{
  "id": 804,
  "url": "https://arxiv.org/abs/2606.20101v2",
  "title": "Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow",
  "summary": "Audio editing aims to modify specific content in an existing audio clip according to a natural language instruction while preserving the remaining acoustic content. Despite the remarkable progress of diffusion models, existing training-based editing methods mainly rely on the local inductive biases and cross-attention interaction in convolutional U-Net backbones, which often hinder long-range semantic alignment and precise understanding and localization of instructions. In contrast, diffusion tr",
  "authors": "Liting Gao, Yonggang Zhu, Yaru Chen, Dongyu Wang, Shubin Zhang, Zhenbo Li et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-18T11:20:08.000Z",
  "fetched_at": "2026-07-14T14:14:50.321Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/804",
  "original_url": "https://arxiv.org/abs/2606.20101v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}