ICLR

IConMark: Robust Interpretable Concept-Based Watermark For AI Images

Vinu Sankar Sadasivan, Mehrdad Saberi, Soheil Feizi

Comments Accepted at ICLR 2025 Workshop on GenAI Watermarking (WMARK)

On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations

Guojun Xiong, Shufan Wang, Daniel Jiang, Jian Li

机构 * Harvard University（哈佛大学） ； Stony Brook University（石溪大学） ； Meta 纠错

Comments ICLR 2025

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization

Jui-Nan Yen, Si Si, Zhao Meng, Felix Yu, Sai Surya Duvvuri, Inderjit S. Dhillon, Cho-Jui Hsieh, Sanjiv Kumar

机构 * UCLA（加州大学洛杉矶分校） ； Google（谷歌） ； UT Austin（得克萨斯大学奥斯汀分校） 纠错

Comments Published as an oral paper at ICLR 2025. The code for our project is available at https://github.com/gkevinyen5418/LoRA-RITE

DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback

Guojun Xiong, Ujwal Dinesha, Debajoy Mukherjee, Jian Li, Srinivas Shakkottai

机构 * Harvard University（哈佛大学） ； Texas A&M University（德克萨斯大学） ； Stony Brook University（石溪大学） 纠错

Comments ICLR 2025

Metalic: Meta-Learning In-Context with Protein Language Models

Jacob Beck, Shikha Surana, Manus McAuliffe, Oliver Bent, Thomas D. Barrett, Juan Jose Garau Luis, Paul Duckworth

机构 * InstaDeep 纠错

Comments Published at The Thirteenth International Conference on Learning Representations (ICLR 2025). Code is provided at https://github.com/instadeepai/metalic. Also relevant to searches for "metallic", "meta-learning in-context", "LLM", and "protein language model"

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

Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation

Qing Wu, Chenhe Du, Xuanyu Tian, Jingyi Yu, Yuyao Zhang, Hongjiang Wei

机构 * ShanghaiTech University（上海科技大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments Accepted by ICLR 2025 Spotlight

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

Yuancheng Xu, Udari Madhushani Sehwag, Alec Koppel, Sicheng Zhu, Bang An, Furong Huang, Sumitra Ganesh

Comments Published at the Thirteenth International Conference on Learning Representations (ICLR 2025)

Divergence of Empirical Neural Tangent Kernel in Classification Problems

Zixiong Yu, Songtao Tian, Guhan Chen

机构 * Noah’s Ark Lab, Huawei Technologies Ltd.（华为技术有限公司诺亚实验室） ； Department of Mathematical Sciences, Tsinghua University（清华大学数学科学系） ； Department of Statistics and Data Science, Tsinghua University（清华大学统计与数据科学系） 纠错

Comments This is the revised version of our paper accepted at ICLR 2025, originally titled "Divergence of Neural Tangent Kernel in Classification Problems"

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Jiacheng Chen, Tianhao Liang, Sherman Siu, Zhengqing Wang, Kai Wang, Yubo Wang, Yuansheng Ni, Wang Zhu, Ziyan Jiang, Bohan Lyu, Dongfu Jiang, Xuan He, Yuan Liu, Hexiang Hu, Xiang Yue, Wenhu Chen

机构 * Core Contributors（核心贡献者） ； Tiger-AI-Lab（虎鲸人工智能实验室） 纠错

Comments ICLR 2025 camera-ready version. Project page: https://tiger-ai-lab.github.io/MEGA-Bench/

Topic Modeling as Multi-Objective Contrastive Optimization

Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu

机构 * Institute of Data Science (IDS), National University of Singapore (NUS)（数据科学研究所（IDS），新加坡国立大学） ； Nanyang Technological University (NTU)（南洋理工大学） ； Carnegie Mellon University (CMU)（卡内基梅隆大学） 纠错

Comments Accepted at ICLR 2024 (poster). Official version available at: https://openreview.net/forum?id=HdAoLSBYXj

IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

Shaokun Zhang, Xiaobo Xia, Zhaoqing Wang, Ling-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； The University of Sydney（悉尼大学） ； Tsinghua University（清华大学） ； Xidian University（西安电子科技大学） 纠错

Comments Accepted by ICLR 2024

Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation

Sua Lee, Kyubum Shin, Jung Ho Park

机构 * Seoul National University（首尔国立大学） ； Naver AI 纠错

Comments Published as a conference paper at ICLR 2025

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Yunfei Xie, Ce Zhou, Lang Gao, Juncheng Wu, Xianhang Li, Hong-Yu Zhou, Sheng Liu, Lei Xing, James Zou, Cihang Xie, Yuyin Zhou

机构 * Huazhong University of Science and Technology（华中科技大学） ； UC Santa Cruz（加州大学圣克ruz分校） ； Harvard University（哈佛大学） ； Stanford University（斯坦福大学） 纠错

Comments The dataset is publicly available at https://yunfeixie233.github.io/MedTrinity-25M/. Accepted to ICLR 2025

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning

Wei-Cheng Huang, Chun-Fu Chen, Hsiang Hsu

机构 * Global Technology Applied Research（全球技术应用研究） 纠错

Comments Accepted by ICLR 2024

DICE: Data Influence Cascade in Decentralized Learning

Tongtian Zhu, Wenhao Li, Can Wang, Fengxiang He

机构 * Zhejiang University（浙江大学） ； University of Edinburgh（爱丁堡大学） 纠错

Comments Published as a poster at ICLR 2025

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

Sebastian Sanokowski, Wilhelm Berghammer, Martin Ennemoser, Haoyu Peter Wang, Sepp Hochreiter, Sebastian Lehner

