[
  {
    "id": "lit_2605_26014",
    "type": "article",
    "title": "STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models",
    "author": [
      {
        "literal": "Yiming Liang"
      },
      {
        "literal": "Yixiao Chen"
      },
      {
        "literal": "Yiyang Zhou"
      },
      {
        "literal": "Yixuan Wang"
      },
      {
        "literal": "Shoubin Yu"
      },
      {
        "literal": "Andong Deng"
      },
      {
        "literal": "Fuxiao Liu"
      },
      {
        "literal": "Qin Zhang"
      },
      {
        "literal": "Chen Chen"
      },
      {
        "literal": "Mohit Bansal"
      },
      {
        "literal": "Huaxiu Yao"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2026,
          5,
          25
        ]
      ]
    },
    "genre": "Preprint",
    "archive": "arXiv",
    "number": "arXiv:2605.26014",
    "URL": "https://arxiv.org/abs/2605.26014",
    "custom": {
      "record_url": "https://latent-implicit-thinking.github.io/papers/2605.26014/",
      "first_public": "2026-05-25",
      "collection": "core",
      "citation_basis": "ArXiv preprint, using its initial submission date; source URL is not version-pinned."
    }
  }
]