XPENG and Peking University's collaboration leads to FastDriveVLA, cutting down autonomous driving AI data by 7.5x.
XPENG and Peking University have made a significant research advancement by creating FastDriveVLA, a new visual token pruning framework. This technology allows autonomous driving AI to mimic human driving behavior by concentrating solely on crucial data. Through this innovation, a remarkable 7.5x reduction in unnecessary information processing has been achieved, optimizing the efficiency of autonomous driving systems.
Source: Unusual Whales The copyright of this article belongs to the original author/organization.
The views expressed herein are solely those of the author and do not reflect the stance of the platform. The content is intended for investment reference purposes only and shall not be considered as investment advice. Please contact us if you have any questions or suggestions regarding the content services provided by the platform.
Post your comment
No Comments