视觉语言模型 | 刘圣鼎https://sendinga.github.io/zh/tag/%E8%A7%86%E8%A7%89%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/视觉语言模型Hugo Blox Builder (https://hugoblox.com)zh-HansWed, 11 Feb 2026 00:00:00 +0000https://sendinga.github.io/media/icon_hu0b7a4cb9992c9ac0e91bd28ffd38dd00_9727_512x512_fill_lanczos_center_3.png视觉语言模型https://sendinga.github.io/zh/tag/%E8%A7%86%E8%A7%89%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/VULCAN: Vision-Language-Model Enhanced Multi-Agent Cooperative Navigation for Indoor Fire-Disaster Responsehttps://sendinga.github.io/zh/publication/vulcan-ein-2026/Wed, 11 Feb 2026 00:00:00 +0000https://sendinga.github.io/zh/publication/vulcan-ein-2026/<p>我们的论文 <strong>VULCAN</strong> 已被 <strong>IEEE INFOCOM 2026 Workshop on Embodied Intelligence Networks（EIN）</strong> 录用！</p> <p>这项工作提出了一种面向室内火灾响应的多智能体协同导航新方法，利用视觉语言模型提升应急响应机器人的态势感知与协作能力。</p>