RoboJEPA: Scaling Robotic Latent World Models
- Published
- Source
- arXiv
- Paper number
- 1173
- Field
- AI / General
- arXiv ID
- 2610.10515
Key points
- They ran scaling experiments by training world models from 22M up to 8B parameters on data from 12 robot platforms (about 2.87M trajectories).
- Prediction error decreased following a power-law as compute increased, and the law accurately extrapolated to larger scales than those measured.
- Offline prediction error correlates strongly with real robot planning success rate, making it possible to gauge model quality without physical experiments.
- Given only a single goal image, a real robot arm could zero-shot plan and carry out long-horizon tasks such as grasping and pick-and-place without any additional training.
- The 8B-parameter model is the largest JEPA predictor built to date, and all checkpoints and code have been released.
Paper links
External research summaries. These are not HDATF publications or measured product results.