Sonia Joseph's AI research, essays, and commentary on the industry
There has been a lot of confusion around world models. Depending on who you ask, a world model is a generative model, a 3D reconstruction model, or a latent-space prediction model. I would like to propose a fourth definition– one that goes back to the original- the Internal
Authors: Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake Richards, and Mike Rabbat. Work done at Meta Superintelligence Labs. Full preprint: https://arxiv.org/abs/2602.07050 This post walks through our main findings and intuition behind our interpretability study of physics representations in video
The content of this short post will be already obvious to many researchers, but it's still worth writing out explicitly, especially when I see some assumptions that newer researchers are making. Tldr : The logit lens is a convenient way to investigate internal representations. But it can be misleading,
Multimodal interpretability, from sparse feature circuits with SAEs, to vision transformers leveraging CLIP's shared text-image space.