Discrete Diffusion vs BERT Masking Objectives

nandofioretto · x · 2026-07-13

The masked / absorbing-state setting in discrete diffusion is essentially very much like putting BERT's masked LM objective into a loop: first train the model to "fill in the blanks", and then during generation, gradually sample by repeatedly unmasking.

The key benefits of this approach are:

The author summarizes it in one sentence: there is actually only a layer of "loop iteration" between discrete diffusion and BERT-style masked modeling.

Original post →

More from Research

Research channel →