arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Cambridge(剑桥大学)

共收录 1290
2601.16900 2026-01-26 cs.LG cs.CV

Embedding -based Crop Type Classification in the Groundnut Basin of Senegal

基于嵌入的塞内加尔花生盆地作物类型分类

Madeline C. Lisaius, Srinivasan Keshav, Andrew Blake, Clement Atzberger

机构 * The University of Cambridge Department of Computer Science(剑桥大学计算机科学系) dClimate Labs(dClimate实验室)

AI总结 本文提出基于TESSERA嵌入的方法,用于提高塞内加尔花生盆地作物类型分类的准确性,实验显示其比现有方法更有效。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.16429 2026-01-26 cs.CV cs.AI

AlphaFace: High Fidelity and Real-time Face Swapper Robust to Facial Pose

AlphaFace: 高保真和实时的面部交换器,对面部姿态具有鲁棒性

Jongmin Yu, Hyeontaek Oh, Zhongtian Sun, Angelica I Aviles-Rivero, Moongu Jeon, Jinhong Yang

机构 * University of Cambridge(剑桥大学) University of Kent(肯特大学) Tsinghua University(清华大学) Gwangju Institute of Science and Technology(全州科学技术院) Inje University(庆北大学)

AI总结 AlphaFace通过结合视觉-语言模型和CLIP嵌入,实现高保真和实时的面部交换,提升对极端面部姿态的鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.16276 2026-01-26 cs.CL cs.AI cs.GT cs.LG cs.MA

GameTalk: Training LLMs for Strategic Conversation

GameTalk: 训练 LLMs 进行战略性对话

Victor Conchello Vendrell, Max Ruiz Luyten, Mihaela van der Schaar

机构 * University of Cambridge(剑桥大学)

AI总结 GameTalk 通过多轮互动训练 LLMs 实现战略性决策,优于传统方法,尤其在奖励塑造下表现突出。

Comments 32 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15824 2026-01-26 cs.CR cs.AI

Introducing the Generative Application Firewall (GAF)

引入生成应用防火墙(GAF)

Joan Vendrell Farreny, Martí Jordà Roca, Miquel Cornudella Gaya, Rodrigo Fernández Baón, Víctor García Martínez, Eduard Camacho Sucarrats, Alessandro Pignati

机构 * University of the Aegean(爱琴海大学) University of Cambridge(剑桥大学) OWASP GenAI Security Project(OWASP生成式AI安全项目) University of Liverpool(利物浦大学) MIT Computer Science and Artificial Intelligence Laboratory(MIT计算机科学与人工智能实验室) Center for AI and Digital Policy(人工智能与数字政策中心) Huawei(华为) Cloud Security Alliance(云安全联盟)

AI总结 本文提出GAF,一种统一保护LLM应用的架构层,整合现有防御措施并扩展至自主代理与工具交互。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.08991 2026-01-26 cs.LG cs.SE

Optimising for Energy Efficiency and Performance in Machine Learning

在机器学习中优化能耗与性能

Emile Dos Santos Ferreira, Andrei Paleyes, Neil D. Lawrence

机构 * University of Cambridge(剑桥大学) Pasteur Labs(Pasteur实验室)

AI总结 本文提出ECOpt工具,通过优化能耗与性能平衡,提升机器学习模型的环境效益和性能表现。

Comments Accepted to CAIN'26

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06230 2026-01-26 cs.AI

Learning Logical Rules using Minimum Message Length

通过最小信息量学习逻辑规则

Ruben Sharma, Sebastijan Dumančić, Ross D. King, Andrew Cropper

机构 * University of Cambridge(剑桥大学) Delft University of Technology(代尔夫特理工大学) Chalmers University of Technology(查尔姆斯理工大学) University of Helsinki(赫尔辛基大学)

AI总结 本文提出了一种基于最小信息量的逻辑规则学习方法,通过平衡假设复杂性与数据拟合,实现了在多个领域中的高效学习。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10805 2026-01-26 cs.LG

Detecting High-Stakes Interactions with Activation Probes

通过激活探针检测高风险交互

Alex McKenzie, Urja Pawar, Phil Blandfort, William Bankes, David Krueger, Ekdeep Singh Lubana, Dmitrii Krasheninnikov

