AdaJEPA: An Adaptive Latent World Model
- Published
- Source
- arXiv
- Paper number
- 530
- Field
- Machine Learning
- arXiv ID
- 2606.32026
Key points
- The first test-time adaptation framework for a JEPA world model, using a Plan-Execute-Adapt-Replan loop.
- It performs self-supervised adaptation from observed transitions alone, without additional expert demonstrations.
- It achieves large gains with only one gradient step per MPC replanning step.
- It produces significant improvements over the fixed model on both in-distribution and out-of-distribution target-reaching tasks.
- It shows especially large gains when training data is limited.
- It compares online buffer management strategies using recent-N and hard-N approaches.
Paper links
External research summaries. These are not HDATF publications or measured product results.