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
2506.10117 2025-06-13 cs.CV cs.ET

A Manually Annotated Image-Caption Dataset for Detecting Children in the Wild

Klim Kireev, Ana-Maria Creţu, Raphael Meier, Sarah Adel Bargal, Elissa Redmiles, Carmela Troncoso

机构 * MPI-SP & EPFL Bochum, Germany(MPI-SP与苏黎世联邦理工学院博希姆分校) EPFL Lausanne, Switzerland(苏黎世联邦理工学院拉沃斯分校) Cyber-Defence Campus armasuisse S+T Thun, Switzerland(网络安全防御校园armasuisse S+T图恩分校) Georgetown University Washington, D.C., USA(乔治城大学华盛顿特区)

Comments 14 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.02348 2025-06-13 cs.LG stat.ML

Simplicity bias and optimization threshold in two-layer ReLU networks

Etienne Boursier, Nicolas Flammarion

机构 * INRIA, LMO, Université Paris-Saclay, Orsay, France(INRIA、LMO、巴黎-萨克雷大学、欧萨斯分校、法国) TML Lab, EPFL, Switzerland(TML实验室、瑞士联邦理工学院)

Comments ICML camera ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09955 2025-06-12 cs.LG cs.CV

Canonical Latent Representations in Conditional Diffusion Models

Yitao Xu, Tong Zhang, Ehsan Pajouheshgar, Sabine Süsstrunk

机构 * Image and Visual Representation Lab(图像与视觉表示实验室) École polytechnique fédérale de Lausanne(洛桑联邦理工学院)

Comments 45 pages,41 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14387 2025-06-12 cs.CL

How Do Multilingual Language Models Remember Facts?

Constanza Fierro, Negar Foroutan, Desmond Elliott, Anders Søgaard

机构 * Department of Computer Science, University of Copenhagen(哥本哈根大学计算机科学系) EPFL(瑞士联邦理工学院)

Comments 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.01078 2025-06-12 cs.CV

Unseen Visual Anomaly Generation

Han Sun, Yunkang Cao, Hao Dong, Olga Fink

机构 * EPFL(瑞士联邦理工学院) HUST(哈尔滨工业大学) ETH Zurich(苏黎世联邦理工学院)

Comments 8 pages excluding supplementary

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06985 2025-06-12 cs.LG cs.CR stat.ML

Certified Unlearning for Neural Networks

Anastasia Koloskova, Youssef Allouah, Animesh Jha, Rachid Guerraoui, Sanmi Koyejo

机构 * Stanford University, USA(斯坦福大学) 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
2312.04540 2025-06-12 cs.LG cs.AI cs.CV cs.MA cs.RO

Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations

Ahmad Rahimi, Po-Chien Luan, Yuejiang Liu, Frano Rajič, Alexandre Alahi

机构 * École Polytechnique Fédérale de Lausanne(瑞士联邦理工学院) Stanford University(斯坦福大学) ETH Zurich(苏黎世联邦理工学院)

Comments CVPR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07280 2025-06-11 cs.CV cs.AI

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models

Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Alexandre Alahi, Paolo Favaro

机构 * University of Bern(伯恩大学) EPFL(瑞士联邦理工学院)

Comments 27 pages, 23 figures, 9 tables. Project page: https://pabloacuaviva.github.io/Gen2Gen/

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.02545 2025-06-11 cs.LG cond-mat.dis-nn

Optimal Spectral Transitions in High-Dimensional Multi-Index Models

Leonardo Defilippis, Yatin Dandi, Pierre Mergny, Florent Krzakala, Bruno Loureiro

机构 * Département d’Informatique, École Normale Supérieure, PSL & CNRS(信息学院,巴黎高等师范学院,PSL与CNRS) Information, Learning, and Physics Laboratory, EPFL, Switzerland(信息、学习与物理实验室,瑞士联邦理工学院) Sloan School of Management, MIT, United States(斯隆管理学院,麻省理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08143 2025-06-11 cs.LG

Accelerating Spectral Clustering under Fairness Constraints

Francesco Tonin, Alex Lambert, Johan A. K. Suykens, Volkan Cevher

机构 * EPFL(苏黎世联邦理工学院)

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.13887 2025-06-10 cs.LG cs.SD eess.AS

What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain

Petr Grinberg, Ankur Kumar, Surya Koppisetti, Gaurav Bharaj

机构 * EPFL(瑞士联邦理工学院) Reality Defender Inc.(Reality Defender公司)

