ICLR

Beyond Next Token Prediction: Patch-Level Training for Large Language Models

Chenze Shao, Fandong Meng, Jie Zhou

机构 * Pattern Recognition Center, WeChat AI, Tencent Inc（模式识别中心、微信AI、腾讯公司） 纠错

Comments ICLR 2025 Spotlight

Offline Reinforcement Learning for Microgrid Voltage Regulation

Shan Yang, Yongli Zhu

机构 * School of System Science and Engineering（系统科学与工程学院） 纠错

Comments This paper has been accepted and presented at ICLR 2025 in Singapore, Apr. 28, 2025

Heterogeneous graph neural networks for species distribution modeling

Lauren Harrell, Christine Kaeser-Chen, Burcu Karagol Ayan, Keith Anderson, Michelangelo Conserva, Elise Kleeman, Maxim Neumann, Matt Overlan, Melissa Chapman, Drew Purves

机构 * Google Research（谷歌研究） ； Google DeepMind（谷歌DeepMind） 纠错

Comments 13 pages, 3 figures,

Journal ref ICLR 2025 Workshop on Tackling Climate Change with Machine Learning

Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation

Bo Meng, Chenghao Xu, Yongli Zhu

机构 * School of System Science and Engineering（系统科学与工程学院） 纠错

Comments This paper has been accepted and presented at ICLR 2025 in Singapore, Apr. 28, 2025

When repeats drive the vocabulary: a Byte-Pair Encoding analysis of T2T primate genomes

Marina Popova, Iaroslav Chelombitko, Aleksey Komissarov

机构 * JetBrains Neapolis University（JetBrains尼泊利大学） ； aglabx 纠错

Comments ICLR 2025 Workshop on Machine Learning for Genomics Explorations

Deep Signature: Characterization of Large-Scale Molecular Dynamics

Tiexin Qin, Mengxu Zhu, Chunyang Li, Terry Lyons, Hong Yan, Haoliang Li

机构 * City University of Hong Kong（香港城市大学） ； Chengdu Institute of Biological Products co. Ltd（成都生物制品研究所） ； University of Oxford（牛津大学） 纠错

Comments ICLR 2025

Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning

Xinyue Wang, Biwei Huang

机构 * University of California San Diego（加州大学圣地亚哥分校） 纠错

Comments Published as a conference paper at ICLR 2025

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

Yunyue Wei, Shanning Zhuang, Vincent Zhuang, Yanan Sui

机构 * Tsinghua University（清华大学） ； Google DeepMind（谷歌DeepMind） 纠错

Comments Accepted by ICLR 2025

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

Hao Cui, Zahra Shamsi, Gowoon Cheon, Xuejian Ma, Shutong Li, Maria Tikhanovskaya, Peter Norgaard, Nayantara Mudur, Martyna Plomecka, Paul Raccuglia, Yasaman Bahri, Victor V. Albert, Pranesh Srinivasan, Haining Pan, Philippe Faist, Brian Rohr, Ekin Dogus Cubuk, Muratahan Aykol, Amil Merchant, Michael J. Statt, Dan Morris, Drew Purves, Elise Kleeman, Ruth Alcantara, Matthew Abraham, Muqthar Mohammad, Ean Phing VanLee, Chenfei Jiang, Elizabeth Dorfman, Eun-Ah Kim, Michael P Brenner, Viren Jain, Sameera Ponda, Subhashini Venugopalan

机构 * Google（谷歌） ； Harvard（哈佛大学） ； University of Zurich（苏黎世大学） ； NIST（国家标准与技术研究院） ； UMD College Park（大学公园大学分校） ； Rutgers（罗格斯大学） ； FU Berlin（柏林自由大学） ； Modelyst ； Cornell（康奈尔大学） 纠错

Comments Accepted at ICLR 2025 main conference

Nesterov acceleration in benignly non-convex landscapes

Kanan Gupta, Stephan Wojtowytsch

机构 * Department of Mathematics, University of Pittsburgh（数学系，匹兹堡大学） 纠错

Comments ICLR 2025 Spotlight

Improving Tropical Cyclone Forecasting With Video Diffusion Models

Zhibo Ren, Pritthijit Nath, Pancham Shukla

Comments Recommended for spotlight presentation at the ICLR 2025 workshop on Tackling Climate Change with Machine Learning. 7 pages, 7 figures

Leveraging State Space Models in Long Range Genomics

Matvei Popov, Aymen Kallala, Anirudha Ramesh, Narimane Hennouni, Shivesh Khaitan, Rick Gentry, Alain-Sam Cohen

机构 * InstaDeep 纠错

Comments Accepted at ICLR 2025 (Spotlight @ LMRL) - Project page: https://anirudharamesh.github.io/iclr-long-range-genomics/

Moral Alignment for LLM Agents

Elizaveta Tennant, Stephen Hailes, Mirco Musolesi

机构 * University College London（伦敦大学学院） ； University of Bologna（博洛尼亚大学） 纠错

Comments Published at the 13th International Conference on Learning Representations (ICLR'25), Singapore, Apr 2025. https://openreview.net/forum?id=MeGDmZjUXy

Looped Transformers for Length Generalization

Ying Fan, Yilun Du, Kannan Ramchandran, Kangwook Lee

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Massachusetts Institute of Technology（麻省理工学院） ； UC Berkeley（加州大学伯克利分校） 纠错

