2606.10651
2026-06-10
cs.CV
新提交
57%
Kwai Keye-VL-2.0 Technical Report
Kwai Keye-VL-2.0 技术报告
Kwai Keye Team, Bin Wen, Changyi Liu, Chengru Song, Chongling Rao, Guowang Zhang, Han Li, Haonan Fan, Hengrui Ju, Jiankang Chen, Jiapeng Chen, Jiawei Yuan, Kaixuan Yang, Kaiyu Jiang, Kun Gai, Lingzhi Zhou, Na Nie, Sen Na, Tianke Zhang, Tingting Gao, Xuanyu Zheng, Yulong Chen, Fan Yang, Haixuan Gao, Lele Yang, Mingqiao Liu, Muxi Diao, Qi Zhang, Qile Su, Wei Chen, Wentao Hong, Xingyu Lu, Yancheng Long, Yankai Yang, Yingxin Li, Yiyang Fan, Yu Xia, Yuzhe Chen, Ziliang Lai, Chuan Yi, Haonan Jia, Tianming Liang, Weixin Xu, Xiaoxiao Ma, Yang Tian, Yufei Han, Feng Han, Hang Li, Jing Wang, Jinghui Jia, Junmin Chen, Junyu Shi, Ruilin Zhang
机构
*
Kuaishou Group（快手集团）
专题命中
视频理解
：video understanding(abstract)；分类 cs.CV
AI总结
提出开源MoE多模态基础模型Keye-VL-2.0，首次将DeepSeek稀疏注意力适配到GQA架构，支持无损256K上下文处理，并通过跨模态多教师策略蒸馏和上下文/视频强化学习解决多任务对齐中的灾难性遗忘，在长视频理解和智能体任务上达到同类最优。
