SOURCE-LINKED INTELLIGENCE

Does Latent Planning Survive Point Clouds? Action-Conditioned JEPA World Models for Geometric Observations

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

JEPA world models make latent-space planning a practical route to control, but they are built almost exclusively on images. Whether latent prediction survives geometric observations is unclear: point clouds are sparse, unordered, and self-occluded, and with 0.3-15% of scene points moving, the slow-feature optimum of latent prediction compounds with the geometric shortcut of 3D self-supervision. We lift three canonical JEPA designs to point clouds, frozen-encoder, distribution-prior, and action-sensitive, and re-sense the stable-worldmodel benchmark so that only the observation differs from the

Read original source ↗ Open in workspace

recordType

paper

region

Global