Video models reveal a “Physics Emergence Zone” where motion direction becomes readable

mathemagic1an · x · 2026-07-29

A new interpretability study examines how large video transformers represent physics internally, using probing, subspace geometry, patch-level decoding, and attention ablations.

Related event: Research Shows 4M-Parameter Video Models Emerge Physical World Representations(4 posts)→

Original post →

More from Research

Research channel →