial College London(帝国理工学院伦敦分校)

AI总结 本文提出ProtoPathway框架,通过统一全切片成像和转录组学,利用编码器生成生物基础的表示,以提升癌症生存预测的生物可解释性和计算效率。

Comments Currently under peer review

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.09593 2026-05-21 eess.IV cs.AI cs.CV

SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms

SMILE-UHURA挑战 -- 从超高分辨率7T磁共振血管造影中进行微血管分割

Soumick Chatterjee, Hendrik Mattern, Marc Dörner, Alessandro Sciarra, Florian Dubost, Hannes Schnurre, Rupali Khatun, Chun-Chih Yu, Tsung-Lin Hsieh, Yi-Shan Tsai, Yi-Zeng Fang, Yung-Ching Yang, Juinn-Dar Huang, Marshall Xu, Siyu Liu, Fernanda L. Ribeiro, Saskia Bollmann, Karthikesh Varma Chintalapati, Chethan Mysuru Radhakrishna, Sri Chandana Hudukula Ram Kumara, Raviteja Sutrave, Abdul Qayyum, Moona Mazher, Imran Razzak, Cristobal Rodero, Steven Niederren, Fengming Lin, Yan Xia, Jiacheng Wang, Riyu Qiu, Liansheng Wang, Arya Yazdan Panah, Rosana El Jurdi, Guanghui Fu, Janan Arslan, Ghislain Vaillant, Romain Valabregue, Didier Dormont, Bruno Stankoff, Olivier Colliot, Luisa Vargas, Isai Daniel Chacón, Ioannis Pitsiorlas, Pablo Arbeláez, Maria A. Zuluaga, Stefanie Schreiber, Oliver Speck, Andreas Nürnberger

机构 * Faculty of Computer Science, Otto von Guericke University Magdeburg(奥托·冯·格里克大学马格德堡分校计算机科学学院) Data and Knowledge Engineering Group, Otto von Guericke University Magdeburg(奥托·冯·格里克大学马格德堡分校数据与知识工程小组) Human Technopole(人类技术极地) Biomedical Magnetic Resonance, Otto von Guericke University Magdeburg(生物医学磁共振,奥托·冯·格里克大学马格德堡分校) Department of Neurology, Medical Faculty, University Hospital of Magdeburg(马格德堡大学医院医学系神经科) German Centre for Neurodegenerative Diseases(德国神经退行性疾病研究中心) Centre for Behavioural Brain Sciences, Magdeburg(行为脑科学中心,马格德堡) Department of Neurology, University Hospital Zurich(苏黎世大学医院神经科) Department of Consultation-Liaison-Psychiatry and Psychosomatic Medicine, University Hospital Zurich(苏黎世大学医院咨询-联络精神病学与心身医学科) Stanford University(斯坦福大学) Translational Radiobiology, Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg(转化放射生物学,放射肿瘤学部,埃尔兰根大学医院,埃尔兰根-纽伦堡弗里德里希-亚历山大大学) National Yang Ming Chiao Tung University(阳明交通大学) School of Electrical Engineering and Computer Science, University of Queensland(昆士兰大学电气工程与计算机科学学院) Australian eHealth Research Centre, CSIRO(澳大利亚eHealth研究中心,CSIRO) National Heart and Lung Institute, Faculty of Medicine, Imperial College London(英国伦敦帝国理工学院医学系国家心脏和肺研究所) Hawkes Institute, Department of Computer Science, University College London(霍克斯研究所,伦敦大学学院计算机科学系) School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院) Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates(阿布扎克穆罕默德·本·扎耶德人工智能大学) The Alan Turing Institute, London, UK(艾伦·图灵研究所,伦敦,英国) School of Computing, University of Leeds(利兹大学计算学院) Department of Computer Science at School of Informatics, Xiamen University(厦门大学信息学院计算机科学系) Manteia Technologies Co., Ltd, Xiamen, China(厦门Manteia技术有限公司) Leicester International Institute, Dalian University of Technology(大连理工大学利兹国际学院) Sorbonne Université, Institut du Cerveau - Paris Brain Institute(索邦大学,巴黎脑研究所) Centre of Formation and Research in Artificial Intelligence, Universidad de Los Andes, Colombia(智利洛斯安德斯大学人工智能培训与研究中心) Data Science Department, EURECOM, Sophia Antipolis, France(EURECOM数据科学系,法国索菲亚安蒂波利斯)

