# TAPESTRY: Using a Single Backbone for Both Video Generation and Robot Control

- Source: arXiv cs.RO
- Published: 2026-10-28T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/e3us9g5q1xhels7n2qkoqdihn
- Original: https://arxiv.org/abs/2610.36823

## Summary

TAPESTRY treats robot actions as single-patch tokens in the latent space of a video model, adapting a pretrained video diffusion Transformer into a robot policy that requires no video generation at inference time.