{
  "id": 6357,
  "url": "https://arxiv.org/abs/2604.03956v2",
  "title": "VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models",
  "summary": "Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new unlearning challenge: removing unsafe, spurious, or privacy-sensitive behaviors without degrading perception, language grounding, and action control. In OpenVLA-style policies, behavior is produced through a fused visual encoder, a cross-modal projector, and a language backbone that predicts tokenized robot actions, so undesirable knowledge can be distrib",
  "authors": "Ravi Ranjan, Agoritsa Polyzou",
  "category": "research",
  "topics": "privacy-surveillance,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-05T04:23:18.000Z",
  "fetched_at": "2026-07-14T16:32:24.293Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6357",
  "original_url": "https://arxiv.org/abs/2604.03956v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}