Speaker:

Yu Sun

Talk Title:

Test-Time Training

Date and Location:

Tuesday, February 24, 2026

Bahen Centre for Information Technology, BA 3200

This lecture is open to the public. No registration is required, but space is limited.

The grad roundtable that follows the talk is open only to current University of Toronto Department of Computer Science graduate students.

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.

About Yu Sun:

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. Yuobtained his PhD in EECS from UC Berkeley and BS in CS from Cornell University.