Hi! I'm Zhiyu (aka. Ryan), a PhD student at University of California, Merced advised by Professor Wan Du. Previously, I graduated from UC Berkeley with a Bachelor's degree in Computer Science, at age 19.

My research is broadly situated in the field of Responsible AI and aims to advance the development of artificial intelligence systems that are safe, ethical, and beneficial to society. I believe that AI alignment can be achieved through system design that incorporates certain human values and preferences. Based on this, my work focuses on developing safety and ethics modules in autonomous AI agents, as well as improving the interpretability and explainability of AI systems. I have published my work across both ML+Systems venues, including DAC, BuildSys, and ICLR.

In the past, I've worked at Lawrence Berkeley National Laboratory (Research Affliate), Siemens AG (Engineering Intern), and Duolingo (Marketing Contractor).