SplitJEPA separates stable and changing factors in learned world models
SplitJEPA advances self-supervised learning by decomposing latent representations into invariant and variant factors without requiring reconstruction. This addresses a core challenge in world models: enabling agents to distinguish what persists across observations from what changes, critical for robust robotic control and embodied AI. By extending Joint Embedding Predictive Architectures, the work sidesteps the computational overhead of generative approaches while maintaining interpretability of learned state factors. The technique matters for scaling embodied systems that must generalize across visual perturbations and environmental shifts.62
