Zhenda Xie 解振达

Zhenda Xie is currently a researcher at DeepSeek AI, actively pursuing advancements in AGI (Artificial General Intelligence), with a particular research focus on the Pre-training and Scaling of Foundation Models.
He received his Ph.D. degree from Tsinghua University in 2023, specializing in self-supervised visual representation learning under the supervision of Prof. Baining Guo. During his doctoral studies, he collaborated closely with Dr. Han Hu, Dr. Yue Cao and Zheng Zhang as a research intern at Microsoft Research Asia (MSRA) from 2018 to 2023. Prior to that, he received the B.Eng. degree from University of Science and Technology of China(USTC) in 2018 and was awarded as Outstanding Graduates.
If you are interested in pursuing an internship or a full-time research position, please do not hesitate to reach out by sending an email.

News

• 2023.03  Two papers on understanding MIM and data scalability of MIM accepted by CVPR 2023.
• 2022.03  Two papers accepted by CVPR 2022.
• 2021.12  Code available for SimMIM.
• 2021.05  Code available for Self-Supervised Learning with Swin Transformers.
• 2021.03  Code available for PixPro.
• 2021.03  One paper accepted by CVPR 2021.
• 2021.01  Code available for PIC.
• 2020.09  One paper accepted by NeurIPS 2020.
• 2020.08  Code available for Spatially Adaptive Inference.
• 2020.07  One paper accepted by ECCV 2020.

Publications

(^† indicates Equal Contribution)

• Revealing the Dark Secrets of Masked Image Modeling Zhenda Xie^†, Zigang Geng^†, Jingcheng Hu, Zheng Zhang, Han Hu, Yue Cao Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
• On Data Scaling in Masked Image Modeling [code] Zhenda Xie, Zheng Zhang, Yue Cao, Yutong Lin, Yixuan Wei, Qi Dai, Han Hu Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
• Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation Yixuan Wei^†, Han Hu^†, Zhenda Xie, Zheng Zhang, Yue Cao, Jianmin Bao, Dong Chen, Baining Guo Tech Report, 2022.
• SimMIM: A Simple Framework for Masked Image Modeling [code] Zhenda Xie^†, Zheng Zhang^†, Yue Cao^†, Yutong Lin, Jianmin Bao, Zhuliang Yao, Qi Dai, Han Hu^† Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
• Swin Transformer V2: Scaling Up Capacity and Resolution [code] Ze Liu^†, Han Hu^†, Yutong Lin, Zhuliang Yao, Zhenda Xie, Yixuan Wei, Jia Ning, Yue Cao, Zheng Zhang,
  Li Dong, Furu Wei, Baining Guo Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
• Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning [code] Yansong Tang^†, Zhenyu Jiang^†, Zhenda Xie^†, Yue Cao, Zheng Zhang, Philip H. S. Torr, Han Hu ICCV SRVU workshop, 2021.
• Self-Supervised Learning with Swin Transformers [code] Zhenda Xie^†, Yutong Lin^†, Zhuliang Yao, Zheng Zhang, Qi Dai, Yue Cao, Han Hu Tech Report, 2021.
• Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning [code] Zhenda Xie^†, Yutong Lin^†, Zheng Zhang, Yue Cao, Stephen Lin, Han Hu Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
• Parametric Instance Classification for Unsupervised Visual Feature Learning [code] Yue Cao^†, Zhenda Xie^†, Bin Liu^†, Yutong Lin, Zheng Zhang, Han Hu Conference on Neural Information Processing Systems (NeurIPS), 2020.
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [code] Zhenda Xie^†, Zheng Zhang^†, Xizhou Zhu, Gao Huang, Stephen Lin European Conference on Computer Vision (ECCV), 2020. (Oral)
• Local Relation Networks for Image Recognition Han Hu, Zheng Zhang, Zhenda Xie, Stephen Lin International Conference on Computer Vision (ICCV), 2019.

Experiences

• 2019.08 - 2023.06Research Intern, Microsoft Research Asia (Mentor: Dr. Han Hu).
• 2018.02 - 2019.08Research Intern, Microsoft Research Asia (Mentor: Dr. Jifeng Dai).

Selected Honors

• National ScholarshipTsinghua University, 2021.
• Future Researchers ScholarshipTsinghua University, 2018. (169 this year.)
• Outstanding GraduatesUniversity of Science and Technology of China, 2018. (71/1802)
• National ScholarshipUniversity of Science and Technology of China, 2016.