{
  "id": "2502.07827",
  "title": "Implicit Language Models are RNNs: Balancing Parallelization and Expressivity",
  "authors": "Mark Schöne, Babak Rahmani, Heiner Kremer, Fabian Falck, Hitesh Ballani, Jannes Gladrow",
  "first_public": "2025-02-10",
  "venue": "ICML 2025",
  "arxiv": "2502.07827",
  "paper_url": "https://arxiv.org/abs/2502.07827",
  "lens": [
    "recurrent",
    "analysis"
  ],
  "representation": [
    "continuous-state"
  ],
  "computation": [
    "recurrent",
    "parallel"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "theory",
    "architecture",
    "efficiency"
  ],
  "evidence": [
    "formal",
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Connects implicit language models to recurrent computation and analyzes the trade-off between parallel training and expressive sequential depth.",
  "provenance": "Primary-source literature search, 2026-09-04",
  "author_names": [
    "Mark Schöne",
    "Babak Rahmani",
    "Heiner Kremer",
    "Fabian Falck",
    "Hitesh Ballani",
    "Jannes Gladrow"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2502-07827",
  "citation_date": "2025-02-10",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/citation.csl.json",
  "publication": {
    "title": "Implicit Language Models are RNNs: Balancing Parallelization and Expressivity",
    "author_names": [
      "Mark Schöne",
      "Babak Rahmani",
      "Heiner Kremer",
      "Fabian Falck",
      "Hitesh Ballani",
      "Jannes Gladrow"
    ],
    "year": 2025,
    "type": "paper-conference",
    "container_title": "Proceedings of the 42nd International Conference on Machine Learning",
    "publisher": "PMLR",
    "pages": "53439-53466",
    "volume": "267",
    "url": "https://proceedings.mlr.press/v267/schone25a.html",
    "source_url": "https://proceedings.mlr.press/v267/schone25a.html",
    "verified_at": "2026-10-18"
  },
  "publication_bibtex_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/publication.bib",
  "publication_csl_url": "https://latent-implicit-thinking.github.io/papers/2502.07827/publication.csl.json",
  "method_comparisons": [
    {
      "title": "Recurrent depth and fixed points",
      "text": "Recurrent depth and fixed-point models repeat computation in different ways. Geiping and colleagues reuse a transformer block, allowing the number of passes to change at inference. The implicit state-space models studied by Schöne and colleagues instead iterate toward a fixed point, with experiments testing when approximate convergence is sufficient. Both add computation without adding a written reasoning trace, but their stopping rules and training costs differ.",
      "source_ids": [
        "2502.05171",
        "2502.07827"
      ],
      "source_urls": [
        "https://proceedings.neurips.cc/paper_files/paper/2025/hash/3b01972cf31e6fa0fe29e4b8b5c2a0a1-Abstract-Conference.html",
        "https://proceedings.mlr.press/v267/schone25a.html"
      ],
      "source_labels": [
        "Recurrent-depth paper",
        "Implicit state-space paper"
      ],
      "topic_id": "recurrent",
      "topic_label": "Recurrent reasoning",
      "topic_url": "https://latent-implicit-thinking.github.io/topics/recurrent-reasoning/"
    }
  ]
}