I completed my M.S. in Computer Science at University of Southern California, where I worked with Prof. Jieyu Zhao in the LIME Lab. Previously, I earned my Bachelor's degree from Harbin Institute of Technology and worked as a Research Assistant in the HIT Massive Data Computing Lab, collaborating with Prof. Hongzhi Wang and Prof. Xiaoou Ding.

My work focuses on building reliable and practical AI systems, with interests in LLM agents, multi-agent systems, multimodal AI, and large-scale AI evaluation.

Haoxuan is currently seeking full-time AI Engineer opportunities.
Contact Haoxuan

Selected Projects

Publications

BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents
Haoxuan Li, Mingyu Derek Ma, Jen-tse Huang, Zhaotian Weng, Wei Wang, Jieyu Zhao
SoCal NLP Symposium 2024
SituationalPriv: A Context-Aware Framework for Privacy Detection and Protection in Vision-Language Models
Zhaotian Weng*, Haoxuan Li*, Jieyu Zhao
NeurIPS 2025 Workshop on Efficient Reasoning
What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning
Zhaotian Weng, Haoxuan Li, Xin Eric Wang, Kuan-Hao Huang, Jieyu Zhao
EACL 2026
Time Series Data Quality Rules Discovery with Both Row and Column Dependencies
Xiaoou Ding, Yingze Li, Chen Wang, Hongzhi Wang, Haoxuan Li
Journal of Software 2023
IoT Data Cleaning Techniques: A Survey
Xiaoou Ding, Hongzhi Wang, Genglong Li, Haoxuan Li, Yingze Li, Yida Liu
Intelligent and Converged Networks 2022

Service

  • Official Reviewer, COLM 2026