Published papers at CVPR 2024, ICML 2025 (oral), and ICCV 2025 (highlight) on topics like diffusion models, personalization, and interpretability. Co-organizer of the P13N workshop on Personalization in Generative AI at ICCV 2025.
Research Experience
Researching generative AI at Virginia Tech, focusing on how to tell image and video models exactly what to do (and why they do it). Interned with Amazon AGI and Adobe FireFly, and collaborated with Google. Once deployed image-generation services used by millions of people without issues.
Education
Ph.D. Student in Computer Science at Virginia Tech
Background
Research interests include autoregressive vision models, controllable generation, mechanistic interpretability, and zero-shot editing. Aiming to make generative models trusted sidekicks for creators, not just black boxes.
Miscellany
Shares fresh paper notes and open-source snippets on his blog or Twitter. Often found with a cup of coffee, stress-testing newly trained models.