arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Learning Representations · 会议 · Machine Learning

共收录 9454
2409.10773 2025-06-10 math.OC stat.ML

Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity

Cedar Site Bai, Brian Bullins

Comments ICLR 2025 Oral

Journal ref ICLR 2025: https://openreview.net/forum?id=fMTPkDEhLQ

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.11458 2025-06-10 cs.LG cs.GT

Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness

Maayan Ehrenberg, Roy Ganz, Nir Rosenfeld

机构 * Faculty of Computer Science(计算机科学学院) Technion – Israel Institute of Technology(技术学院–以色列理工学院)

Journal ref ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.17656 2025-06-10 cs.LG q-bio.QM

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg

机构 * Department of Computer Science, Aalto University(艾尔沃斯大学计算机科学系) YaiYai Ltd(YaiYai有限公司)

Comments Accepted at ICLR 2025. Code available at https://github.com/Aalto-QuML/DiffAlign

Journal ref Proceedings of the International Conference on Learning Representations (ICLR) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.12519 2025-06-10 cs.CL

Rational Decision-Making Agent with Internalized Utility Judgment

Yining Ye, Xin Cong, Shizuo Tian, Yujia Qin, Chong Liu, Yankai Lin, Zhiyuan Liu, Maosong Sun

机构 * Tsinghua University(清华大学) Renmin University of China(中国人民大学)

Comments Published as a conference paper at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06582 2025-06-10 cs.LG stat.ML

Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing

Diaaeldin Taha, James Chapman, Marzieh Eidi, Karel Devriendt, Guido Montúfar

机构 * Max Planck Institute for Mathematics in the Sciences(马克斯·普朗克数学研究所) UCLA(加州大学洛杉矶分校) Center for Scalable Data Analytics and Artificial Intelligence(可扩展数据与人工智能中心) University of Oxford(牛津大学)

Comments 50 pages, 12 figures, published at ICLR 2025. The Thirteenth International Conference on Learning Representations. 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.11586 2025-06-10 cs.AI cs.CL

Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space

Zhiliang Chen, Xinyuan Niu, Chuan-Sheng Foo, Bryan Kian Hsiang Low

机构 * Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系) Institute for Infocomm Research (I2R), A*STAR, Singapore(新加坡A*STAR信息与通信研究所) Centre for Frontier AI Research (CFAR), A*STAR, Singapore(新加坡A*STAR前沿人工智能研究中心)

Comments ICLR 2025 Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.11011 2025-06-10 cs.LG cs.CL stat.ML

Data Shapley in One Training Run

Jiachen T. Wang, Prateek Mittal, Dawn Song, Ruoxi Jia

机构 * Princeton University(普林斯顿大学) UC Berkeley(加州大学伯克利分校) Virginia Tech(弗吉尼亚理工学院)

Comments ICLR 2025 Outstanding Paper Runner-Up

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.08258 2025-06-09 cs.CV

In Search of Forgotten Domain Generalization

Prasanna Mayilvahanan, Roland S. Zimmermann, Thaddäus Wiedemer, Evgenia Rusak, Attila Juhos, Matthias Bethge, Wieland Brendel

机构 * University of Tübingen(图宾根大学) Tübingen AI Center(图宾根人工智能中心) Max-Planck-Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) ELLIS Institute Tübingen(图宾根ELLIS研究所)

Comments ICLR 2025 camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.03136 2025-06-09 cs.LG cs.AI cs.CC stat.ML

Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models

Jerry Yao-Chieh Hu, Maojiang Su, En-Jui Kuo, Zhao Song, Han Liu

机构 * Northwestern University(西北大学) University of Science and Technology of China(中国科学技术大学) National Yang Ming Chiao Tung University(阳明交通大学) Simons Institute UC Berkeley(伯克利Simons研究所)

Comments Accepted at ICLR 2025. v2 matches the camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.16525 2025-06-09 cs.LG cs.AI cs.CL stat.ML

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Jerry Yao-Chieh Hu, Wei-Po Wang, Ammar Gilani, Chenyang Li, Zhao Song, Han Liu

Comments Accepted at ICLR 2025. v2 matches the camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00401 2025-06-06 cs.LG cs.AI stat.ML

Spectro-Riemannian Graph Neural Networks

Karish Grover, Haiyang Yu, Xiang Song, Qi Zhu, Han Xie, Vassilis N. Ioannidis, Christos Faloutsos

机构 * Carnegie Mellon University(卡内基梅隆大学) Texas A&M University(德克萨斯农工大学) Amazon(亚马逊公司)

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.14915 2025-06-06 cs.LG math.AG

Can Transformers Do Enumerative Geometry?

