ICML 2025 Conference Submissions

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
Kristina Nikolić, Luze Sun, Jie Zhang, Florian Tramèr
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Theoretical Limitations of Ensembles in the Age of Overparameterization
Niclas Dern, John Patrick Cunningham, Geoff Pleiss
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
Representative Language Generation
Charlotte Peale, Vinod Raman, Omer Reingold
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation
Rui Sun, Huayu Mai, Wangkai Li, Yujia Chen, Naisong Luo, Yuan Wang, Tianzhu Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro, Julia Kempe
- 22 Jan 2025 (modified: 18 Jun 2025)
- Submitted to ICML 2025
- Readers: Everyone
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
David Reber, Sean M Richardson, Todd Nief, Cristina Garbacea, Victor Veitch
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
Santiago Cortes-Gomez, Naveen Janaki Raman, Aarti Singh, Bryan Wilder
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
An analytic theory of creativity in convolutional diffusion models
Mason Kamb, Surya Ganguli
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 oral
- Readers: Everyone
Optimization for Neural Operators can Benefit from Width
Pedro Cisneros-Velarde, Bhavesh Shrimali, Arindam Banerjee
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
Sharan Vaswani, Reza Babanezhad Harikandeh
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Direct Prediction Set Minimization via Bilevel Conformal Classifier Training
Yuanjie Shi, Hooman Shahrokhi, Xuesong Jia, Xiongzhi Chen, Jana Doppa, Yan Yan
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
Jiazheng Li, Lu Yu, Qing Cui, Zhiqiang Zhang, JUN ZHOU, Yanfang Ye, Chuxu Zhang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
Walter Mayor, Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
Edward Y Chang
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
Michael Crawshaw, Blake Woodworth, Mingrui Liu
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
Yuhui Wang, Qingyuan Wu, Dylan R. Ashley, Francesco Faccio, Weida Li, Chao Huang, Jürgen Schmidhuber
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
Junwei Deng, Weijing Tang, Jiaqi W. Ma
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Adaptive Flow Matching for Resolving Small-Scale Physics
Stathi Fotiadis, Noah D Brenowitz, Tomas Geffner, Yair Cohen, Michael Pritchard, Arash Vahdat, Morteza Mardani
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Validating Mechanistic Interpretations: An Axiomatic Approach
Nils Palumbo, Ravi Mangal, Zifan Wang, Saranya Vijayakumar, Corina S. Pasareanu, Somesh Jha
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Primal-Dual Neural Algorithmic Reasoning
Yu He, Ellen Vitercik
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 spotlightposter
- Readers: Everyone
Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
Tong Yang, Bo Dai, Lin Xiao, Yuejie Chi
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
Seongho Son, William Bankes, Sayak Ray Chowdhury, Brooks Paige, Ilija Bogunovic
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation
Kevin Han Huang, Ni Zhan, Elif Ertekin, Peter Orbanz, Ryan P Adams
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone
Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
Jiawei Ge, Yuanhao Wang, Wenzhe Li, Chi Jin
- Published: 01 May 2025, Last Modified: 18 Jun 2025
- ICML 2025 poster
- Readers: Everyone