# RynnWorld-Latent preprint reports gains from synthetic robot demonstrations

_Published Tuesday, October 27, 2026 at 10:07 PM EDT · Robotics, Science, AI · Latest · Tier 2 — Notable_

Researchers report that synthetic demonstrations from RynnWorld-Latent improved real-world robot policy success rates over training only on real demonstrations in their evaluated settings. The preprint describes a video world model trained across human videos, robot demonstrations and simulation using a shared representation of actions.

The model was pretrained on 23 datasets comprising approximately 553.5M frames, then adapted to target robots. One route generates demonstrations from target robot commands; another transfers motion to an edited starting image and pairs the generated sequence with retargeted robot actions.

Experiments included two real-robot platforms. Synthetic training also improved policy success rates on LIBERO and LIBERO-Plus, although the abstract gives no numerical success-rate comparisons.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2610.36791v1)

---
Canonical: https://techandbusiness.org/newswire/4nM5moj21WvlwLTOG2Fkaa
Published: 2026-10-28T02:07:14.762Z
Story chronology: 2026-10-27T07:54:16.000Z
Retrieved: 2026-10-28T04:44:34.455Z
Publisher: Tech & Business (techandbusiness.org)