Wentao Zhu

Assistant Professor

wtzhu@eitech.edu.cn

Background Information: 

Wentao Zhu is an Assistant Professor and Ph.D. Advisor at EIT. His research focuses on computer vision, embodied intelligence, digital twins, and cognitive computing. He previously received his Ph.D. (2025) and Bachelor's degrees in both Computer Science and Economics (2020) from Peking University.


He has published as first author in top conferences and journals such as IEEE TPAMI, CVPR, ICCV, ECCV, NeurIPS, ICLR, and ICML, and he frequently serves as a reviewer for these venues. He was an intern researcher and consultant at Qualcomm AI Research, Shanghai Artificial Intelligence Laboratory, and SenseTime, and he was a visiting scholar at MMLab, The Chinese University of Hong Kong, and Stanford University. Currently, he is an Area Chair for NeurIPS 2025 and is organizing the first Workshop on Humanoid Agents at CVPR 2025. He is a committee member of the 3D Vision Technical Committee of the China Society of Image and Graphics. His accolades include the Peking University Challenge Cup Special Grand Prize, Peking University National Scholarship, AAAI Scholarship, Apple WWDC Scholarship, and NeurIPS Outstanding Reviewer award. 


Personal webpage: https://wentao.live/ 


Research Field:

His main research focuses on the intersection of computer vision, embodied intelligence, and cognitive science, with the aim of developing artificial intelligence that can perceive, understand, and naturally interact with humans. His work covers human behavior perception and modeling (such as motion capture, 3D reconstruction, and retargeting), understanding and reasoning (including video understanding and activity recognition), and human–agent interaction in physical and social environments, with a view toward enhancing the social cognition and reasoning abilities of embodied agents by drawing on mechanisms from cognitive science. The related research outcomes have been successfully applied in real-world systems by companies such as Huawei, Qualcomm, and Apple.


Educational Background:

2020–2025: Ph.D. in Computer Science, Center for Frontier Computing Research, Peking University

2016–2020: Bachelor's Degree in Computer Science, School of EECS, Peking University

2017–2020: Bachelor's Degree (Double Degree) in Economics, National School of Development, Peking University


Work Experience:

2025–Present: Assistant Professor, EIT


Academic Part-time Jobs (Partial):

2024–2025: Research Intern, Qualcomm AI Research

2020–2022: Research Intern, Shanghai Artificial Intelligence Laboratory

2019–2020: Research Intern, SenseTime

2018–2019: Visiting Student, Multimedia Laboratory, The Chinese University of Hong Kong

2018: Visiting Student, Stanford University (International Honors Program)

2025: Area Chair, NeurIPS

2025: Organizer, 1st Workshop on Humanoid Agents at CVPR

2022–Present: Reviewer for international journals, including IEEE TPAMI, IJCV, ACM TOG, IEEE TVCG, IEEE TIP

2021–Present: Reviewer for international conferences, including CVRP, ICCV, ECCV, NeurIPS, ICLR, ICML


Awards and Honors:

2024: Peking University National Scholarship

2023: NeurIPS Outstanding Reviewer

2023: Peking University Ubiquant Scholarship

2023: Peking University Outstanding Research Award

2022: AAAI Scholarship

2021: Grand Prize (Highest Honor) in the 29th “Challenge Cup” at Peking University

2018: Peking University Sino Scholarship

2018: Apple WWDC Scholarship


Representative Works:

Google Scholar: http://scholar.google.com/citations?hl=en&user=ZEhMnIMAAAAJ


He has published multiple papers at top conferences and journals in the field of Artificial Intelligence, with first-author papers in IEEE TPAMI, CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, etc. 


10 Representative Works (# refers to the first author, * refers to the corresponding author)

1. W. Zhu#, X. Ma, Z. Liu, L. Liu, W. Wu, and Y. Wang, "MotionBERT: A Unified Perspective on Learning Human Motion Representations," ICCV 2023.

2. W. Zhu#, Z. Zhang, and Y. Wang, "Language Models Represent Beliefs of Self and Others," ICML 2024.

3. W. Zhu#, X. Ma*, D. Ro*, H. Ci, J. Zhang, J. Shi, F. Gao, Q. Tian, and Y. Wang, "Human Motion Generation: A Survey," T-PAMI 2024.

4. W. Zhu#, J. Qin#, Y, Lou, H. Ye, X. Ma, H. Ci, and Y. Wang, "Social Motion Prediction with Cognitive Hierarchies," NeurIPS 2023.

5. W. Zhu#, Z. Yang#, Z. Di, W. Wu, Y. Wang, and C. C. Loy, "MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks," AAAI 2022.

6. H. Wang#, W. Zhu#, L. Miao, Y. Xu, F. Gao, Q. Tian, and Y. Wang, "Aligning Human Motion Generation with Human Perceptions," ICLR 2025.

7. H. Ye#, W. Zhu#, C. Wang, R. Wu, and Y. Wang, "Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection," ECCV 2022.

8. Z. Yang*, W. Zhu#, W. Wu, C. Qian, Q. Zhou, B. Zhou, and C. C. Loy, "TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting," CVPR 2020.

9. J. Qin, S. Ban, W. Zhu*, Y. Wang, and D. Samaras, "Learning Human-aware Robot Policies for Adaptive Assistance," RA-L 2025.

10. S. Ban, J. Fan, X. Ma, W. Zhu*, Y. Qiao, and Y. Wang, "Real-time Holistic Robot Pose Estimation with Unknown States," ECCV 2024.