Alibaba· QwenNew model

Qwen-VLA: From Understanding the World to Acting in It

Alibaba announces Qwen-VLA, a general-purpose Vision-Language-Action model built on the Qwen multimodal backbone, designed to extend visual perception, language understanding, and spatial reasoning into continuous action generation and trajectory prediction for embodied intelligence tasks such as robotic manipulation and vision-language navigation.

From the source

Qwen-VLA is a general-purpose Vision-Language-Action model. Built upon the Qwen multimodal backbone, it extends visual perception, language understanding, and spatial reasoning into continuous action generation and trajectory prediction.

qwen.ai

Announced

29 May 2026 09:00 UTC

Detected

28 Aug 2026 13:23 UTC (+91d after)