机构 * LASR Labs(LASR实验室) University College London(伦敦大学学院) MILA Harvard University(哈佛大学) NTT Research(NTT研究所) Goodfire University of Cambridge(剑桥大学)

AI总结 通过激活探针检测高风险交互,实现高效且资源敏感的监控系统

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15293 2026-01-23 cs.HC cs.RO

Social Robotics for Disabled Students: An Empirical Investigation of Embodiment, Roles and Interaction

面向残疾学生的社会机器人:关于具身性、角色和互动的经验研究

Alva Markelius, Fethiye Irmak Doğan, Julie Bailey, Guy Laban, Jenny L. Gibson, Hatice Gunes

机构 * University of Cambridge, CST(剑桥大学,CST) University of Cambridge, EDUC(剑桥大学,EDUC)

AI总结 本研究探讨残疾学生对基于机器人的支持的感知,比较不同互动角色和具身类型的影响,揭示具身性对社会性和隐私感知的作用,以及不同残疾类型间的差异。

Comments Preprint. Accepted at ACM IEEE International Conference on Human Robot Interaction 2026, Edinburgh, Scotland, UK

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06299 2026-01-23 cs.CY cs.AI cs.CL cs.LG

How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare

恶意AI群如何威胁民主:代理AI与大语言模型的融合标志着信息战争的新前沿

Daniel Thilo Schroeder, Meeyoung Cha, Andrea Baronchelli, Nick Bostrom, Nicholas A. Christakis, David Garcia, Amit Goldenberg, Yara Kyrychenko, Kevin Leyton-Brown, Nina Lutz, Gary Marcus, Filippo Menczer, Gordon Pennycook, David G. Rand, Maria Ressa, Frank Schweitzer, Dawn Song, Christopher Summerfield, Audrey Tang, Jay J. Van Bavel, Sander van der Linden, Jonas R. Kunst

机构 * Department of Sustainable Communication Technologies, SINTEF Digital(可持续通信技术系,SINTEF数字) Max Planck Institute for Security and Privacy(安全与隐私研究所) Department of Mathematics, City St George’s University of London(数学系,圣乔治大学) Macrostrategy Research Initiative(战略研究计划) Human Nature Lab, Yale University(人性实验室,耶鲁大学) Department of Politics and Public Administration, University of Konstanz(政治与公共管理系,康斯坦茨大学) Harvard Business School, Harvard University(哈佛商学院,哈佛大学) Department of Psychology, University of Cambridge(心理学系,剑桥大学) Department of Computer Science, University of British Columbia(计算机科学系,不列颠哥伦比亚大学) Department of Human Centered Design & Engineering, University of Washington(以人为本设计与工程系,华盛顿大学) Department of Psychology, New York University(心理学系,纽约大学) Observatory on Social Media and Luddy School of Informatics, Computing, and Engineering, Indiana University(社交媒体观察所和信息、计算与工程学院,印第安纳大学)

AI总结 本文探讨了恶意AI群通过融合代理AI与大语言模型对民主构成的威胁,并提出多方面的干预措施。

Comments 5 Pages, This is the author's version of the work. It is posted here by permission of the AAAS for personal use, not for redistribution. The definitive version was published in Science on January 22, 2026, DOI: 10.1126/science.adz1697

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15254 2026-01-22 stat.ML cs.AI cs.LG

Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible?

大量实验、少量重复、不配对数据和稀疏效应:因果推断是否可能?

Felix Schur, Niklas Pfister, Peng Ding, Sach Mukherjee, Jonas Peters

机构 * Department of Mathematics, ETH Zurich(苏黎世联邦理工学院数学系) Department of Statistics, UC Berkeley(伯克利大学统计系) German Center for Neurodegenerative Diseases (DZNE) & University of Bonn(德国神经退行性疾病研究中心(DZNE)及波恩大学) MRC Biostatistics Unit, University of Cambridge(剑桥大学医学研究委员会生物统计学单位)

AI总结 本文提出了一种在不配对数据和稀疏因果效应下,通过GMM型估计量和ℓ1正则化方法估计因果效应的统计方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15164 2026-01-22 cs.RO cs.AI

