AI RESEARCH
Self-Speculative Masked Diffusions
arXiv CS.LG
•
ArXi:2510.03929v2 Announce Type: replace-cross We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality.