Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models 事件

Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models arXiv:2506.19037v5 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow, autoregressive behavior. We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-