{
  "id": 11587,
  "url": "https://arxiv.org/abs/2607.15275v1",
  "title": "RoboTTT: Context Scaling for Robot Policies",
  "summary": "Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference latency. At this context length, we unlock new robot capabilities: one-shot in-context imitation from human video demonstrations, on-the-fly policy improvement, robustness to perturb",
  "authors": "Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng, Fengyuan Hu, Yunhao Ge, Jimmy Wu, Tianyuan Dai, Scott Reed, Li Fei-Fei, Yuke Zhu, Linxi \"Jim\" Fan",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-16T17:59:06.000Z",
  "fetched_at": "2026-07-18T05:10:55.931Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/11587",
  "original_url": "https://arxiv.org/abs/2607.15275v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}