Email: yusun [at] berkeley.edu
I'm an Incoming Assistant Professor in Computer Science at the University of Washington (currently serving as an Affiliate Professor), and a researcher at OpenAI. I was a postdoc at Stanford University and a part-time researcher at NVIDIA. I completed my PhD in 2023 at UC Berkeley, advised by Alyosha Efros and Moritz Hardt. My PhD thesis is Test-Time Training.
My academic research focuses on continual learning, specifically a conceptual framework called test-time training, where each test instance defines its own learning problem.
For a complete list of papers, please see my Google Scholar.
End-to-End Test-Time Training for Long Context
Arnuv Tandon*, Karan Dalal*, Xinhao Li*, Daniel Koceja*, Marcel Rød*, Sam Buchanan, Xiaolong Wang, Jure Leskovec, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin, Jed McCaleb, Yejin Choi, Yu Sun* (*: core contributors)
[paper]
[code]
Learning to Discover at Test Time
Mert Yuksekgonul*, Daniel Koceja*, Xinhao Li*, Federico Bianchi*, Jed McCaleb, Xiaolong Wang, Jan Kautz, Yejin Choi, James Zou†, Carlos Guestrin†, Yu Sun* (*: core contributors)
ICML 2026
[paper]
[code]
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt
ICML 2020
[paper]
[website]
[talk]