I am a third-year computer science student at UCLA. I work closely with Yijia Xiao and I am advised by Professor Wei Wang and Professor Yuchen Cui. I also actively collaborate with Yuchen Wu from the University of Washington, and work jointly with Professor Jindong Wang at William & Mary. I have worked on multimodal large language models, reasoning, and agentic systems, with applications in biology, finance, and robotics. During my time working on agents and reasoning for finance applications, I co-founded the opensource research community Tauric Research with my amazing mentor Yijia Xiao. I am currently interested in questions of safety, robustness, and interpretability in foundational models and their applications. I was named a Goldwater Scholar in 2025.
This site hosts my writings, research, and ways to get in touch.
Introduced the need to study personalized safety in LLMs. Argued that alignment should not be purely global, but tailored to a user's background since risk profiles vary across users. Showed where current models fall short, and introduced an inference-time mitigation approach using LLM-guided Monte Carlo Tree Search.
Trading-R1 is an RL-trained reasoning LLM that transforms heterogeneous financial signals into structured, auditable investment theses and volatility-aware trade ratings by learning multi-perspective financial reasoning through reverse chain-of-thought distillation and an easy-to-hard RL curriculum, achieving superior risk-adjusted backtest performance over generic instruction-following and reasoning models.
A multi-agent LLM framework for financial trading, with agents crawling technical, news, sentiment, and more to make a trading decision. GitHub (27k stars)
ProteinGPT is a multimodal LLM that accelerates protein research by enabling natural language interaction with protein sequences and structures. Trained on over 130,000 proteins, it integrates evolutionary-scale protein folding and inverse folding models (esm2) to encode sequence and structural information, aligns these modalities with language, and is instruction-tuned to deliver an interactive, high-performance protein-focused chat experience.