flâneur

Unitree’s founder disputes VLA consensus, backs video-trained models for robotics

kr-asia.com · 755 words · saved by 1 readers

When most in the industry think of Unitree Robotics, they see a company focused on building robot hardware. But at the World Robot Conference (WRC), founder Wang Xingxing offered a different narrative. During his keynote at WRC, Wang dedicated a large portion of his talk to large models, algorithms, and data. It was a shift that didn’t go unnoticed. His comments sparked debate, particularly his critique of the vision-language-action (VLA) framework driving many of today’s embodied robots. Wang didn’t mince words: he called the VLA architecture “relatively dumb.” The main problem, in his view, is data, or the lack thereof. VLA models require vast, high-quality datasets to function effectively in the real world. While the scarcity of such data is widely acknowledged, many companies have pursued brute-force methods: gathering real-world robot data, generating simulation data, or building specialized data collection infrastructure. Wang believes that emphasis is misplaced. “People are payi

Describing VLA models as “relatively dumb,” he outlined an alternative approach to embodied intelligence. When most in the industry think of Unitree Robotics, they see a company focused on building robot hardware. But at the World Robot Conference (WRC) , founder Wang Xingxing offered a different narrative. During his keynote at WRC, Wang dedicated a large portion of his talk to large models, algorithms, and data. It was a shift that didn’t go unnoticed. His comments sparked debate, particularly his critique of the vision-language-action (VLA) framework driving many of today’s embodied robots.

saved by

related reading