Baran Hashemi, Roderic G. Corominas, Alessandro Giacchetto

机构 * ORIGINS Data Science Lab(ORIGINS数据科学实验室) Technical University Munich(慕尼黑技术大学) Department of Mathematics(数学系) Harvard University(哈佛大学) Departement Mathematik(数学系) ETH Zürich(苏黎世联邦理工学院)

Comments Published at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.09887 2025-06-05 cs.LG math.OC

OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling

Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, Jing Tang

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) The Hong Kong University of Science and Technology(香港科技大学) University of California, Merced(加州大学梅德福分校) ETH Zurich(苏黎世联邦理工学院) City University of Hong Kong(香港城市大学) Huawei Noah’s Ark Lab(华为诺亚实验室) Sun Yat-sen University(中山大学) MBZUAI Chongqing University(重庆大学)

Journal ref The Thirteenth International Conference on Learning Representations, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.09583 2025-06-05 cs.CL cs.AI cs.LG

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Jianguang Lou, Chongyang Tao, Xiubo Geng, Qingwei Lin, Shifeng Chen, Yansong Tang, Dongmei Zhang

机构 * Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院) Microsoft Corporation(微软公司) Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)

Comments This paper has been accepted to ICLR 2025 as an Oral presentation

详情

展开后加载摘要…

URL PDF HTML 收藏
2209.01205 2025-06-05 cs.LG cs.AI cs.CV

Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion

Han Wu, Jie Yin, Bala Rajaratnam, Jianyuan Guo

机构 * The University of Sydney(悉尼大学) University of California, Davis(加州大学戴维斯分校)

Comments Published at ICLR 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02612 2025-06-04 cs.LG cs.AI stat.ML

Simple, Good, Fast: Self-Supervised World Models Free of Baggage

Jan Robine, Marc Höftmann, Stefan Harmeling

机构 * TU Dortmund(图鲁姆大学) Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔人工智能与机器学习研究所)

Comments Published as a conference paper at ICLR 2025. Code is available at https://github.com/jrobine/sgf

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.18913 2025-06-04 cs.CV

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

Tongda Xu, Xiyan Cai, Xinjie Zhang, Xingtong Ge, Dailan He, Ming Sun, Jingjing Liu, Ya-Qin Zhang, Jian Li, Yan Wang

机构 * Institute for AI Industry Research, Tsinghua University(清华大学人工智能产业研究院) Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系) New York University(纽约大学) Hong Kong University of Science and Technology(香港科学与技术大学) SenseTime Research(商汤科技研究院) The Chinese University of Hong Kong(香港中文大学) Kuaishou Technology(快手科技) Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院)

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.00418 2025-06-04 cs.CL cs.AI

Self-Evolved Reward Learning for LLMs

Chenghua Huang, Zhizhen Fan, Lu Wang, Fangkai Yang, Pu Zhao, Zeqi Lin, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

机构 * School of Computer Science, Fudan University(复旦大学计算机学院) School of Computer Science, Peking University(北京大学计算机学院) Microsoft(微软公司)

Comments 23 pages,6 figures,Accepted to ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.02416 2025-06-04 cs.LG cs.CV

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

Seyedmorteza Sadat, Otmar Hilliges, Romann M. Weber

Comments Published as a conference paper at ICLR 2025

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.02687 2025-06-04 cs.LG cs.CV

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Seyedmorteza Sadat, Manuel Kansy, Otmar Hilliges, Romann M. Weber

Comments Published as a conference paper at ICLR 2025

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.15861 2025-06-04 cs.LG cs.DC

Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization

Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang

机构 * Rochester Institute of Technology(罗切斯特理工学院) Google Inc.(谷歌公司) ComboCurve Inc.(ComboCurve公司) Amazon.com Inc.(亚马逊公司)

