Shi Dong (董仕)
Abstract
I received my PhD from Stanford University, and my doctoral research, advised by Prof. Benjamin Van Roy, develops a general and versatile framework to study reinforcement learning. Motivated by the passion for natural languages, I am now dedicated to understanding and unleashing the power of reinforcement learning in large language models (LLMs). Prior to joining Google DeepMind, I was a Senior Researcher at Knowledge and Language Team, Microsoft, where I had the fortune to work with Chenguang Zhu. Beyond research, I am a devout fan of British history and culture.
Professional Experience
Education
Invited Talks
Honors
Activities
Languages
|