{
  "id": 19171,
  "url": "https://arxiv.org/abs/2608.13277v1",
  "title": "Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model",
  "summary": "We ask whether language-model pre-training can be decomposed into smaller, independently trainable jobs that can later be recomposed into a coherent larger model. We introduce Mixture of Training (MoT), a scaffolded modular pre-training procedure that partitions a target Transformer into contiguous layer blocks, trains each block inside a frozen pretrained aligner scaffold, and then recomposes the trained blocks with an optional short end-to-end adaptation pass. On a 1.3B-parameter Gemma-style m",
  "authors": "Mohammed Sabry, Sean Augenstein, Keith Rush, Lucio Dery",
  "category": "research",
  "topics": "jobs-economy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T14:13:46.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19171",
  "original_url": "https://arxiv.org/abs/2608.13277v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}