I am a second-year PhD student at Princeton advised by Prof. Sanjeev Arora; I also work closely with Profs. Peter Henderson and Micah Goldblum (Columbia). I'm gratefully supported by the Gordon Wu Fellowship and the Ezoe Memorial Recruit Foundation.
I previously finished my B.S./M.S. at Columbia, where I was part of the Egleston Scholars Program and worked with Profs. Kathleen McKeown, Daniel Hsu, and Nakul Verma.
Research Interests: I'm broadly interested in AI safety (e.g., developing a scientific understanding of failure modes in current frontier models) and misalignment (e.g., understanding and mitigating reward/goal misgeneralization). Please feel free to reach out; I'm always happy to chat about research!
Google Scholar · GitHub · Twitter · Email
Do Thinking Tokens Help with Safety?
, Abhishek Panigrahi, Sanjeev Arora
NeurIPS 2026 (Spotlight); ICML 2026 AI4GOOD Workshop (
Best Paper Award, Oral)
Measuring the Limits of Continual Learning for LLMs
Nimit Kalra*, *, Zerzar Bukhari, Ang Li, Sanae
Lotfi, Liam Fowl, Micah Goldblum
ICML 2026 CompLearn Workshop
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur, , Yinghui He, Liam Fowl, Sanjeev
Arora
NeurIPS 2026; ICML 2026 FoGen Workshop
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Yinghui He, Simran Kaur, Adithya Bhaskar, Yongjin Yang, Jiarui Liu, , Liam Fowl, Abhishek Panigrahi, Danqi Chen,
Sanjeev Arora
ICML 2026 RLxF Workshop (Oral)
Reranking-based Generation for Unbiased Perspective Summarization
, Nicholas Deas, Kathleen McKeown
ACL 2025 (Findings)
Speak Easy: Eliciting Harmful Instructions from LLMs with Simple Interactions
Yik Siu Chan*, *, Yuxin Xiao*, Marzyeh Ghassemi
ICML 2025
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship
Attribution
Milad Alshomary, , Marianna Apidianaki, Ajay
Patel,
Smaranda Muresan, Kathleen McKeown
COLING 2025
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language
Explanations
Yanda Chen, Ruiqi Zhong, , Chen Zhao, He He,
Jacob Steinhardt,
Zhou Yu, Kathleen McKeown
ICML 2024 (Spotlight)
Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt
Design
Strategies
Linyong Nan, Yilun Zhao, Weijin Zou, , Jaesung
Tae, Ellen
Zhang, Arman Cohan, Dragomir Radev
EMNLP 2023 (Findings)
The Effect of Model Capacity on the Emergence of In-Context Learning in Transformers
Berkan Ottlik*, *, Daniel Hsu, Clayton Sanford
ICLR 2024 (ME-FoMo Workshop)
Contrastive Loss is All You Need to Recover Analogies as Parallel Lines
, Fei-Tzin Lee, Nakul Verma
ACL 2023 (RepL4NLP Workshop)