@misc{arxiv_2611_04916,
  title = {Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling},
  author = {{Kling Team} and {Dong Chen} and {Jialu Chen} and {Xinlong Chen} and {Yifan Dai} and {Haotian Dong} and {Binzong Geng} and {Yushuo Guan} and {Minghui Guo} and {Guanlin He} and {Guanxiao He} and {Jingyun Hua} and {Yanwei Huang} and {Yiyan Ji} and {Xueping Jia} and {Yizhuo Jia} and {Bozhou Li} and {Jiaze Li} and {Min Li} and {Shihao Li} and {Shujie Li} and {Shengyi Liao} and {Weihong Lin} and {Shiyuan Liu} and {Xinyu Liu} and {Siyang Mao} and {Xiaoru Qu} and {Dianmo Sheng} and {Yang Shi} and {Jiafu Tang} and {Longxiang Tang} and {Yuqi Tang} and {Chengzhuo Tong} and {Kuo Wang} and {Qixun Wang} and {Rui Wang} and {Tianduo Wang} and {Yuran Wang} and {Zekun Wang} and {Zihao Wang} and {Boyang Xia} and {Yifan Xu} and {Liu Yang} and {Zhenlong Yuan} and {Bohan Zeng} and {Mujin Zhang} and {Yuanxing Zhang} and {Zhicheng Zhang} and {Zhuoran Zhang} and {Yuanhong Zheng} and {Kun Gai} and {Chengru Song} and {Pengfei Wan}},
  eprint = {2611.04916},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.04916}
}