SOURCE-LINKED INTELLIGENCE

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods distill pretrained bidirectional video diffusion models into causal AR students through Distribution Matching Distillation (DMD), but the generated videos often suffer from over-saturation and over-smoothing issues, resulting in limited visual quality and realism. The key contributing factor is the mode-seeking behavior of the reverse KL objective in DMD, which can cause the student distribution to collapse onto only a few modes of the teacher distribution. To address this, we pr

Read original source ↗ Open in workspace

recordType

paper

region

Global