Vincent is an Assistant Professor at MIT, where he leads the Scene Representation Group, a research group focused on AI for computer vision and robotics. He finished his PhD at Stanford and his undergrad at TU Munich and the CDTM. His goal is to build AI that can learn models of our world self-supervised, e.g. a robot equipped only with a camera that learns to reason about the geometry, materials, objects, and physics of its environment.
Event: What's next after ChatGPT? The next wave of AI and autonomous machines (October 29)