{
  "id": "2605.26014",
  "title": "STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models",
  "authors": "Yiming Liang, Yixiao Chen, Yiyang Zhou, Yixuan Wang, Shoubin Yu, Andong Deng, Fuxiao Liu, Qin Zhang, Chen Chen, Mohit Bansal, Huaxiu Yao",
  "first_public": "2026-05-25",
  "added_at": "2026-11-02",
  "venue": "arXiv",
  "arxiv": "2605.26014",
  "paper_url": "https://arxiv.org/abs/2605.26014",
  "html_url": "https://arxiv.org/html/2605.26014v1",
  "lens": [
    "internalized",
    "continuous"
  ],
  "representation": [
    "continuous-state",
    "multimodal-latent"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "distillation",
    "supervised"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "Trains a video-language model to answer through a bounded sequence of continuous hidden states. First aligns these states with features from generated thought videos, then trains with answer-only supervision; inference uses the latent sequence without generating intermediate videos.",
  "provenance": "Primary-source literature review, 2026-11-02",
  "author_names": [
    "Yiming Liang",
    "Yixiao Chen",
    "Yiyang Zhou",
    "Yixuan Wang",
    "Shoubin Yu",
    "Andong Deng",
    "Fuxiao Liu",
    "Qin Zhang",
    "Chen Chen",
    "Mohit Bansal",
    "Huaxiu Yao"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2605.26014/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2605-26014",
  "citation_date": "2026-05-25",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2605.26014/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2605.26014/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2605.26014/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2605.26014/citation.csl.json",
  "pdf_url": "https://arxiv.org/pdf/2605.26014"
}
