I am a second-year Master student at the University of Southern California, advised by Prof. Jieyu Zhao in the LIME Lab. Previously, I earned my Bachelor’s degree at Harbin Institute of Technology(HIT) and worked as a Research Assistant in HIT Massive Data Computing Lab under the guidance of Prof. Hongzhi Wang and Xiaoou Ding.

My research focuses on Natural Language Processing, with a highly interested in the intersection with NLP x {Engineering, Finance, Biology, etc.}. Recently, my research has devoted significant attention to building trustworthy NLP models, as well as developing and applying Large Language Model Agents and Vision-Language Models to reduce bias and protect privacy.

Publications

^* indicates equal contribution.

BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents [PDF] [PROJECT PAGE] [CODE] Haoxuan Li, Mingyu Derek Ma, Jen-tse Huang, Zhaotian Weng, Wei Wang, Jieyu Zhao arXiv preprint

SituationalPriv: A Context-Aware Framework for Privacy Detection and Protection in Vision-Language Models [PDF coming soon] [CODE] Zhaotian Weng*, Haoxuan Li*, Jieyu Zhao Under preparation

What’s Missing in Vision-Language Models? Probing Their Struggles with Causal Reasoning [PDF] [PROJECT PAGE] [CODE] Zhaotian Weng, Haoxuan Li, Kuan-Hao Huang, Jieyu Zhao arXiv preprint

Time Series Data Quality Rules Discovery with Both Row and Column Dependencies [PDF] [PROJECT PAGE] Xiaoou Ding, Yingze Li, Chen Wang, Hongzhi Wang, Haoxuan Li Journal of Software (2023)

IoT data cleaning techniques: A survey [PDF] [PROJECT PAGE] Xiaoou Ding, Hongzhi Wang, Genglong Li, Haoxuan Li, Yingze Li, Yida Liu Intelligent and Converged Networks (2022)