Comments Accepted to ICASSP 2025

Journal ref Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2025, pp. 1-5

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06933 2025-06-10 cs.LG cs.AI cs.CR cs.CV

Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry

Mahdi Salmani, Alireza Abdollahpoorrostam, Seyed-Mohsen Moosavi-Dezfooli

机构 * University of Southern California(南加州大学) EPFL(瑞士联邦理工学院) Apple(苹果公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.00228 2025-06-10 cs.CV

Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion

David Geissbühler, Hatef Otroshi Shahreza, Sébastien Marcel

机构 * Idiap Research Institute, Martigny, Switzerland \' E cole Polytechnique F\' e d\' e rale de Lausanne (EPFL), Lausanne, Switzerland

Comments Accepted in ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.13778 2025-06-10 cs.CV cs.RO

Certified Human Trajectory Prediction

Mohammadhossein Bahari, Saeed Saadatnejad, Amirhossein Askari Farsangi, Seyed-Mohsen Moosavi-Dezfooli, Alexandre Alahi

机构 * EPFL(苏黎世联邦理工学院) Apple(苹果公司)

Comments CVPR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.07529 2025-06-09 cs.LG math.OC

Training Deep Learning Models with Norm-Constrained LMOs

Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher

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
2506.05346 2025-06-06 cs.CR cs.CL cs.LG

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets

Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song, Tsung-Yi Ho, Pin-Yu Chen, Yaoqing Yang

机构 * Dartmouth College(达特茅斯学院) EPFL(苏黎世联邦理工学院) UC Berkeley(加州大学伯克利分校) CUHK(香港大学) IBM Research(IBM研究院)

Comments Project Page: https://hsiung.cc/llm-similarity-risk/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04623 2025-06-06 cs.GR cs.CV

VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection

Wuyang Li, Zhu Yu, Alexandre Alahi

机构 * École Polytechnique Fédérale de Lausanne (EPFL)(瑞士联邦理工学院) Zhejiang University(浙江大学)

Comments Project Page: https://vita-epfl.github.io/VoxDet/

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.12656 2025-06-06 cs.CL cs.AI

Evaluating Morphological Compositional Generalization in Large Language Models

Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Duygu Ataman, Lonneke van der Plas

机构 * EPFL(瑞士联邦理工学院) Idiap Research Institute(Idiap研究机构) Duke University(杜克大学) Brandeis University(布兰迪斯大学) LMU Munich(慕尼黑大学) University of Cambridge(剑桥大学) Johns Hopkins University(约翰霍普金斯大学) Università della Svizzera Italiana(瑞士意大利大学) New York University(纽约大学)

Comments Accepted to NAACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.18370 2025-06-06 quant-ph cs.AI cs.LG stat.ML

Learning pure quantum states (almost) without regret

Josep Lumbreras, Mikhail Terekhov, Marco Tomamichel

机构 * Centre for Quantum Technologies, National University of Singapore(量子技术中心,新加坡国立大学) School of Computer and Communication Sciences, EPFL(信息与通信科学学院,洛桑联邦理工学院) Department of Electrical and Computer Engineering, National University of Singapore(电子与计算机工程系,新加坡国立大学)

Comments 28 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.18223 2025-06-05 cs.CV cs.IR q-bio.NC q-bio.QM

MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps

Valentin Gabeff, Haozhe Qi, Brendan Flaherty, Gencer Sumbül, Alexander Mathis, Devis Tuia

机构 * EPFL(苏黎世联邦理工学院)

Comments CVPR 2025; Benchmark and code at: https://github.com/eceo-epfl/MammAlps. After submission of v1, we noticed that a few audio files were not correctly aligned with the corresponding video. We fixed the issue, which had little to no impact on performance. We also now report results for three runs

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13967 2025-06-05 cs.CV cs.LG

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Roman Bachmann, Jesse Allardice, David Mizrahi, Enrico Fini, Oğuzhan Fatih Kar, Elmira Amirloo, Alaaeldin El-Nouby, Amir Zamir, Afshin Dehghan

机构 * Apple(苹果公司) Swiss Federal Institute of Technology Lausanne (EPFL)(瑞士联邦理工学院洛桑分校)

Comments ICML 2025. Project page at https://flextok.epfl.ch/

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11673 2025-06-05 cs.LG stat.ML

