{
  "id": 23,
  "url": "https://arxiv.org/abs/2607.11081v1",
  "title": "Controlling Motion Transfer in Diffusion Transformers via Attention Heads",
  "summary": "Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify distinct heads specialized for motion and spatial structure. Based on this insight, we propose a head-a",
  "authors": "Sunyoung Jung, Jiwoo Park, Yoonseok Choi, Kyobin Choo, Ming-Hsuan Yang, Seong Jae Hwang",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-13T04:44:14.000Z",
  "fetched_at": "2026-07-14T14:14:15.663Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/23",
  "original_url": "https://arxiv.org/abs/2607.11081v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}