AI RESEARCH
Discrete Stochastic Localization for Non-autoregressive Generation
arXiv CS.CL
•
ArXi:2602.16169v2 Announce Type: replace-cross Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not continuity itself, but a representation in which denoising depends on timestep-indexed noise regimes. We