{
  "id": 16828128,
  "title": "TAPESTRY: A Single Backbone for Video Generation and Robot Control",
  "url": "https://urgent.news/2026/10/27/tapestry-a-single-backbone-for-video-generation-and-robot-control",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-27T08:23:30.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.36823v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Pretrained video generation models encode rich priors about physical interactions, but leveraging them for robot control typically requires either resource-intensive video generation at test time or action heads trained from scratch that do not fully utilize the pretrained backbone. We introduce Tokenizing Actions as Video Patches in a Shared Transformer Policy (TAPESTRY), a world action model…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}