arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

EPFL(洛桑联邦理工学院)

共收录 857
2410.05090 2025-06-27 cs.LG stat.ML

HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation

Xinyu Zhou, Simin Fan, Martin Jaggi

机构 * Machine Learning and Optimization Lab, EPFL(机器学习与优化实验室,EPFL)

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.14712 2025-06-27 cs.LG cs.CR cs.DC

Balancing Privacy, Robustness, and Efficiency in Machine Learning

Youssef Allouah, Rachid Guerraoui, John Stephan

机构 * EPFL, Switzerland(苏黎世联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.08745 2025-06-26 cs.CL cs.AI

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers

Clément Dumas, Chris Wendler, Veniamin Veselovsky, Giovanni Monea, Robert West

机构 * ENS Paris-Saclay(巴黎萨克雷大学) Université Paris-Saclay(巴黎萨克雷大学) Northeastern(东北大学) Princeton(普林斯顿大学) Cornell(康奈尔大学) EPFL(洛桑联邦理工学院)

Comments 20 pages, 14 figures, previous version published under the title "How Do Llamas Process Multilingual Text? A Latent Exploration through Activation Patching" at the ICML 2024 mechanistic interpretability workshop at https://openreview.net/forum?id=0ku2hIm4BS

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19613 2025-06-25 cs.AI

Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI

Sha Zhang, Suorong Yang, Tong Xie, Xiangyuan Xue, Zixuan Hu, Rui Li, Wenxi Qu, Zhenfei Yin, Tianfan Fu, Di Hu, Andres M Bran, Nian Ran, Bram Hoex, Wangmeng Zuo, Philippe Schwaller, Wanli Ouyang, Lei Bai, Yanyong Zhang, Lingyu Duan, Shixiang Tang, Dongzhan Zhou

机构 * University of Science and Technology of China(中国科学技术大学) Nanjing University(南京大学) University of New South Wales(新南威尔士大学) Shanghai Jiao Tong University(上海交通大学) Peking University(北京大学) Harbin Institute of Technology(哈尔滨工业大学) Tongji University(同济大学) The University of Sydney, Oxford(悉尼大学,牛津) Renmin University of China(中国人民大学) Swiss Federal Institute of Technology Lausanne(苏黎世联邦理工学院) Shanghai Institute of Ceramics, Chinese Academy of Sciences(中国科学院上海硅酸盐研究所) Shanghai AI Laboratory(上海人工智能实验室) Shanghai AI Laboratory & The Chinese University of Hong Kong(上海人工智能实验室 & 香港中文大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16986 2025-06-25 cs.RO

Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration

Yuntao Ma, Yang Liu, Kaixian Qu, Marco Hutter

机构 * ETH Zürich(苏黎世联邦理工学院) Swiss Federal Institute of Technology Lausanne(洛桑联邦理工学院)

Comments 8 pages, IROS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.05563 2025-06-25 cs.CL cs.AI cs.LG

Rational Metareasoning for Large Language Models

C. Nicolò De Sabbata, Theodore R. Sumers, Badr AlKhamissi, Antoine Bosselut, Thomas L. Griffiths

机构 * Princeton University(普林斯顿大学) EPFL(洛桑联邦理工学院) Anthropic(Anthropic公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.17050 2025-06-25 cs.LG

HeNCler: Node Clustering in Heterophilous Graphs via Learned Asymmetric Similarity

Sonny Achten, Zander Op de Beeck, Francesco Tonin, Volkan Cevher, Johan A. K. Suykens

机构 * ESAT-STADIUS, KU Leuven(ESAT-STADIUS,根特大学) LIONS, EPFL(LIONS,苏黎世联邦理工学院)

Comments Accepted at International Conference on Artificial Neural Networks (ICANN 2025), Special Session on Neural Network for Graphs and Beyond

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06832 2025-06-24 cs.AI cs.CL cs.GT cs.IT cs.NE math.IT

Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures

Clément Hongler, Andrew Emil

机构 * EPFL(苏黎世联邦理工学院)

Comments 42 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17296 2025-06-24 cs.CL cs.AI

Semantic uncertainty in advanced decoding methods for LLM generation

Darius Foodeei, Simin Fan, Martin Jaggi

机构 * EPFL, Lausanne Switzerland(日内瓦联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16219 2025-06-23 cs.RO

Probabilistic Collision Risk Estimation for Pedestrian Navigation

Amine Tourki, Paul Prevel, Nils Einecke, Tim Puphal, Alexandre Alahi

机构 * Biped Robotics SA Honda Research Institute Europe GmbH(本田欧洲研究机构) Honda Research Institute Japan Co., Ltd.(本田日本研究机构) École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09705 2025-06-23 cs.RO

