{
  "id": 13017,
  "url": "https://arxiv.org/abs/2607.20061",
  "title": "ReferTrack: Referring Then Tracking for Embodied Visual Tracking",
  "summary": "Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning often operates in abstract spatial latents that are difficult to supervise and weakly aligned with explicit image-space detections. To address this, we introduce ReferTrack, a referring-then-tracking para",
  "authors": "Hanjing Ye, Tianle Zeng, Jiazhao Zhang, Shaoan Wang, Zibo Zhang, Weisi Situ",
  "category": "research",
  "topics": "privacy-surveillance,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-21T20:00:00.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/13017",
  "original_url": "https://arxiv.org/abs/2607.20061",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}