I am a Ph.D. candidate in Computer Science at Arizona State University,
working in the Knowledge Discovery and Data Mining (KDD) Lab under Dr. Yanjie Fu.
My research focuses on improving the reliability and generalization of large language model (LLM)
reasoning using causal inference and mechanistic interpretability, with an emphasis on invariant mechanism discovery,
spurious correlation mitigation, and robust evaluation.
My work investigates whether LLMs encode causally invariant reasoning processes or rely on spurious correlations,
combining interventional analysis, causal mediation, and mechanistic interpretability to understand and improve
model behavior under distribution shifts.
Prior to my Ph.D., I completed my Master’s in Computer Science at Arizona State University
and worked in industry as a Senior Software Engineer at Fidelity Investments and a Software Development Engineer
at Amazon Alexa AI. My experience spans large-scale machine learning systems, probabilistic modeling,
and production-grade decision pipelines.
I am currently a Doctoral Researcher at Dow Chemicals under the National Academy of Engineering (NAE)
Frontiers of Engineering program, developing causal-aware, neuro-symbolic multi-agent reinforcement
learning frameworks for AI-driven materials discovery and simulation.
Outside of research, I enjoy photography and teaching programming,
particularly working with students interested in creative problem-solving and building systems from first principles.
