Kwai Keye Vl Video Understanding

Build an 8B multimodal model specializing in short-form video understanding. Combines four-stage pre-training with instruction-tuning and reinforcement learning to enable advanced reasoning about dynamic video content while maintaining general vision-language capabilities.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 9496068195

Frequently asked questions

npx get-skill add adu2021/kwai-keye-vl-video-understanding