From Movement Primitives to Distance Fields to Dynamical Systems

Yiming Li, Sylvain Calinon

机构 * Idiap Research Institute(日内瓦研究所) EPFL(苏黎世联邦理工学院)

Comments 8 pages, 8 Figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.13183 2025-06-23 cs.CV

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Guoxing Sun, Rishabh Dabral, Heming Zhu, Pascal Fua, Christian Theobalt, Marc Habermann

机构 * Max Planck Institute for Informatics(马克斯·普朗克研究所信息学研究所) VIA Research Center(VIA研究中心) EPFL(瑞士联邦理工学院)

Comments Accepted at CVPR 2025, Project page: https://vcai.mpi-inf.mpg.de/projects/DUT/

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.11511 2025-06-23 eess.IV cs.CV

Event Cameras Meet SPADs for High-Speed, Low-Bandwidth Imaging

Manasi Muglikar, Siddharth Somasundaram, Akshat Dave, Edoardo Charbon, Ramesh Raskar, Davide Scaramuzza

机构 * Robotics and Perception Group, University of Zurich, Switzerland(苏黎世大学机器人与感知组) Camera Culture Group, MIT Media Lab, USA(MIT媒体实验室相机文化组) EPFL, Lausanne, Switzerland(日内瓦联邦理工学院)

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05253 2025-06-23 cs.CV

Contour Integration Underlies Human-Like Vision

Ben Lonnqvist, Elsa Scialom, Abdulkadir Gokce, Zehra Merchant, Michael H. Herzog, Martin Schrimpf

机构 * École Polytechnique Fédérale de Lausanne (EPFL), Switzerland(瑞士联邦理工学院(EPFL))

Comments ICML Camera Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15594 2025-06-19 cs.CL cs.AI cs.LG

WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts

Negar Foroutan, Angelika Romanou, Matin Ansaripour, Julian Martin Eisenschlos, Karl Aberer, Rémi Lebret

机构 * EPFL(苏黎世联邦理工学院) Google DeepMind(谷歌DeepMind) Universidad Nacional de Córdoba(国家科隆大学)

Comments ACL 2025 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15397 2025-06-19 cs.LG cs.DS cs.SI

Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control

Sepehr Elahi, Paula Mürmann, Patrick Thiran

机构 * EPFL(苏黎世联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14865 2025-06-19 cs.RO

Efficient and Real-Time Motion Planning for Robotics Using Projection-Based Optimization

Xuemin Chi, Hakan Girgin, Tobias Löw, Yangyang Xie, Teng Xue, Jihao Huang, Cheng Hu, Zhitao Liu, Sylvain Calinon

机构 * Department of Control Science and Engineering, Zhejiang University(控制科学与工程系,浙江大学) Swiss Cobotics Competence Center(瑞士协作机器人能力建设中心) Idiap Research Institute(Idiap研究机构) EPFL(瑞士联邦理工学院)

Comments submitted to IROS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14371 2025-06-18 cs.CL cs.HC

ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection

Lucile Favero, Daniel Frases, Juan Antonio Pérez-Ortiz, Tanja Käser, Nuria Oliver

机构 * ELLIS Alicante(ELLIS阿利坎特) Universidad Alfonso X el Sabio(阿尔fonso X el Sabio大学) Universitat d’Alacant(阿利坎特大学) École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

Comments Proceedings of the 12th Workshop on Argument Mining

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13986 2025-06-18 cs.RO

Diffusion-based Inverse Observation Model for Artificial Skin

Ante Maric, Julius Jankowski, Giammarco Caroleo, Alessandro Albini, Perla Maiolino, Sylvain Calinon

机构 * Idiap Research Institute(Idiap研究机构) École Polytechnique Fédérale de Lausanne (EPFL)(瑞士联邦理工学院(EPFL)) Oxford Robotics Institute (ORI), University of Oxford(牛津大学机器人研究所)

Comments Accepted to RSS 2025 workshop on Navigating Contact Dynamics in Robotics

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.05804 2025-06-18 cs.CV cs.AI

InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write

Blagoj Mitrevski, Arina Rak, Julian Schnitzler, Chengkun Li, Andrii Maksai, Jesse Berent, Claudiu Musat

机构 * Google DeepMind(谷歌DeepMind) EPFL(苏黎世联邦理工学院)

Comments Accepted by Transactions on Machine Learning Research

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12505 2025-06-17 cs.CV

Fine-Grained HDR Image Quality Assessment From Noticeably Distorted to Very High Fidelity

Mohsen Jenadeleh, Jon Sneyers, Davi Lazzarotto, Shima Mohammadi, Dominik Keller, Atanas Boev, Rakesh Rao Ramachandra Rao, António Pinheiro, Thomas Richter, Alexander Raake, Touradj Ebrahimi, João Ascenso, Dietmar Saupe

