{
  "id": 1299,
  "url": "https://arxiv.org/abs/2606.08530v2",
  "title": "GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation",
  "summary": "Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments. We argue that this stems from the lack of a unified geometry-aware manipulation representation, leaving existing VLAs vulnerable to low-level trajectory supervision, misaligned 3D features, and embodiment differences. To address this, we propose GEAR-VLA, a VLA framework for learning unified geometry-aware ac",
  "authors": "Yuan Zhang, Shiqi Zhang, Yedong Shen, Shuai Dong, Jiajun Deng, Xin Zhang et al.",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-07T09:23:16.000Z",
  "fetched_at": "2026-07-14T14:15:07.848Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1299",
  "original_url": "https://arxiv.org/abs/2606.08530v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}