Awesome World Models / arXiv

Grounding Video Models to Actions through Goal Conditioned Exploration

作者：作者信息待提取 · 来源：World Models for Embodied AI · 发布日期：2024 · 分类：2. World Models for Manipulation

具身智能机器人操作视频生成
新标签打开 AlphaXiv新标签打开 Project新标签打开 Code
Grounding Video Models to Actions through Goal Conditioned Exploration figure
AlphaXiv 中文概览（可滚动查看）