Awesome World Models / arXiv

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

作者：作者信息待提取 · 来源：World Models for Embodied AI · 发布日期：2024 · 分类：3. World Models for Navigation

具身智能机器人导航语言先验
新标签打开 AlphaXiv新标签打开 Code
NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning figure
AlphaXiv 中文概览（可滚动查看）