Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video Distillation

2026-09-10

AI Summary

为解决少步蒸馏导致的视频多样性崩溃问题，提出不确定性DMD方法，在自回归生成初期和后期分别引入时间步扰动和随机缓存写入机制，恢复视频多样性和动态性。

Abstract

Few-step distillation improves the efficiency of autoregressive (AR) video generation, but often causes diversity collapse: under the same prompt, different noise samples tend to produce highly similar videos with weakened motion dynamics. We analyze this degradation in Distribution Matching Distillation (DMD)-distilled AR video generators and find that, in the autoregressive setting, it takes the form of a structured uncertainty collapse: the mode-seeking bias of DMD maps different noise samples to nearly identical first chunks, and the deterministic AR cache then propagates this collapsed state to all subsequent chunks, turning a local loss of stochasticity at the rollout root into a global suppression of temporal variation. Based on this analysis, we propose Uncertainty DMD, a simple uncertainty-injection framework that restores stochasticity at two key stages of AR generation: a timestep perturbation for the first chunk to increase first-chunk diversity, and a stochastic cache-writing mechanism for later chunks to preserve uncertainty in autoregressive conditioning. The method requires no architectural changes and introduces only lightweight perturbation operations. The same perturbation mechanisms are used during both training and inference. Experiments show that Uncertainty DMD consistently improves diversity and motion dynamics while maintaining comparable per-sample visual quality.

Problem

• Few-step Distillation
• Diversity Collapse
• Autoregressive Video Generation

Innovation

• Uncertainty DMD
• timestep perturbation
• stochastic cache-writing
• diversity restoration
• autoregressive video generation