ICML 2025 Conference Submissions

How to set AdamW's weight decay as you scale model and dataset size
Xi Wang, Laurence Aitchison
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
ZipAR: Parallel Autoregressive Image Generation through Spatial Locality
Yefei He, Feng Chen, Yuanyu He, Shaoxuan He, Hong Zhou, Kaipeng Zhang, Bohan Zhuang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Point Cloud Dataset Distillation
Deyu Bo, Xinchao Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning Input Encodings for Kernel-Optimal Implicit Neural Representations
Zhemin Li, Liyuan Ma, Hongxia Wang, Yaoyun Zeng, Xiaolong Han
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Efficient Network Automatic Relevance Determination
Hongwei Zhang, Ziqi Ye, Xinyuan Wang, Xin Guo, Zenglin Xu, Yuan Cheng, Zixin Hu, Yuan Qi
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Label Distribution Propagation-based Label Completion for Crowdsourcing
Tong Wu, Liangxiao Jiang, Wenjun Zhang, Chaoqun Li
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
TLLC: Transfer Learning-based Label Completion for Crowdsourcing
Wenjun Zhang, Liangxiao Jiang, Chaoqun Li
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
On the Out-of-Distribution Generalization of Self-Supervised Learning
Wenwen Qiang, Jingyao Wang, Zeen Song, Jiangmeng Li, Changwen Zheng
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Rectified Robust Policy Optimization for Robust Constrained Reinforcement Learning without Strong Duality
Shaocong Ma, Ziyi Chen, Yi Zhou, Heng Huang
- 20 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Attention-Only Transformers via Unrolled Subspace Denoising
Peng Wang, Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu, Yi Ma
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
Weiqiu You, Helen Qu, Marco Gatti, Bhuvnesh Jain, Eric Wong
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
Amir Najafi, Samin Mahdizadeh Sani, Farzan Farnia
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
Junwei Su, shan Wu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
Junwei Su, Chuan Wu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
Junwei Su, Chuan Wu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Adversarial Combinatorial Semi-bandits with Graph Feedback
Yuxiao Wen
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Dynamic Range Reduction via Branch-and-Bound
Thore Gerlach, Nico Piatkowski
- 19 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
Aviv Bick, Eric P. Xing, Albert Gu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
Yuanhe Zhang, Fanghui Liu, Yudong Chen
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training
Geon-Woo Kim, Junbo Li, Shashidhar Gandham, Omar Baldonado, Adithya Gangidi, Pavan Balaji, Zhangyang Wang, Aditya Akella
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
Zhongweiyang Xu, Xulin Fan, Zhong-Qiu Wang, Xilin Jiang, Romit Roy Choudhury
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Permutation Equivariant Neural Networks for Symmetric Tensors
Edward Pearce-Crump
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Non-invasive electromyographic speech neuroprosthesis: a geometric perspective
Harshavardhana T Gowda, Ferdous Rahimi, Lee M. Miller
- 19 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Flow Q-Learning
Seohong Park, Qiyang Li, Sergey Levine
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone