Show-O: One single transformer to unify multimodal understanding and generation

{
  "doi": null,
  "year": 2024,
  "title": "Show-O: One single transformer to unify multimodal understanding and generation",
  "venue": "arXiv",
  "authors": [
    "Jinheng Xie",
    "Weijia Mao",
    "Zechen Bai",
    "David Junhao Zhang",
    "Weihao Wang",
    "Kevin Qinghong Lin",
    "Yuchao Gu",
    "Zhijie Chen",
    "Zhenheng Yang",
    "Mike Zheng Shou"
  ],
  "arxiv_id": "2408.12528",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}