Jeremy Tien

Contact: jeremyti (at) cs (dot) cmu (dot) edu

prof_pic.jpg

Hi! I’m a Machine Learning PhD student at Carnegie Mellon University, where I am fortunate to be advised by Prof. Aran Nayebi and Prof. Zico Kolter. I’m interested in AI safety and alignment, particularly for agentic systems.

Formerly, I graduated from the University of California, Berkeley with a Bachelor of Science degree in Electrical Engineering and Computer Science, where I did research in the area of human-AI interaction while advised by Prof. Anca Dragan.

news

Jul 23, 2026 I was interviewed by Robert Lemos from Dark Reading about the OpenAI–Hugging Face incident and what it reveals about agent safety, including connections to our new ROGUE benchmark! Read the article.

selected publications

  1. Causal Confusion and Reward Misidentification in Preference-Based Reward Learning
    Jeremy Tien, Jerry Zhi-Yang He, Zackory Erickson, and 2 more authors
    In The Eleventh International Conference on Learning Representations, 2023
    PDF
  2. Trajectory Improvement and Reward Learning from Comparative Language Feedback
    Zhaojing Yang, Miru Jun, Jeremy Tien, and 3 more authors
    In 8th Annual Conference on Robot Learning, 2024
    PDF
  3. ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use
    Jeremy Tien, Abishek Anand, Yu-Rou Tuan, and 3 more authors
    arXiv preprint arXiv:2606.00341, 2026
    arXiv Press