V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks

V-CAGE:面向可扩展长时间跨度具身任务的上下文感知生成与验证

Yaru Liu, Ao-bo Wang, Nanyang Ye

机构 * Department of Computer Science and Technology, University of Cambridge, Cambridge, England.(计算机科学与技术系,剑桥大学,剑桥,英格兰) Shanghai Jiao Tong University, Shanghai, China(上海交通大学,上海,中国) Wuhan University, Wuhan, Hubei, China(武汉大学,武汉,湖北,中国)

AI总结 V-CAGE通过上下文感知生成与验证框架,提升大规模具身任务数据集的物理和语义保真度,提高下游策略性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14235 2026-01-22 astro-ph.IM astro-ph.CO cs.AI cs.LG stat.ML

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

人工智能/机器学习在Rubin LSST暗能量科学合作中的机遇

LSST Dark Energy Science Collaboration, Eric Aubourg, Camille Avestruz, Matthew R. Becker, Biswajit Biswas, Rahul Biswas, Boris Bolliet, Adam S. Bolton, Clecio R. Bom, Raphaël Bonnet-Guerrini, Alexandre Boucaud, Jean-Eric Campagne, Chihway Chang, Aleksandra Ćiprijanović, Johann Cohen-Tanugi, Michael W. Coughlin, John Franklin Crenshaw, Juan C. Cuevas-Tello, Juan de Vicente, Seth W. Digel, Steven Dillmann, Mariano Javier de León Dominguez Romero, Alex Drlica-Wagner, Sydney Erickson, Alexander T. Gagliano, Christos Georgiou, Aritra Ghosh, Matthew Grayling, Kirill A. Grishin, Alan Heavens, Lindsay R. House, Mustapha Ishak, Wassim Kabalan, Arun Kannawadi, François Lanusse, C. Danielle Leonard, Pierre-François Léget, Michelle Lochner, Yao-Yuan Mao, Peter Melchior, Grant Merz, Martin Millon, Anais Möller, Gautham Narayan, Yuuki Omori, Hiranya Peiris, Laurence Perreault-Levasseur, Andrés A. Plazas Malagón, Nesar Ramachandra, Benjamin Remy, Cécile Roucelle, Jaime Ruiz-Zapatero, Stefan Schuldt, Ignacio Sevilla-Noarbe, Ved G. Shah, Tjitske Starkenburg, Stephen Thorp, Laura Toribio San Cipriano, Tilman Tröster, Roberto Trotta, Padma Venkatraman, Amanda Wasserman, Tim White, Justine Zeghal, Tianqing Zhang, Yuanyuan Zhang

