Fast-JEPA speeds latent world model planning 2.41x with 96.5% success rate

ylecun · x · 2026-11-21

Yann LeCun amplified Fast-JEPA, a new paper from a multi-institution team (Wuhan University, HIT, HUST and others, with internship work at DeepCybo) tackling the success-latency tradeoff in latent world model planning.

The problem: latent world models compare candidate action sequences via recursive rollout, which is expensive at test time.

Key results:

Paper and code are both available.

Original post →

More from Embodied

Embodied channel →