{
  "id": "2609.01343",
  "title": "SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers",
  "authors": "Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu, Shaofan Liu, Jiaheng Liu, Wenhao Huang, Shen Yan, Jian Li",
  "first_public": "2026-09-01",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2609.01343",
  "paper_url": "https://arxiv.org/abs/2609.01343",
  "lens": [
    "recurrent",
    "analysis"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "recurrent",
    "depth-wise"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "scaling",
    "architecture",
    "efficiency"
  ],
  "evidence": [
    "empirical",
    "scaling",
    "mechanistic"
  ],
  "modality": [
    "language"
  ],
  "summary": "Loops the middle half of a mixture-of-experts transformer twice while matching an unlooped baseline on computation, parameter count, and KV-cache size. Studies how the comparison changes with model scale and examines the attention patterns produced by revisiting layers.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "author_names": [
    "Shaowen Wang",
    "Ge Zhang",
    "Kairong Luo",
    "Yuhao Wu",
    "Shaofan Liu",
    "Jiaheng Liu",
    "Wenhao Huang",
    "Shen Yan",
    "Jian Li"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.01343/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-01343",
  "citation_date": "2026-09-01",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.01343/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.01343/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.01343/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.01343/citation.csl.json"
}