Concept
Diffusion language model
A diffusion language model generates text by iteratively denoising a sequence of masked or noised tokens, rather than predicting one token at a time left to right. Think of it like an image diffusion model, except the state being refined is a grid of discrete token positions…
The rest of “Diffusion language model” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→