Scaling Properties of Text Conditioning in Visual Generation

  • 类型:arxiv
  • 标识:2607.29679
  • 链接:https://arxiv.org/abs/2607.29679
  • 主分类:multimodal
  • 形态:method
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • 影响力被引:0
  • TLDR:Surprisingly, it is found that the converged diffusion loss scales with the amount of structured language in the prompt, and two complementary measures are adapted: a white-box likelihood metric (GPG) and a black-box attribute metric (ED).
  • 待LLM分类:否
  • 标题中文:文本条件在视觉生成中的缩放特性
  • TLDR中文:研究发现收敛后的扩散损失与提示中结构化语言量成比例关系,并采用两个互补度量:白盒似然指标(GPG)与黑盒属性指标(ED)。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-03-agent-rag-longcontext-candidates.json
  • [S2 enrich]