Creativity in diffusion models stems from denoiser architecture interacting with the target distribution, shown via explicit generated-sample distributions for linear, polynomial, and bottleneck denoisers plus UNET ablation experiments.
U-net: Convolutional networks for biomedical image segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diffusion Models, Denoiser Architecture and Creativity
Creativity in diffusion models stems from denoiser architecture interacting with the target distribution, shown via explicit generated-sample distributions for linear, polynomial, and bottleneck denoisers plus UNET ablation experiments.