World Models, Robotics, and the Future of 3D AI

Language models are these general horizontal engines for processing streams of discrete text, discrete tokens. And our thesis is that there exists another category of model called world models that should be based in visual understanding, should be based in physical understanding, that can be used to generate, simulate, reconstruct worlds.

It goes beyond the title with direct discussion of like, yeah, right, including: Those have had tons of applications from, you know, everything that we know and love today.

1. 01Language models are these general horizontal engines for processing streams of discrete text, discrete tokens
2. 02And our thesis is that there exists another category of model called world models that should be based in visual understanding, should be based in physical understanding, that can
3. 03And if we can build these with the right generality, they should be applicable to tons of different industries, right?