RGDM generates data by reversing renormalization-group-style coarse-graining, using a colored-noise schedule and projection layers to sample coarse-to-fine, and outperforms a vanilla DDPM on protein and image benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.stat-mech 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative diffusion model with inverse renormalization group flows
RGDM generates data by reversing renormalization-group-style coarse-graining, using a colored-noise schedule and projection layers to sample coarse-to-fine, and outperforms a vanilla DDPM on protein and image benchmarks.