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

Paper recorded by Signals 4 on 2026-08-29 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-29 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.CV · 计算机视觉 · first seen 2026-09-01

Abstract

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

Read on arXiv →