Google Research

Xinchen Yan


My primary research interests lie in the intersection of deep representation learning and generative modeling with structured and multimodal data. More specifically, my research has been focused on three related topics: (1) controllable visual content generation and manipulation, (2) self-supervised learning of object shape and motion, and (3) scalable and robust perception simulation for robotic applications. Besides, I have a broad range of interests in developing deep generative models for vision, graphics, and robotics. Please visit my personal homepage for more information on my research.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work