OpenWAM Pretraining
Project | Code | Pretraining guide
A visual foundation for robot world models. OpenWAM Pretraining learns to predict how robot scenes evolve from observed video and text conditioning. Trained on single-view and multiview robot video, it provides a shared visual backbone for future prediction and downstream world-action modeling.
The model learns visual dynamics without action supervision. Its weights can be used for video prediction or as an initialization for adapting OpenWAM to video-action policies and dynamics models.
Causal Video Generation
The current release generates the future one chunk at a time. It starts from one observed latent frame, then predicts chunks of four latent frames, conditioning each chunk on the initial observation and preceding video. This autoregressive structure allows generation to progress without attending to later chunks.
Training uses chunk-causal teacher forcing, with earlier clean video providing context for each noisy target chunk. Earlier repository revisions used a bidirectional prefix/suffix objective; this checkpoint continues that pretraining with the causal objective and should be used with chunk-by-chunk generation rather than a single bidirectional prediction of the entire future.
Use with OpenWAM
The release includes model weights, a reference configuration, and checksums. The pretraining guide covers data preparation, shared frontend assets, training, and video inference. See the project page for the broader approach to composing video prediction and robot control.