Yuanshun (Kevin) Yao

Email: kevinyaowork [at] gmail.com
[Resume]
[Google Scholar]
[LinkedIn]

Bio
I'm a researcher at ByteDance Research in San Jose, CA. I work on trustworthy (i.e. responsible) large language models (LLMs), i.e. LLM alignment for security, privacy, and reliable responses.

I got a PhD in computer science from the University of Chicago, advised by Prof. Ben Zhao and Prof. Heather Zheng, working on AI safety. Before that, I got three B.S. degrees in computer science, mathematics, statistics from the University of Minnesota - Twin Cities. I interned at Google twice and received Siebel Scholarship. My work has been covered by WIRED, Scientific American, Forbes, Fortune, The Verge, Business Insider, Engadget, New York Post, Nvidia, etc.

I sometimes write to help myself figure things out and have fun.

Writings