Welcome to Xuan’s Homepage!

I am an Assistant Professor in the Department of Computer Science at Virginia Tech (VT), and a faculty member of the Sanghani Center for Artificial Intelligence and Data Analytics.

My research focuses on efficient and reliable foundation model systems, with an emphasis on post-training, inference, and agentic decision-making. I am particularly interested in multimodal systems operating in complex, real-world environments, including science, healthcare, and robotics. My work has been recognized by the NSF CAREER Award (2025), NVIDIA Academic Grant (2025), Cisco Research Award (2025), and the NAACL Best Demo Paper Award (2021).

I received my Ph.D. in Computer Science from the University of Illinois at Urbana-Champaign (UIUC) under the supervision of Dr. Jiawei Han. During my Ph.D. study, I also worked at IBM Research as a summer intern. I received my M.S. in Statistics and my M.S. in Biochemistry from UIUC. I received my B.S. in Biological Science from Tsinghua University, China.

Here is my full CV.

News and Highlights

• (4/6/26) Two papers are accepted by ACL’26. Congratulations to my student Gaurav for their work on LLM overthinking!
• (4/6/26) I am honored to receive the VT COE Outstanding New Assistant Professor Award!
• (2/21/26) One paper is accepted by CVPR’26. Congratulations to my student Meng for their work on tool-augmented reasoning in VLM agents!
• (1/30/26) We are excited to present our tutorial of “Large Language Models and Agentic AI for Biomedical Informatics” at ISMB’26. Looking forward to seeing everyone in DC!
• (1/26/26) One paper is accepted by ICLR’26. Congratulations to my student Gaurav for their work on benchmark-free evaluation of language model reasoning!
• (12/18/25) We are grateful to receive a new Cisco Research Award to support our research on VideoGym: Verifiable Video Understanding with Tool-Augmented Reasoning and Online Reinforcement Learning.
• (12/16/25) We are grateful to receive a new grant from the Commonwealth Cyber Initiative (CCI) to support our research on A Secure Low-Code Platform for Scalable Multi-Agent AI Deployment.
• (12/9/25) We are excited to present our tutorial of “Towards Effective and Efficient Multi-Agent Language Model Systems: Foundations, Prospects, and Applications” at ACL’26. Looking forward to seeing everyone in San Diego!
• (11/7/25) One paper is accepted by AAAI’26. Congratulations to my student Zhenyu for their work on small language models as a judge for reasoning evaluation!
• …

Prospective Students

My lab at Virginia Tech has openings for PhD/MS students, Postdoc researchers, and research internship opportunities for undergraduate students. If you are interested in working with me, please check this page.