Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation 文章

ArXiv CS.CV2026-06-04NEWSen作者: Boyuan Xiao, Bohong Chen, Yumeng Li, Ji Feng, Yao-Xiang Ding, Kun Zhou
查看原文 →
关系图谱

Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation · 相关技术

相关技术

Vision-Language-Action modelVision-Language Models