Xianjie ZHANG ( 张现杰 )
Ph.D. of Software Engineering

Dalian University of Technology

Location: Beijing, China
Short Bio | Career & Education History | Research Experiences | Publications | Awards & Honors | Services

Email: xj_zh@foxmail.com;
[Zhihu] [CV] [Google Scholar] [Github] [LinkedIn]

News

Short Bio

I am currently working as an Algorithm Technology Developer at Academy of Satellite Application Innovation.

Previously, I worked as a Senior Algorithm Researcher at Haomo AI Technology (Great Wall Motors (2023-2025)), focusing on autonomous driving and decision-making systems.

I received my Ph.D. degree from the School of Software Technology at Dalian University of Technology in 2023. I also had the opportunity to work as a visiting Ph.D. student at Singapore Management University under the supervision of Prof. Pradeep Varakantham (2021-2022).

Research Interests: My research focuses on reinforcement learning, multi-agent systems, causal inference, and their real-world applications. I am particularly interested in:

  • Offline reinforcement learning and off-policy evaluation
  • Multi-agent coordination and communication
  • Causal inference in learning systems
  • Adversarial robustness in RL
  • Applications in autonomous systems and optimization

Career & Education History

Publications

 "*" means equal contribution.

  • Yifei Cao, Yu Liu, Guolong Wang, Zhu Liu, Kai Wang, Xianjie ZHANG, Jizhe Yu, Xun Tu, "EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization", AAAI, 2026. [Paper]

  • Jiahao Sun, Yu Liu, Xianjie ZHANG, Yifei Cao, Li Hong, Kai Wang. "Learn to Walk with Continuous-Action for Knowledge-Enhanced Recommendation System", IJCNN, 2024. [Paper]

  • Xianjie ZHANG, Jiahao Sun, Chen Gong, Kai wang, Yifei Cao, Hao Chen, Yu Liu. "Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling", AAMAS, 2024. [Paper]

  • Xianjie ZHANG, Pradeep Varakantham, Hao Jiang, "Future Aware Pricing and Matching for Sustainable On-Demand Ride Pooling", AAAI, 2023. [Paper]

  • Xianjie ZHANG, Yu Liu, Xiujuan Xu, Qiong Huang, Hangyu Mao, Anil Carie, "Structural relational inference actor-critic for multi-agent reinforcement learning", Neurocomputing, 2021. [Paper]

  • Xianjie ZHANG, Yu Liu, Hangyu Mao, Chao Yu, "Common belief multi-agent reinforcement learning based on variational recurrent models", Neurocomputing, 2022. [Paper]

  • Xianjie ZHANG, Yu Liu, Wen Jun Li, Chen Gong, "Pruning the Communication Bandwidth between Reinforcement Learning Agents through Causal Inference", Sensors, 2023. [Paper]

  • Chen Gong, Qiang He, Yunpeng Bai, Zhou Yang, Xiaoyu Chen, Xinwen Hou, Xianjie ZHANG, Yu Liu, Guoliang Fan. "The f-Divergence Reinforcement Learning Framework". [Arxiv]

    • Doctoral Dissertation:

  • 张现杰 (Xianjie Zhang). 面向多智能体深度强化学习的协同方法研究（Research on Collaborative Methods for Multi-Agent Deep Reinforcement Learning）[D]. Doctoral Dissertation, Dalian University of Technology. 2023.

    • Patent:

  • XX, XX, 张现杰（Xianjie Zhang）, 等. 轨迹预测模型训练方法及电子设备. (自动驾驶相关). 2024.

  • 刘宇, 张现杰（Xianjie Zhang）, 等. 基于变分循环网络模型的信念一致多智能体强化学习方法. CN114037048B (已授权). 2023.

    • Blog:

  • 张现杰 (Xianjie Zhang). 从深度强化学习到多智体强化学习（From Reinforcement Learning to Multi-agent Reinforcement Learning）[Blog]. 2019.

  • 张现杰 (Xianjie Zhang). 扩散模型 (Diffusion Models)[Blog]. 2023.

    • Awards & Honors

    Awards:

    Honors:

    • 2016, Hebei, Provincial-level Outstanding Graduate
    • 2023, Dalian University Of Technology, School-level Outstanding Graduate

    Services
    • CCF-A Conference Reviewer:
    • 2022, 2023, 2024, 2025 ICML
    • 2022, 2023, 2024, 2025 NeurIPS
    • 2024, 2025, 2026 ICLR
    • 2025 ACMMM, 2026(Program Committee) ACMMM
    • 2026 CVPR
    • 2025 ICCV
    • 2026 ECCV
    • 2025 IJCNN
    • 2025 AISTATS
    • 2025 BMVC
    • 2026 AISTATS
    • Journal Reviewer:
    • Neurocomputing
    • IEEE Transactions on Emerging Topics in Computational Intelligence
    • International Journal of Machine Learning and Cybernetics
    • Neural Processing Letters


    © Xianjie Zhang | Last Update: OCT 2023