Spectral Prior for Reducing Exposure Bias in Diffusion Models

  • 类型:arxiv
  • 标识:2607.22091
  • 链接:https://arxiv.org/abs/2607.22091
  • 主分类:multimodal
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:Spectral Alignment is proposed, a lightweight, guidance-based method that calibrates the power spectrum of intermediate predictions to a pre-computed prior and is complementary to Classifier-Free Guidance (CFG).
  • OpenAlex ID:W7171402503
  • OpenAlex DOI:10.48550/arxiv.2607.22091
  • DOI:10.48550/arxiv.2607.22091
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.22091
  • OpenAlex更新:2026-08-29
  • 待LLM分类:否
  • 标题中文:[标题中文] 降低扩散模型 Exposure Bias 的频谱先验
  • TLDR中文:提出 Spectral Alignment,一种基于 guidance 的轻量级方法,将中间预测的功率谱校准到预先计算的先验,并与 Classifier-Free Guidance (CFG) 互补。
  • 来源文件:
  • /inbox/tom/_candidates/2026-07-27-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-28-rag-retrieval-reranking-candidates.json
  • /inbox/tom/_candidates/2026-07-28-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]