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
2511.19390 2025-11-25 cs.LG astro-ph.SR cs.AI stat.ML

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

通过多尺度推理方案利用扩散模型预测部分可观测的动力系统

Rudy Morel, Francesco Pio Ramunno, Jeff Shen, Alberto Bietti, Kyunghyun Cho, Miles Cranmer, Siavash Golkar, Olexandr Gugnin, Geraud Krawezik, Tanya Marwah, Michael McCabe, Lucas Meyer, Payel Mukhopadhyay, Ruben Ohana, Liam Parker, Helen Qu, François Rozet, K. D. Leka, François Lanusse, David Fouhey, Shirley Ho

机构 * The Polymathic AI Collaboration(多学科人工智能协作) Flatiron Institute(Flatiron研究所) University of Geneva(日内瓦大学) FHNW(FHNW大学) Princeton University(普林斯顿大学) New York University(纽约大学) University of Cambridge(剑桥大学) University of Kyiv(基辅大学) University of California, Berkeley(加州大学伯克利分校) University of Liège(列日大学) NorthWest Research Associates(北威州研究协会) Nagoya University(名古屋大学) Université Paris-Saclay, Université Paris Cité, CEA, CNRS, AIM(巴黎萨克雷大学、巴黎cité大学、CEA、CNRS、AIM)

AI总结 本文提出一种多尺度推理方案,利用扩散模型有效预测部分可观测的长记忆动力系统,应用于太阳动态和活跃区域演化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00416 2025-11-25 cs.RO cs.CV

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding

Evo-0:具有隐式空间理解的视觉-语言-动作模型

Tao Lin, Gen Li, Yilei Zhong, Yanwen Zou, Yuxin Du, Jiting Liu, Encheng Gu, Bo Zhao

机构 * School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院) EvoMind Tech(EvoMind科技) IAAR-Shanghai(IAAR-上海) University of Cambridge(剑桥大学)

AI总结 Evo-0通过隐式整合3D几何特征,提升视觉-语言-动作模型在现实世界中的空间理解能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16001 2025-11-25 cs.LG cs.AI

AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Prediction

AutoHFormer:高效的层次自回归变换器用于时间序列预测

Qianru Zhang, Honggang Wen, Ming Li, Dong Huang, Siu-Ming Yiu, Christian S. Jensen, Pietro Liò

机构 * School of Computing and Data Science, The University of Hong Kong (HKU)(计算与数据科学学院,香港大学) Zhejiang Key Laboratory of Intelligent Education Technology and Application, Zhejiang Normal University (ZJNU)(智能教育技术与应用浙江省重点实验室,浙江师范大学) Department of Computer Science, National University of Singapore (NUS)(计算机科学系,新加坡国立大学) Department of Computer Science, Aalborg University (AU)(计算机科学系,奥尔堡大学) Department of Computer Science and Technology, Cambridge University (Cambridge)(计算机科学与技术系,剑桥大学)

AI总结 AutoHFormer通过层次时间建模、动态窗口注意力和自适应时间编码,实现了高效且精确的时间序列预测,训练速度提升10.76倍,内存减少6.06倍。

Comments 14 pages

Journal ref ICDE'2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.07250 2025-11-24 quant-ph cs.AI cs.LG math-ph math.MP stat.ML

Toward Super-polynomial Quantum Speedup of Equivariant Quantum Algorithms with SU($d$) Symmetry

迈向具有SU(d)对称性的等变量子算法超多项式量子加速

Han Zheng, Zimu Li, Sergii Strelchuk, Risi Kondor, Junyu Liu

机构 * Department of Statistics, The University of Chicago, Chicago, IL 60637, USA(统计学系,芝加哥大学) DAMTP, Center for Mathematical Sciences, University of Cambridge, Cambridge CB30WA, UK(数学系,剑桥大学) Department of Computer Science, University of Oxford(计算机科学系,牛津大学) Department of Computer Science, The University of Chicago, Chicago, IL 60637, USA(计算机科学系,芝加哥大学) Pritzker School of Molecular Engineering, The University of Chicago, Chicago, IL 60637, USA(分子工程学院,芝加哥大学) Kadanoff Center for Theoretical Physics, The University of Chicago, Chicago, IL 60637, USA(理论物理中心,芝加哥大学) Department of Computer Science, The University of Pittsburgh, Pittsburgh, PA 15260, USA(计算机科学系,匹兹堡大学)

