image

This is Xinyu! I am a Ph.D. student at the Department of Statistics and Data Science at the University of Pennsylvania, working with Dr. Weijie Su. In the meantime, I work with by Dr. Tanwi Mallick at the Mathematics and Computer Science Division at the Argonne National Laboratory.

My recent work focuses on probing and improving the safety aspects of deploying AI models. In general, I am interested in the theory and applications of machine learning and statistics. In my spare time, I also participate in hackathons and data science competitions. Here is my CV.

I finished my master’s degree in computer science at the University of Texas at Austin in 2021, advised by Dr. Anna Gal and Dr. Ngoc Tran.


Upcoming Presentations

I will be presenting posters at the following workshops at NeurIPS 2024:

  • WildfireGPT: Tailored Large Language Model for Wildfire Analysis
    Tackling Climate Change with Machine Learning Workshop

  • A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners
    Workshop on Statistical Frontiers in LLMs and Foundation Models

I will present at the Joint Mathematics Meetings (JMM) 2025:

  • Debiasing Watermarks for Large Language Models via Importance Sampling
    AMS Special Session on Trustworthy AI Applications Including Machine Learning, PINN, and Inverse Problems

  • Unveiling Large Language Model Vulnerabilities: A Geometric and Topological Approach to Adversarial Robustness
    AMS Special Session on MRC Mathematics of Adversarial, Interpretable, and Explainable AI