AI RESEARCH
When Does LeJEPA Learn a World Model?
arXiv CS.LG
•
ArXi:2605.26379v1 Announce Type: cross A representation that scrambles the true degrees of freedom of the world cannot reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization) linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability, in a broad class of worlds where latents evolve under stationary, additive-noise transitions. Our main result is that among all such worlds, the Gaussian is the unique latent distribution for which this guarantee holds.