AI总结 该研究提出了一种基于SU(d)对称性的等变量子算法框架,通过增强置换量子计算模型PQC+,实现了超多项式量子加速,并展示了PQC+在经典模拟上的不可行性。

Comments Presented in TQC 2022

Journal ref Phys. Rev. A 112, 052435 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06039 2025-11-21 cs.LG

Do-PFN: In-Context Learning for Causal Effect Estimation

Do-PFN:基于上下文的学习用于因果效应估计

Jake Robertson, Arik Reuter, Siyuan Guo, Noah Hollmann, Frank Hutter, Bernhard Schölkopf

机构 * Prior Labs ELLIS Institute Tübingen(ELLIS研究所图宾根) University of Freiburg(弗赖堡大学) Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所) University of Cambridge(剑桥大学)

AI总结 Do-PFN通过预训练在多种因果结构上的合成数据,实现基于上下文的学习,无需因果图知识即可准确估计因果效应。

Comments Neurips 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.10819 2025-11-21 cs.AI cs.LG

PoE-World: Compositional World Modeling with Products of Programmatic Experts

PoE-World: 通过程序专家的乘积进行组合世界建模

Wasu Top Piriyakulkij, Yichao Liang, Hao Tang, Adrian Weller, Marta Kryven, Kevin Ellis

机构 * Cornell University(康奈尔大学) University of Cambridge(剑桥大学) The Alan Turing Institute(艾伦·图灵研究所) Dalhousie University(达尔豪斯大学)

AI总结 PoE-World通过程序专家的乘积有效建模复杂非网格世界领域,利用LLMs学习世界模型并实现高效泛化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.13246 2025-11-21 cs.CL cs.AI

Atomic Calibration of LLMs in Long-Form Generations

大语言模型在长文本生成中的原子校准

Caiqi Zhang, Ruihan Yang, Zhisong Zhang, Xinting Huang, Sen Yang, Dong Yu, Nigel Collier

机构 * University of Cambridge(剑桥大学) Fudan University(复旦大学) Tencent AI Lab(腾讯AI实验室) The Chinese University of Hong Kong(香港中文大学)

AI总结 本研究提出原子校准方法,用于改进大语言模型在长文本生成中的校准能力,揭示置信度方法与生成过程中置信度变化的关联。

Comments ACL 2025 KnowFM Oral / AACL-IJCNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.03628 2025-11-21 cs.CL

GPTopic: Dynamic and Interactive Topic Representations

GPTopic: 动态和交互式主题表示

Arik Reuter, Bishnu Khadka, Anton Thielmann, Christoph Weisser, Sebastian Fischer, Benjamin Säfken

机构 * University of Cambridge(剑桥大学) LMU Munich(慕尼黑大学) TU Clausthal(Clausthal技术大学) BASF(巴斯夫) Tribhuvan University(特里布文大学) MCML

AI总结 GPTopic利用大型语言模型创建动态交互式主题表示,通过直观界面提升主题建模的可访问性和全面性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19873 2025-11-20 cs.CV cs.NA math.NA

Deep Spectral Prior

Yanqi Cheng, Xuxiang Zhao, Tieyong Zeng, Pietro Lio, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero

机构 * University of Cambridge(剑桥大学) Qiuzhen College, Tsinghua University(清华大学求真学院) The Chinese University of Hong Kong(香港中文大学) YMSC, Tsinghua University(清华大学数学科学中心)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15196 2025-11-20 stat.ML cs.LG hep-lat

Particle Monte Carlo methods for Lattice Field Theory

David Yallup

机构 * Kavli Institute for Cosmology Cambridge, University of Cambridge(卡弗里宇宙学研究所剑桥,剑桥大学)

Comments To appear in the NeurIPS 2025 workshop, Frontiers in Probabilistic Inference: Sampling Meets Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14889 2025-11-20 cs.LG

Bringing Federated Learning to Space

Grace Kim, Filip Svoboda, Nicholas Lane

机构 * Stanford University(斯坦福大学) University of Cambridge(剑桥大学)

Comments 15 pages, 9 figures, 3 tables accepted to IEEE Aeroconf 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03475 2025-11-20 math.OC cs.LG eess.IV

Solving Imaging Inverse Problems Using Plug-and-Play Denoisers: Regularization and Optimization Perspectives

Hong Ye Tan, Subhadip Mukherjee, Junqi Tang

机构 * University of Cambridge(剑桥大学) IIT Kharagpur(印度理工学院哈里科特分校) University of Birmingham(伯明翰大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14631 2025-11-19 cs.CL cs.AI cs.CV cs.MA

Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilities

Kahaan Gandhi, Boris Bolliet, Inigo Zubeldia

机构 * Department of Physics, University of Cambridge, Cambridge, United Kingdom(剑桥大学物理系) Kavli Institute for Cosmology, University of Cambridge, Cambridge, United Kingdom(剑桥大学卡弗利天文研究所) Department of Physics and Astronomy, Haverford College, 370 Lancaster Avenue, Haverford, PA 19041, USA(哈弗福德学院物理与天文学系) Division of Physics, Mathematics and Astronomy, California Institute of Technology, Pasadena, CA 91125, USA(加州理工学院物理、数学与天文学系) Institute of Astronomy, University of Cambridge, Cambridge, United Kingdom(剑桥大学天文研究所)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10240 2025-11-19 cs.AR cs.LG

Graph Neural Networks Based Analog Circuit Link Prediction

Guanyuan Pan, Tiansheng Zhou, Jianxiang Zhao, Zhi Li, Yugui Lin, Bingtao Ma, Yaqi Wang, Pietro Liò, Shuai Wang

机构 * HDU-ITMO Joint Institute, Hangzhou Dianzi University(杭州电子科技大学信息处理联合研究所) Intelligent Information Processing Laboratory, Hangzhou Dianzi University(杭州电子科技大学智能信息处理实验室) Innovation Center for Electronic Design Automation Technology, Hangzhou Dianzi University(杭州电子科技大学电子设计自动化技术创新中心) School of Computer Science and Technology, South China Business College, Guangdong University of Foreign Studies(广东外语外贸大学南方商学院计算机科学与技术学院) Department of Computer Science and Technology, University of Cambridge(剑桥大学计算机科学与技术系)

Comments Code and data will be made available on request to the corresponding author

Journal ref Pan, G., Zhou, T., Zhao, J., Li, Z., Lin, Y., Ma, B., ... & Wang, S. (2026). Graph Neural Networks Based Analog Circuit Link Prediction. Engineering Applications of Artificial Intelligence, 163, 113035

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13701 2025-11-18 cs.LG

Learning stochasticity: a nonparametric framework for intrinsic noise estimation

Gianluigi Pillonetto, Alberto Giaretta, Mauro Bisiacco

机构 * Department of Information Engineering, University of Padova(信息工程系,帕多瓦大学) Department of Pathology, Cambridge University(病理学系,剑桥大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13229 2025-11-18 cs.LG stat.ML

Laplace Learning in Wasserstein Space

Mary Chriselda Antony Oliver, Michael Roberts, Carola-Bibiane Schönlieb, Matthew Thorpe

机构 * Department of Applied Mathematics and Theoretical Physics, The University of Cambridge(应用数学与理论物理系,剑桥大学) Department of Medicine, The University of Cambridge(医学系,剑桥大学) Department of Statistics, The University of Warwick(统计系,沃里克大学)

Comments 46 page, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12691 2025-11-18 cs.CV cs.AI

R$^{2}$Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection

Shuaike Shen, Ke Liu, Jiaqing Xie, Shangde Gao, Chunhua Shen, Ge Liu, Mireia Crispin-Ortuzar, Shangqi Gao

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Cambridge(剑桥大学) Zhejiang University(浙江大学) ETH Zurich(苏黎世联邦理工学院) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.10390 2025-11-18 cs.CV

HIBMatch: Hypergraph Information Bottleneck for Semi-supervised Alzheimer's Progression

Zhongying Deng, Shujun Wang, Angelica I Aviles-Rivero, Zoe Kourtzi, Carola-Bibiane Schönlieb

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) Department of Biomedical Engineering, The Hong Kong Polytechnic University(生物医学工程系,香港理工大学) Research Institute for Artificial Intelligence of Things, The Hong Kong Polytechnic University(物联网人工智能研究所,香港理工大学) Yau Mathematical Sciences Centre, Tsinghua University(叶德平数学科学中心,清华大学)

Comments Accepted to the IEEE Journal of Biomedical and Health Informatics (To appear)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12934 2025-11-18 cs.LG

Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines

Alex Gower

机构 * University of Cambridge(剑桥大学) Nokia Bell Labs(诺基亚贝尔实验室)

Comments 5 pages, 2 figures, NeurIPS 2025 Machine Learning and the Physical Sciences (ML4PS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04864 2025-11-13 cs.CV

Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction

Kyle Fogarty, Chenyue Cai, Jing Yang, Zhilin Guo, Cengiz Öztireli

机构 * University of Cambridge(剑桥大学) Princeton University(普林斯顿大学)

