Biography

I am currently a 3rd-Year Master student at Shenzhen International Graduate School, Tsinghua University, under the guidance of Chun Yuan. I got my B.Eng. degree at school of Astronautics, Beihang University. I interned at Bytedance's AI Lab (adviced by Zhe Li) and IDEA (adviced by Ailing Zeng and Yu Li).

Currently, my research topic is video generation and model compression, with a particular focus on knowledge distillation. I devote to improve various models' performance for various tasks, including cv, language, understanding, generation and so on.

I am an algorithm engineer at WeChat, Tencent (Shenzhen, China) since 2024.


Selected Publications


ViTKD: Feature-based Knowledge Distillation for Vision Transformers   GitHub stars

Zhendong Yang, Zhe Li, Ailing Zeng, Zexian Li, Chun Yuan, Yu Li
Computer Vision and Pattern Recognition 2024, Workshop (CVPRW 2024, Oral)

Paper 
Effective Whole-body Pose Estimation with Two-stages Distillation   GitHub stars

Zhendong Yang, Ailing Zeng, Chun Yuan, Yu Li
International Conference on Computer Vision 2023, CV4Metaverse Workshop (ICCVW 2023, Oral)

Paper  zhihu
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels   GitHub stars

Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang, Chun Yuan, Yu Li
International Conference on Computer Vision 2023 (ICCV 2023)

Paper  zhihu
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers   GitHub stars

Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang
International Conference on Machine Learning 2023 (ICML 2023)

Paper  zhihu
Masked Generative Distillation   GitHub stars

Zhendong Yang*, Zhe Li*, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan
European Conference on Computer Vision 2022 (ECCV 2022)

Paper  zhihu
Focal and Global Knowledge Distillation for Detectors   GitHub stars

Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, Chun Yuan
Computer Vision and Pattern Recognition 2022 (CVPR 2022)

Paper  zhihu

Honors & Awards

Academic Service


last updated at .