{
  "id": "2506.17218",
  "title": "Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens",
  "authors": "Zeyuan Yang, Xueyang Yu, Delin Chen, Maohao Shen, Chuang Gan",
  "first_public": "2025-06-20",
  "venue": "arXiv",
  "arxiv": "2506.17218",
  "paper_url": "https://arxiv.org/abs/2506.17218",
  "lens": [
    "learned-tokens",
    "continuous"
  ],
  "representation": [
    "multimodal-latent"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "supervised"
  ],
  "questions": [
    "capability",
    "interpretability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "Uses latent visual tokens as an internal imagery channel for multimodal reasoning without rendering every intermediate state.",
  "provenance": "Primary-source literature search, 2026-09-04",
  "author_names": [
    "Zeyuan Yang",
    "Xueyang Yu",
    "Delin Chen",
    "Maohao Shen",
    "Chuang Gan"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2506.17218/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2506-17218",
  "citation_date": "2025-06-20",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2506.17218/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2506.17218/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2506.17218/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2506.17218/citation.csl.json"
}