{"ID":6537667,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11081","arxiv_id":"2607.11081","title":"Controlling Motion Transfer in Diffusion Transformers via Attention Heads","abstract":"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-aware controllable motion transfer framework that requires no parameter updates. Our method refines motion cues from motion-specialized heads via semantic correspondence guidance and preserves structure through selective feature injection. This head-level control not only enables accurate motion transfer but also provides an interpretable foundation for controllable video generation with DiTs.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.11081","url_pdf":"https://arxiv.org/pdf/2607.11081v1","authors":"[\"Sunyoung Jung\",\"Jiwoo Park\",\"Yoonseok Choi\",\"Kyobin Choo\",\"Ming-Hsuan Yang\",\"Seong Jae Hwang\"]","published":"2026-07-13T04:44:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}