Comments Accepted at 3DV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08438 2025-11-12 astro-ph.CO astro-ph.IM cs.LG

Galactification: painting galaxies onto dark matter only simulations using a transformer-based model

Shivam Pandey, Christopher C. Lovell, Chirag Modi, Benjamin D. Wandelt

机构 * Department of Physics and Astronomy, Johns Hopkins University(约翰霍普金斯大学物理与天文学系) Kavli Institute for Cosmology, University of Cambridge(剑桥大学卡弗利宇宙研究所) Center for Cosmology and Particle Physics, New York University(纽约大学宇宙与粒子物理中心)

Comments 8 pages, 4 figures. , accepted at Machine Learning and the Physical Sciences Workshop at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08203 2025-11-12 cs.CV

Twist and Compute: The Cost of Pose in 3D Generative Diffusion

Kyle Fogarty, Jack Foster, Boqiao Zhang, Jing Yang, Cengiz Öztireli

机构 * University of Cambridge(剑桥大学)

Comments Accepted to EurIPS 2025 Workshop on Principles of Generative Modeling (PriGM)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07007 2025-11-11 cs.CV cs.AI cs.LG

TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding

Duc Nguyen, Yan-Ling Lai, Qilin Zhang, Prabin Gyawali, Benedikt Schwab, Olaf Wysocki, Thomas H. Kolbe

机构 * Technical University of Munich(慕尼黑技术大学) University of Cambridge(剑桥大学)

Comments The paper accepted for 3DV 2026 (International Conference on 3D Vision 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05728 2025-11-11 cs.LG cs.AI cs.IT math.IT

Compressing Chemistry Reveals Functional Groups

Ruben Sharma, Ross D. King

机构 * Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK(化学工程与生物技术系,剑桥大学,剑桥,英国)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.09026 2025-11-11 stat.AP cs.LG stat.ML

Probabilistic Wind Power Modelling via Heteroscedastic Non-Stationary Gaussian Processes

Domniki Ladopoulou, Dat Minh Hong, Petros Dellaportas

机构 * Department of Statistical Science, University College London(统计科学系,伦敦大学学院) Department of Engineering, University of Cambridge(工程系,剑桥大学) Department of Statistics, Athens University of Economics and Business(统计系,雅典经济与商业大学)

Comments 13 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.17493 2025-11-11 cs.LG cs.AI q-fin.CP

A Novel Loss Function for Deep Learning Based Daily Stock Trading System

Ruoyu Guo, Haochen Qiu, Xuelun Hou

机构 * Virginia Commonwealth University(弗吉尼亚 Commonwealth 大学) University of Cambridge(剑桥大学) Brandeis University(布兰迪斯大学)

Comments 27 pages, 11 figures, GitHub repo: https://github.com/Tony-Guo-1/daily_trading_strategy

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.04116 2025-07-08 cs.CV stat.AP stat.ME

Integrated Gaussian Processes for Robust and Adaptive Multi-Object Tracking

Fred Lydeard, Bashar I. Ahmad, Simon Godsill

机构 * Probabilistic Systems, Information, and Inference Group, Department of Engineering, University of Cambridge(概率系统、信息与推断组,工程系,剑桥大学)

Comments 18 pages, 5 figures, submitted to IEEE Transactions on Aerospace and Electronic Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03910 2025-07-08 cs.LG stat.ML

Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces

Henry B. Moss, Sebastian W. Ober, Tom Diethe

机构 * School of Mathematical Sciences, Lancaster University, UK(数学科学学院,兰卡斯特大学) Department of Applied Maths and Theoretical Physics, University of Cambridge, UK(应用数学与理论物理系,剑桥大学)

Comments Accepted for publication at the International Conference on Machine Learning (ICML) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12204 2025-07-08 cs.RO cs.SY eess.SY

D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations

Yuhao Zhang, Keisuke Okumura, Heedo Woo, Ajay Shankar, Amanda Prorok

机构 * University of Cambridge(剑桥大学) National Institute of Advanced Industrial Science and Technology(国家先进工业科学与技术研究院)

Comments Accepted by 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.03335 2025-07-08 cs.CL cs.CY

iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News

Tiancheng Hu, Nigel Collier

机构 * University of Cambridge(剑桥大学)

Comments Dataset available at https://huggingface.co/datasets/pitehu/inews

详情

展开后加载摘要…

URL PDF HTML 收藏