I am a PhD student studying computer science at the University of California, Santa Cruz, advised by Prof. Chenguang Wang and very fortunate to closely work with Prof. Dawn Song. I am also a Visiting Researcher at Scale AI. Previously, I completed my Bachelor’s degree in Data Science from the Mathematics Department at Washington University in St. Louis, where I was advised by Prof. Ulugbek Kamilov and graduated with Highest Distinction. You can find my full CV here.
My research focuses on developing methods to better interpret and ensure the safety and performance of large language models (LLMs) and LLM agents.
Research Interests: LLM Interpretability, Alignment & Safety, Agentic AI
📢 Announcements
- May 2026: 3 works accepted to ICML 2026!
- April 2026: Peer preservation and agent security formalization now out!
- January 2026: RepIt is accepted to ICLR 2026!
- December 2025: Our workshop on Agent Safety is accepted to ICLR - see you all in Brazil! I will be in NeurIPS this week as well.
- September 2025: RepIt and SteeringSafety are now on arXiv!
- August 2025: I will be moving with my advisor to UCSC to continue my PhD! Additionally, AgentVigil was accepted to EMNLP 2025!
- March 2025: Excited to share COSMIC accepted to ACL 2025! 🎉
📄 Featured Publications
Find the full list of publications here
📰 Media Coverage
- WIRED — AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted — April 2026
- Fortune — AI models will secretly scheme to protect other AI models from being shut down, researchers find — April 2026
🤝 Service & Engagement
- Workshop Co-Organizer: Agents in the Wild: Safety, Security, and Beyond, ICLR 2026, Brazil
🌟 Featured in Agentic AI Weekly by Berkeley RDI
Sponsors — Platinum: ScaleAI, Skywork · Gold: Lambda, AG2 - Workshop Reviewer: ACL KnowFM 2025, NeurIPS ResponsibleFM 2025
Open Source Software
- MassGen — Contributor
⭐ 900+ GitHub stars