机构 * Université Paris Cité, CNRS, CEA, Astroparticule et Cosmologie, F-75013 Paris, France Department of Physics, University of Michigan, Ann Arbor, MI 48109, USA Leinweber Institute of Theoretical Physics, University of Michigan, Ann Arbor, MI 48109, USA Argonne National Laboratory, 9700 South Cass Avenue, Lemont, IL 60439, USA Cavendish Astrophysics, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK Kavli Institute for Cosmology, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK SLAC National Accelerator Laboratory, Menlo Park, CA 94025, USA Department of Computer Science, University of Milan, Milan, Italy Université Paris Cité, CNRS, Astroparticule et Cosmologie, F-75013 Paris, France Université Paris-Saclay, CNRS/IN2P3, IJCLab, 91405 Orsay, France Department of Astronomy Astrophysics, University of Chicago, Chicago, IL 60637, USA Kavli Institute for Cosmological Physics, University of Chicago, Chicago, IL 60637, USA NSF-Simons AI Institute for the Sky (SkAI), 172 E. Chestnut St., Chicago, IL 60611, USA Fermi National Accelerator Laboratory, P.O. Box 500, Batavia, IL 60510, USA Universit\'e Clermont-Auvergne, CNRS, LPCA, 63000 Clermont-Ferrand, France Kavli Institute for Particle Astrophysics Cosmology, Stanford University, Stanford, CA 94305, USA Department of Physics, Stanford University, 382 Via Pueblo Mall, Stanford, CA 94305, USA Engineering Faculty, Universidad Autonoma de San Luis Potosi, Zona Universitaria, San Luis Potosi, 78290, Mexico Stanford Artificial Intelligence Laboratory, Stanford University, Stanford, CA 94305, USA Kavli Institute of Cosmological Physics, University of Chicago, Chicago, IL 60637, USA The NSF AI Institute for Artificial Intelligence Center for Astrophysics Harvard \& Smithsonian, 60 Garden Street, Cambridge, MA 02138, USA Department of Physics Kavli Institute for Astrophysics Space Research, Massachusetts Institute of Technology, Cambridge, MA 02139, USA Institut de Física d'Altes Energies (IFAE), The Barcelona Institute of Science Institute of Astronomy Kavli Institute for Cosmology, University of Cambridge, Madingley Road, Cambridge, CB3 0HA, UK Imperial Centre for Inference Cosmology (ICIC), Imperial College London, Blackett Laboratory, Prince Consort Road, London SW7 2AZ, UK Data Science Institute, The University of Chicago, Chicago, IL 60615, USA Department of Physics, The University of Texas at Dallas, Richardson, TX 75080, USA Department of Physics, Duke University, Durham, NC 27708, USA Université Paris-Saclay, Université Paris Cité, CEA, CNRS, AIM, F-91191 Gif-sur-Yvette, France School of Mathematics, Statistics Physics, Newcastle University, Newcastle upon Tyne, NE1 7RU, United Kingdom Department of Astrophysical Sciences, Princeton University, Princeton, NJ 08544, USA Astronomy, University of the Western Cape, Bellville, Cape Town, 7535, South Africa Astronomy, University of Utah, Salt Lake City, UT 84112, USA Department of Astrophysical Sciences, Princeton University, Peyton Hall, Princeton, NJ 08544, USA Department of Astronomy, University of Illinois Urbana Champaign, 1002 W. Green St., Urbana, IL, 61801, USA Institute for Particle Physics Astrophysics, ETH Zürich, Wolfgang-Pauli-Strasse 27, CH-8093 Zurich, Switzerland Swinburne University of Technology, Hawthorn, Victoria 3122, Australia Ciela - Montr\'eal Institute for Astrophysical Data Analysis Mila - Quebec Artificial Intelligence Institute, Montréal, QC H2S 3H1, Canada Advanced Research Computing Centre, University College London, 90 High Holborn, London WC1V 6LJ, UK Finnish Centre for Astronomy with ESO (FINCA), University of Turku, FI-20014 Turku, Finland Department of Physics, P.O. Box 64, University of Helsinki, FI-00014 Helsinki, Finland Astronomy, Northwestern University, Evanston, IL, USA Center for Interdisciplinary Exploration Research in Astrophysics, Northwestern University, Evanston, IL, USA Scientific Data Science, International School for Advanced Study, Via Bonomea 265, I-34136 Trieste, Italy Department of Statistics, University of Michigan, Ann Arbor, MI 48109, USA PITT PACC, University of Pittsburgh, Pittsburgh, PA 15260, USA NSF NOIRLab, 950 N. Cherry Ave., Tucson, AZ 85719, USA

AI总结 本文探讨了AI/ML在LSST暗能量科学合作中的应用机遇,强调了大规模贝叶斯推断、物理指导方法和主动学习等关键方法学优先事项,并讨论了新兴技术在重塑工作流程中的潜力。

Comments 84 pages. This is v1.0 of the DESC's white paper on AI/ML, a collaboration document that is being made public but which is not planned for submission to a journal

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14027 2026-01-21 cs.AI

Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics

Numina-Lean-Agent: 一种面向形式数学的开放且通用的代理推理系统

Junqi Liu, Zihao Zhou, Zekai Zhu, Marco Dos Santos, Weikun He, Jiawei Liu, Ran Wang, Yunzhou Xie, Junqiao Zhao, Qiufeng Wang, Lihong Zhi, Jia Li, Wenda Li

机构 * Academy of Mathematics and Systems Science, University of Chinese Academy of Sciences(中国科学院数学与系统科学研究院) Tongji University(同济大学) University of Cambridge(剑桥大学) Imperial College London(伦敦帝国学院) University of Edinburgh(爱丁堡大学) University of Liverpool(利物浦大学) Xi'an Jiaotong-Liverpool University(西安交通大学利物浦大学)

