Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Understand

We introduce Self Forcing, a novel training paradigm for autoregressive video diffusion models.

• It addresses the longstanding issue of exposure bias, where models trained on ground-truth context must generate sequences conditioned on their own imperfect outputs during inference.
• Unlike prior methods that denoise future frames based on ground-truth context frames, Self Forcing conditions each frame's generation on previously self-generated outputs by performing autoregressive rollout with key-value (KV) caching during training.
• This strategy enables supervision through a holistic loss at the video level that directly evaluates the quality of the entire generated sequence, rather than relying solely on traditional frame-wise objectives.