AI RESEARCH
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
arXiv CS.LG
•
ArXi:2604.02340v1 Announce Type: new Recent advances in masked diffusion language models (MDLMs) narrow the quality gap to autoregressive LMs, but their sampling remains expensive because generation requires many full-sequence denoising passes with a large Transformer and, unlike autoregressive decoding, cannot benefit from KV caching. In this work, we exploit the flexibility of the diffusion framework and study model scheduling, where a smaller MDLM replaces the full model at a subset of denoising steps.