I am Yaowen Ye (or Elwin, or 叶耀文), a first-year CS PhD student at UC Berkeley advised by Prof. Jacob Steinhardt and Prof. Stuart Russell. I work on understanding the limitations of human oversight of AI systems and developing scalable approaches to address them. Directions I am exploring include:

Building scaling laws for evaluating scalable oversight proposals.
Investigating risks in multi-agent systems where existing oversight methods may fail to scale.
Studying the robustness of RLHF under unreliable human supervision.

Ultimately, I aim to ensure that humans can maintain meaningful oversight of AI systems as they scale, thereby keeping them safe.

Feel free to reach out if you're interested in my research! I also enjoy mentoring, so if you are an undergrad and think my advice might be helpful, I'd be happy to connect.

Before joining Berkeley, I did my undergrad at The University of Hong Kong. During my undergrad, I also worked on cognitive reasoning, intuitive physics, learning on graphs, and recommender systems. I was fortunate to be advised by Prof. Yixin Zhu at PKU Cognitive Reasoning Lab and Prof. Chao Huang at HKU Data Intelligence Lab.

Links: [X] [Email] [Give me feedback!]

Publications

2025

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
Preprint, 2025.
Xiaoyuan Zhu, Yaowen Ye*, Tianyi Qiu*, Hanlin Zhu†, Sijun Tan†, Ajraf Mannan, Jonathan Michala, Raluca Ada Popa, Willie Neiswanger. [paper]

Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision.
International Conference on Learning Representations (ICLR), 2025. Spotlight presentation.
Yaowen Ye*, Cassidy Laidlaw* and Jacob Steinhardt. [paper]

2023

Graph Masked Autoencoder for Sequential Recommendation.
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023.
Yaowen Ye, Chao Huang and Lianghao Xia. [paper]

Masked Graph Transformer for Recommendation.
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023.
Chaoliu Li, Chao Huang, Lianghao Xia, Xubin Ren, Yaowen Ye and Yong Xu. [paper]

Miscellaneous

My favorite landscape architect is Yuchen Xiong.
I am a co-founder of HKU AI4Good, a student group focused on AI safety, alignment, and undergrad AI research.
I am a big fan of Vladimir Horowitz and Claude Debussy! I love classical music, film music, harmony theory, and impromptu piano.
I love photography and cinematography and graphic design (like elegant posters, slides, and websites).
I was a co-leader of HKU Astar, a team that builds cool competitive robots.
My MBTI is INFJ.

Friend Links

(Alphabetical order)