{
  "id": 4288,
  "url": "https://arxiv.org/abs/2605.15536v1",
  "title": "SkiP: When to Skip and When to Refine for Efficient Robot Manipulation",
  "summary": "Previous imitation learning policies predict future actions at every control step, whether in smooth motion phases or precise, contact-rich operation phases. This uniform treatment is wasteful: most steps in a manipulation trajectory traverse free space and carry little task-relevant information, while a small fraction of \\emph{key} steps around contacts, grasps, and alignment demand dense, high-resolution prediction. We propose a novel \\emph{action relabeling} mechanism: at each timestep in a s",
  "authors": "Mingtong Dai, Guanqi Peng, Yongjie Bai, Feng Yan, Chunjie Chen, Lingbo Liu et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-15T02:16:34.000Z",
  "fetched_at": "2026-07-14T16:30:54.919Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4288",
  "original_url": "https://arxiv.org/abs/2605.15536v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}