A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples

  • 类型：arxiv
  • 标识：2607.29122
  • 链接：https://arxiv.org/abs/2607.29122
  • 主分类：multimodal
  • 形态：method
  • 被引：3
  • 被引来源：Semantic Scholar
  • S2被引：3
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：This work attaches a lightweight prediction head to an intermediate layer, keep the backbone frozen, and use the discrepancy between the intermediate and final predictions as a self-guidance direction during sampling to train a frozen, pretrained pixel diffusion model that can guide itself.
  • OpenAlex ID：W7172311830
  • OpenAlex DOI：10.48550/arxiv.2607.29122
  • DOI：10.48550/arxiv.2607.29122
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.29122
  • OpenAlex更新：2026-08-29
  • 副分类：engineering
  • 待LLM分类：否
  • 标题中文：冻结的像素空间扩散模型可借助自身采样进行自我引导
  • TLDR中文：本文在中间层附加轻量预测头，保持 backbone 冻结，并利用中间预测与最终预测的差异作为采样时的自引导方向，训练一个能够自引导的冻结预训练像素扩散模型
  • 来源文件：
  • /inbox/tom/_candidates/2026-08-04-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]