I am a final-year Ph.D. candidate at Paul G. Allen School of Computer Science & Engineering, University of Washington, advised by Prof. Yejin Choi. I am also a graduate student researcher at NVIDIA and was previously a student researcher at Allen Institute for Artificial Intelligence (Ai2).

My research centers on Humanistic, Pluralistic, and Coevolutionary AI Safety and Alignment aiming to foster the long-term secure, sustainable, and synergistic coevolution of AI and humanity:

From Human to AI: Developing human-centered, ever-evolving, and future-oriented AI systems, anchored in interdisciplinary insights into human intelligence, values, and global needs.

From AI to Human: Advancing the frontiers of human knowledge, augmenting human capabilities, and addressing consequential sociotechnical challenges through robust, efficient, and scalable innovations in data, learning algorithms, and AI system design.

My current research focuses on developing data, algorithmic, and system-level solutions to address sociotechnical challenges in AI safety, security, and LLM alignment, often through multi-agent, RL, and data synthesis angles. My works have spearheaded research on moral and (pluralistic) value reasoning of LLMs. I also work on scalable, steerable methods for pluralistic alignment, proactive interventions to mitigate long-term risks such as the erosion of human creativity and democracy, and the creation of socially beneficial AI systems that advance collective well-being.

Publications (*, + indicate equal contribution) Google Scholar

Education & Experience

Education

Professional Experience

Awards

Teaching & Services

Courses

Conference Tutorials

Guest Lectures

Workshop Organizations

Talks

Personal