AI总结 Numina-Lean-Agent通过通用编码代理实现形式数学推理,解决Putnam 2025全部问题并成功形式化Brascamp-Lieb定理。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.13885 2026-01-21 cs.CL cs.AI

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores

在更少项目中获得可靠的排名:基于连续评分的自适应LLM评估

Esma Balkır, Alice Pernthaller, Marco Basaldella, José Hernández-Orallo, Nigel Collier

机构 * Trismik Leverhulme Centre for the Future of Intelligence, University of Cambridge(Leverhulme智能未来研究中心,剑桥大学) Universitat Politècnica de València(瓦伦西亚理工大学) University of Cambridge(剑桥大学)

AI总结 本文提出了一种基于连续评分的自适应LLM评估方法,通过异方差正态分布替代伯努利分布,实现更高效的模型排名,使用2%的项目提升了排名相关性并达到95%的准确率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.03597 2026-01-21 cs.CL cs.AI

From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs

从链式到图式:面向通用领域LLM的自结构化推理

Yingjian Chen, Haoran Liu, Yinhong Liu, Sherry T. Tong, Aosong Feng, Jinghui Lu, Juntao Zhang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

机构 * University of Tokyo(东京大学) Texas A&M University(德克萨斯大学) University of Cambridge(剑桥大学) Yale University(耶鲁大学) Xiaomi EV(小米电动汽车) Henan University(河南大学)

AI总结 本文提出自图推理框架SGR,通过结构化图表示提升LLM在通用领域问答中的推理一致性与准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.13079 2026-01-21 cond-mat.dis-nn cs.LG cs.NE physics.optics

Polychronous Wave Computing: Timing-Native Address Selection in Spiking Networks

多时序波计算:脉冲神经网络中的时序本征寻址

Natalila G. Berloff

机构 * Department of Applied Mathematics and Theoretical Physics, University of Cambridge(应用数学与理论物理系,剑桥大学)

AI总结 多时序波计算通过相位编码和并行模板相关性评估,实现高效的脉冲神经网络路由与地址选择。

Comments 23 pages, Supplementary Materials are available at https://www.damtp.cam.ac.uk/user/ngb23/publications/SM_PWC.pdf

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12893 2026-01-21 cs.LG cs.AI

AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs

AdaNODEs: 利用神经ODEs实现时间序列预测的测试时间适应

Ting Dang, Soumyajit Chatterjee, Hong Jia, Yu Wu, Flora Salim, Fahim Kawsar

机构 * The University of Melbourne, Australia(墨尔本大学) Nokia Bell Labs, UK(诺基亚贝尔实验室) The University of Auckland, New Zealand(奥克兰大学) University of Cambridge, UK(剑桥大学) The University of New South Wales, Australia(新南威尔士大学) University of Glasgow, UK(格拉斯哥大学)

AI总结 AdaNODEs通过神经ODEs提出了一种无源测试时间适应方法,专门针对时间序列预测任务,有效提升了模型在分布变化中的适应性和预测性能。

Comments Accepted by ICASSP 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11518 2026-01-19 cs.CL

How Long Is a Piece of String? A Brief Empirical Analysis of Tokenizers

字符串有多长?对分词器的简要实证分析

Jonathan Roberts, Kai Han, Samuel Albanie

机构 * University of Cambridge(剑桥大学) The University of Hong Kong(香港大学)

AI总结 本文通过实证分析揭示了不同分词器和文本分布下token长度的显著差异,挑战了传统对token长度的简化假设。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11516 2026-01-19 stat.ML cs.LG physics.chem-ph physics.comp-ph

FEAT: Free energy Estimators with Adaptive Transport

FEAT: 基于自适应传输的自由能估计器

Jiajun He, Yuanqi Du, Francisco Vargas, Yuanqing Wang, Carla P. Gomes, José Miguel Hernández-Lobato, Eric Vanden-Eijnden

