Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster

ArXi:2605.18204v1 Announce Type: cross Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized distributions, which makes it difficult for the model to learn the target process in a small number of steps and necessitates a long, computationally expensive sampling procedure.