TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning
2026年5月5日·
,
,
,
,
,
,
,
·
0 分钟阅读时长
Tao Wu
Li Yang
Gen Zhan
Yabin Zhang
Yiting Liao
Junlin Li
Deliang Fu
Li Zhang
Limin Wang
类型
出版物
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
