arXiv Computer Vision· Songze Li, Haoming Gu, Ziyang Gong, Zhitong Wang, Gengze Zhou, Zun Wang, Yuhan Zhu, Tianxiang Jiang, Juanzi Li, Qi Wu, Weinan Zhang, Yu Qiao, Wenwei Zhang, Yi Wang·· 20 小时前AI 评分22
RSI-Nav:策略同步语言-动作双自举的导航数据递归自改进框架
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
AI 导读
RSI-Nav 是一个面向视觉语言导航的数据中心递归自改进框架,通过策略同步的语言-动作双自举,在共享模型中统一了视觉-语言到动作的指令跟随与视觉-动作到语言的指令生成。
来源:arXiv Computer Vision · arxiv.org