ICML 2025 Workshop EXAIT Submissions

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh, Zebang Shen, Niao He, Andreas Krause
- Published: 12 Jun 2025, Last Modified: 09 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Instance-Dependent Fixed-Budget Pure Exploration in Reinforcement Learning
Yeongjong Kim, Yeoneung Kim, Kwang-Sung Jun
- Published: 12 Jun 2025, Last Modified: 04 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Kevin: Multi-Turn RL for Generating CUDA Kernels
Carlo Baronio, Pietro Marsella, Ben Pan, Simon Guo, Silas Alberti
- Published: 12 Jun 2025, Last Modified: 30 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
Qiuyi Zhang, David Madras, Joshua Safyan
- Published: 12 Jun 2025, Last Modified: 02 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
- Published: 12 Jun 2025, Last Modified: 04 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
In-Context Learning for Pure Exploration
Alessio Russo, Ryan Welch, Aldo Pacchiano
- Published: 12 Jun 2025, Last Modified: 09 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Strategic Vantage Selection for Learning Viewpoint-Agnostic Manipulation Policies
Sreevishakh Vasudevan, Som Sagar, Ransalu Senanayake
- Published: 12 Jun 2025, Last Modified: 07 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
Amrith Setlur, Matthew Y. R. Yang, Charlie Victor Snell, Jeremiah Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar
- Published: 12 Jun 2025, Last Modified: 25 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Exploration in Reinforcement Learning towards Higher Moment Regularisations
Ke Sun, Yingnan Zhao, Enze Shi, Yafei Wang, Xiaodong Yan, Bei Jiang, Linglong Kong
- Published: 12 Jun 2025, Last Modified: 30 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
Thomas Schmied, Jörg Bornschein, Jordi Grau-Moya, Markus Wulfmeier, Razvan Pascanu
- Published: 12 Jun 2025, Last Modified: 10 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
Xiaojun Guo, Ang Li, Yifei Wang, Stefanie Jegelka, Yisen Wang
- Published: 12 Jun 2025, Last Modified: 21 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
EVOLvE: Evaluating and Optimizing LLMs ForIn-Context Exploration
Allen Nie, Yi Su, Bo Chang, Jonathan Lee, Ed H. Chi, Quoc V Le, Minmin Chen
- Published: 12 Jun 2025, Last Modified: 21 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Reinforcement Learning with Action Chunking
Qiyang Li, Zhiyuan Zhou, Sergey Levine
- Published: 12 Jun 2025, Last Modified: 20 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Testing LLM Understanding of Scientific Literature through Expert-Driven Question Answering: Insights from High-Temperature Superconductivity
Haoyu Guo, Maria Tikhanovskaya, Paul Raccuglia, Alexey Vlaskin, Christopher Co, Daniel J. Liebling, Scott Ellsworth, Matthew Abraham, Elizabeth Dorfman, N.P. Armitage, John M. Tranquada, Senthil Todadri, Antoine Georges, Subir Sachdev, Steven Kivelson, B. J. Ramshaw, Chunhan Feng, Olivier Gingras, Vadim Oganesyan, Michael Brenner et al. (2 additional authors not shown)
- Published: 12 Jun 2025, Last Modified: 09 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Provably Learning from Language Feedback
Wanqiao Xu, Allen Nie, Ruijie Zheng, Aditya Modi, Adith Swaminathan, Ching-An Cheng
- Published: 12 Jun 2025, Last Modified: 07 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Rethinking Exploration In Asynchronous Bayesian Optimization: Standard Acquisition Is All You Need
Ben Riegler, James A C Odgers, Vincent Fortuin
- Published: 12 Jun 2025, Last Modified: 02 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
Leander Diaz-Bone, Marco Bagatella, Jonas Hübotter, Andreas Krause
- Published: 12 Jun 2025, Last Modified: 25 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Stabilizing protein fitness predictors via the PCS framework
Omer Ronen, Alex Y. Zhao, Ron Boger, Chengzhong Ye, Bin Yu
- Published: 12 Jun 2025, Last Modified: 06 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Towards Unsupervised Multi-Agent Reinforcement Learning via Task-Agnostic Exploration
Riccardo Zamboni, Mirco Mutti, Marcello Restelli
- Published: 12 Jun 2025, Last Modified: 25 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Reimagining Parameter Space Exploration with Diffusion Models
Lijun Zhang, Xiao Liu, Hui Guan
- Published: 12 Jun 2025, Last Modified: 25 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
From Words to Rewards: Leveraging Natural Language for Reinforcement Learning
Belen Martin Urcelay, Andreas Krause, Giorgia Ramponi
- Published: 12 Jun 2025, Last Modified: 07 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
Jiaqi WANG, Kevin Qinghong Lin, James Cheng, Mike Zheng Shou
- Published: 12 Jun 2025, Last Modified: 07 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
A Diffusion Model to Shrink Proteins While Maintaining their Function
Ethan Baron, Alan Nawzad Amin, Ruben Weitzman, Debora Susan Marks, Andrew Gordon Wilson
- Published: 12 Jun 2025, Last Modified: 25 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM
Thang Duong, Minglai Yang, Chicheng Zhang
- Published: 12 Jun 2025, Last Modified: 09 Jul 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
Michael S Yao, James Gee, Osbert Bastani
- Published: 12 Jun 2025, Last Modified: 21 Jun 2025
- EXAIT@ICML 2025 Poster
- Readers: Everyone