← Wednesday, October 14, 2026ResearchPaper

LeWAM trains a world model and action policy end to end

huggingface.co by Minghao Fu et al. Editor score 8/10

LeWAM jointly trains latent-state prediction and action flow matching, improving success from 28.6% to 89.7% on contact-rich tasks and planning 32.3× faster. The results make an integrated latent-world-model approach worth examining for embodied control.

What

LeWAM is an end-to-end JEPA for control that jointly trains latent-state prediction and action flow matching.

Method

An isotropic Gaussian latent constraint lets one model execute policies directly or plan by evaluating sampled actions with learned latent dynamics.

Why it matters

In reported tests, it improved success rates on contact-rich and long-horizon tasks and planned 32.3 times faster than prior JEPAs in visual planning.

Read on huggingface.co → Code · 228 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.