{
  "id": 49,
  "url": "https://arxiv.org/abs/2607.10180v1",
  "title": "ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception",
  "summary": "We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. The benchmark decomposes active perception into three hierarchical tasks: Aerial Embodied Question Answering (Air-EQA), Observation Behavior Planning (OBP), and Fine-grained Language-guided UAV Control (FLUC), explicitly connecting high-level task understanding, behavior planning, and low-level control. The datasets are collected from both real-world and si",
  "authors": "Weichen Zhang, Shiquan Yu, Yinan Zhu, Peizhi Tang, Shilong Ji, Zhiyuan Deng et al.",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-11T07:58:04.000Z",
  "fetched_at": "2026-07-14T14:14:15.665Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/49",
  "original_url": "https://arxiv.org/abs/2607.10180v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}