Peizhao (Percy) Li

Ph.D. Candidate in AI/ML

peizhaoli [AT] brandeis.edu

Bio

My name is Peizhao Li, pronounced as 'Pay-Jow Lee' and written as '李沛钊' in Chinese. I am an AI Scientist at GE HealthCare, working on LLMs & Foundation Models for healthcare applications. I am based in Bellevue, WA. Prior to this, I received my Ph.D. from Brandeis University. Throughout my Ph.D. studies, I had the opportunity to work as a research intern at Google Research, Amazon Alexa AI, Adobe Research, Mitsubishi Electric Research Laboratories (MERL), NEC Laboratories America, and also as a research fellow at Harvard University.

I research Artificial Intelligence and Machine Learning. I have worked on several topics such as Responsible AI, Multimodal Learning, Computer Vision, and Natural Language Processing. The title of my thesis proposal is 'Harmonizing Fairness with Utility in Data and Learning.' In my dissertation research, I develop methods from both computational and data-centric perspectives to make machine learning models fair and non-discriminatory, and simultaneously have no or minimal side effects on utility performance. My dissertation research was recognized by a NIJ Graduate Research Fellowship and a Meta Ph.D. Research Fellowship Finalist.

I am very fortunate to have Prof. Hongfu Liu as my Ph.D. advisor.

Recent Publications

Papers ordered chronologically. For full publications, please refer to my Google Scholar profile.

"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection

Anshuman Chhabra, Peizhao Li, Prasant Mohapatra, Hongfu Liu

ICLR'24: International Conference on Learning Representations, 2024 (Oral)

Learning Antidote Data to Individual Unfairness

Peizhao Li, Ethan Xia, Hongfu Liu

ICML'23: International Conference on Machine Learning, 2023

Characterizing the Influence of Graph Elements

Zizhang Chen, Peizhao Li, Hongfu Liu, Pengyu Hong

ICLR'23: International Conference on Learning Representations, 2023

Robust Fair Clustering: A Novel Fairness Attack and Defense Framework

Anshuman Chhabra, Peizhao Li, Prasant Mohapatra, Hongfu Liu

ICLR'23: International Conference on Learning Representations, 2023

Achieving Fairness at No Utility Cost via Data Reweighing with Influence

Peizhao Li, Hongfu Liu

ICML'22: International Conference on Machine Learning, 2022