{
  "id": 353,
  "url": "https://arxiv.org/abs/2607.00926v1",
  "title": "Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm",
  "summary": "Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative Meta-Learning with Human Feedback (GMHF), a novel framework that bridges this domain gap by leveraging expert intuition to guide data synthesis. Grounded in a theoretical analysis of generalization error, we derive bounds demonstrating that aligning the distribution of",
  "authors": "Midhun Parakkal Unni, Samuel Kaski",
  "category": "research",
  "topics": "environment",
  "orgs": "meta",
  "regions": null,
  "published_at": "2026-07-01T13:29:54.000Z",
  "fetched_at": "2026-07-14T14:14:28.437Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/353",
  "original_url": "https://arxiv.org/abs/2607.00926v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}