{
  "id": "2604.02371",
  "title": "Internalized Reasoning for Long-Context Visual Document Understanding",
  "authors": "Austin Veselka",
  "first_public": "2026-03-31",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2604.02371",
  "paper_url": "https://arxiv.org/abs/2604.02371",
  "lens": [
    "internalized"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "depth-wise"
  ],
  "training": [
    "supervised"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision",
    "language"
  ],
  "summary": "Trains on synthetic traces that rank document pages and extract relevant evidence, then uses low-strength model merging to internalize the trained reasoning behavior. Compares answering with and without written reasoning on long visual documents.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "author_names": [
    "Austin Veselka"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2604.02371/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2604-02371",
  "citation_date": "2026-03-31",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2604.02371/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2604.02371/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2604.02371/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2604.02371/citation.csl.json"
}