机构 * University of Konstanz, Germany(康斯坦茨大学) Cloudinary, Belgium(Cloudinary公司) EPFL, Switzerland(瑞士联邦理工学院) IST-IT, Portugal(葡萄牙IST-IT机构) Huawei, Germany(华为公司) TU Ilmenau, Germany(图林根工业大学) RWTH Aachen, Germany(亚琛工业大学) IT-UBI, Portugal(葡萄牙IT-UBI机构) Fraunhofer IIS, Germany(弗劳恩霍夫研究所)

Comments This paper has been accepted to QoMEX 2025. The work is funded by the DFG (German Research Foundation) - Project ID 496858717, titled "JND-based Perceptual Video Quality Analysis and Modeling". D.S. is funded by DFG Project ID 251654672

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10949 2025-06-17 cs.CR cs.AI

Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors

Chen Yueh-Han, Nitish Joshi, Yulin Chen, Maksym Andriushchenko, Rico Angell, He He

机构 * New York University(纽约大学) École Polytechnique Fédérale de Lausanne(瑞士联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.04263 2025-06-17 cs.LG

DeFoG: Discrete Flow Matching for Graph Generation

Yiming Qin, Manuel Madeira, Dorina Thanou, Pascal Frossard

机构 * EPFL, Lausanne, Switzerland(苏黎世联邦理工学院)

Comments The first two authors contributed equally to this work. Accepted at International Conference on Machine Learning (ICML) 2025

Journal ref International Conference on Machine Learning (ICML) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.06778 2025-06-17 cs.CL

Fast-and-Frugal Text-Graph Transformers are Effective Link Predictors

Andrei C. Coman, Christos Theodoropoulos, Marie-Francine Moens, James Henderson

机构 * Idiap Research Institute(Idiap研究机构) EPFL(瑞士联邦理工学院) KU Leuven(根特大学)

Comments Accepted to ACL 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.11486 2025-06-17 cs.LG cs.DC

Boosting Resource-Constrained Federated Learning Systems with Guessed Updates

Mohamed Yassine Boukhari, Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires, Othmane Safsafi, Rishi Sharma

机构 * EPFL(瑞士联邦理工学院)

Comments 18 pages, 12 figures

Journal ref IEEE Transactions on Parallel and Distributed Systems. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12204 2025-06-17 cs.LG cs.AI cs.OS

Semantic Scheduling for LLM Inference

Wenyue Hua, Dujian Ding, Yile Gu, Yujie Ren, Kai Mei, Minghua Ma, William Yang Wang

机构 * University of California, Santa Barbara(加州大学圣芭芭拉分校) University of British Columbia(不列颠哥伦比亚大学) University of Washington, Seattle(华盛顿大学(西雅图)) EPFL(苏黎世联邦理工学院) Rutgers University, New Brunswick(罗格斯大学新 Brunswick分校) Microsoft(微软公司)

Comments 18 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.15013 2025-06-16 cs.LG

Fast Inference with Kronecker-Sparse Matrices

Antoine Gonon, Léon Zheng, Pascal Carrivain, Quoc-Tung Le

机构 * ENS de Lyon, CNRS, Inria, Université Claude Bernard Lyon 1, LIP, UMR 5668, 69342, Lyon cedex 07, France Huawei Lagrange Mathematics Computing Research Center, Paris, France Institute of Mathematics, EPFL, Lausanne, Switzerland Toulouse School of Economics, Toulouse, France

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.15006 2025-06-16 cs.LG stat.ML

A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations

Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval

机构 * ENS(巴黎综合理工学院) CNRS(国家科学研究中心) Inria(法国国家信息与自动化技术研究所) Université Claude Bernard Lyon 1(里昂第一大学) LIP(实验室) UMR 5668(统一研究机构) EPFL(苏黎世联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.17539 2025-06-16 cs.LG math.OC stat.ML

Critical Influence of Overparameterization on Sharpness-aware Minimization

Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee

机构 * POSTECH EPFL(苏黎世联邦理工学院)

Comments UAI 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10165 2025-06-13 cs.LG cs.SD eess.AS

The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset

Gilad Landau, Miran Özdogan, Gereon Elvers, Francesco Mantegna, Pratik Somaiya, Dulhan Jayalath, Luisa Kurth, Teyun Kwon, Brendan Shillingford, Greg Farquhar, Minqi Jiang, Karim Jerbi, Hamza Abdelhedi, Yorguin Mantilla Ramos, Caglar Gulcehre, Mark Woolrich, Natalie Voets, Oiwi Parker Jones

机构 * PNPL Google DeepMind(谷歌DeepMind) MetaAI Mila Université de Montréal(蒙特利尔大学) EPFL(苏黎世联邦理工学院) OHBA WIN N University of Oxford(WIN N 奥xford大学)

Journal ref NeurIPS 2025 Competition Track

详情

展开后加载摘要…

URL PDF HTML 收藏