arXiv · cs.AI · Long Li, Qichao Zhao, Yue Yang, Fan Xu, Zhe Wang, Alan Wee-Chung Liew, Chao Qu, Heng Tao Shen, Shirui Pan · 10 小时前模型评分47
Spotter：让具身模型主导，视觉语言模型（VLM，Vision-Language Model） 负责反思纠错
Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
导读
Spotter 提出一种角色反转的协作方式：具身模型持续主导执行，视觉语言模型（VLM，Vision-Language Model）并行监控，仅在检测到错误时介入反思并纠正。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We propose Spotter, which reverses the roles: the embodied model leads and executes continuously, while the VLM runs in parallel, monitors through a lightweight local screener, intervenes only when an error is detected, reflects on and corrects it, and returns control.”
- “Our code is available at this https URL .”
来源：arXiv · cs.AI · arxiv.org