Research
Generative Modeling with Bayesian Sample Inference
arXiv:2502.07580v4 Announce Type: replace Abstract: We present a novel view of diffusion-like generative modeling from the perspective of iterative Gaussian posterior inference. By treating the genera
arXiv:2502.07580v4 Announce Type: replace Abstract: We present a novel view of diffusion-like generative modeling from the perspective of iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we formulate the sampling process in the language of Bayesian probability: at each step, a model predicts the unknown sample from our current belief state and we compute a posterior belief from that prediction. Based on this formulation, we propose the generative model Bayesian Sample Inference (BSI). In addition to a rigorous theoretical analysis, we show that our perspective includes Bayesian Flow Networks (BFNs) and that BSI and BFNs represent the two opposite ends of a range of isotropic hyper-priors over the initial belief state. In our experiments, we demonstrate that BSI improves sample quality over both BFNs and the closely related Variational Diffusion Models on ImageNet32 and ImageNet64, while achieving equivalent log-likelihoods on both datasets.
Related
- Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation
- Provable Diffusion Posterior Sampling for Bayesian Inversion
- A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Models
- Fine-Tuning Masked Diffusion for Provable Self-Correction
Source: arXiv cs.LG | 2026-08-17