Yu Ying Chiu (Kelly Chiu)
PhD student at UC Berkeley working on AI safety and alignment.
kellycyy [at] berkeley [dot] edu
Hi, I’m Kelly, a first-year PhD student at UC Berkeley, where I work with Prof. Serina Chang and Prof. Stuart Russell. I’m affiliated with the Center for Human-Compatible Artificial Intelligence (CHAI) and Berkeley Artificial Intelligence Research (BAIR).
I work on AI safety and alignment. My research asks how AI systems should navigate conflicting human values and how pluralistic input can inform concrete alignment objectives and evaluations.
Before Berkeley, I worked on evaluating AI values and moral reasoning, cultural understanding, and AI behavior in mental-health settings at the University of Washington, through the ML Alignment & Theory Scholars (MATS) program with Anthropic, and at New York University.
