KUAISHOU open-sources multimodal large model Kwai Keye-VL AI that can instantly understand short videos
Kuaishou released a new multimodal large model, Kwai Keye-VL, which performs excellently in video understanding, capable of transforming video content into efficient solutions and intelligently selecting thinking modes, balancing efficiency and creativity. In addition to its outstanding performance in complex visual perception and video understanding, Kwai Keye-VL also surprises with its logical reasoning capabilities, achieving a high score of 140 in the 2025 National Mathematics Examination. Currently, Kwai Keye-VL has been officially open-sourced, providing powerful tools and support for developers and researchers
Source: Zhitong 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