Yuan Xia ☕️
Yuan Xia Yuan Shia

5th Year Ph.D. Student & Applied Scientist & Researcher

About Me

Yuan Xia is currently pursuing a Ph.D. in Computer Science at the University of Southern California(USC). She specializes in areas of large language models (LLMs), multimodel AI, autonomous driving, distributed systems and software engineering. She leads a student group at CPS-VIDA Lab, which develops LLMs on perception system monitoring, driving event detection and program syntheis. She worked at Microsoft for building up multimodality LLM agentic workflow. She also worked at Bell Labs for machine learning researching, focusing on improving LLM logical reasoning.

Download CV
Interests
  • Large Language Models
  • Multimodality AI
  • Distributed Systems and Software Engineering
Education
  • Ph.D. Computer Science

    University of Southern California

  • BSc Computer Science & Honors Degree

    University of California, Irvine

📚 My Research

I’m a Ph.D. student at USC. I blog about machine learning, generative models, and intelligent systems.

I develop and incorporate advanced Generative Model(LLMs) in the logic reasoning, property learning, motion event summarization for complex intelligent systems. These techniques further aid the system monitoring and anomaly detection process.

Please reach out to collaborate 😃

Our student group now has new positions to undergraduate and graduate students! Feel free to reach out!

Featured Publications
Recent Publications
(2025). Guiding Likely Invariant Synthesis on Distributed Systems with Large Language Models. In FMCAD 2025.
(2025). LLM-guided Predicate Discovery and Data Augmentation for Learning Likely Program Invariants. In SAC 2025.
(2025). Discovering Likely Invariants for Distributed Systems Through Runtime Monitoring and Learning. In VMCAI 2025.
(2024). Systematic Translation from Natural Language Robot Task Descriptions to STL. In AISoLA 2024.
(2023). Statistical Verification using Surrogate Models and Conformal Inference and a Comparison with Risk-aware Verification. In TCPS 2023.
Recent & Upcoming Talks