机构 * University of Cambridge(剑桥大学) Cornell University(康奈尔大学) Xaira Therapeutics ML Lab, Capital Fund Management(ML实验室,资本基金管理公司) Courant Institute of Mathematical Sciences, NYU(纽约大学数学科学学院)

AI总结 FEAT提出了一种基于自适应传输的自由能估计框架,通过结合平衡与非平衡方法,提供一致且方差最小的估计器,并在多个科学领域中验证了其有效性。

Comments Accepted to NeurIPS 2025; the first two authors contribute equally to this work

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00928 2026-01-19 cs.LG cs.AI

Superposition in Graph Neural Networks

图神经网络中的叠加

Lukas Pertl, Han Xuanyuan, Pietro Liò

机构 * University of Cambridge(剑桥大学)

AI总结 本文研究了图神经网络中特征方向的共享,通过实验揭示了宽度、池化和激活函数对模型几何结构的影响,提出了更可解释的GNN设计方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06125 2026-01-19 math.OC cs.IT cs.LG math.IT math.PR

Convergence of linear programming hierarchies for Gibbs states of spin systems

线性规划层次在自旋系统吉布斯态下的收敛性

Hamza Fawzi, Omar Fawzi

机构 * DAMTP, University of Cambridge, United Kingdom(剑桥大学 DAMTP 实验室,英国) Univ Lyon, Inria, ENS Lyon, UCBL, LIP, France(里昂大学,法国国家信息与自动化技术研究院,里昂高等师范学校, UCBL,LIP,法国)

AI总结 本文研究了两种线性规划层次在自旋系统吉布斯态下的收敛性,证明了在空间混合和马尔可夫链快速混合条件下,能够高效近似局部期望值并提供严格上下界。

Comments 11 pages

Journal ref Transactions on Machine Learning Research (11/2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09421 2026-01-16 cs.CL cs.AI

Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing

BabyLMs中的偏见动态:朝着更高效的计算 sandbox 以民主化预训练去偏研究

Filip Trhlik, Andrew Caines, Paula Buttery

机构 * Department of Computer Science & Technology, University of Cambridge(计算机科学与技术系,剑桥大学) ALTA Institute, University of Cambridge(ALTA研究所,剑桥大学)

AI总结 通过低成本BabyLMs研究偏见动态,降低预训练成本,促进公平语言模型的民主化研究。

Comments 21 pages, 18 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22310 2026-01-16 cs.LG cs.AI cs.CV

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

从沉睡到删除:通过权重空间正则化实现抗篡改的遗忘

Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer, Eleni Triantafillou

机构 * University of Cambridge(剑桥大学) The Alan Turing Institute(艾伦·图灵研究所) Mila(Mila研究所) Google DeepMind(谷歌DeepMind)

AI总结 通过权重空间正则化方法,提升大型语言模型对重新学习攻击的抗性,实现从沉睡到删除的高效遗忘机制。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03055 2026-01-16 cs.LG cs.AI

Permissive Information-Flow Analysis for Large Language Models

宽松的信息流分析用于大型语言模型

Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf, David Krueger, Andrew Paverd, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Menglin Xia, Santiago Zanella-Béguelin

机构 * University of Cambridge(剑桥大学) Microsoft(微软公司) Mila

AI总结 本文提出了一种更宽松的信息流分析方法,通过传播对模型输出有影响的样本标签来提高大型语言模型的安全性和隐私保护效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09697 2026-01-15 cs.CV

Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering

通过稀疏扩散和3D渲染实现静态场景的高效摄像机控制视频生成

Jieying Chen, Jeffrey Hu, Joan Lasenby, Ayush Tewari

机构 * University of Cambridge(剑桥大学)

AI总结 本文提出SRENDER方法,通过稀疏扩散和3D渲染生成静态场景的高效视频,使视频生成速度提升40倍,保持高质量和稳定性。

Comments Project page: https://ayushtewari.com/projects/srender/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04562 2026-01-15 cs.LG

LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models

LeMat-GenBench:一种统一的晶体生成模型评估框架

Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui, Andy Xu, Georgia Channing, Daniel Levy, Clémentine Fourrier, Nikita Kazeev, Chaitanya K. Joshi, Sékou-Oumar Kaba, Félix Therrien, Alex Hernandez-Garcia, Rocío Mercado, N. M. Anoop Krishnan, Alexandre Duval

