ICML 2025 Conference Submissions

Boosting Protein Graph Representations through Static-Dynamic Fusion
Pengkang Guo, Bruno Correia, Pierre Vandergheynst, Daniel Probst
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
Terje Mildner, Oliver Hamelijnck, Paris Giampouras, Theodoros Damoulas
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
Ju-Seung Byun, Andrew Perrault
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Stronger Neyman Regret Guarantees for Adaptive Experimental Design
Georgy Noarov, Riccardo Fogliato, Martin Andres Bertran, Aaron Roth
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Joint Localization and Activation Editing for Low-Resource Fine-Tuning
Wen Lai, Alexander Fraser, Ivan Titov
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
Multiple-policy Evaluation via Density Estimation
Yilei Chen, Aldo Pacchiano, Ioannis Paschalidis
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
Yukang Yang, Declan Iain Campbell, Kaixuan Huang, Mengdi Wang, Jonathan D. Cohen, Taylor Whittington Webb
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
Carlota Parés Morlans, Michelle Yi, Claire Chen, Sarah A Wu, Rika Antonova, Tobias Gerstenberg, Jeannette Bohg
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
CoastalBench: A Decade-Long High-Resolution Dataset to Emulate Complex Coastal Processes
Zelin Xu, Yupu Zhang, Tingsong Xiao, Maitane Olabarrieta Lizaso, Jose M. Gonzalez-Ondina, Zibo Liu, Shigang Chen, Zhe Jiang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Probabilistic Factorial Experimental Design for Combinatorial Interventions
Divya Shyamal, Jiaqi Zhang, Caroline Uhler
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation
Shyam Nuggehalli, Jifan Zhang, Lalit K Jain, Robert D Nowak
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Auditing $f$-differential privacy in one run
Saeed Mahloujifar, Luca Melis, Kamalika Chaudhuri
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
Dujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang, Daniel Madrigal, Mirian Del Carmen Hipolito Garcia, Menglin Xia, Laks V. S. Lakshmanan, Qingyun Wu, Victor Rühle
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
Alexander Bienstock, Ujjwal Kumar, Antigoni Polychroniadou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models
Etowah Adams, Liam Bai, Minji Lee, Yiyang Yu, Mohammed AlQuraishi
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Which Attention Heads Matter for In-Context Learning?
Kayo Yin, Jacob Steinhardt
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning with Expected Signatures: Theory and Applications
Lorenzo Lucchese, Mikko S. Pakkanen, Almut E. D. Veraart
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning
Ankit Pratap Singh, Ahmed Ali Abbasi, Namrata Vaswani
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
Aditya Gorla, Ryan Wang, Zhengtong Liu, Ulzee An, Sriram Sankararaman
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Constrained Pareto Set Identification with Bandit Feedback
Cyrille Kone, Emilie Kaufmann, Laura Richert
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Theoretical Framework For Overfitting In Energy-based Modeling
Giovanni Catania, Aurélien Decelle, Cyril Furtlehner, Beatriz Seoane
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving
Ankit Bhardwaj, Amar Phanishayee, Deepak Narayanan, Ryan Stutsman
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
The Lock-in Hypothesis: Stagnation by Algorithm
Tianyi Qiu, Zhonghao He, Tejasveer Chugh, Max Kleiman-Weiner
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Wasserstein Flow Matching: Generative Modeling Over Families of Distributions
Doron Haviv, Aram-Alexandre Pooladian, Dana Pe'er, Brandon Amos
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone