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.
Denoising diffusion implicit models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.
Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details and VAE quality predicting SR performance (R²=0.67).
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.
-
P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.
-
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details and VAE quality predicting SR performance (R²=0.67).