Yan Zhou (Terry)

I am a first-year Master’s student in Data Science at Harvard University. My research interests include mechanistic interpretability, AI safety, and efficient machine learning. My current work focuses on using mechanistic interpretability to understand safety-relevant model behaviours. I am also working on model compression, extending the Boomerang Distillation technique.

I am currently working with Jonathan Geuter and Sara Kangaslahti at Harvard’s ML Foundations Group, advised by Prof. David Alvarez-Melis. I am also working with Dr. Shichang Zhang at the AI4LIFE Lab, advised by Prof. Hima Lakkaraju and Prof. Yonatan Belinkov. Previously, I completed my Bachelor’s degree in Politics and Data Science at the London School of Economics.

I am always happy to discuss research ideas! Please feel free to reach out to me at terryzhou [at] fas [dot] harvard [dot] edu.