Theodore Zhao

About Me

I am a Research Scientist, working on vision and multimodal foundation models at Apple. Previously, I worked at at Microsoft, where I worked on vision and multimodal learning across a range of research projects. I received my PhD and Master degrees in Applied Mathematics from University of Washington with research focus on probabilistic and multiscale temporal modelling, advised by Prof. Tim Leung. During PhD, I interned at Microsoft Research, Harborview Medical Center, Rotella Capital, and Parametric. I received my Bachelor degree in Physics from Fudan University in Shanghai, China.

• Multimodal Intelligence: Vision-Language Models, Multimodal Foundation Models, Grounding, and Reasoning.
• Visual Representation Learning: Self-Supervised Learning, Sparse and Efficient Representations, Video Understanding, and World Modeling.
• Learning and Reasoning: Reinforcement Learning, Verifier-based Learning, and Multi-objective Learning.

I am particularly interested in building generalizable intelligence grounded in visual and multimodal representations, and I am always happy to discuss research and potential collaborations.!