Simple Self-Conditioning Adaptation for Masked Diffusion Models

Masked diffusion models (MDMs) discard clean-state predictions for tokens that remain masked, limiting cross-step refinement. This paper proposes Self-Conditioned Masked Diffusion Models (SCMDM), a post-training adaptation that conditions each denoising step on the model's own previous clean-state predictions. This enhances performance without significant architectural changes or extra evaluations.