{
  "absUrl": "https://arxiv.org/abs/2611.18112v1",
  "arxivId": "2611.18112",
  "arxivVersion": 1,
  "arxivVersionedId": "2611.18112v1",
  "authors": [
    {
      "affiliations": [
        "Alibaba Group"
      ],
      "name": "Yuhuan You"
    },
    {
      "affiliations": [
        "Zhejiang University"
      ],
      "name": "Wenxiang Guo"
    },
    {
      "affiliations": [
        "Alibaba Group"
      ],
      "name": "Zhifang Guo"
    },
    {
      "affiliations": [
        "Alibaba Group"
      ],
      "name": "Yuxuan Wang"
    },
    {
      "affiliations": [
        "Alibaba Group"
      ],
      "name": "Jin Xu"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2611.18112v1",
  "originalTitle": "Any Channel Count, One Token Stream: Incorporating Spatial Audio Understanding and Reasoning into Large Audio-Language Models",
  "pdfUrl": "https://arxiv.org/pdf/2611.18112v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}