Comments Accepted by ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.13882 2025-06-03 cs.CV

Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

Long Le, Jason Xie, William Liang, Hung-Ju Wang, Yue Yang, Yecheng Jason Ma, Kyle Vedder, Arjun Krishna, Dinesh Jayaraman, Eric Eaton

机构 * University of Pennsylvania(宾夕法尼亚大学)

Comments ICLR 2025. Project website and open-source code: https://articulate-anything.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01672 2025-06-03 cs.LG

Minimal Impact ControlNet: Advancing Multi-ControlNet Integration

Shikun Sun, Min Zhou, Zixuan Wang, Xubin Li, Tiezheng Ge, Zijie Ye, Xiaoyu Qin, Junliang Xing, Bo Zheng, Jia Jia

机构 * Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系) Taobao & Tmall Group of Alibaba(阿里巴巴淘宝与天猫集团) BNRist, Tsinghua University(清华大学BNRist) Key Laboratory of Pervasive Computing, Ministry of Education(教育部普适计算重点实验室)

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00849 2025-06-03 cs.LG cs.AI

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

Qi Chen, Jierui Zhu, Florian Shkurti

机构 * Department of Computer Science, University of Toronto(计算机科学系,多伦多大学) Department of Statistical Sciences, University of Toronto(统计科学系,多伦多大学) Data Science Institute(数据科学研究所) Vector Institute(向量研究所) Robotics Institute(机器人研究所)

Comments ICLR 2025 Accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17414 2025-06-03 cs.CY cs.AI cs.LG

Opportunities and Challenges of Frontier Data Governance With Synthetic Data

Madhavendra Thakur, Jason Hausenloy

机构 * Independent Researcher(独立研究者)

Comments Published at the ICLR 2025 Workshop on Human-AI Coevolution (HAIC)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.05315 2025-06-03 cs.LG cs.IR cs.SE

LoRACode: LoRA Adapters for Code Embeddings

Saumya Chaturvedi, Aman Chadha, Laurent Bindschaedler

机构 * Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所) AWS GenAI(AWS生成人工智能)

Comments Accepted at the Deep Learning for Code (DL4C) Workshop at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14673 2025-06-03 stat.ML cs.LG

Self-supervised contrastive learning performs non-linear system identification

Rodrigo González Laiz, Tobias Schmidt, Steffen Schneider

机构 * Institute of Computational Biology, Computational Health Center, Helmholtz Munich and Munich Center for Machine Learning (MCML)(计算生物学研究所、计算健康中心、海德堡慕尼黑和慕尼黑机器学习中心)

Comments Published as a conference paper at the Thirteenth International Conference on Learning Representations (ICLR 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.10882 2025-06-03 cs.CL

SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models

Zhuang Li, Yuncheng Hua, Thuy-Trang Vu, Haolan Zhan, Lizhen Qu, Gholamreza Haffari

机构 * School of Computing Technologies, RMIT University, Australia(皇家墨尔本理工大学计算机科技学院) 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) Department of Data Science & AI, Monash University, Australia(墨尔本大学数据科学与人工智能系)

Comments 35 pages (9th version), developed over 1.5 years. Previously submitted to EMNLP 2024 and ICLR 2025, with revisions based on extensive review feedback. Now accepted to ACL 2025 main

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.16646 2025-06-03 cs.LG cs.CR

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective

Ming-Yu Chung, Sheng-Yen Chou, Chia-Mu Yu, Pin-Yu Chen, Sy-Yen Kuo, Tsung-Yi Ho

机构 * National Taiwan University(台湾大学) The Chinese University of Hong Kong(香港中文大学) National Yang Ming Chiao Tung University(阳明交通大学) IBM Research(IBM研究院)

Comments 21 pages, 1 figures, 17 tables

Journal ref Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.13391 2025-06-03 cs.LG cs.AI cs.NE

Learning Successor Features with Distributed Hebbian Temporal Memory

Evgenii Dzhivelikian, Petr Kuderov, Aleksandr I. Panov

机构 * MIPT(莫斯科物理技术学院) AIRI(人工智能研究所)

Comments Poster on ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