ICML 2025 Conference Submissions

Understanding the difficulties of posterior predictive estimation
Abhinav Agrawal, Justin Domke
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Scaling Sparse Feature Circuits For Studying In-Context Learning
Dmitrii Kharlapenko, Stepan Shabalin, Arthur Conmy, Neel Nanda
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
Gabriel Thompson, Kai Yue, Chau-Wai Wong, Huaiyu Dai
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Tokenized Bandit for LLM Decoding and Alignment
Suho Shin, Chenghao Yang, Haifeng Xu, MohammadTaghi Hajiaghayi
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones
Urszula Julia Komorowska, Francisco Vargas, Alessandro Rondina, Pietro Lio, Mateja Jamnik
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
Lily H Zhang, Hamid Dadkhahi, Mara Finkelstein, Firas Trabelsi, Jiaming Luo, Markus Freitag
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Scalable Solver for 2p0s Differential Games with One-Sided Payoff Information and Continuous Actions, States, and Time
Mukesh Ghimire, Lei Zhang, Zhe Xu, Yi Ren
- 22 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Black-Box Adversarial Attacks on LLM-Based Code Completion
Slobodan Jenko, Niels Mündler, Jingxuan He, Mark Vero, Martin Vechev
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Accurate Identification of Communication Between Multiple Interacting Neural Populations
Belle Liu, Jacob Sacks, Matthew D. Golub
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Fully Dynamic Embedding into $\ell_p$ Spaces
Kiarash Banihashem, Xiang Chen, MohammadTaghi Hajiaghayi, Sungchul Kim, Kanak Mahadik, Ryan A. Rossi, Tong Yu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
Felipe Pinto Coelho Nuti, Tim Franzmeyer, Joao F. Henriques
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
Amirhossein Roknilamouki, Arnob Ghosh, Ming Shi, Fatemeh Nourzad, Eylem Ekici, Ness Shroff
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
Xinshuai Dong, Ignavier Ng, Boyang Sun, Haoyue Dai, Guang-Yuan Hao, Shunxing Fan, Peter Spirtes, Yumou Qiu, Kun Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
Zihan Zhang, Yuxin Chen, Jason D. Lee, Simon Shaolei Du, Ruosong Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Star Attention: Efficient LLM Inference over Long Sequences
Shantanu Acharya, Fei Jia, Boris Ginsburg
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Grokking at the Edge of Linear Separability
Alon Beck, Noam Itzhak Levi, Yohai Bar-Sinai
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
ULPT: Prompt Tuning with Ultra-Low-Dimensional Optimization
Zijun Wu, Yongchang Hao, Lili Mou
- 22 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
Bart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
Michael Munn, Susan Wei
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
Akhil Jalan, Yassir Jedra, Arya Mazumdar, Soumendu Sundar Mukherjee, Purnamrita Sarkar
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
On the Importance of Gaussianizing Representations
Daniel Eftekhari, Vardan Papyan
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Wait-Less Offline Tuning and Re-solving for Online Decision Making
Jingruo Sun, Wenzhi Gao, Ellen Vitercik, Yinyu Ye
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A standard transformer and attention with linear biases for molecular conformer generation
Viatcheslav Gurev, Timothy Rumbell
- 22 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
Integer Programming for Generalized Causal Bootstrap Designs
Jennifer Rogers Brennan, Sebastien Lahaie, Adel Javanmard, Nick Doudchenko, Jean Pouget-Abadie
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone