ICLR

Probabilistic Geometric Principal Component Analysis with application to neural data

Han-Lin Hsieh, Maryam M. Shanechi

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； Viterbi School of Engineering（维特比工程学院） ； University of Southern California（南加州大学） 纠错

Comments Published at the International Conference on Learning Representations (ICLR) 2025. Code is available at GitHub https://github.com/ShanechiLab/PGPCA.git

Journal ref ICLR 2025

ATLAS: Benchmarking and Adapting LLMs for Global Trade via Harmonized Tariff Code Classification

Pritish Yuvraj, Siva Devarakonda

Journal ref Paper in Review For ICLR 2026 (Workshop)

Packed-Ensembles for Efficient Uncertainty Estimation

Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, Gianni Franchi

机构 * Université Paris-Saclay, CEA, SGLS（巴黎萨克雷大学、CEA、SGLS） ； U2IS, ENSTA, Institut Polytechnique de Paris（U2IS、ENSTA、巴黎理工学院） ； LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI、巴黎电信学院、巴黎理工学院） 纠错

Comments Published as a conference paper at ICLR 2023 (notable 25%)

Post-hoc Reward Calibration: A Case Study on Length Bias

Zeyu Huang, Zihan Qiu, Zili Wang, Edoardo M. Ponti, Ivan Titov

机构 * University of Edinburgh（爱丁堡大学） ； Alibaba Group（阿里巴巴集团） ； INF Technology（INF技术） ； University of Amsterdam（阿姆斯特丹大学） 纠错

Comments ICLR 2025

Guided Sequence-Structure Generative Modeling for Iterative Antibody Optimization

Aniruddh Raghu, Sebastian Ober, Maxwell Kazman, Hunter Elliott

机构 * BigHat Biosciences（BigHat生物技术公司） ； University of Washington（华盛顿大学） 纠错

Comments GEM Workshop, ICLR 2025

FOSSIL: Regret-minimizing weighting for robust learning under imbalance and small data

J. Cha, J. Lee, J. Cho, J. Shin

机构 * Gwinnett Technical College（金尼特技术学院） ； Intel Corporation（英特尔公司） ； Prairie View A&M University（普里奥里视黑人大学） ； Ohio State University（俄亥俄州立大学） 纠错

Comments 24 pages, 6 figures, submitted to ICLR 2025

T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design

Jiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao, Robinson Piramuthu, Wenhu Chen, William Yang Wang

机构 * UC Santa Barbara（加州大学圣芭芭拉分校） ； UC Los Angeles（加州大学洛杉矶分校） ； Amazon AGI（亚马逊人工智能实验室） ； University of Waterloo（滑铁卢大学） 纠错

Comments Accepted by ICLR 2025. Project Page: https://t2v-turbo-v2.github.io/

Cutting Through the Noise: Boosting LLM Performance on Math Word Problems

Ujjwala Anantheswaran, Himanshu Gupta, Kevin Scaria, Shreyas Verma, Chitta Baral, Swaroop Mishra

机构 * Arizona State University（亚利桑那州立大学） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

Comments Published at ICLR 2025 Workshop on Reasoning and Planning for LLMs

STRIDE: Subset-Free Functional Decomposition for XAI in Tabular Settings

Chaeyun Ko

机构 * Independent Researcher（独立研究者） 纠错

Comments Major revision for submission to ICLR 2026. Substantially revised abstract, introduction, and discussion. Added new 'component surgery' analysis and updated benchmark results for clarity. (12 pages, 2 figures)

Pitfalls of Evidence-Based AI Policy

Stephen Casper, David Krueger, Dylan Hadfield-Menell

Comments Accepted to the ICLR 2025 blog post track

Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)

Maja Pavlovic

机构 * Queen Mary University London（伦敦玛丽女王大学） 纠错

Comments https://openreview.net/forum?id=BxBeCjQd2y

Journal ref https://iclr-blogposts.github.io/2025/blog/calibration/

Your Image is Secretly the Last Frame of a Pseudo Video

Wenlong Chen, Wenlin Chen, Lapo Rastrelli, Yingzhen Li

机构 * Imperial College London（伦敦帝国学院） ； University of Cambridge（剑桥大学） ； MPI for Intelligent Systems, Tübingen（图宾根智能系统研究所） 纠错

Comments Presented at the ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy (DeLTa). 1-frame results for CIFAR10 in Table 2 corrected. Code released

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

Richard Bergna, Sergio Calvo-Ordoñez, Felix L. Opolka, Pietro Liò, Jose Miguel Hernandez-Lobato

机构 * Department of Engineering, University of Cambridge（剑桥大学工程系） ； Mathematical Institute, University of Oxford（牛津大学数学系） ； Oxford-Man Institute of Quantitative Finance, University of Oxford（牛津大学量化金融研究所） ； Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系） 纠错

Comments Accepted at ICLR 2025 as Spotlight. 18 pages including appendix

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

Jiawei Wang, Jiacai Liu, Yuqian Fu, Yingru Li, Xintao Wang, Yuan Lin, Yu Yue, Lin Zhang, Yang Wang, Ke Wang

机构 * ByteDance Seed（字节跳动种子） 纠错

Comments ICLR 2026 Under review

Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals

Cheng Chen, Haiyan Yin, Ivor Tsang

机构 * Australian Artificial Intelligence Institute (AAII), University of Technology Sydney, Australia（澳大利亚人工智能研究所（AAII）、悉尼技术大学） ； Centre for Frontier AI Research, Institute of High Performance Computing（前沿人工智能研究中心、高性能计算研究所） ； Agency for Science, Technology and Research, Singapore（科技研究局（新加坡）） ； College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院、南洋理工大学） 纠错

