{
  "id": 18473,
  "url": "https://www.frontiersin.org/articles/10.3389/frobt.2026.1865290",
  "title": "ConceptACT: episode-level concepts for sample-efficient robotic imitation learning",
  "summary": "Imitation learning enables robots to acquire complex manipulation skills from human demonstrations, but current methods rely solely on low-level sensorimotor data while ignoring the rich semantic knowledge humans naturally possess about tasks. We present ConceptACT, an extension of Action Chunking with Transformers that leverages episode-level semantic concept annotations during training to improve learning efficiency. Unlike language-conditioned approaches that require semantic input at deploym",
  "authors": "Jakob Karalus",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T00:00:00.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "x-frontiers-in-robotics-and-ai",
  "source_name": "Frontiers in Robotics and AI",
  "source_homepage": "https://www.frontiersin.org/journals/robotics-and-ai",
  "ethics_ai_record_url": "https://ethics.ai/record/18473",
  "original_url": "https://www.frontiersin.org/articles/10.3389/frobt.2026.1865290",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}