ICLR

The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE

Andrei Chernov, Oleg Novitskij

Comments Accepted at the ICLR Workshop on Neural Network Weights as a New Data Modality 2025

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

Jun Zhang, Jue Wang, Huan Li, Lidan Shou, Ke Chen, Yang You, Guiming Xie, Xuejian Gong, Kunlong Zhou

Comments Accepted at ICLR 2025

SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

Yuqi Lin, Hengjia Li, Wenqi Shao, Zheng Yang, Jun Zhao, Xiaofei He, Ping Luo, Kaipeng Zhang

Comments Accepted to ICLR 2025

Skill Expansion and Composition in Parameter Space

Tenglong Liu, Jianxiong Li, Yinan Zheng, Haoyi Niu, Yixing Lan, Xin Xu, Xianyuan Zhan

Comments ICLR 2025, 37 pages

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics

Lu Yi, Jie Peng, Yanping Zheng, Fengran Mo, Zhewei Wei, Yuhang Ye, Yue Zixuan, Zengfeng Huang

Comments published at ICLR 2025

Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

Akash Kumar, Zsolt Kira, Yogesh Singh Rawat

Comments ICLR'25 Main Conference. Project Page: https://akash2907.github.io/cospal_webpage

Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks

Maximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto, Janine Strotherm, Luca Hermes, Alessandro Sperduti, Eyke Hüllermeier, Barbara Hammer

Comments Preprint Version. Accepted at ICLR 2025

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

Jiale Cheng, Xiao Liu, Cunxiang Wang, Xiaotao Gu, Yida Lu, Dan Zhang, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang

Comments ICLR 2025

Transformers Struggle to Learn to Search

Abulhair Saparov, Srushti Pawar, Shreyas Pimpalgaonkar, Nitish Joshi, Richard Yuanzhe Pang, Vishakh Padmakumar, Seyed Mehran Kazemi, Najoung Kim, He He

Comments Published as a conference paper at ICLR 2025

Convex Formulations for Training Two-Layer ReLU Neural Networks

Karthik Prakhya, Tolga Birdal, Alp Yurtsever

Comments Published as a conference paper at ICLR 2025

L3Ms -- Lagrange Large Language Models

Guneet S. Dhillon, Xingjian Shi, Yee Whye Teh, Alex Smola

Comments International Conference on Learning Representations (ICLR), 2025

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

Shilin Lu, Zihan Zhou, Jiayou Lu, Yuanzhi Zhu, Adams Wai-Kin Kong

Comments Accepted by ICLR 2025

AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models

Kim Sung-Bin, Oh Hyun-Bin, JungMok Lee, Arda Senocak, Joon Son Chung, Tae-Hyun Oh

Comments ICLR 2025

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

Minhyuk Seo, Hyunseo Koh, Jonghyun Choi

Comments ICLR 2025 Spotlight

Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning

Yan Scholten, Stephan Günnemann

Comments Accepted at ICLR 2025 (Spotlight)

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

Ge Li, Dong Tian, Hongyi Zhou, Xinkai Jiang, Rudolf Lioutikov, Gerhard Neumann

Comments Accepted as a Spotlight at ICLR 2025

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

SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models

Haotian Xia, Zhengbang Yang, Junbo Zou, Rhys Tracy, Yuqing Wang, Chi Lu, Christopher Lai, Yanjun He, Xun Shao, Zhuoqing Xie, Yuan-fang Wang, Weining Shen, Hanjie Chen

Comments ICLR 2025 Poster

MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction

Hossein Resani, Behrooz Nasihatkon

Comments Accepted to ICLR 2025, Singapore

Pyramidal Flow Matching for Efficient Video Generative Modeling

Yang Jin, Zhicheng Sun, Ningyuan Li, Kun Xu, Kun Xu, Hao Jiang, Nan Zhuang, Quzhe Huang, Yang Song, Yadong Mu, Zhouchen Lin

Comments ICLR 2025

Reasoning Elicitation in Language Models via Counterfactual Feedback

Alihan Hüyük, Xinnuo Xu, Jacqueline Maasch, Aditya V. Nori, Javier González

Comments The 13th International Conference on Learning Representations (ICLR 2025)

Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory

Alexander Levine, Peter Stone, Amy Zhang

Comments ICLR 2025

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

Yu Ying Chiu, Liwei Jiang, Yejin Choi

Comments Accepted into ICLR 2025 (spotlight)

GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation

Yangtao Chen, Zixuan Chen, Junhui Yin, Jing Huo, Pinzhuo Tian, Jieqi Shi, Yang Gao

Comments ICLR 2025. The first two authors contributed equally

Policy Prototyping for LLMs: Pluralistic Alignment via Interactive and Collaborative Policymaking

K. J. Kevin Feng, Inyoung Cheong, Quan Ze Chen, Amy X. Zhang

Comments Bidirectional Human-AI Alignment (Bi-Align) Workshop @ ICLR 2025

Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation

Jiaming Shen, Ran Xu, Yennie Jun, Zhen Qin, Tianqi Liu, Carl Yang, Yi Liang, Simon Baumgartner, Michael Bendersky

Comments ICLR 2025 SSI-FM version

Composable Interventions for Language Models

Arinbjorn Kolbeinsson, Kyle O'Brien, Tianjin Huang, Shanghua Gao, Shiwei Liu, Jonathan Richard Schwarz, Anurag Vaidya, Faisal Mahmood, Marinka Zitnik, Tianlong Chen, Thomas Hartvigsen

Comments Published at ICLR 2025

Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention

Tongzhou Liao, Barnabás Póczos

Comments Published as a conference paper at ICLR 2025

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith

Comments ICLR 2025, 32 pages, 8 figures, 9 tables

Scaling Large Language Model-based Multi-Agent Collaboration

Chen Qian, Zihao Xie, YiFei Wang, Wei Liu, Kunlun Zhu, Hanchen Xia, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, Maosong Sun

Comments Accepted to ICLR-2025

P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks

Malyaban Bal, Abhronil Sengupta

Comments Accepted at ICLR 2025