{
  "id": 248,
  "url": "https://arxiv.org/abs/2607.03865v1",
  "title": "High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching",
  "summary": "Generative models such as diffusion and flow matching have advanced robotic visuomotor policies by modeling multimodal action distributions, but their multi-step sampling or ODE solving introduces inference latency. Existing one-step acceleration methods often compress the whole generation process into a single large update, leading to spatial deviation, frequency distortion, and mode averaging. This paper proposes a high-fidelity one-step generative visuomotor policy framework that addresses th",
  "authors": "Yuran Chen, Xinye Cai, Zhonglin Gong, Yang Huang",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-04T13:12:38.000Z",
  "fetched_at": "2026-07-14T14:14:24.247Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/248",
  "original_url": "https://arxiv.org/abs/2607.03865v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}