Test-Time Training
Yu Sun (Stanford University)
Colloquium
Thursday, March 5, 2026, 3:30 pm
Gates Center (CSE2), G20 | Amazon Auditorium
Abstract
"Most AI models are trained only before the test instances arrive and then fixed during deployment, even though making good predictions on test instances is the ultimate goal of training. What if we continue to train a model after each test instance arrives? In this talk, we discuss how this conceptual framework, known as test-time training, leads to long-term memory that scales differently with context length, and enables AI to discover new results on open scientific problems.
Bio
"Yu Sun is a postdoc at Stanford University and a researcher at NVIDIA. His research focuses on continual learning, specifically a conceptual framework known as test-time training, where each test instance defines its own learning problem. Yu obtained his PhD in EECS from UC Berkeley and BS in CS from Cornell University.
This talk will be streamed live on our YouTube channel. Link will be available on that page one hour prior to the event.