AI总结 该研究旨在解决公共标注数据集不足的问题,通过提供一个包含时间飞行血管造影的7T MRI标注数据集,评估了多种深度学习方法在微血管分割任务中的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21049 2026-05-21 cs.CL

Cross-lingual robustness of LLM-brain alignment and its computational roots

LLM-脑对齐的跨语言鲁棒性及其计算根源

Ni Yang, Rui He, Philipp Homan, Iris Sommer, Davide Staub, Wolfram Hinzen

机构 * Grammar and Cognition Lab, Department of Translation & Language Sciences, Universitat Pompeu Fabra(语言与翻译科学系语法与认知实验室,庞培法华大学) Department of Adult Psychiatry and Psychotherapy, University of Zurich(苏黎世大学成人精神病学与心理治疗系) Neuroscience Center Zurich, University of Zurich and ETH Zurich(苏黎世大学神经科学中心与苏黎世联邦理工学院) Center for Clinical Neuroscience and Cognition and Department of Psychiatry, University of Groningen, University Medical Center Groningen(格罗宁根大学临床神经科学与认知中心及精神病学系,格罗宁根大学医学中心) Scalable Scientific Machine Learning Lab, Imperial College London, Department of Earth Science and Engineering(伦敦帝国理工学院可扩展科学机器学习实验室,地球科学与工程系) Institut Català de Recerca i Estudis Avançats (ICREA), Barcelona, Spain(加泰罗尼亚高级研究与研究机构(ICREA),巴塞罗那,西班牙)

AI总结 该研究探讨了大型语言模型与大脑对齐的跨语言鲁棒性,通过多语言全脑编码框架分析了中文、英语和法语在自然故事听觉过程中大脑与LLM的对齐情况,发现其在空间上具有跨语言重叠性,但无法通过预测不确定性或表征几何来解释。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.20782 2026-05-21 cs.LG

Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health

因果机器学习并非万能:健康领域观察性因果推断的路线图

Donna Tjandra, Trenton Chang, Sonali Parbhoo, Rajesh Ranganath, Andre Kurepa Waschka, William Mitchell, Maggie Makar, Shalmali Joshi, Finale Doshi-Velez, Leo Anthony Celi, Jenna Wiens

机构 * Division of Computer Science and Engineering, University of Michigan(密歇根大学计算机科学与工程系) Department of Electrical and Electronic Engineering, Imperial College London(伦敦帝国理工学院电子与电气工程系) Courant Institute of Mathematical Sciences, New York University(纽约大学Courant数学科学研究所) Center for Data Science, New York University(纽约大学数据科学中心) Department of Mathematics & Statistics, Elon University(埃洛伊大学数学与统计学系) Department of Ophthalmology, Cambridge University Hospitals(剑桥大学医院眼科部) Department of Biomedical Informatics, Columbia University(哥伦比亚大学生物医学信息学系) School of Engineering and Applied Science, Harvard University(哈佛大学工程与应用科学学院) Laboratory for Computational Physiology, Institute for Medical Engineering and Science, Massachusetts Institute of Technology(麻省理工学院医学工程与科学研究所计算生理学实验室) Department of Medicine, Beth Israel Deaconess Medical Center(贝斯以色列德aconess医疗中心医学部) Department of Biostatistics, Harvard T.H. Chan School of Public Health(哈佛T.H. Chan公共卫生学院生物统计学系)

