Janus: Decoupling visual encoding for unified multimodal understanding and generation

{
  "doi": null,
  "year": 2024,
  "title": "Janus: Decoupling visual encoding for unified multimodal understanding and generation",
  "venue": "arXiv",
  "authors": [
    "Chengyue Wu",
    "Xiaokang Chen",
    "Zhiyu Wu",
    "Yiyang Ma",
    "Xingchao Liu",
    "Zizheng Pan",
    "Wen Liu",
    "Zhenda Xie",
    "Xingkai Yu",
    "Chong Ruan"
  ],
  "arxiv_id": "2410.13848",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}