Presented two papers at NeurIPS 2025 (one oral, one poster); won the Outstanding Paper Award at the AIA workshop @ COLM 2025; co-presented a tutorial on Guardrails and Security for LLMs at ACL 2025; co-organized the Socially Responsible Language Modelling Research (SoLaR) Workshop at NeurIPS 2024 and COLM 2025.
Research Experience
Interned with NVIDIA NeMo Guardrails team; gave guest lectures at multiple international conferences including NeurIPS 2025, COLM 2025, and ACL 2025.
Education
Ph.D. Candidate, Paul G. Allen School of Computer Science & Engineering, University of Washington, advised by Prof. Yejin Choi. Graduate student researcher at NVIDIA and previously a student researcher at Allen Institute for Artificial Intelligence (Ai2).
Background
Research Interests: Humanistic, Pluralistic, and Coevolutionary AI Safety and Alignment, aiming to foster the long-term secure, sustainable, and synergistic coevolution of AI and humanity. 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.
Miscellany
On the job market for 2026; enjoys outdoor activities like hiking.