{
  "absUrl": "https://arxiv.org/abs/2609.35345",
  "arxivId": "2609.35345",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Michel Olvera"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Paraskevas Stamatiadis"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Changhong Wang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Gaël Richard"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.35345",
  "originalTitle": "Probing Large Audio-Language Models for Compositional Understanding of Sounding Actions",
  "pdfUrl": "https://arxiv.org/pdf/2609.35345.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}