About me
I am a final-year PhD student at Stevens Institute of Technology (2021–present), advised by Prof. Yue Ning. My research spans Foundation Models, LLM Post-Training & Agents, Reliable & Verifiable AI Systems, and Graph Learning.
My work focuses on developing robust and trustworthy machine learning models that can adapt to diverse real-world scenarios. I address critical challenges including LLM reasoning and verification through neurosymbolic approaches, out-of-distribution (OOD) generalization under distribution shifts, and continual learning on graph-structured data. I am also passionate about applying advanced ML methods to impactful domains such as predictive healthcare and AI for science.
I have industry experience at Amazon Web Services (Applied Scientist Intern, Fall 2025) working on neurosymbolic verification for reliable LLM reasoning, and at Meta AI / FAIR (ML Engineer Intern, Summer 2025) working on pruning-aware training for efficient neural networks.
Feel free to reach out if you share similar research interests or have innovative ideas in these areas. I am always open to discussions and collaborations!
News
Industry Experience
Neurosymbolic Verification for Reliable LLM Reasoning
Pruning-aware Training for CNNs and Vision Transformers
Education
- Stevens Institute of Technology, Ph.D in Computer Science, 2021 - 2026 (Expected)
- Virginia Polytechnic Institute and State University, M.S. in Mechanical Engineering (Robotics Focus), 2018 - 2020
- University of Arizona, B.S. in Mechanical Engineering; Minor in Mathematics, 2014 - 2018