Randall Balestriero(@randall_balestr):LeJEPA already identified the world's latents--up to some mixing. There is now a very simple post-training recipe to undo that ambiguity and to recover the disentangled world's features! What a time to be Gaussian :) 📄

Randall Balestriero

@randall_balestr

AI Researcher: From theory to practice (and back) Postdoc @MetaAI with @ylecun PhD @RiceUniversity with @rbaraniuk Masters @ENS_Ulm @Paris_Sorbonne

Joined April 2020

246 Following 6.9K Followers

Randall Balestriero@randall_balestr

2026.10.08 19:15

LeJEPA already identified the world's latents--up to some mixing. There is now a very simple post-training recipe to undo that ambiguity and to recover the disentangled world's features! What a time to be Gaussian :) 📄

Yujia Zheng@YujiaZheng9

2026.10.08 18:29

Is it possible to provably recover individual latent variables of the true world, even without reconstruction (e.g., JEPA)? Yes, with DSReg, a simple regularization that can be applied post hoc to your pretrained model!