Motion-guided Contrastive Regularization For Latent World Models
The authors identify “static collapse” in JEPA-style latent world models trained with distributional regularization (e.g., SIGReg): encoders may preserve episode-specific static background while suppressing manipulation-relevant state changes. They propose motion-guided contrastive regularization that matches predicted latent transitions to candidates from the same episode, using optical-flow similarity to create soft targets. They report large planning gains on OGBench-Cube-RB and LIBERO-Object versus LeWM.
