Hugging Face Papers ↗ · 2026-11-15
JEPA4R:具身 JEPA 世界模型与 4D 点规划
媒体报道 Hugging Face Papers 原文语言:中文
JEPA4R 使用单目深度相机点云进行4D点规划,在200步预测中平均误差仅1.1 cm,并在OGBench、MetaWorld(98.4%)和Adroit Relocate(88.0%)等基准上超越像素JEPA模型,实现零样本真实机械臂控制。
全文
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.
View arXiv page View PDF Project page GitHub 2 Add to collection
正文以来源语言显示。