#machine learning
Jul 2026
Multi-Mask Diffusion Language Models for Few-Step Generation
This work proposes a multi-mask diffusion model (MultiMDM) that preserves the masking structure towards few-step generation and derives a closed-form ELBO training objective for MultiMDM that supports continual training from pretrained MDMs.
Sijin Chen, Yinuo Ren, Heyang Zhao et al.
· arXiv.org · 0 citations