Generative Worlds for Spatial and Embodied Intelligence

Abstract: Understanding, navigating, and interacting with the 3D physical real world has long been a central challenge in the development of artificial intelligence. This talk presents a fundamental framework for generating explorable 3D worlds that enable AI systems to reason more deeply and act more intelligently in space. By simulating outcomes and refining internal beliefs, these generative worlds foster informed embodiment, where agents learn to plan, interact, and adapt within the physical world. I further illustrate how this paradigm extends to real-world domains such as robotics and medical treatment planning.