VPFB learns an energy field whose gradient flow matches a Gaussian-to-data homotopy, reaching CIFAR-10 FID 6.72 without MCMC training.
(2021b), (2) an energy model parameterized by the NCSN++ architecture from Song et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching
VPFB learns an energy field whose gradient flow matches a Gaussian-to-data homotopy, reaching CIFAR-10 FID 6.72 without MCMC training.