A generative model learns to refine noisy observations via Bayesian posterior updates, matching diffusion-model performance and yielding a Cox-process SDE for count data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Posterior Mean Matching: Generative Modeling through Online Bayesian Inference
A generative model learns to refine noisy observations via Bayesian posterior updates, matching diffusion-model performance and yielding a Cox-process SDE for count data.