{
  "id": "2609.34538",
  "title": "Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers",
  "authors": "Guanghao Li, Zihan Su, Hao Yu, Jinyang Jiang, Tao Ren, Zehao Li, Feng Lu, Ming Tang, Chun Yuan",
  "first_public": "2026-09-28",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2609.34538",
  "paper_url": "https://arxiv.org/abs/2609.34538",
  "lens": [
    "recurrent",
    "beyond-sequential"
  ],
  "representation": [
    "hidden-state",
    "cache-memory"
  ],
  "computation": [
    "recurrent",
    "depth-wise",
    "parallel"
  ],
  "training": [
    "inference-only"
  ],
  "questions": [
    "efficiency",
    "architecture",
    "interpretability"
  ],
  "evidence": [
    "empirical",
    "mechanistic"
  ],
  "modality": [
    "language"
  ],
  "summary": "Uses shallower-loop queries with values from deeper loops to improve draft-token predictions in a looped language model. Studies the different rates at which queries, keys, and values develop, and uses that difference for self-speculative decoding.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "author_names": [
    "Guanghao Li",
    "Zihan Su",
    "Hao Yu",
    "Jinyang Jiang",
    "Tao Ren",
    "Zehao Li",
    "Feng Lu",
    "Ming Tang",
    "Chun Yuan"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.34538/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-34538",
  "citation_date": "2026-09-28",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.34538/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.34538/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.34538/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.34538/citation.csl.json"
}