AI总结 本文探讨了因果机器学习在观察性数据中的应用,强调了验证有效性假设和合理使用因果机器学习的重要性,提出了加强因果分析严谨性和可解释性的模板。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16812 2026-05-21 cs.LG cs.CR

Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy

Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy

Youngmok Ha, Viktor Schlegel, Yidan Sun, Anil Anthony Bharath

机构 * Imperial College London(帝国理工学院伦敦分校) Imperial College London, Imperial Global Singapore(帝国理工学院伦敦分校,帝国全球新加坡)

AI总结 本文提出了一种基于雅可比矩阵的各向异性噪声重塑方法,以在局部差分隐私下提升表示的效用。该方法通过识别任务关键子空间,选择性地衰减噪声,并将标准LDP的各向同性噪声重塑为各向异性分布,从而在保持每个维度隐私预算的同时,异质地调节噪声影响,显著提升数据效用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06824 2026-05-21 cs.LG

Efficient numeracy in language models through single-token number embeddings

通过单token数字嵌入提升语言模型的数值处理效率

Linus Kreitner, Paul Hager, Jonathan Mengedoht, Georgios Kaissis, Daniel Rueckert, Martin J. Menten

机构 * Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany(人工智能在医疗和医学中的Chair,慕尼黑技术大学(TUM)和慕尼黑技术大学医院,德国慕尼黑) Department of Computing, Imperial College London, UK(计算系,伦敦帝国学院,英国) Munich Center for Machine Learning (MCML), Munich, Germany(慕尼黑机器学习中心(MCML),德国慕尼黑) Hasso Plattner Institute for Digital Engineering, University of Potsdam, Germany(哈索·platzer研究所数字工程学院,波茨坦大学,德国)

AI总结 本文提出BitTokens,一种利用IEEE 754二进制浮点表示将数字编码为单token的方法,使语言模型能更高效地处理数值计算,从而提升其解决复杂问题的能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.09723 2026-05-21 cs.CL

AI-Assisted Scientific Assessment: A Case Study on Climate Change

AI辅助的科学评估:气候变化案例研究

Christian Buck, Levke Caesar, Michelle Chen Huebscher, Massimiliano Ciaramita, Erich M. Fischer, Zeke Hausfather, Özge Kart Tokmak, Reto Knutti, Markus Leippold, Joseph Ludescher, Katharine J. Mach, Sofia Palazzo Corner, Kasra Rafiezadeh Shahi, Johan Rockström, Joeri Rogelj, Boris Sakschewski

机构 * Potsdam Institute for Climate Impact Research (PIK), Member of the Leibniz Association(波茨坦气候影响研究所(PIK),莱比锡协会成员) Institute for Atmospheric and Climate Science, ETH Zurich(大气与气候科学研究所,苏黎世联邦理工学院) University of Zurich(苏黎世大学) University of Miami(迈阿密大学) Centre for Environmental Policy, Imperial College London(伦敦帝国理工学院环境政策中心) Grantham Institute for Climate Change and Environment, Imperial College London(伦敦帝国理工学院气候变化与环境研究所) Energy, Climate and Environment Program, International Institute for Applied Systems Analysis(国际应用系统分析研究所能源、气候与环境项目)

AI总结 本文探讨了AI在科学评估中的应用,通过与气候科学领域13名科学家的合作,测试了基于Gemini的AI环境在评估大西洋经向翻转环流(AMOC)稳定性方面的效果,展示了AI在加速科学流程和提升报告质量方面的贡献,同时强调了专家补充和监督的重要性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.00470 2026-05-20 cs.LG cs.CV

Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection

少即是多:通过最小可解释子集选择实现高效的黑盒属性分析

Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Li Liu, Hua Zhang, Xiaochun Cao

