ICLR

Accelerating Training with Neuron Interaction and Nowcasting Networks

Boris Knyazev, Abhinav Moudgil, Guillaume Lajoie, Eugene Belilovsky, Simon Lacoste-Julien

Comments ICLR 2025, code is https://github.com/SamsungSAILMontreal/nino

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, Tomas Pfister

Comments Accepted to ICLR 2025

Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation

Zhi Cen, Huaijin Pi, Sida Peng, Qing Shuai, Yujun Shen, Hujun Bao, Xiaowei Zhou, Ruizhen Hu

Comments Accepted as ICLR 2025 conference paper

Safety Representations for Safer Policy Learning

Kaustubh Mani, Vincent Mai, Charlie Gauthier, Annie Chen, Samer Nashed, Liam Paull

Comments Accepted at International Conference on Learning Representations (ICLR) 2025

QPM: Discrete Optimization for Globally Interpretable Image Classification

Thomas Norrenbrock, Timo Kaiser, Sovan Biswas, Ramesh Manuvinakurike, Bodo Rosenhahn

Journal ref The Thirteenth International Conference on Learning Representations, 2025

Can Textual Gradient Work in Federated Learning?

Minghui Chen, Ruinan Jin, Wenlong Deng, Yuanyuan Chen, Zhi Huang, Han Yu, Xiaoxiao Li

Comments Accepted at ICLR 2025

Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning

Berken Utku Demirel, Christian Holz

Comments To appear at the International Conference on Learning Representation (ICLR) 2025

Beyond Worst-Case Dimensionality Reduction for Sparse Vectors

Sandeep Silwal, David P. Woodruff, Qiuyi Zhang

Comments To appear in ICLR 2025

ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments

Hojae Han, Seung-won Hwang, Rajhans Samdani, Yuxiong He

Comments ICLR 2025

Implicit Search via Discrete Diffusion: A Study on Chess

Jiacheng Ye, Zhenyu Wu, Jiahui Gao, Zhiyong Wu, Xin Jiang, Zhenguo Li, Lingpeng Kong

Comments ICLR 2025

Learning Mask Invariant Mutual Information for Masked Image Modeling

Tao Huang, Yanxiang Ma, Shan You, Chang Xu

Comments ICLR 2025

Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning

Xinran Li, Xiaolu Wang, Chenjia Bai, Jun Zhang

Comments Accepted by the Thirteenth International Conference on Learning Representations (ICLR 2025)

UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting

Haoyuan Li, Yanpeng Zhou, Tao Tang, Jifei Song, Yihan Zeng, Michael Kampffmeyer, Hang Xu, Xiaodan Liang

Comments ICLR 2025; Corrected citation of Uni3D;

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning

Zenan Li, Zhaoyu Li, Wen Tang, Xian Zhang, Yuan Yao, Xujie Si, Fan Yang, Kaiyu Yang, Xiaoxing Ma

Comments Published as a conference paper at ICLR 2025. Code is available at https://github.com/Lizn-zn/NeqLIPS/

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

Zhiyuan Liu, Yanchen Luo, Han Huang, Enzhi Zhang, Sihang Li, Junfeng Fang, Yaorui Shi, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua

Comments ICLR 2025, 10 pages

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Ziteng Wang, Jun Zhu, Jianfei Chen

Comments ICLR 2025

Student-Informed Teacher Training

Nico Messikommer, Jiaxu Xing, Elie Aljalbout, Davide Scaramuzza

Journal ref International Conference on Learning Representations (ICLR) 2025

SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction

Yang Zhou, Hao Shao, Letian Wang, Steven L. Waslander, Hongsheng Li, Yu Liu

Comments Camera-ready version for ICLR 2025

Training-free Diffusion Model Alignment with Sampling Demons

Po-Hung Yeh, Kuang-Huei Lee, Jun-Cheng Chen

Comments 35 pages

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

Formation of Representations in Neural Networks

Liu Ziyin, Isaac Chuang, Tomer Galanti, Tomaso Poggio

Comments ICLR 2025 Spotlight

On the Optimal Memorization Capacity of Transformers

Tokio Kajitsuka, Issei Sato

Comments Published at ICLR 2025

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Xiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, Ming Jin

Comments Accepted by the 13th International Conference on Learning Representations (ICLR 2025)

RRM: Robust Reward Model Training Mitigates Reward Hacking

Tianqi Liu, Wei Xiong, Jie Ren, Lichang Chen, Junru Wu, Rishabh Joshi, Yang Gao, Jiaming Shen, Zhen Qin, Tianhe Yu, Daniel Sohn, Anastasiia Makarova, Jeremiah Liu, Yuan Liu, Bilal Piot, Abe Ittycheriah, Aviral Kumar, Mohammad Saleh

Comments Accepted in ICLR 2025

Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

Zuyan Liu, Yuhao Dong, Ziwei Liu, Winston Hu, Jiwen Lu, Yongming Rao

Comments Accepted to ICLR 2025

Solving Video Inverse Problems Using Image Diffusion Models

Taesung Kwon, Jong Chul Ye

Comments ICLR 2025; 25 pages, 17 figures

Real-Time Video Generation with Pyramid Attention Broadcast

Xuanlei Zhao, Xiaolong Jin, Kai Wang, Yang You

Comments ICLR 2025

ThinK: Thinner Key Cache by Query-Driven Pruning

Yuhui Xu, Zhanming Jie, Hanze Dong, Lei Wang, Xudong Lu, Aojun Zhou, Amrita Saha, Caiming Xiong, Doyen Sahoo

Comments ICLR 2025 (Spotlight)

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation

Gaurav Sahu, Abhay Puri, Juan Rodriguez, Amirhossein Abaskohi, Mohammad Chegini, Alexandre Drouin, Perouz Taslakian, Valentina Zantedeschi, Alexandre Lacoste, David Vazquez, Nicolas Chapados, Christopher Pal, Sai Rajeswar Mudumba, Issam Hadj Laradji

Comments Accepted to ICLR 2025

On Speeding Up Language Model Evaluation

Jin Peng Zhou, Christian K. Belardi, Ruihan Wu, Travis Zhang, Carla P. Gomes, Wen Sun, Kilian Q. Weinberger

Comments ICLR 2025

MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Qi He, Wangmeng Xiang, Hanyuan Chen, Jin-Peng Lan, Xianhui Lin, Kang Zhu, Bin Luo, Yifeng Geng, Xuansong Xie, Alexander G. Hauptmann

Comments Accepted by ICLR 2025, Project: https://modelscope.cn/studios/WordArt/WordArt