I’m a Research Scientist at Google DeepMind, working on Gemini Omni and Genie, with a focus on physical realism. Previously, I was an Applied Scientist at Amazon AGI, where I built Nova Canvas, Nova Reel, Titan Image Generator, and Custom Labels. I completed my PhD at University of Maryland, College Park, where I worked with Prof. Tom Goldstein and Prof. Hanan Samet on accelerating and understanding deep neural networks.