Dr. Yue Zhao

Biography

Yue Zhao is an Assistant Professor in the Department of Computer Science at the University of Southern California and a faculty member of the USC Machine Learning Center. He leads the FORTIS Lab (Foundations of Reliable Trustworthy Intelligent Systems) with research focusing on building reliable, safe, and scalable AI systems. His work centers around understanding and mitigating failure modes in modern AI, particularly in large language models and agentic systems. Zhao’s research encompasses LLM safety, robustness, and system-level evaluation, grounded in the foundations of anomaly detection and out-of-distribution evaluation. He has authored over 60 papers in top-tier venues and is recognized for his significant open-source contributions, which have surpassed 35 million downloads. His tools are widely adopted across academia, industry, and government sectors, including notable organizations such as NASA and Tesla. Zhao has received numerous accolades for his research, including the Capital Research Award and the Amazon Research Award, and serves as an Associate Action Editor for esteemed journals. His research interests are focused on the systems-level evaluation of AI and its implications in high-impact applications across various domains, including healthcare and climate modeling.

Research Interests

Awards