Hey!
I'm a junior (third-year) at Princeton University studying computer science and math, grateful to be advised by Tom Griffiths, Zhuang Liu, and Peter Henderson. I was born in the Bay Area 🌉 but have lived in Kingston, Ontario, Canada 🇨🇦 for my entire life.
This summer, I will be joining the Center for AI Safety as a Research Intern.
I'm interested in uncovering how foundation models behave under informationally imperfect (unreliable, incomplete, deceptive, conflicting, etc.) yet realistic conditions from train-time to deployment, and the real-world consequences of these limitations.
Outside of research, I like to play Wordle, Globle, Travle, GeoGuessr/Geotastic, and the NYT Mini. My life goal is to defeat the Ender Dragon in Minecraft Survival Mode.
Updates
- Jun–Aug 2026: Incoming Research Intern at the Center for AI Safety (CAIS) in San Francisco.
- Apr 2026: Presenting two papers on LLMs navigating conflicts of interest (AIAgentsWild) and a closer look at positional biases (ICBINB) at ICLR 2026, see you in Rio de Janeiro!
- Feb 2026: My co-author Xuechunzi Bai presented our paper on LLMs naturally developing stereotypical beliefs as one of four Invited Symposia speakers at SPSP 2026 in Chicago!
- Jan 2026: Excited to have recevied the Outstanding CS Independent Work Prize for my work on LLM vigilance failures!
- Dec 2025: Presenting two papers on LLM vigilance failures (main) and emergent social biases (MTI-LLM) at NeurIPS 2025, see you in San Diego! Very grateful to be funded by the NeurIPS Scholar Award!
- Oct 2025: Our paper on LLM vigilance failures was accepted as a Spotlight Oral at PragLM @ COLM 2025, see you in Montréal!
- Jul 2025: Presenting our paper on parallels between human overthinking and LLM CoT failures at ICML 2025, see you in Vancouver!