15 new papers from UBC Computer Science at world’s premier machine learning conference
UBC researchers had 15 papers accepted at ICML 2026, including two Spotlight papersUBC Computer Science researchers will be in Seoul, South Korea from July 6 - 11, 2026 for the43rd International Conference on. . .
UBC researchers had 15 papers accepted at ICML 2026, including two Spotlight papersUBC Computer Science researchers will be in Seoul, South Korea from July 6 - 11, 2026 for the43rd International Conference on Machine Learning (ICML 2026). ICML is one of the leading conferences for machine learning researchers to gather and discuss the latest advances in the field. With nearly 24,000 submissions to the conference this year, a total of 6,352 papers were accepted. This year, researchers from UBC’s Computer Science department had 15 papers accepted into the conference. Two noteworthy papers, one from ProfessorMargo Seltzerand one from Assistant ProfessorEvan Shelhamer, were named “Spotlight” papers and are in the top 2. 2% of paper submissions. CLARITree: Cholesky and Lookahead Accelerations for Regression with Interpretable Piecewise Linear TreesYixiao Wang, Hayden McTavish, Varun Babbar,Margo Seltzer, Cynthia RudinConvergence Rate of the Last Iterate of Stochastic Proximal AlgorithmsKevin Kurian Thomas Vaidyan,Michael Friedlander*, Ahmet Alacaoglu*Efficient Rashomon Set Approximation for Decision TreesZakk Heile, Hayden McTavish, Varun Babbar,Margo Seltzer, Cynthia RudinFlatland: The Adventures of Gradient Descent with Large Step SizesLeonardo Galli,Curtis Fox, Wiebke Bartolomaeus,Mark Schmidt, Holger RauhutImproving Neural Topic Modeling with Semantically-Grounded Soft Label DistributionsRaymond Li,Amirhossein Abaskohi,Chuyuan Li,Gabriel Murray,Giuseppe CareniniPluralistic LeaderboardsNika Haghtalab, Ariel Procaccia, Han Shao,Serena Wang,KunheYangPrivate and Stable Test-time Adaptation with Differential PrivacyZefeng Li*,Qiaoyue Tang*,Mathias Lécuyer†,Evan ShelhamerRashomon Sets of Falling TreesVarun Babbar, Zachery Boner,Margo Seltzer, Cynthia RudinSpotlight PosterReasoning Models Are Test Exploiters: Rethinking Multiple ChoiceNarun Raman,Taylor Lundy,Kevin Leyton-BrownRobust AI Evaluation through Maximal LotteriesHadiKhalaf,Serena Wang,Daniel Halpern,ItaiShapira, Flavio Calmon, Ariel ProcacciaSelf-Soupervision: Cooking Model Soups without LabelsAnthony Fuller, James Green,Evan ShelhamerSpotlight PosterSegmentation From Attention: Training-Free Layer Selection and One-Shot Tuning for Segmentation in VLMsMir Rayat Imtiaz Hossain, Mennatullah Siam,Leonid Sigal,James LittleSequential Kernel-based Conditional Independence Testing via Adaptive BettingZheng He,Danica J SutherlandTowards Parameter-Free Temporal Difference LearningYunxiang LI,Mark Schmidt, Reza Babanezhad, Sharan VaswaniThe Safety-Aware Denoiser for Text Diffusion ModelsAmman Yusuf,Zhejun Jiang,Mi Jung Park