About

I am an Assistant Professor in the Department of Computer Science at Florida State University, where I serve as the founder and director of RAI (Responsible AI) Lab. I obtained my Ph.D. degree from the University of Virginia, where I was fortunate to work with Prof. Jundong Li.

[Recruiting PhDs & Interns, 4-5 more available PhD positions for 2026 & 2027]: I am actively seeking ambitious students for Ph.D. or research intern roles (may be withheld if no qualifying candidates). Please email me with your CV, transcripts, and brief descriptions of your preferred research topics. Kindly mark the subject with [PhD Application] or [Research Intern Application]. Magic Word: Please add appoggiatura in the email subject to ensure attention.

[Recruiting Postdocs, 2 available Postdocs positions for 2027]: I am actively seeking ambitious researchers for 2 Postdoc positions (may be withheld if no qualifying candidates). Please email me with your CV with highlighted funding records and brief descriptions of your preferred research topics. Kindly mark the subject with [Postdoc Application]. Magic Word: Please add appoggiatura in the email subject to ensure attention.

Research Summary: My research studies the full lifecycle of knowledge in modern AI systems with a particular focus on large language models (LLMs): how knowledge is integrated into AI models, how it is exposed and safely accessed via AI models, how it is turned into responsible utility with AI models, and how it ultimately leads to reliable regeneration of new knowledge. I have abundant research works under these topics with 70+ published research papers in the following areas [see full list]:

• Effective Integration of Knowledge: LLM Pre-training & Post-training; Retrieval-Augmented Generation; Knowledge Editing
• Secure Accessibility of Knowledge: Model Extraction Attack & Defense; Memorization & Privacy Protection; Model & Data Ownership Verification
• Responsible Utilization of Knowledge: LLM Interpretability; AI Alignment; LLM-as-a-Judge; Multi-Agent Systems; AI Agent Harness
• Reliable Regeneration of Knowledge: AI for Science: Natural Hazards & Resilience; Healthcare; Mathematics; Social Science

News

• Aug. 2026: Six papers accepted by EMNLP 2026 (4 main and 2 findings). Congrats to Shuze and Yuyang!
• May 2026: Two papers accepted by SIGKDD 2026. Congrats to Bolin!
• May 2026: We are open-sourcing EpiGraph, the world’s first epilepsy knowledge graph curated from 48,166 papers spanning the past 35 years, enabling the community to build generalists for evidence-intensive epilepsy reasoning in the wild! Check our arXiv paper here, our GitHub Repo here, and our webpage here!

• April 2026: One paper paper accepted by ICML 2026. Congrats to Bolin!
• April 2026: One paper paper accepted by IJCAI 2026. Congrats to Lincan!
• April 2026: Delivered an invited talk of A Guide to Write Good Research Grant Proposals at FSU CS Board of Advisors (BOA) Meeting.
• April 2026: Truly honored to receive the only Faculty Research Award at FSU Computer Science Department over the past two years. Such credit also goes to my talented students and interns, and my inspiring colleagues and collaborators — cannot achieve this without any of you!!
• April 2026: Congrats to my student Lincan Li for winning the FSU CS 2026 Graduate Leadership Award!
• April 2026: Congrats to my student Xueqi Cheng for winning the FSU 2026 OLLI Scholarship recipient (one of the four)!
• April 2026: One paper accepted by ACL 2026.
• March 2026: One paper accepted by IEEE ICHI 2026.
• March 2026: Two papers accepted by IJCNN 2026 at IEEE WCCI 2026.
• March 2026: We are open-sourcing one of our recent work, LangSkills, with 101K+ structured skills distilled from 62K+ research papers and 23K+ tech sources, packaged for fast offline search. Check our webpage here and our GitHub here!

• March 2026: One paper accepted by ICLR 2026 Workshop on Principled Design for Trustworthy AI - Interpretability, Robustness, and Safety across Modalities.
• Feb. 2026: We are open-sourcing our interactive AI demo site How AI Works under Encyclopedia World! See our GitHub repo here!

• Feb. 2026: We are open-sourcing our geospatial visualization site GeoLive under Encyclopedia World! See our GitHub repo here!
• Jan. 2026: One paper accepted by ICLR 2026.
• Jan. 2026: One paper accepted by TKDE 2026.
• Nov. 2025: One paper accepted by SIGKDD 2026.
• Nov. 2025: Received the Second Prize Award in BlueSky Track of ICDM, 2025
• Nov. 2025: Two papers accepted by AAAI 2026.
• Nov. 2025: Received the Best Short Paper Award at ACM SIGSPATIAL 2025.
• Oct. 2025: One paper accepted by AACL 2025.
• Oct. 2025: One paper accepted by WSDM 2026.
• Oct. 2025: One paper accepted by IEEE BigData.
• Oct. 2025: Featured interview by WCTV (CBS News)!
  
• Oct. 2025: Invited talk at National Science Foundation PATh CICI Presentation Series.
• Oct. 2025: Awarded the FSU Honors in the Major Mentor Materials Grant.
• Oct. 2025: Awarded Featured AI Researcher by Campus Partners at Florida State University.
• Sept. 2025: One paper accepted by ICDM 2025 Bluesky Track.
• Sept. 2025: One paper accepted by NeurIPS 2025.
• Sept. 2025: Our lab was featured in FSU news! Check it out here.
• Aug. 2025: We published a brand new library focusing on the model extraction attack & defense for graph machine learning! Check our Github Repo and our Official Website!

Invited Talks (Selected)

• 08/2026, Invited Talk at FSU AI Bootcamp, Tallahassee: Guest Lecture: Why Your Model Agrees with You
• 07/2026, Invited Talk at SPGAI Workshop @DAC 2026, Los Angeles: Protecting the Knowledge Assets of Generative and Agentic AI
• 05/2026, Invited Talk at Nokia, San Jose: Toward Trustworhty Machine Learning as a Service
• 05/2026, Invited Talk at ACM Conference on Al and Agentic Systems (CAIS 2026): ClawSkills: A Large-Scale Skill Library for Autonomous AI Agents
• 04/2026, FSU CS Board of Advisors (BOA) Meeting: A Guide to Write Good Research Grant Proposals
• 04/2026, FSU Department of Psychology: Towards Foundation Models for Epilepsy — Diagnosis, Prediction, Medication, and Atomatic Scientific Discovery
• 02/2026, FSU-FAMU College of Engineering: Graph-Based Machine Learning as a Service
• 11/2025, Invited panelist at ACM SIGSPATIAL 2025
• 10/2025, University of Delaware: Unleashing the Power of Graph-Based Machine Learning as a Service
• 10/2025, National Science Foundation PATh CICI Presentation Series: Toward Secure Machine Learning as a Service for Collaborative Scientific Research
• 08/2025, Harvard University: Secure Machine Learning as a Service & Interdisciplinary Applications in Healthcare
• 07/2025, Florida State University: Navigating Secure Machine Learning as a Service
• 06/2025, Harvard University: Model Extraction Attacks on Large Language Models
• 04/2025, Rice University: Political-LLM
• 03/2025, UIIC Summit @DistribuTech: AI in Utility Operations
• 02/2025, Harvard University: Model Extraction Attacks Against Graph Learning Models
• 10/2024, INFORMS: Responsible Graph Machine Learning
• 10/2024, Case Western University: Unleashing the Power of Algorithmic Fairness