H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
Overview
This research presents H-JEPA, an end-to-end method for training hierarchical action-conditioned JEPAs. The approach optimizes progress toward goals at a top level while using lower levels to predict finer details, effectively discarding fast, unpredictable data in favor of slower, task-relevant states. Experiments across four simulated environments show that a three-level hierarchy improves success rates on Visual AntMaze from 18% to 73% with reduced compute. The method also extends to real-robot videos from DROID using inverse-dynamics supervision, improving offline planning fidelity while lowering planner compute requirements.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalH-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
This research presents H-JEPA, an end-to-end method for training hierarchical action-conditioned JEPAs. The approach optimizes progress toward goals at a top level while using lower levels to predict finer details, effectively discarding fast, unpredictable data in favor of slower, task-relevant states. Experiments across four simulated environments show that a three-level hierarchy improves success rates on Visual AntMaze from 18% to 73% with reduced compute. The method also extends to real-robot videos from DROID using inverse-dynamics supervision, improving offline planning fidelity while lowering planner compute requirements.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).