Lab Info

We develop efficient and trustworthy machine learning through algorithmic and system-level innovations.

Our research focuses on making large-scale models more computationally scalable, resilient to real-world challenges, and aligned with ethical principles.

Recent Highlights
One paper accepted to ICML 2026; two papers accepted to ICIP 2026.
04/2026
Paper accepted to CCS 2026.
04/2026
Paper accepted to TMLR.
03/2026
Paper accepted to CVPR 2026 (Findings Track).
03/2026
Paper accepted to ICLR 2026.
01/2026
Students
Ph.D. Students
To be added.
Undergraduate and Master's Students
To be added.
Alumni
To be added.