SALD: Self-Referenced Advantage Learning for Diffusion Models

Key points

• Inspired by this internal-reference principle, we investigate how diffusion models can identify self-referenced training signals without external demonstrations or teacher networks.1
• We introduce SALD, a self-referenced training framework that evaluates each image-caption pair at two noise levels using the same model.1
• The proposed Advantage-Guided Diffusion (AGD) converts this relative error into a differentiable sample-level weight.1
• Temporal Advantage Memory (TAM) accumulates relative difficulty across training and adapts the future gap between the two noise levels.1

Sources (1)

• [1]SALD: Self-Referenced Advantage Learning for Diffusion Models
  Hugging Face Daily Papers · Oct 7, 12:00 AM

  Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrationor feedback-augmented contexts, with the help of a teacher network, which is driven by the student's learned parameters.

  Inspired by this internal-reference principle, we investigate how diffusion models can identify self-referenced training signals without external demonstrations or teacher networks.

Extractive summary: sentences quoted from the sources.