Conservative flows generate by running probability-preserving stochastic dynamics initialized at data points rather than noise, using corrected Langevin or predictor-corrector mechanisms on top of any pretrained flow model and showing gains on Swiss-roll, ImageNet-256 and Oxford Flowers-102.
Maximum likelihood training of score-based diffusion models.Advances in neural information processing systems, 34: 1415–1428
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.
citing papers explorer
-
Conservative Flows: A New Paradigm of Generative Models
Conservative flows generate by running probability-preserving stochastic dynamics initialized at data points rather than noise, using corrected Langevin or predictor-corrector mechanisms on top of any pretrained flow model and showing gains on Swiss-roll, ImageNet-256 and Oxford Flowers-102.
-
Dual Ascent Diffusion for Inverse Problems
A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.