{
  "id": "2607.15178",
  "title": "T²MLR: Transformer with Temporal Middle-Layer Recurrence",
  "authors": "Ziyang Cai, Xingyu Zhu, Yihe Dong, Yinghui He, Sanjeev Arora",
  "first_public": "2026-07-16",
  "venue": "arXiv",
  "arxiv": "2607.15178",
  "paper_url": "https://arxiv.org/abs/2607.15178",
  "lens": [
    "recurrent"
  ],
  "representation": [
    "hidden-state",
    "cache-memory"
  ],
  "computation": [
    "recurrent",
    "stateful",
    "token-wise"
  ],
  "training": [
    "pretraining",
    "supervised"
  ],
  "questions": [
    "architecture",
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Carries a cached middle-layer state from one token position into an earlier layer at the next position, providing localized temporal recurrence that can also be retrofitted into pretrained transformers.",
  "provenance": "Primary-source literature search, 2026-09-05",
  "author_names": [
    "Ziyang Cai",
    "Xingyu Zhu",
    "Yihe Dong",
    "Yinghui He",
    "Sanjeev Arora"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2607.15178/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2607-15178",
  "citation_date": "2026-07-16",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2607.15178/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2607.15178/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2607.15178/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2607.15178/citation.csl.json"
}