SOURCE-LINKED INTELLIGENCE

Spectral-Target Physical Latent Structuring for JEPA-Style World Models

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Latent world models have become increasingly popular as a method to predict and plan in latent space rather than pixel space. Recent architectures, such as LeWorldModel (LeWM), jointly train the encoder and predictor using regularization techniques like SIGReg to prevent representation collapse. Even with such regularization preventing representation collapse, we identify a new world model failure mode of physical representation laziness, particularly noted in highly dynamic environments. For these lazy cases, the learned latent states do not collapse but nonetheless fail to represent key phys

Read original source ↗ Open in workspace

recordType

paper

region

Global