Colored Noise Sampling: dyeing injected noise to boost diffusion sample quality
serrjoa · x · 2026-09-27
Researchers introduce Colored Noise Sampling (CNS): instead of injecting white noise, the SDE sampler exploits the inherent spectral bias of diffusion models, dynamically coloring the injected noise to focus on frequencies where details are missing.
The authors report substantially improved FID, in a 9-part technical thread.
More from Research
- Spatial-Interactor teaches VLMs spatial reasoning through physical interaction — arankomatsuzaki · 2026-09-27
- DeepMind researcher explains why AI hasn't transformed physics yet — DaniloJRezende · 2026-09-27
- WTF paper fine-tunes flow maps with optimal transport, cutting RL training compute up to 280x — yeewhye · 2026-09-27
- IIT Delhi lands 4 NeurIPS 2026 main-track papers on multilingual interpretability and distillation — Tanmoy_Chak · 2026-09-27
- First PhD paper accepted at NeurIPS 2026: Sparse layers key to scaling looped LMs — burny_tech · 2026-09-27
- Finnish study of 2,000+ workers finds no clear link between AI use and exhaustion — derrikson · 2026-09-27