{
  "id": 6581,
  "url": "https://arxiv.org/abs/2603.28762v2",
  "title": "On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers",
  "summary": "Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generativ",
  "authors": "Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-30T17:59:13.000Z",
  "fetched_at": "2026-07-14T16:32:37.307Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6581",
  "original_url": "https://arxiv.org/abs/2603.28762v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}