Metropolis-adjusted Langevin correctors using score-based acceptance probabilities, including an exact Bernoulli factory method and a Simpson's rule approximation, reduce sampling bias in diffusion models and improve FID scores.
Neural Computation , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
FEM is a conditional energy model for hybrid Bayesian networks that uses learned embeddings and valley regularization to enable accurate multimodal posterior inference and compositional sampling.
citing papers explorer
-
Metropolis-Adjusted Diffusion Models
Metropolis-adjusted Langevin correctors using score-based acceptance probabilities, including an exact Bernoulli factory method and a Simpson's rule approximation, reduce sampling bias in diffusion models and improve FID scores.
-
Free Energy Manifold: Score-Based Inference for Hybrid Bayesian Networks
FEM is a conditional energy model for hybrid Bayesian networks that uses learned embeddings and valley regularization to enable accurate multimodal posterior inference and compositional sampling.