{
  "id": 1408,
  "url": "https://arxiv.org/abs/2606.06491v1",
  "title": "TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies",
  "summary": "Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Language-Action models (VLAs) only inherit a single fixed speed from training demonstrations. Prior efforts to accelerate VLAs through model compression, KV-cache reuse, or reinforcement learning only shift the policy from one fixed speed to another, and leave deceleration almost unexplored. We observe that the magnitude of ",
  "authors": "Dong Jing, Jingchen Nie, Tianqi Zhang, Jiaqi Liu, Huaxiu Yao, Zhiwu Lu et al.",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-04T17:59:40.000Z",
  "fetched_at": "2026-07-14T14:15:17.099Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1408",
  "original_url": "https://arxiv.org/abs/2606.06491v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}