Self Gradient Forcing: Native Long Video Extrapolation
Merged summary
TL;DR - Self Gradient Forcing (SGF) trains autoregressive video diffusion models to encode earlier generated frames into more useful causal memory. It improves long-video consistency and enables extrapolation from a 5-second training window to several-minute videos.
- Addresses the “historical context-gradient gap,” where future losses cannot improve earlier key-value cache representations.
- Uses a two-pass method: a no-gradient autoregressive rollout followed by parallel context-gradient reconstruction.
- Avoids backpropagation through the full serial rollout while restoring future-to-context supervision.
- Outperforms Self Forcing in identity, layout/background consistency, and temporal stability across long-horizon experiments.
Sources (1)
Self Gradient Forcing: Native Long Video Extrapolation
TL;DR - Self Gradient Forcing (SGF) trains autoregressive video diffusion models to encode earlier generated frames into more useful causal memory. It improves long-video consistency and enables extrapolation from a 5-second training window to several-minute videos.
- Addresses the “historical context-gradient gap,” where future losses cannot improve earlier key-value cache representations.
- Uses a two-pass method: a no-gradient autoregressive rollout followed by parallel context-gradient reconstruction.
- Avoids backpropagation through the full serial rollout while restoring future-to-context supervision.
- Outperforms Self Forcing in identity, layout/background consistency, and temporal stability across long-horizon experiments.