机构 * ELLIS Unit Linz, LIT AI Lab, Johannes Kepler University Linz, Austria（林茨ELLIS单元、LIT AI实验室、林茨约瑟夫·冯·海德里希大学，奥地利） ； Department of Electrical & Computer Engineering, Georgia Institute of Technology（电气与计算机工程系，佐治亚理工学院） ； NXAI Lab & NXAI GmbH, Linz, Austria（NXAI实验室及NXAI GmbH，林茨，奥地利） 纠错

Comments Accepted at ICLR 2025

On the relation between trainability and dequantization of variational quantum learning models

Elies Gil-Fuster, Casper Gyurik, Adrián Pérez-Salinas, Vedran Dunjko

机构 * Dahlem Center for Complex Quantum Systems, Freie Universität Berlin（弗里堡柏林自由大学复杂量子系统中心） ； Lorentz Instituut, Universiteit Leiden（莱顿大学洛伦兹研究所） ； LIACS, Universiteit Leiden（莱顿大学信息科学与计算研究所） 纠错

Comments 25 pages, 3 figures, published as a conference paper in Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025)

Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models

Eunseop Yoon, Hee Suk Yoon, Mark A. Hasegawa-Johnson, Chang D. Yoo

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） ； University of Illinois at Urbana-Champaign (UIUC)（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments ICLR 2025

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora

Journal ref International Conference on Learning Representations (ICLR 2025)

Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages

Wanru Zhao, Yihong Chen, Royson Lee, Xinchi Qiu, Yan Gao, Hongxiang Fan, Nicholas D. Lane

机构 * University of Cambridge（剑桥大学） ； University College London（伦敦大学学院） ； Samsung AI Center（三星人工智能中心） ； Flower Labs（Flower实验室） 纠错

Comments ICLR 2024

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Xiao Fu, Xian Liu, Xintao Wang, Sida Peng, Menghan Xia, Xiaoyu Shi, Ziyang Yuan, Pengfei Wan, Di Zhang, Dahua Lin

Comments ICLR 2025. Project Page & Code & Data: http://fuxiao0719.github.io/projects/3dtrajmaster

MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science

Erle Zhu, Yadi Liu, Zhe Zhang, Xujun Li, Jin Zhou, Xinjie Yu, Minlie Huang, Hongning Wang

机构 * The Conversational AI (CoAI) Group（对话人工智能小组） ； Department of Computer Science & Technology（计算机科学与技术系） ； Department of Electrical Engineering（电子工程系） 纠错

Journal ref Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025

Quantifying the Importance of Data Alignment in Downstream Model Performance

Krrish Chawla, Aryan Sahai, Mario DePavia, Sudharsan Sundar, Brando Miranda, Elyas Obbad, Sanmi Koyejo

机构 * stanford（斯坦福大学） 纠错

Journal ref ICLR DMLR Data-centric Machine Learning Research (2024), ICML DataWorld (2025)

Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data

Brando Miranda, Alycia Lee, Sudharsan Sundar, Allison Casasola, Rylan Schaeffer, Elyas Obbad, Sanmi Koyejo

机构 * Department of Computer Science, Stanford University（计算机科学系，斯坦福大学） 纠错

Journal ref Published as workshop paper in the Data-centric Machine Learning Research (DMLR) Workshop, ICLR 2024

MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered

Imran Mirza, Cole Huang, Ishwara Vasista, Rohan Patil, Asli Akalin, Sean O'Brien, Kevin Zhu

机构 * Algoverse AI Research（Algoverse AI研究院） 纠错

Comments Accepted to Building Trust in LLMs @ ICLR 2025 and NAACL SRW 2025

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

Zhiyuan Zhou, Andy Peng, Qiyang Li, Sergey Levine, Aviral Kumar

机构 * UC Berkeley（加州大学伯克利分校） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Journal ref International Conference on Learning Representation (ICLR) 2025

Guaranteed Generation from Large Language Models

Minbeom Kim, Thibaut Thonet, Jos Rozen, Hwaran Lee, Kyomin Jung, Marc Dymetman

机构 * Seoul National University（首尔国立大学） ； NAVER Labs Europe（NAVER欧洲实验室） ； NAVER AI Lab（NAVER人工智能实验室） ； Sogang University（成均馆大学） 纠错

Comments ICLR 2025

Long-Context Linear System Identification

Oğuz Kaan Yüksel, Mathieu Even, Nicolas Flammarion

机构 * EPFL Lausanne, Switzerland（洛桑联邦理工学院） ； Inria – ENS Paris, France（法国巴黎国家科学研究中心 – 巴黎高等师范学院） 纠错

Comments Published at ICLR 2025. This version includes minor corrections and improved grammar from the published version. 34 pages, 4 figures

Journal ref O. K. Yüksel, M. Even, N. Flammarion, "Long-Context Linear System Identification", in The Thirteenth International Conference on Learning Representations, 2025

Transformers from Diffusion: A Unified Framework for Neural Message Passing

Qitian Wu, David Wipf, Junchi Yan

Comments Published in Journal of Machine Learning Research (JMLR). Extended from DIFFormer in ICLR 2023

Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts

Lizhang Chen, Bo Liu, Kaizhao Liang, Qiang Liu

Comments ICLR 2024 Spotlight