{
  "absUrl": "https://arxiv.org/abs/2610.00691v1",
  "arxivId": "2610.00691",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.00691v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Zhuo Ning"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "AmirHossein Naghi Razlighi"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Sagi Polaczek"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Daniel Cohen-Or"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Ali Mahdavi-Amiri"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.00691v1",
  "originalTitle": "Soundwich: Video Generation with Layered and Controllable Audio",
  "pdfUrl": "https://arxiv.org/pdf/2610.00691v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}