ICML 2025 Conference Submissions

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse, Patrick Knab, Sascha Marton, Christian Bartelt, Margret Keuper
- Published: 01 May 2025, Last Modified: 07 Jul 2025
- ICML 2025 poster
- Readers: Everyone
SPEX: Scaling Feature Interaction Explanations for LLMs
Justin Singh Kang, Landon Butler, Abhineet Agarwal, Yigit Efe Erginbas, Ramtin Pedarsani, Bin Yu, Kannan Ramchandran
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
S4S: Solving for a Fast Diffusion Model Solver
Eric Frankel, Sitan Chen, Jerry Li, Pang Wei Koh, Lillian J. Ratliff, Sewoong Oh
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
Rogelio A. Mancisidor, Robert Jenssen, Shujian Yu, Michael Kampffmeyer
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
Cheng Xin, Fan Xu, Xin Ding, Jie Gao, Jiaxin Ding
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
Junyan Liu, Lillian J. Ratliff
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Language Models over Canonical Byte-Pair Encodings
Tim Vieira, Tianyu Liu, Clemente Pasti, Yahya Emara, Brian DuSell, Benjamin LeBrun, Mario Giulianelli, Juan Luis Gastaldi, Timothy J. O'Donnell, Ryan Cotterell
- Published: 01 May 2025, Last Modified: 19 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Provable Zero-Shot Generalization in Offline Reinforcement Learning
Zhiyong Wang, Chen Yang, John C.S. Lui, Dongruo Zhou
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Not All Wrong is Bad: Using Adversarial Examples for Unlearning
Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
Jingyu Liu, Beidi Chen, Ce Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
Amer Krivošija, Alexander Munteanu, André Nusser, Chris Schwiegelshohn
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points
Justin Lee, Behnaz Moradijamei, Heman Shakeri
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping
Sam Gijsen, Kerstin Ritter
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
Ibrahim Fayad, Max Zimmer, Martin Schwartz, Fabian Gieseke, Philippe CIAIS, Gabriel Belouze, Sarah Brood, Aurélien de Truchis, Alexandre d'Aspremont
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Optimizing Test-Time Compute via Meta Reinforcement Finetuning
Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, Aviral Kumar
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Potemkin Understanding in Large Language Models
Marina Mancoridis, Bec Weeks, Keyon Vafa, Sendhil Mullainathan
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
Leo de Castro, Daniel Escudero, Adya Agrawal, Antigoni Polychroniadou, Manuela Veloso
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations
Jason Qin, Hans-Hermann Wessels, Carlos Fernandez-Granda, Yuhan Hao
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Training Deep Learning Models with Norm-Constrained LMOs
Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees
Tomer Meir, Uri Shalit, Malka Gorfine
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
On Explaining Equivariant Graph Networks via Improved Relevance Propagation
Hongyi Ling, Haiyang Yu, Zhimeng Jiang, Na Zou, Shuiwang Ji
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
Kunal Jha, Wilka Carvalho, Yancheng Liang, Simon Shaolei Du, Max Kleiman-Weiner, Natasha Jaques
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Swarnadeep Saha, Xian Li, Marjan Ghazvininejad, Jason E Weston, Tianlu Wang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone