Robots are getting smarter with the upgrade of multimodal large models, which serve as their "brains." On Thursday, China’s AI company SenseTime unveiled its updated multimodal large model — SenseNova V6. The new version integrates text, images, and videos, offering users a more natural and immersive interactive experience. Join CGTN to explore how this large model enables robots to see and think more deeply.
Copyright © 2020 CGTN. Beijing ICP prepared NO.16065310-3