I am a research-track Assistant Professor of Nursing Data Science since 2024, affiliated with the Nell Hodgson Woodruff School of Nursing’s Center for Data Science at Emory University.
I received my Ph.D. in Computer Science and Informatics at Laney Graduate School, Emory University, advised by Dr. Carl Yang in Emory Graph Mining Lab. I also worked closely with Dr. Jinho Choi in syntactic parsing, Dr. Yuanzhe Xi in kernel methods (Gaussian processes), Dr. Xiao Hu in physiological foundation model.
Prior to joining Emory, I was a visiting student at Arizona State University, advised by Dr. Yezhou Yang. Before that, I receieved my bachelor and master degrees from BUPT and worked in industry for several years.

My research interests include AI for healthcare, large language models, knowledge graph, multimodal learning.

Latest News

• [Nov 2024]: Many thanks to Atlanta Interdisciplinary Artificial Intelligence Network for funding our AI.humanity project “Understanding Generative AI’s Impact to Users from Various Religious Background” under the Seed Grants program.
• [Mar 2024]: I’m honored to receive the MCBIOS Young Scientist Excellence Award (4th-place winner). Thanks the MCBIOS committee!
• [Mar 2024]: our survey on Domain Speciliazation of LLM is honorably mentioned by the 2024 Economic Report of the President from the White House (LinkIn post»)
• [Oct 2023]: our paper on multimodal learning has been accepted by Findings of EMNLP’23. This is a co-first author paper with Yongchen Qian. Yongchen was a undergrad at Emory and he contributed a lot to this project. It is always my pleasure to work with motivated students.
• [June 2023]: present my LLM solution for biomedical knowledge fusion in the Doctoral Symposium of Conference on Health, Inference, and Learning’2023 at Cambridge, MA.
• [May 2023]: start my internship at Google X–Mineral, Mountain View, CA this summer. Please check out our work about building trustworthy multimodal LLMs at arXiv».
• [Spring 2023]: several papers get accepted in the warm spring😸 Two of them are my first-author papers– GT-D2G (concept map generation) by IEEE TKDE, and HiPrompt (biomedical knowledge fusion) by SIGIR’23. Others are joint works with my amazing collaborators– closed-book QG with Xiangjue Dong (question generation) by EACL, and Cellcano (cell type identification) with Wenjing Ma by Nature Communications.

Students Worked with Me

• [2024-now] Simon Liu. Undergrad at Emory.
• [2024-now] Katie Shao. Undergrad at Emory.
• [2024-now] Tung Dinh. Honors Undergrad at Emory (Thesis committee).
• [2022-2023] Yongchen Qian. Undergrad at Emory; first position: M.S. of Software Engineering at CMU.
• [2021-2023] Jacob Choi. Undergrad at Emory; first position: M.S. of Computer Science at USC.

Publications