{
  "absUrl": "https://arxiv.org/abs/2610.21588v1",
  "arxivId": "2610.21588",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.21588v1",
  "authors": [
    {
      "affiliations": [
        "POSTECH"
      ],
      "name": "Kim Sung-Bin"
    },
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Lee Jung-Mok"
    },
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Jinwoo Jung"
    },
    {
      "affiliations": [
        "POSTECH"
      ],
      "name": "Oh Hyun-Bin"
    },
    {
      "affiliations": [
        "Hankuk University of Foreign Studies"
      ],
      "name": "Hyeonggon Ryu"
    },
    {
      "affiliations": [
        "The University of Texas at Austin"
      ],
      "name": "David Harwath"
    },
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Tae-Hyun Oh"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.21588v1",
  "originalTitle": "Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMs",
  "pdfUrl": "https://arxiv.org/pdf/2610.21588v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}