Best of Both Worlds: Regret Minimization versus Minimax Play

Adrian Müller, Jon Schneider, Stratis Skoulakis, Luca Viano, Volkan Cevher

机构 * ETH Zürich(苏黎世联邦理工学院) Google Research(谷歌研究) Aarhus University(奥胡斯大学) EPFL(苏黎世联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.18282 2025-06-05 cs.LG

Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective

Yunzhen Yao, Lie He, Michael Gastpar

机构 * LINX, EPFL, Lausanne, Switzerland(日内瓦EPFL实验室) School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China(上海金融学院计算机与人工智能学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03096 2025-06-04 cs.CV cs.LG

FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens

Christian Schlarmann, Francesco Croce, Nicolas Flammarion, Matthias Hein

机构 * Tübingen AI Center University of Tübingen(图宾根人工智能中心大学) EPFL(瑞士联邦理工学院)

Comments Code and models available at https://github.com/chs20/fuselip

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02783 2025-06-04 cs.CV

SAMJ: Fast Image Annotation on ImageJ/Fiji via Segment Anything Model

Carlos Garcia-Lopez-de-Haro, Caterina Fuster-Barcelo, Curtis T. Rueden, Jonathan Heras, Vladimir Ulman, Daniel Franco-Barranco, Adrian Ines, Kevin W. Eliceiri, Jean-Christophe Olivo-Marin, Jean-Yves Tinevez, Daniel Sage, Arrate Munoz-Barrutia

机构 * Bioengineering Department(生物工程系) Universidad Carlos III de Madrid(卡洛斯三世大学) Instituto de Investigación Sanitaria Gregorio Marañón(Gregorio Marañón卫生研究院) Institut Pasteur, Université Paris Cité(巴黎研究院) University of Wisconsin(威斯康星大学) University of La Rioja(拉里奥ja大学) VSB – Technical University of Ostrava(奥斯特拉瓦技术大学) Masaryk University(马萨里克大学) MRC Laboratory of Molecular Biology(分子生物学实验室) University of Cambridge(剑桥大学) Donostia International Physics Center (DIPC)(Donostia国际物理中心) CNRS UMR 3691 Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02664 2025-06-04 stat.ML cond-mat.dis-nn cs.LG

Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model

Hugo Tabanelli, Pierre Mergny, Lenka Zdeborova, Florent Krzakala

机构 * Information Learning and Physics Laboratory, École Polytechnique Fédérale de Lausanne (EPFL)(信息学习与物理实验室,瑞士联邦理工学院(EPFL)) Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL)(计算统计物理实验室,瑞士联邦理工学院(EPFL))

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01406 2025-06-03 cs.CL

Speech-to-Speech Translation Pipelines for Conversations in Low-Resource Languages

Andrei Popescu-Belis, Alexis Allemann, Teo Ferrari, Gopal Krishnamani

机构 * HEIG-VD / HES-SO Bhaasha Sàrl EPFL(苏黎世联邦理工学院)

Comments Proceedings of MT Summit 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.06118 2025-06-03 cs.CL

Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning

Alexis Allemann, Àlex R. Atrio, Andrei Popescu-Belis

机构 * HEIG-VD / HES-SO Pi School EPFL(苏黎世联邦理工学院)

Comments Proceedings of MT Summit 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00544 2025-06-03 cs.LG

Best Practices for Multi-Fidelity Bayesian Optimization in Materials and Molecular Research

Víctor Sabanza-Gil, Riccardo Barbano, Daniel Pacheco Gutiérrez, Jeremy S. Luterbacher, José Miguel Hernández-Lobato, Philippe Schwaller, Loïc Roch

机构 * EPFL(苏黎世联邦理工学院) Atinary Technologies Inc.(Atinary技术公司) University of Cambridge(剑桥大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24802 2025-06-02 cs.LG

ByzFL: Research Framework for Robust Federated Learning

Marc González, Rachid Guerraoui, Rafael Pinot, Geovani Rizk, John Stephan, François Taïani

机构 * Universitat Politècnica de Catalunya (UPC)(巴塞罗那技术大学) Ecole Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院) Sorbonne Université, Université Paris Cité, CNRS(索邦大学、巴黎cité大学、国家科学研究中心) Université de Rennes, Inria, CNRS, IRISA(雷恩大学、法国国家科学研究中心、IRISA)

详情

展开后加载摘要…

URL PDF HTML 收藏