Awesome World Models / arXiv

Goal-VLA: Image-Generative VLMs as Object-Centric World Models Empowering Zero-shot Robot Manipulation

作者：作者信息待提取 · 来源：World Models for Embodied AI · 发布日期：2025 · 分类：5. World Models x VLAs / Unifying World Models and VLAs in one model

具身智能机器人操作视觉语言动作/策略学习对象中心
新标签打开 AlphaXiv新标签打开 Project
Goal-VLA: Image-Generative VLMs as Object-Centric World Models Empowering Zero-shot Robot Manipulation figure
AlphaXiv 中文概览（可滚动查看）