{
  "id": "2611.07783",
  "title": "PBPO: Prefix-Block Policy Optimization for Diffusion Language Models",
  "authors": "Katherine Tieu, Dongqi Fu, Si Zhang, Hanqing Zeng, Tianxin Wei, Chenglin Wei, Yinglong Xia, Hong Li, Jingrui He",
  "first_public": "2026-11-05",
  "added_at": "2026-11-09",
  "venue": "arXiv",
  "arxiv": "2611.07783",
  "paper_url": "https://arxiv.org/abs/2611.07783",
  "html_url": "https://arxiv.org/html/2611.07783v1",
  "lens": [
    "beyond-sequential"
  ],
  "representation": [
    "discrete-token"
  ],
  "computation": [
    "diffusion",
    "parallel"
  ],
  "training": [
    "reinforcement-learning"
  ],
  "questions": [
    "capability",
    "efficiency",
    "theory"
  ],
  "evidence": [
    "empirical",
    "formal"
  ],
  "modality": [
    "language"
  ],
  "summary": "Trains diffusion language models with policy updates conditioned on completed prefix blocks. Applies importance weights and clipping to individual tokens within each block, avoiding the unstable product of all token ratios.",
  "provenance": "Primary-source literature review, 2026-11-09",
  "author_names": [
    "Katherine Tieu",
    "Dongqi Fu",
    "Si Zhang",
    "Hanqing Zeng",
    "Tianxin Wei",
    "Chenglin Wei",
    "Yinglong Xia",
    "Hong Li",
    "Jingrui He"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2611.07783/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2611-07783",
  "citation_date": "2026-11-05",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2611.07783/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2611.07783/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2611.07783/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2611.07783/citation.csl.json",
  "pdf_url": "https://arxiv.org/pdf/2611.07783"
}