AI RESEARCH
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
arXiv CS.AI
•
ArXi:2601.15593v2 Announce Type: replace-cross Masked Diffusion Language Models (MDLMs) promise parallel token generation and arbitrary-order decoding, yet it remains unclear to what extent current models truly realize these capabilities. We characterize MDLM behavior along two dimensions -- parallelism strength and generation order -- using Average Finalization Parallelism (AFP) and Kendall's tau. We evaluate eight mainstream MDLMs (up to 100B parameters) on 58 benchmarks spanning knowledge, reasoning, and programming.