{
  "id": "2609.34408",
  "title": "Distilling Visual Reasoning into Text Space",
  "authors": "Wenhan Yang, Nilay Naharas, Ali Payani, Baharan Mirzasoleiman",
  "first_public": "2026-09-28",
  "venue": "arXiv",
  "arxiv": "2609.34408",
  "paper_url": "https://arxiv.org/abs/2609.34408",
  "lens": [
    "internalized"
  ],
  "representation": [
    "hidden-state",
    "text-latent-hybrid"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "distillation",
    "supervised",
    "reinforcement-learning"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision",
    "language"
  ],
  "summary": "Distills a teacher's interleaved visual and textual reasoning into a student that no longer generates intermediate visual representations. The student still writes a textual chain of thought; what is internalized is the visual portion of the reasoning.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "added_at": "2026-10-18",
  "author_names": [
    "Wenhan Yang",
    "Nilay Naharas",
    "Ali Payani",
    "Baharan Mirzasoleiman"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.34408/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-34408",
  "citation_date": "2026-09-28",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.34408/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.34408/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.34408/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.34408/citation.csl.json"
}