Awesome World Models / arXiv

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

作者：作者信息待提取 · 单位：Hong Kong University of Science and Technology, ByteDance Seed · 来源：World Models for Embodied AI · 发布日期：2025 · 分类：5. World Models x VLAs / Combining World Models and VLAs

具身智能视觉语言动作/策略学习语言先验视觉语言桥接
新标签打开 AlphaXiv新标签打开 Project
WMPO: World Model-based Policy Optimization for Vision-Language-Action Models figure
AlphaXiv 中文概览（可滚动查看）