机器人学2025

Qwen-VLA: Vision-Language-Action Model from Alibaba

Darshan Nagendra Prasad, Lars Ullrich, Knut Graichen et al.Alibaba

摘要

Qwen-VLA is a vision-language-action model built upon the Qwen foundation, integrating strong visual understanding with action generation for general-purpose robot control across diverse embodiments.

VLAQwenvision-language-actionAlibabarobot control

技术细节

数据集
Qwen-VLA-Data
模型骨架

Qwen-VLA

京ICP备2026064258号-1