I'm a Research Scientist at Amazon, where I develop large-scale multimodal AI systems for real-world operational and customer experiences. I received my Ph.D. in Computer Science from the University of North Carolina at Charlotte in 2026, advised by Prof. Pu Wang in the GENIUS Lab. I was previously a Research Scientist Intern at Google's Extended Reality (AR/VR) team. My work includes a U.S. Patent on 3D human pose and movement estimation from monocular images.

My research lies at the intersection of computer vision, generative modeling, and multimodal learning. My current focus is on foundation models that unify real-time 3D human perception with high-fidelity motion synthesis — including generative masked modeling for pose and mesh recovery, streamable co-speech gesture generation, and large-scale multimodal systems for video understanding.

Email| Google Scholar| GitHub| LinkedIn| Twitter