World Labs· Marble / AtlasResearch paper

World Labs introduces a functional taxonomy of world models, categorizing them into three types: renderers, simulators, and planners, each serving distinct roles in AI's understanding of space and time.

From the source

The first kind of world model is a renderer. A renderer outputs observations in the form of pixels meant for human eyes, and the quality that matters most is visual fidelity. The second kind is a simulator. A simulator outputs state: a geometrically, physically or dynamically faithful representation of the world that humans and computer programs can both compute on and interact with. The third kind is a planner. A planner outputs actions.

worldlabs.ai