{
  "absUrl": "https://arxiv.org/abs/2611.06083",
  "arxivId": "2611.06083",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Peiran Wu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Fangfei Gou"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Zhaoxi Mu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Changhao Zhang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Jian Liu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Weiqiang Wang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Yuntao Wang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Yuanchun Shi"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Junxiao Shen"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2611.06083",
  "originalTitle": "SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?",
  "pdfUrl": "https://arxiv.org/pdf/2611.06083.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}
