arXiv · 2611.19771
JEPA4R: Embodied JEPA World Models with 4D Point Planning
Abstract
Joint-embedding predictive architecture (JEPA) world models predict future embeddings instead of pixels and plan in latent space. Two challenges remain: 2D images leave the metric geometry that manipulation acts on implicit and entangled with appearance, and what these models imagine stays hidden, as they are mostly judged in simulation by short-horizon latent planning. We present JEPA4R, a JEPA world model that observes single-depth-camera point clouds, predicts and plans in their latent space, and acts through a policy head on its frozen latents; we call this 4D point planning. A decoder on the frozen world model shows what it imagines as 4D point clouds, with a mean point error within 1.1 cm over 200 steps. Under the policy-learning protocols of OGBench and CortexBench, JEPA4R leads pixel JEPA models on OGBench Cube-Single, Cube-Double, Cube-Triple and Scene, and ranks first on MetaWorld and Adroit Relocate with 98.4% and 88.0%, above the runner-up, R3M, at 96.0% and 65.3%. Trained only in a digital twin, JEPA4R and its policy heads run zero-shot on the real arm with both a gripper and a dexterous hand.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Jiarui Dong, Zhiheng Liang, Yanjun Li, Zeyu Zhang, Heejeong Nam, Haoyu Chen, Hao Tang. 2026-11-15. JEPA4R: Embodied JEPA World Models with 4D Point Planning. https://searcharxiv.com/abs/2611.19771
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.