LLaVA-OneVision-1.5: Fully open framework for democratized multimodal training

{
  "doi": null,
  "year": 2025,
  "title": "LLaVA-OneVision-1.5: Fully open framework for democratized multimodal training",
  "venue": "arXiv",
  "authors": [
    "Xiang An",
    "Yin Xie",
    "Kaicheng Yang",
    "Wenkang Zhang",
    "Xiuwei Zhao",
    "Zheng Cheng",
    "Yirui Wang",
    "Songcen Xu",
    "Changrui Chen",
    "Chunsheng Wu"
  ],
  "arxiv_id": "2509.23661",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}