{
  "id": "2609.03807",
  "title": "Almost Free State Prediction Separation",
  "previous_titles": [
    "Free Pause Tokens"
  ],
  "authors": "John Langford, Nathan Godey, Giovanni Monea, Yoav Artzi, Harry Dong, Ying Fan, Gustavo de Rosa, Zheng Zhan",
  "first_public": "2026-09-03",
  "venue": "arXiv",
  "arxiv": "2609.03807",
  "paper_url": "https://arxiv.org/abs/2609.03807",
  "lens": [
    "learned-tokens",
    "beyond-sequential"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "parallel",
    "depth-wise"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "architecture",
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Moves pause-token computation into a parallel, weight-shared prediction stream, providing additional internal compute without increasing generated sequence length or key/value-cache length.",
  "provenance": "Primary-source literature search, 2026-09-05",
  "author_names": [
    "John Langford",
    "Nathan Godey",
    "Giovanni Monea",
    "Yoav Artzi",
    "Harry Dong",
    "Ying Fan",
    "Gustavo de Rosa",
    "Zheng Zhan"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.03807/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-03807",
  "citation_date": "2026-09-03",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.03807/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.03807/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.03807/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.03807/citation.csl.json"
}