News
ICML 2026 Accepted Papers
This year marks the forty-third International Conference on Machine Learning (ICML). Supported by the International Machine Learning Society, ICML is one of the biggest, and most prestigious, academic conferences for artificial intelligence. This year’s conference took place from July 6th through 11th at the COEX Convention & Exhibition Center, Seoul, South Korea. This year CAIDA had fourteen members with papers accepted for ICML. A big congratulations to our members and their teams for their success! You can see the CAIDA papers below, and the remainder of ICML’s selections here.
Main Conference Papers:
CLARITree: Cholesky and Lookahead Accelerations for Regression with Interpretable Piecewise Linear Trees
Yixiao Wang, Hayden McTavish, Varun Babbar, Margo Seltzer, Cynthia Rudin
Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
Kevin Kurian Thomas Vaidyan, Michael Friedlander, Ahmet Alacaoglu
Efficient Rashomon Set Approximation for Decision Trees
Zakk Heile, Hayden McTavish, Varun Babbar, Margo Seltzer, Cynthia Rudin
Flatland: The Adventures of Gradient Descent with Large Step Sizes
Leonardo Galli, Curtis Fox, Wiebke Bartolomaeus, Mark Schmidt, Holger Rauhut
Improving Neural Topic Modeling with Semantically-Grounded Soft Label Distributions
Raymond Li, Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini
Pluralistic Leaderboards
Nika Haghtalab, Ariel Procaccia, Han Shao, Serena Wang, Kunhe Yang
Private and Stable Test-time Adaptation with Differential Privacy
Zefeng Li, Qiaoyue Tang, Mathias Lécuyer, Evan Shelhamer
Rashomon Sets of Falling Trees
Varun Babbar, Zachery Boner, Margo Seltzer, Cynthia Rudin
*Spotlight Poster
Reasoning Models Are Test Exploiters: Rethinking Multiple Choice
Narun Raman, Taylor Lundy, Kevin Leyton-Brown
Robust AI Evaluation through Maximal Lotteries
Hadi Khalaf, Serena Wang, Daniel Halpern, Itai Shapira, Flavio Calmon, Ariel Procaccia
Self-Soupervision: Cooking Model Soups without Labels
Anthony Fuller, James Green, Evan Shelhamer
*Spotlight Poster
Segmentation From Attention: Training-Free Layer Selection and One-Shot Tuning for Segmentation in VLMs
Mir Rayat Imtiaz Hossain, Mennatullah Siam, Leonid Sigal, James Little
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
Zheng He, Danica J Sutherland
Towards Parameter-Free Temporal Difference Learning
Yunxiang LI, Mark Schmidt, Reza Babanezhad, Sharan Vaswani
The Safety-Aware Denoiser for Text Diffusion Models
Amman Yusuf, Zhejun Jiang, Mi Jung Park