# Optical Flow

When a JEPA-style world model is regularized only through its embedding distribution, the encoder can treat the fixed background of each episode as its main content and suppress the state changes produced by robot-object interaction, a failure the authors call static collapse. The new method contrasts the predicted latent transition with transitions to other observations from the same episode, and uses optical-flow similarity as soft targets so candidates with similar motion receive similar supervision. Planning success rises from 52% to 78% over LeWM on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while four other visual-control benchmarks stay comparable.

When a JEPA-style world model is regularized only through its embedding distribution, the encoder can treat the fixed background of each episode as its main content and suppress the state changes produced by robot-object interaction, a failure the authors call static collapse. The new method contrasts the predicted latent transition with transitions to other observations from the same episode, and uses optical-flow similarity as soft targets so candidates with similar motion receive similar supervision. Planning success rises from 52% to 78% over LeWM on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while four other visual-control benchmarks stay comparable.