{
  "absUrl": "https://arxiv.org/abs/2610.40640v1",
  "arxivId": "2610.40640",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.40640v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Derong Jin"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Xiyi Chen"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Ming C. Lin"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Ruohan Gao"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.40640v1",
  "originalTitle": "SonoWorld4D: From One Video to a 4D Audio-Visual Scene via Diffusion Synchronization",
  "pdfUrl": "https://arxiv.org/pdf/2610.40640v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}