机构 * Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所) University of Chinese Academy of Sciences(中国科学院大学) College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院) School of Artificial Intelligence, University of Science and Technology Beijing(北京科技大学人工智能学院) Department of Mechanical Engineering, Imperial College London(伦敦帝国理工学院机械工程系) Center for Machine Vision and Signal Analysis (CMVS), University of Oulu(奥卢大学机器视觉与信号分析中心) School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区计算机科学与技术学院)

AI总结 本文提出了一种高效的黑盒属性分析方法LiMA,通过将重要区域的属性分析转化为子模函数子集选择的优化问题,以更少的区域提供更准确的解释,并在多个基准模型上展示了显著的改进。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17581 2026-05-20 math.OC cs.LG

Time-optimal neural feedback control of nilpotent systems as a binary classification problem

时间最优神经反馈控制的nilpotent系统作为二分类问题

Sara Bicego, Samuel Gue, Dante Kalise, Nelly Villamizar

机构 * Department of Mathematics, Imperial College London, United Kingdom(伦敦帝国学院数学系,英国) Department of Mathematics, Swansea University, United Kingdom(斯旺西大学数学系,英国)

AI总结 本文提出了一种用于线性nilpotent系统时间最优反馈控制律合成的计算方法,通过将问题转化为二分类问题来构建时间最优深度神经网络。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.18835 2026-05-20 cs.LG

StampFormer: A Physics-Guided Material-Geometry-Coupled Multimodal Model for Rapid Prediction of Physical Fields in Sheet Metal Stamping

StampFormer: 一种基于物理的材料-几何耦合多模态模型,用于快速预测冲压板料的物理场

Jiajie Luo, Mohamed Mohamed, Osama Hassan, Haosu Zhou, Yingxue Zhao, Haoran Li, Xinrun Li, Zhutao Shao, Yang Long, Nan Li, Jichun Li

机构 * Dyson School of Design Engineering, Imperial College London(帝国理工学院设计工程学院) School of Computing, Newcastle University(新castle大学计算机学院) Department of Computing, Imperial College London(帝国理工学院计算系) Multi-X Solution Limited(Multi-X解决方案有限公司) Department of Computer Science, Durham University(达勒姆大学计算机科学系) Department of Mechanical Engineering, Faculty of Engineering, Helwan University(Helwan大学工程学院机械工程系)

AI总结 本文提出StampFormer模型,通过结合材料和几何信息,实现对冲压板料物理场的快速准确预测,从而提高设计效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.18553 2026-05-19 cs.CV cs.AI

StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video

StableHand: 世界空间双臂运动估计中的质量感知流匹配

Huajian Zeng, Chaohua Yao, Yuantai Zhang, Jiaqi Yang, Rolandos Alexandros Potamias, Xingxing Zuo

机构 * Mohamed bin Zayed University of Artificial Intelligence(莫扎德·本·泽德人工智能大学) University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Imperial College London(伦敦帝国理工学院)

AI总结 本文提出StableHand,一种质量感知的流匹配框架,用于从第一人称视频中恢复世界空间双臂的4D运动,通过分解手部姿态估计器提取的观测质量为四个通道,并利用学习的质量网络预测质量信号,以提高运动估计的鲁棒性。

Comments Project Page: https://huajian-zeng.github.io/projects/stablehand/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.18226 2026-05-19 cs.CL cs.AI

Context Memorization for Efficient Long Context Generation

上下文记忆用于高效长上下文生成

Yasuyuki Okoshi, Hao Mark Chen, Guanxi Lu, Hongxiang Fan, Masato Motomura, Daichi Fujiki

机构 * Institute of Science Tokyo, Japan(东京科学研究所) Imperial College London, UK(伦敦帝国学院)

AI总结 本文提出了一种无需训练的上下文记忆方法,通过将前缀外部化为轻量级的预计算注意力状态查找表,以提高长上下文生成的准确性和效率,同时减少注意力计算的延迟。

详情

展开后加载摘要…

URL PDF HTML 收藏