Comments 11 pages, 10 figures

Journal ref Published ICLR 2025 Workshop on Scaling Self-Improving Foundation Models without Human Supervision

DEQuify your force field: More efficient simulations using deep equilibrium models

Andreas Burger, Luca Thiede, Alán Aspuru-Guzik, Nandita Vijaykumar

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； Acceleration Consortium（加速联盟） ； NVIDIA（英伟达） 纠错

Comments AI4MAT-ICLR-2025 Spotlight https://openreview.net/forum?id=XACVRYePQQ

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

Pablo Lemos, Sammy Sharief, Nikolay Malkin, Salma Salhi, Connor Stone, Laurence Perreault-Levasseur, Yashar Hezaveh

机构 * Mila – Québec Artificial Intelligence Institute（魁北克人工智能研究所） ； Ciela Institute（Ciela研究所） ； Université de Montréal（蒙特利尔大学） ； SanboxAQ ； CCA – Flatiron Institute（CCA-Flatiron研究所） ； University of Edinburgh（爱丁堡大学） ； Trottier Space Institute（特罗特里尔空间研究所） 纠错

Comments Published as a conference paper at ICLR 2025

Calibrating Transformers via Sparse Gaussian Processes

Wenlong Chen, Yingzhen Li

机构 * Imperial College London（伦敦帝国学院） 纠错

Comments Published at The Eleventh International Conference on Learning Representations (ICLR 2023). ECE updated, typo fixed

How Far Are We from True Unlearnability?

Kai Ye, Liangcai Su, Chenxiong Qian

机构 * The University of Hong Kong（香港大学） 纠错

Comments This paper has been accepted by ICLR 2025

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

Ce Zhang, Zifu Wan, Zhehan Kan, Martin Q. Ma, Simon Stepputtis, Deva Ramanan, Russ Salakhutdinov, Louis-Philippe Morency, Katia Sycara, Yaqi Xie

机构 * School of Computer Science, Carnegie Mellon University（计算机科学系，卡内基梅隆大学） 纠错

Comments Accepted by ICLR 2025. Project page: https://zhangce01.github.io/DeGF/

When Do Neural Networks Learn World Models?

Tianren Zhang, Guanyu Chen, Feng Chen

机构 * Department of Automation, Tsinghua University, Beijing, China（自动化系，清华大学，北京，中国） 纠错

Comments ICML 2025; ICLR 2025 World Models Workshop (oral, outstanding paper award)

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory

Francesco Mori, Stefano Sarao Mannelli, Francesca Mignacco

Comments 22 pages, 12 figures

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025). J. Stat. Mech. (2025) 084004

Multilevel Generative Samplers for Investigating Critical Phenomena

Ankur Singha, Elia Cellini, Kim A. Nicoli, Karl Jansen, Stefan Kühn, Shinichi Nakajima

机构 * BIFOLD ； Technische Universität Berlin（技术大学柏林） ； Università degli Studi di Torino（都灵大学） ； INFN Torino（托斯卡纳国家研究所） ； University of Bonn（波恩大学） ； Helmholtz Institute for Radiation and Nuclear Physics (HISKP)（辐射和核物理研究所） ； Deutsches Elektronen-Synchrotron (DESY)（德国电子同步辐射光源） ； RIKEN Center for AIP（理化学研究所AIP中心） 纠错

Comments 10 pages, 4 figures (main text); 13th International Conference on Learning Representations (ICLR 2025)

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

Error-quantified Conformal Inference for Time Series

Junxi Wu, Dongjian Hu, Yajie Bao, Shu-Tao Xia, Changliang Zou

机构 * School of Statistics and Data Science, LPMC, KLMDASR and LEBPS, Nankai University（统计与数据科学学院，LPMC，KLMDASR和LEBPS，南开大学） ； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） 纠错

Comments ICLR 2025 camera version (fixed the bug where citations could not be properly indexed in Google Scholar)

Concept Bottleneck Large Language Models

Chung-En Sun, Tuomas Oikarinen, Berk Ustun, Tsui-Wei Weng

Comments Accepted to ICLR 2025

Sequential Controlled Langevin Diffusions

Junhua Chen, Lorenz Richter, Julius Berner, Denis Blessing, Gerhard Neumann, Anima Anandkumar

机构 * University of Cambridge（剑桥大学） ； Zuse Institute Berlin（柏林图灵研究所） ； dida Datenschmiede GmbH（dida数据安全公司） ； NVIDIA（NVIDIA公司） ； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； California Institute of Technology（加州理工学院） 纠错

Comments In The Thirteenth International Conference on Learning Representations, 2025

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学Show实验室） ； ByteDance（字节跳动） 纠错

Comments ICLR 2025

Repetition Improves Language Model Embeddings

Jacob Mitchell Springer, Suhas Kotha, Daniel Fried, Graham Neubig, Aditi Raghunathan

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments ICLR 2025

Sesame: Opening the door to protein pockets

Raúl Miñán, Carles Perez-Lopez, Javier Iglesias, Álvaro Ciudad, Alexis Molina

机构 * Department of Artificial Intelligence, Nostrum Biodiscovery（人工智能系，诺斯特姆生物发现） ； Department of Drug Discovery, Nostrum Biodiscovery（药物发现系，诺斯特姆生物发现） ； Department of R&D, Nostrum Biodiscovery（研发部，诺斯特姆生物发现） 纠错

Comments Published at the Proceedings of the 2nd Workshop on Generative and Experimental Perspectives for Biomolecular Design. ICLR 2025

Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval

Shunyu Zhang, Yaobo Liang, Ming Gong, Daxin Jiang, Nan Duan

机构 * Microsoft Research Asia（微软亚洲研究院） 纠错

Comments Published at ICLR 2023