{
  "absUrl": "https://arxiv.org/abs/2609.31193v1",
  "arxivId": "2609.31193",
  "arxivVersion": 1,
  "arxivVersionedId": "2609.31193v1",
  "authors": [
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Jihoo Jung"
    },
    {
      "affiliations": [
        "VGG, University of Oxford"
      ],
      "name": "Youngjoon Jang"
    },
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Joon Son Chung"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.31193v1",
  "originalTitle": "Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs",
  "pdfUrl": "https://arxiv.org/pdf/2609.31193v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}