Bayesian Flow Networks (BFN)
Introduces a new class of generative models that combine Bayesian inference with deep learning.
Ask this paper
Parameters, not noisy data: BFNs operate on parameters of a data distribution rather than on a noisy version of the data itself - a fundamental architectural departure from diffusion models.
Unified data types: Adapts to continuous, discretized, and discrete data with minimal changes to the training procedure - unlike diffusion variants that need per-modality engineering.
Competitive with diffusion: Achieves competitive or better likelihood on image, text, and discrete-data benchmarks compared to diffusion baselines.
Research direction: Opens a new family of generative models with distinct theoretical properties, attracting follow-up work through 2024.