{
  "absUrl": "https://arxiv.org/abs/2609.15215",
  "arxivId": "2609.15215",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yanfeng Shi"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yan Song"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Junhui Li"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Tinggan Huang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Wu Guo"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Haoyu Song"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Ian McLoughlin"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.15215",
  "originalTitle": "Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception",
  "pdfUrl": "https://arxiv.org/pdf/2609.15215.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}