I am a Ph.D. student in the Department of Computer Science at Virginia Tech, advised by Professor Jin-Hee Cho. I am a member of the Trustworthy Cyberspace Lab (tClab).

My research focuses on trustworthy artificial intelligence, reinforcement learning, and large language models. I am particularly interested in developing AI systems that can reason and interact strategically over long-horizon tasks, understanding and mitigating model failures, and designing uncertainty-aware learning methods for socially sensitive and cybersecurity applications.

Research Interests

Trustworthy Artificial Intelligence
Understanding, explaining, detecting, and mitigating individual model failures, including uncertainty, misclassification, robustness, and selective prediction.

Large Language Models and Strategic Dialogue
Developing LLM systems capable of structured, goal-directed, and long-horizon interaction using reinforcement learning and explicit dialogue planning.

Deep Reinforcement Learning
Designing reinforcement learning methods for sequential decision-making under uncertainty, partial observability, and competing objectives.

AI for Online Safety and Cybersecurity
Applying machine learning and LLMs to problems including phishing, scams, misinformation, cybergrooming, and cybersecurity education.

Things Not Peer-Reviewed

A few things that probably do not belong in a research statement:

• My research is about uncertainty. Certainly, academia provides plenty of it.
• I have spent several years teaching machines how to make better decisions. Results for myself are still mixed.
• I somehow went from electronic science to computer science to reinforcement learning to asking language models increasingly complicated questions.
• Science fiction has been talking about silicon-based life for decades. Apparently, it was onto something.
• This website is also an experiment in whether I can maintain something without turning it into a research project.