{
  "id": "2609.35751",
  "title": "How to Loop MoE: Flatten the Experts, Untie the Attention",
  "authors": "Shouren Wang, Chuang Ma, Mohsen Hariri, Debargha Ganguly, Wang Yang, Xiaoqing Tong, Qianying Liu, Xiaotian Han, Vipin Chaudhary",
  "first_public": "2026-09-28",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2609.35751",
  "paper_url": "https://arxiv.org/abs/2609.35751",
  "lens": [
    "recurrent"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "recurrent",
    "depth-wise"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "architecture",
    "efficiency",
    "capability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Builds a looped mixture-of-experts model by pooling experts across layers and revisiting them. Shares experts and routing across passes while giving each pass its own attention parameters.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "author_names": [
    "Shouren Wang",
    "Chuang Ma",
    "Mohsen Hariri",
    "Debargha Ganguly",
    "Wang Yang",
    "Xiaoqing Tong",
    "Qianying Liu",
    "Xiaotian Han",
    "Vipin Chaudhary"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.35751/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-35751",
  "citation_date": "2026-09-28",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.35751/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.35751/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.35751/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.35751/citation.csl.json"
}