OpenWAM: An Open Framework for Composable World-Action Models
OpenWAM is a new open-source framework designed to standardize how robots predict future states and execute actions. By providing a common foundation for world-action models, it allows researchers to compare different training recipes and architectures for robot manipulation.
Why it matters
Standardizing research frameworks accelerates the development of more capable and reliable autonomous robotic systems.
Should a robot predict what it will see before deciding how to act, or generate both together? World–action models make both possible. Comparing these choices is difficult when every system uses a different backbone, dataset, and training recipe. OpenWAM gives them a common foundation so we can study how prediction and control work together.
The framework supports composition within a model and between models. We can change the order in which video and actions are generated and how their tokens attend to one another. We can also connect independently trained components: a video predictor proposes a future, an inverse dynamics model turns it into actions, and a forward dynamics model predicts what a supplied action sequence will do.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in