ICML 2025 Conference Submissions

Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
Junyi Liao, Zihan Zhu, Ethan X Fang, Zhuoran Yang, Vahid Tarokh
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models
Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata, Matthias Bethge, Joshua B. Tenenbaum, Eric Schulz
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Aligned Multi Objective Optimization
Yonathan Efroni, Ben Kretzu, Daniel Jiang, Jalaj Bhandari, Zheqing Zhu, Karen Ullrich
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Organize the Web: Constructing Domains Enhances Pre-Training Data Curation
Alexander Wettig, Kyle Lo, Sewon Min, Hannaneh Hajishirzi, Danqi Chen, Luca Soldaini
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference
Mahendra Singh Thapa, Rui Li
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Field Matching: an Electrostatic Paradigm to Generate and Transfer Data
Alexander Kolesov, S. I. Manukhov, Vladimir Vladimirovich Palyulin, Alexander Korotin
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnovic, Se-Young Yun
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Efficiently Vectorized MCMC on Modern Accelerators
Hugh Dance, Pierre Glaser, Peter Orbanz, Ryan P Adams
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
GraphFLEx: Structure Learning $\underline{\text{F}}$ramework for $\underline{\text{L}}$arge $\underline{\text{Ex}}$panding $\underline{\text{Graph}}$s
Mohit Kataria, Nikita Malik, Sandeep Kumar, Jayadeva Jayadeva
- 23 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
Pengyi Li, Jianye HAO, Hongyao Tang, Yifu Yuan, Jinbin Qiao, Zibin Dong, YAN ZHENG
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
Pierre Ablin, Angelos Katharopoulos, Skyler Seto, David Grangier
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
Chao Ma, Wenbo Gong, Meyer Scetbon, Edward Meeds
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
Chenlu Ye, Yujia Jin, Alekh Agarwal, Tong Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
On the Power of Context-Enhanced Learning in LLMs
Xingyu Zhu, Abhishek Panigrahi, Sanjeev Arora
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals
Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Understanding the Logic of Direct Preference Alignment through Logic
Kyle Richardson, Vivek Srikumar, Ashish Sabharwal
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
Louis Béthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, marco cuturi, Pierre Ablin
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
Shib Sankar Dasgupta, Michael Boratko, Andrew McCallum
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
How Do Large Language Monkeys Get Their Power (Laws)?
Rylan Schaeffer, Joshua Kazdan, John Hughes, Jordan Juravsky, Sara Price, Aengus Lynch, Erik Jones, Robert Kirk, Azalia Mirhoseini, Sanmi Koyejo
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
Nikolaos Chaidos, Angeliki Dimitriou, Maria Lymperaiou, Giorgos Stamou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons
Velibor Bojkovic, Xiaofeng Wu, Bin Gu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment
Yunyi Shen, Hao Sun, Jean-Francois Ton
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Improved and Oracle-Efficient Online $\ell_1$-Multicalibration
Rohan Ghuge, Vidya Muthukumar, Sahil Singla
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Partially Observable Reinforcement Learning with Memory Traces
Onno Eberhard, Michael Muehlebach, Claire Vernade
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone