SFBD-OMNI frames distribution restoration from noisy samples as a one-sided entropic optimal transport problem solved by an EM-like algorithm, provides a recoverability test, and generalizes SFBD to non-Gaussian corruptions with limited clean data.
Diffsound: Discrete diffusion model for text-to-sound generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
SFBD Flow converts the iterative SFBD approach into a continuous optimization framework for diffusion models on noisy samples, with its Online SFBD instantiation outperforming baselines.
citing papers explorer
-
SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples
SFBD-OMNI frames distribution restoration from noisy samples as a one-sided entropic optimal transport problem solved by an EM-like algorithm, provides a recoverability test, and generalizes SFBD to non-Gaussian corruptions with limited clean data.
-
SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples
SFBD Flow converts the iterative SFBD approach into a continuous optimization framework for diffusion models on noisy samples, with its Online SFBD instantiation outperforming baselines.