ICML 2025 Conference Submissions

AutoCATE: End-to-End, Automated Treatment Effect Estimation
Toon Vanderschueren, Tim Verdonck, Mihaela van der Schaar, Wouter Verbeke
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Provable Length Generalization in Sequence Prediction via Spectral Filtering
Annie Marsden, Evan Dogariu, Naman Agarwal, Xinyi Chen, Daniel Suo, Elad Hazan
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Théo Bontempelli, Thomas Bouabça, Tristan Cazenave
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Distillation Scaling Laws
Dan Busbridge, Amitis Shidani, Floris Weers, Jason Ramapuram, Etai Littwin, Russell Webb
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Inverse Flow and Consistency Models
Yuchen Zhang, Jian Zhou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Sub-Problem Quantum Alternating Operator Ansatz for Correlation Clustering
Lucas Fabian Naumann, Jannik Irmai, Bjoern Andres
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Modular Duality in Deep Learning
Jeremy Bernstein, Laker Newhouse
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Differential Coding for Training-Free ANN-to-SNN Conversion
Zihan Huang, Wei Fang, Tong Bu, Peng Xue, Zecheng Hao, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
Junkang Wu, Xue Wang, Zhengyi Yang, Jiancan Wu, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations
Evan Frick, Connor Chen, Joseph Tennyson, Tianle Li, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Ion Stoica
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
Daniel Palenicek, Florian Vogt, Jan Peters
- 23 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
Saul Santos, António Farinhas, Daniel C McNamee, Andre Martins
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Physics-Informed Generative Modeling of Wireless Channels
Benedikt Böck, Andreas Oeldemann, Timo Mayer, Francesco Rossetto, Wolfgang Utschick
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
Jan Schuchardt, Mina Dalirrooyfard, Jed Guzelkabaagac, Anderson Schneider, Yuriy Nevmyvaka, Stephan Günnemann
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
Tianci Liu, Ruirui Li, Zihan Dong, Hui Liu, Xianfeng Tang, Qingyu Yin, Linjun Zhang, Haoyu Wang, Jing Gao
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, Sercan O Arik
- 23 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
Dan-Xuan Liu, Chao Qian
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Functional Alignment Can Mislead: Examining Model Stitching
Damian Smith, Harvey Mannering, Antonia Marcu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Private Model Personalization Revisited
Conor Snedeker, Xinyu Zhou, Raef Bassily
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
Kexin Huang, Junkang Wu, Ziqian Chen, Xue Wang, Jinyang Gao, Bolin Ding, Jiancan Wu, Xiangnan He, Xiang Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
Huafeng Liu, Yiran Fu, Liping Jing, Hui Li, Shuyang Lin, Jingyue Shi, Deqiang Ouyang, Jian Yu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
Aaron Wenteler, Martina Occhetta, Nikhil Branson, Victor Curean, Magdalena Huebner, William Dee, William Connell, Siu Pui Chung, Alex Hawkins-Hooker, Yasha Ektefaie, César Miguel Valdez Córdova, Amaya Gallagher-Syed
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Vintix: Action Model via In-Context Reinforcement Learning
Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Ilya Zisman, Denis Tarasov, Alexander Nikulin, Vladislav Kurenkov
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone