DeepEyes: Incentivizing "thinking with images" via reinforcement learning

{
  "doi": null,
  "year": 2025,
  "title": "DeepEyes: Incentivizing \"thinking with images\" via reinforcement learning",
  "venue": "arXiv",
  "authors": [
    "Ziwei Zheng",
    "Michael Yang",
    "Jack Hong",
    "Chenxiao Zhao",
    "Guohai Xu",
    "Le Yang",
    "Chao Shen",
    "Xing Yu"
  ],
  "arxiv_id": "2505.14362",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}