Xiaoyuan Zhu

Amos • 朱孝缘(Zhū Xiào-yuán)• xzhu9839 [at] usc [dot] edu

xiaoyuan.jpg

Amos • 朱孝缘(Zhū Xiào-yuán)• xzhu9839 [at] usc [dot] edu

Hi, I’m Xiaoyuan ; ) I’m a 4th-year undergrad at USCUSC logo , double majoring in computer science and applied math. I’m fortunate to be advised by Prof. Willie Neiswanger, Prof. Robin Jia, and Prof. Xuezhe Ma. I had wonderful time interning at USC Interaction LabInteraction Lab logo (summer 2023), CAISCAIS logo (winter 2023), and with Prof. Steven Wu at CMU S3DCMU logo (summer 2025) .

My research mainly focuses on developing efficient and effective training-time and inference-time methods to improve model safety and usability . Some broad questions I’m recently interested in :

  • can we identify what can be learned from user feedback, and how to enable models to learn continuously after deployment ?

  • How to improve the sampling and computational efficiency of rollouts in RL, especially in settings with sparser reward ?

Alongside my research, I co-lead USC’s AI Safety Club, a student group promoting safety in advanced AI systems. We run semester-long programs on introductory and technical topics . I’ve also explored computational neuroscience 🧠 .

I’m applying to Ph.D. programs for Fall 2026 ! ✨

news

Jul 07, 2025 Our paper on 🧹 LLM Unlearning has been accepted to COLM 2025
Jun 08, 2025 Our preprint on 🔍 Auditing LLM APIs is now available on arXiv
Oct 08, 2024 Our new version of 🦙 Analysis360 is released !
Apr 18, 2024 I received the Provost’s Undergrad Research Fellowship at USC !

selected publications

  1. Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
    Xiaoyuan Zhu, Yaowen Ye, Tianyi Qiu, Hanlin Zhu, Sijun Tan, and 4 more authors
    arXiv preprint arXiv:2506.06975, 2025
  2. LLM Unlearning Without an Expert Curated Dataset
    Xiaoyuan Zhu, Muru Zhang, Ollie Liu, Robin Jia, and Willie Neiswanger
    In The Conference on Language Modeling, 2025

* Check my google scholar for a full list of publications