LeVJEPA matches V-JEPA 2 with up to 20x less pretraining compute, no heuristics

Cohere_Labs · x · 2026-09-08

Lukas Kuhn et al. (including Yann LeCun) introduce LeVJEPA: the first video encoder trained under LeJEPA's collapse-free objective, dropping the target encoder, masked prediction, stop-gradient and teacher-student schedules.

Paper on arXiv (2608.27395), with a Cohere Labs technical session scheduled.

Original post →

More from Research

Research channel →