Comments ICLR 2025

Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification

Kaizheng Wang, Fabio Cuzzolin, Keivan Shariatmadar, David Moens, Hans Hallez

机构 * DistriNet, Department of Computer Science, KU Leuven, Belgium（DistriNet，计算机科学系，KU Leuven，比利时） ； LMSD, Department of Mechanical Engineering, KU Leuven, Belgium（LMSD，机械工程系，KU Leuven，比利时） ； School of Engineering, Computing and Mathematics, Oxford Brookes University, UK（工程、计算与数学学院，奥克斯福德布鲁克斯大学，英国） ； M-Group, KU Leuven, Belgium（M-Group，KU Leuven，比利时） 纠错

Comments The 13th International Conference on Learning Representations (ICLR). 2025 [Spotlight]

Assessing Robustness to Spurious Correlations in Post-Training Language Models

Julia Shuieh, Prasann Singhal, Apaar Shanker, John Heyer, George Pu, Samuel Denton

机构 * Scale AI 纠错

Comments ICLR '25 Workshop on Spurious Correlation and Shortcut Learning

Physics-informed Temporal Difference Metric Learning for Robot Motion Planning

Ruiqi Ni, Zherong Pan, Ahmed H Qureshi

机构 * Purdue University（普渡大学） ； Lightspeed Studios 纠错

Comments Accepted to ICLR 2025

Score-based Self-supervised MRI Denoising

Jiachen Tu, Yaokun Shi, Fan Lam

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits

Ashish Khisti, M. Reza Ebrahimi, Hassan Dbouk, Arash Behboodi, Roland Memisevic, Christos Louizos

机构 * Qualcomm AI Research（高通人工智能研究） ； University of Toronto（多伦多大学） 纠错

Comments Published as a (spotlight) conference paper at ICLR 2025

DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding

Henry Zheng, Hao Shi, Qihang Peng, Yong Xien Chng, Rui Huang, Yepeng Weng, Zhongchao Shi, Gao Huang

机构 * Department of Automation, BNRist, Tsinghua University（自动化系、BNRist、清华大学） ； AI Lab, Lenovo Research（联想研究院人工智能实验室） 纠错

Comments Accepted by ICLR 2025

MatMMFuse: Multi-Modal Fusion model for Material Property Prediction

Abhiroop Bhattacharya, Sylvain G. Cloutier

机构 * Department of Electrical Engineering, École de technologie supérieure, Montréal, Canada（电气工程系，超技术学院，蒙特利尔，加拿大） 纠错

Comments Presented at AI for Accelerated Materials Design(AI4Mat), ICLR 2025 (https://openreview.net/forum?id=pN4Zg6HBlq#discussion)

Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness

Michael Crawshaw, Mingrui Liu

Comments ICLR 2025

Re-evaluating Open-ended Evaluation of Large Language Models

Siqi Liu, Ian Gemp, Luke Marris, Georgios Piliouras, Nicolas Heess, Marc Lanctot

机构 * Google DeepMind（谷歌DeepMind） 纠错

Comments Published at ICLR 2025

MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Junyi Zhang, Charles Herrmann, Junhwa Hur, Varun Jampani, Trevor Darrell, Forrester Cole, Deqing Sun, Ming-Hsuan Yang

机构 * UC Berkeley（加州大学伯克利分校） ； Google DeepMind（谷歌DeepMind） ； Stability AI ； UC Merced（加州大学默塞德分校） 纠错

Comments Accepted by ICLR 25, Project page: https://monst3r-project.github.io/

C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front

Ruohong Liu, Yuxin Pan, Linjie Xu, Lei Song, Jiang Bian, Pengcheng You, Yize Chen

机构 * University of Oxford（牛津大学） ； The Hong Kong University of Science and Technology（香港科学与技术大学） ； Queen Mary University of London（伦敦大学玛丽女王学院） ； Microsoft Research Asia（微软亚洲研究院） ； Peking University（北京大学） ； University of Alberta（阿尔伯塔大学） 纠错

Comments Published as a conference paper at ICLR 2025. Code available at https://github.com/RuohLiuq/C-MORL

Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport

Zhenyi Zhang, Tiejun Li, Peijie Zhou

机构 * LMAM and School of Mathematical Sciences, Peking University（北京大学应用数学系和数学科学学院） ； Center for Machine Learning Research, Peking University（北京大学机器学习研究中心） ； NELBDA, Peking University（北京大学NELBDA） ； Center for Quantitative Biology, Peking University（北京大学定量生物学中心） ； AI for Science Institute, Beijing（北京人工智能科学研究院） 纠错

Comments Published as a conference paper at ICLR 2025 (oral)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, Greg Durrett

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Johns Hopkins University（约翰霍普金斯大学） ； Princeton University（普林斯顿大学） 纠错

Comments Published at ICLR 2025

Generalizable Human Gaussians from Single-View Image

Jinnan Chen, Chen Li, Jianfeng Zhang, Lingting Zhu, Buzhen Huang, Hanlin Chen, Gim Hee Lee

机构 * National University of Singapore（新加坡国立大学） ； The University of Hong Kong（香港大学） 纠错

Comments ICLR 2025: https://jinnan-chen.github.io/projects/HGM/

Exploring Learning Complexity for Efficient Downstream Dataset Pruning

Wenyu Jiang, Zhenlong Liu, Zejian Xie, Songxin Zhang, Bingyi Jing, Hongxin Wei

机构 * Department of Statistics and Data Science, Southern University of Science and Technology（统计与数据科学系，南方科技大学） ； State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学） 纠错

Comments Accepted by ICLR 2025

Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters

Roberto Garcia, Jerry Liu, Daniel Sorvisto, Sabri Eyuboglu

机构 * Institute of Computational and Mathematical Engineering, Stanford University（计算与数学工程研究所，斯坦福大学） ； Department of Computer Science, Stanford University（计算机科学系，斯坦福大学） 纠错

Comments 16 pages, 5 figures. ICLR 2025