Meta presents RoboJEPA, scaling JEPA predictors to 8B parameters
Scaling laws for robot foundation models are far less mapped than for language models, and this 370x parameter sweep across 12 embodiments offers rare empirical evidence on that front. Using latent prediction error as a proxy for planning ability could reduce costly real-world evaluation for robotics teams. Researchers building embodied or cross-embodiment models will find the scaling trends directly comparable to their own setups.