AI RESEARCH
Unifying Masked Diffusion Models with Various Generation Orders and Beyond
arXiv CS.CL
•
ArXi:2602.02112v2 Announce Type: replace-cross Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise left-to-right) or learns an ordering policy for a pretrained MDM, which incurs extra cost and can yield suboptimal solutions due to the two-stage optimization.