{
  "id": "2609.40316",
  "title": "Scaling Laws for Looped Mixture of Experts",
  "authors": "Yanbei Chen, Anirudh Goyal, Raghuraman Krishnamoorthi",
  "first_public": "2026-09-30",
  "added_at": "2026-10-18",
  "venue": "arXiv",
  "arxiv": "2609.40316",
  "paper_url": "https://arxiv.org/abs/2609.40316",
  "lens": [
    "recurrent",
    "analysis"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "recurrent",
    "depth-wise"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "scaling",
    "architecture",
    "efficiency"
  ],
  "evidence": [
    "empirical",
    "scaling"
  ],
  "modality": [
    "language"
  ],
  "summary": "Fits scaling laws that jointly account for recurrent depth, expert sparsity, model size, and training data in looped mixture-of-experts models. Uses them to study how to allocate resources under compute and memory constraints.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "author_names": [
    "Yanbei Chen",
    "Anirudh Goyal",
    "Raghuraman Krishnamoorthi"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.40316/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-40316",
  "citation_date": "2026-09-30",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.40316/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.40316/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.40316/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.40316/citation.csl.json"
}