End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

摘要

Autoregressive video diffusion models hold promise for worldsimulation but are vulnerable to exposure bias arising from the train–testmismatch. While recent works address this via post-training, they typi-cally rely on a bidirectional teacher model or discriminator. To achievean end-to-end solution, we introduce Resampling Forcing, a teacher-free framework that enables training autoregressive video models fromscratch and at scale. Central to our approach is a self-resampling schemethat simulates inference-time model errors on history frames during train-ing. Conditioned on these degraded histories, a sparse causal mask en-forces temporal causality while enabling parallel training with frame-leveldiffusion loss. To facilitate efficient long-horizon generation, we furtherintroduce history routing, a parameter-free mechanism that dynamicallyretrieves the top-k most relevant history frames for each query. Experi-ments demonstrate that our approach achieves performance comparableto distillation-based baselines while exhibiting superior temporal consis-tency on longer videos owing to native-length training. See our ProjectPage for more details.