Tianyu Bell Pan (潘天钰)
Assistant Professor, College of Medicine and AI for Health Institute, University of Florida
Ph.D., Department of Electrical and Computer Engineering (ECE), University of Florida
My research focuses on multimodal learning, particularly in computer vision. This includes areas such as training (primarily pre-training and structured representation learning), information retrieval, optimization, and reinforcement learning. The tools I utilize are mainly from information theory, control theory, and geometric measure theory.
Office: 2406, Malachowsky Hall, University of Florida, Gainesville, FL, 32606
Email: tpan1@ufl.edu, Tianyu.Pan@medicine.ufl.edu (Primary)
News
08/2026: ViLID: Multimodal Misinformation Detection with Complementary Input- and Rationale-Level Inconsistency Signals is accepted by Pattern Recognition. [Code]
06/2026: Successfully defended my dissertation and now officially Dr. Pan! 🥳
05/2026: From Data Fusion to Foundation Models: A Survey of Multimodal AI in Medicine and Healthcare is available online.
04/2026: GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models is accepted by ACL 2026 (San Diego)!
03/2026: Psychology of Phishing Emails: Quantifying Persuasion Principles and Simulating Detection with Large Language Models is published in Expert Systems with Applications.
01/2026: Multimodal Co-Training with Subtractive Unlabeled-Benefit Bounds is accepted by IEEE ICASSP 2026.
09/2025: Lyapunov-Stable Adaptive Control for Multimodal Concept Drift is accepted by the 39th Conference on Neural Information Processing Systems (NeurIPS 2025).
