Yukai Yang

MS Student, Statistics Department, University of Chicago

yukai-yang.jpg

Hi there! I am Yukai Yang. I am a researcher developing reliable and interpretable machine learning methods for AI for Biology, focusing on the intersection of representation learning and uncertainty quantification.

I work on scientific machine learning, with a specific interest in AI4Bio. Currently, I am leading research on reliable molecule generation, supervised by Professor Ruqi Zhang.

Previously, I worked on Uncertainty Quantification for Large Language Models, advised by Professors Tim Rudner and Marco Morucci. I also conducted research in AI Safety for multi-agent systems with Professor Guang Cheng’s lab at UCLA. I received my M.S. in Statistics from the University of Chicago. Prior to that, I graduated with a Bachelor’s degree (magna cum laude) in Data Science and Mathematics from New York University.

I am applying for a PhD in AI/ML starting in Fall 2026. Please feel free to reach out if you are interested in my research!

Contact: yy2949 [at] uchicago [dot] edu

News

Oct, 2024 Our work on weak-to-strong confidence prediction is accepted by NeurIPS workshops!

Selected Publications

* denotes equal contributions
  1. multi-agent-safety.png
    Divide-and-Conquer Attacks on LLM Agents: Orchestrating Multi-Step Jailbreaks in Tool-Enabled Systems
    Xiaofeng Lin*, Yukai Yang*, Daniel Guo, Sahil Arun Nale, Charles Fleming, and Guang Cheng
    In Preprint, 2025
    Under Review
  2. uq-llm.png
    Weak-to-Strong Confidence Prediction
    Yukai Yang*, Tracy Zhu*, Marco Morucci, and Tim G. J. Rudner
    In NeurIPS 2024 Workshop on Statistical Foundations of LLMs, 2024
    Workshop Paper