# La-JEPA preprint reports faster robot control with a smaller policy model

_Published Friday, November 6, 2026 at 7:19 PM EST · Science, Robotics · Latest · Tier 2 — Notable_

Researchers report that La-JEPA, a compact robot control model, runs substantially faster than Fast-WAM at comparable performance. The preprint also reports average success comparable to pi0.5 on four real-robot tasks.

La-JEPA trains a policy transformer from scratch using features from a pretrained V-JEPA 2.1 encoder. During training, it predicts future features alongside actions; during operation, it generates only actions. It avoids a pretrained generative policy backbone.

The researchers also corrected instructions corrupted by the official LIBERO-Plus evaluator and re-evaluated several baselines. Their state-of-the-art results on that benchmark and RoboTwin 2.0 are limited to policies without embodied pretraining.

## Sources

- [cs.LG updates on arXiv.org](https://arxiv.org/abs/2611.08156)

---
Canonical: https://techandbusiness.org/newswire/k_LPlCOAqdo3wJ1viwWCkk
Published: 2026-11-07T00:19:04.276Z
Story chronology: 2026-11-06T05:00:00.000Z
Retrieved: 2026-11-08T06:10:02.369Z
Publisher: Tech & Business (techandbusiness.org)