H-JEPA teaches world models to plan at multiple levels of abstraction

VentureBeat · Ben Dickson · 2026-10-09 04:00 UTC

H-JEPA learns representations of the world at different timescales, enabling AI systems to break complex goals into smaller, more manageable planning tasks.

Researchers at Yann LeCun’s Advanced Machine Intelligence (AMI) Labs and academic institutions have developed H-JEPA, a world-model architecture that learns to plan at different timescales using separate representations of the environment.

Compared to flat JEPA world models, H-JEPA improves accuracy on navigation tasks while requiring less computation for planning.

The work addresses a challenge in developing AI systems that can understand and act in the physical world. For example, a robot navigating a building must decide where to go while also controlling its movements moment by moment. H-JEPA addresses this by planning across different levels of abstraction, allowing the system to reason about its destination at a high level and progressively translate its plans into precise physical actions.

Read the full story at VentureBeat · All coverage of this story