04:00
2026-08-03
machinebrief.com
machine-learning
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
Researchers introduced FairDiffuseVQVAE, a two-stage tabular diffusion model that achieves fairness by construction through uniform sampling of the protected attribute at inference time, decoupling fi…