Zehua Zang

Zehua Zang (臧泽华)


Postdoctoral Researcher

Supervisor: Prof. Jiahuan Zhou

Wangxuan Institute of Computer Technology, Peking University.

Beijing, China

E-mail: zehua2020@iscas.ac.cn


I am currently a postdoctoral researcher at the Wangxuan Institute of Computer Technology, Peking University. I received my Ph.D. degree from the University of Chinese Academy of Sciences and the Institute of Software, Chinese Academy of Sciences in June 2026. Before that, I received my B.Eng. degree from the School of Computer Science and Technology, Beijing Jiaotong University in June 2019. My research interests include reinforcement learning and continual learning for embodied intelligence.

 

Education

  • Ph.D., University of Chinese Academy of Sciences; Institute of Software, Chinese Academy of Sciences, National Key Laboratory of Space Integrated Information System, Sep. 2020 - Jun. 2026

  • B.Eng., School of Computer Science and Technology, Beijing Jiaotong University, Sep. 2015 - Jun. 2019

 

Research Interests

  • Embodied Intelligence

  • Reinforcement Learning

  • Continual Learning

 

Publications

  1. (CVPR'26)-Zehua Zang, Xi Wang, Fuchun Sun, Xiao Xu, Lixiang Lium, Jiahuan Zhou, Jiangmeng Li, "Test-Time Perturbation Tuning with Delayed Feedback for Vision-Language-Action Models", in The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

  2. (CVPR'26)-Kai Zhu, Zhenyu Cui, Zehua Zang, Jiahuan Zhou, "RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation", in The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

  3. (AAAI'26)-Chuxiong Sun, Peng He, Qirui Ji, Zehua Zang, Jiangmeng Li, Rui Wang, Wei Wang, "M2i2: Learning efficient multi-agent communication via masked state modeling and intention inference", in The 40th Annual AAAI Conference on Artificial Intelligence, 2026

  4. (AAMAS'26)-C. Sun, J. Chen, Zehua Zang, et al., "DR2: Revisiting Visual Reinforcement Learning from the Dimensional Analysis Perspective", in International Conference on Autonomous Agents and Multiagent Systems, 2026

  5. (NN'25)-Zehua Zang, Jiangmeng Li, Chuxiong Sunc, Rui Wang, Lixiang Liu, Fuchun Sun, "Visual Reinforcement Learning via Sequential Consistency Preserved Policy Contrast from Optimal Transport View", in Neural Networks, 2025: 108019

  6. (AAMAS'25)-Zehua Zang, Chuxiong Sun, Lixiang Liu, Fuchun Sun, Changwen Zheng, "Loss of Plasticity: A New Perspective on Solving Multi-Agent Exploration for Sparse Reward Tasks", in Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, 2025, pp. 2299-2308

  7. (ICIC'25)-Zehua Zang, Rui Wang, Lixiang Liu, Fuchun Sun, "A Game of Finding Delicate Data Augmentations: Reinforcement Contrastive Learning of Visual Representations", in International Conference on Intelligent Computing, Singapore: Springer Nature Singapore, 2025, pp. 377-388

  8. (ICIC'25)-Zehua Zang, Qirui Ji, Rui Wang, Kai Li, Lixiang Liu, Fuchun Sun, "Mastering Visual Reinforcement Learning via Positive Unlabeled Policy-Guided Contrast", in International Conference on Intelligent Computing, Singapore: Springer Nature Singapore, 2025, pp. 39-50

  9. (IJCV'25)-Jiangmeng Li, Zehua Zang, Qirui Ji, Chuxiong Sun, Wenwen Qiang, Junge Zhang, Changwen Zheng, Fuchun Sun, Hui Xiong, "Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective", in International Journal of Computer Vision, 2025, 133(6): 3542-3567

  10. (ICME'25)-Yifan Lyu, Zehua Zang, Hongzhou Wu, Lixiang Liu, Jiangmeng Li, "RBDN: A Robust Background Denoising Network for Weakly Supervised Temporal Language Grounding", in 2025 IEEE International Conference on Multimedia and Expo, IEEE, 2025, pp. 1-6

  11. (KBS'24)-Yuanyuan Guo, Zehua Zang, Hang Gao, Xiao Xu, Rui Wang, Lixiang Liu, Jiangmeng Li, "Unsupervised Social Event Detection via Hybrid Graph Contrastive Learning and Reinforced Incremental Clustering", in Knowledge-Based Systems, 2024, 284: 111225

  12. (AAAI'24)-Chuxiong Sun#, Zehua Zang#, Jiabao Li, Jiangmeng Li, Xiao Xu, Rui Wang, Changwen Zheng, "T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration", in Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(13): 15154-15163

Note: # indicates equal contribution.

 

Awards and Honors

  • Merit Student, University of Chinese Academy of Sciences, 2022-2023

  • Outstanding Student Cadre, University of Chinese Academy of Sciences, 2022-2023

  • Second-Class Academic Scholarship for Master's Students, University of Chinese Academy of Sciences, 2020-2023

  • Second-Class Academic Scholarship for Ph.D. Students, University of Chinese Academy of Sciences, 2024-2026

 

Academic Service

  • Reviewer for ICML 2026(Sliver Reviewer Award), CVPR 2026, NeurIPS 2026, ICME 2025 2026, and Knowledge-Based Systems

  • Program Committee Member for AAAI 2026