SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
Self-rectifying diffusion sampling with perturbed-attention guidance
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.
citing papers explorer
-
Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
SAMG uses spatially adaptive guidance scales derived from a geometric analysis of classifier-free guidance to resolve the detail-artifact dilemma in diffusion-based image and video generation.
-
Diffusion Models Memorize in Training -- and Generalize in Inference
Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.