{
  "absUrl": "https://arxiv.org/abs/2609.37200",
  "arxivId": "2609.37200",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Songlin Yang"
    },
    {
      "affiliations": [
        "Tencent Video"
      ],
      "name": "Xiaotong Zhao"
    },
    {
      "affiliations": [
        "The University of Hong Kong"
      ],
      "name": "Jiacheng Zhang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Zhe Wang"
    },
    {
      "affiliations": [
        "Tencent Video"
      ],
      "name": "Toyota Li"
    },
    {
      "affiliations": [
        "Tencent Video"
      ],
      "name": "Eric Liu"
    },
    {
      "affiliations": [
        "Tencent Video"
      ],
      "name": "Alan Zhao"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Anyi Rao"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.37200",
  "originalTitle": "Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL",
  "pdfUrl": "https://arxiv.org/pdf/2609.37200.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}