机构 * Harvey Mudd College, USA(哈维·穆德学院,美国) National University of Singapore, Singapore(新加坡国立大学) University of Cambridge, UK(剑桥大学) Chalmers University of Technology, Sweden(瑞典查尔姆斯理工大学) Indian Institute of Technology Delhi, India(印度德里理工学院)

AI总结 LeMat-GenBench通过统一的评估框架和指标,评估晶体生成模型的稳定性与多样性,揭示稳定性与新颖性之间的权衡,为生成模型的发展提供指导。

Comments 46 pages, 17 figures, 16 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.19828 2026-01-15 cs.CL cs.MA

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Memory-R1: 通过强化学习增强大语言模型代理以管理并利用记忆

Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schütze, Volker Tresp, Yunpu Ma

机构 * Ludwig Maximilian University of Munich(慕尼黑路德维希-马克西米利安大学) Munich Center for Machine Learning(慕尼黑机器学习中心) Technical University of Munich(慕尼黑技术大学) University of Cambridge(剑桥大学) University of Hong Kong(香港大学) Technical University of Darmstadt(达姆施塔特技术大学) University of Edinburgh(爱丁堡大学)

AI总结 Memory-R1通过强化学习框架,使大语言模型具备主动管理与利用外部记忆的能力,有效提升长跨度推理性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13658 2026-01-14 stat.ML cs.LG

Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder

通过物理信息变分自编码器进行对抗性解缠

Ioannis Christoforos Koune, Alice Cicirello

机构 * Department of Civil Engineering and Geosciences(土木工程与地球科学系) Technical University of Delft(代尔夫特理工大学) Department of Engineering(工程系) University of Cambridge(剑桥大学)

AI总结 本文提出了一种结合物理信息和数据驱动的变分自编码器,用于解缠输入信号中的物理因素与混杂影响,提升模型的可解释性和泛化能力。

Journal ref DCE 6 (2025) e50

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14725 2026-01-14 cs.RO cs.HC

Using Mobile AR for Rapid Feasibility Analysis for Deployment of Robots: A Usability Study with Non-Expert Users

利用移动AR进行机器人部署的快速可行性分析:非专家用户的可用性研究

Krzysztof Zielinski, Slawomir Tadeja, Bruce Blumberg, Mikkel Baun Kjærgaard

机构 * Faculty of Engineering, University of Southern Denmark(南部丹麦大学工程学院) Universal Robots A/S(Universal Robots公司) Department of Engineering, University of Cambridge(剑桥大学工程学院)

AI总结 本研究提出了一种基于移动AR的非专家用户可用性工具,用于快速评估机器人部署的可行性,通过实验表明该工具在十分钟内可完成复杂分析,且用户认知负荷低,具有高可用性。

Comments Accepted in IEEE RA-L

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00568 2026-01-14 cs.CV cs.AI cs.LG

Generating crossmodal gene expression from cancer histopathology improves multimodal AI predictions

从癌症组织病理学生成跨模态基因表达以提高多模态AI预测

Samiran Dey, Christopher R. S. Banerji, Partha Basuchowdhuri, Sanjoy K. Saha, Deepak Parashar, Tapabrata Chakraborti

机构 * School of Mathematical & Computational Sciences, Indian Association for the Cultivation of Science(数学与计算科学学院,印度科学培养协会) The Alan Turing Institute(艾伦·图灵研究所) Comprehensive Cancer Center, King’s College London(国王学院综合癌症中心) Department of Computer Science and Engineering, Jadavpur University(计算机科学与工程系,贾瓦德pur大学) MRC Biostatistics Unit, University of Cambridge(剑桥大学医学研究委员会生物统计学单位) Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University(生物统计学、生物信息学与生物数学系,杰斐逊大学) UCL Cancer Institute, Dept of Medical Physics & Biomedical Engineering, University College London(伦敦大学学院癌症研究所,医学物理与生物医学工程系)

AI总结 PathGen通过生成跨模态基因表达提升癌症分级和生存风险预测的多模态AI性能

详情

展开后加载摘要…

URL PDF HTML 收藏