Awesome World Models / arXiv

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

作者：作者信息待提取 · 单位：University of Science and Technology of China, Zhongguancun Academy, Beijing, China, Tong University, Tsinghua University, Eastern Institute of Technology, Ningbo · 来源：World Models for Embodied AI · 发布日期：2026 · 分类：2. World Models for Manipulation

具身智能机器人操作视觉语言动作/策略学习基础世界模型
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model figure
AlphaXiv 中文概览（可滚动查看）