Yunyao Mao

Kling Team, Kuaishou Technology

Email / Google Scholar / GitHub

Yunyao Mao

Biography

I am currently a senior researcher at Kling Team, Kuaishou Technology. My recent work focuses on multimodal video generation and unified models. Previously, I studied at the Department of Electronic Engineering and Information Science, University of Science and Technology of China (USTC), where I received my B.E. in Information Security and pursued Ph.D. research under the supervision of Prof. Houqiang Li and Prof. Wengang Zhou.

We are actively looking for interns and researchers. Feel free to reach me out if you are interested.

Recent News

  • [2025.12] Kling-Omni Technical Report released for multimodal video generation.
  • [2025.06] Obtained Ph.D. degree from University of Science and Technology of China.

Recent Publications

Full List
Kling-Omni Technical Report preview

Kling-Omni Technical Report

Kling Team, Jialu Chen, Yuanzheng Ci, Xiangyu Du, Zipeng Feng, Kun Gai, Sainan Guo, Feng Han, Jingbin He, Kang He, ..., Yunyao Mao, ...

ArXiv Preprint, 2025.

[arXiv] [interface]

Learning Generalizable Human Motion Generator with Reinforcement Learning preview

Learning Generalizable Human Motion Generator with Reinforcement Learning

Yunyao Mao, Xiaoyang Liu, Wengang Zhou, Zhenbo Lu, Houqiang Li

ArXiv Preprint, 2024.

[arXiv]

I2MD preview

I2MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation

Yunyao Mao, Jiajun Deng, Wengang Zhou, Zhenbo Lu, Wanli Ouyang, Houqiang Li

International Journal of Computer Vision (IJCV), 2025.

[arXiv] [code]

CLIP4HOI preview

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection

Yunyao Mao, Jiajun Deng, Wengang Zhou, Li Li, Yao Fang, Houqiang Li

Advances in Neural Information Processing Systems (NeurIPS), 2023.

[paper]

MAMP preview

Masked Motion Predictors are Strong 3D Action Representation Learners

Yunyao Mao, Jiajun Deng, Wengang Zhou, Yao Fang, Wanli Ouyang, Houqiang Li

International Conference on Computer Vision (ICCV), 2023.

[arXiv] [code]

CMD preview

CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

Yunyao Mao, Wengang Zhou, Zhenbo Lu, Jiajun Deng, Houqiang Li

European Conference on Computer Vision (ECCV Oral), 2022.

[arXiv] [code]

JOINT preview

Joint Inductive and Transductive Learning for Video Object Segmentation

Yunyao Mao, Ning Wang, Wengang Zhou, Houqiang Li

International Conference on Computer Vision (ICCV), 2021.

[arXiv] [code]