Hi, I am Zheshun Wu 👋

I am currently a Ph.D. student in the School of Computer Science and Technology at Harbin Institute of Technology, Shenzhen, where I am fortunate to be advised by Prof. Jie Liu (IEEE Fellow) and Prof. Zenglin Xu. During my Ph.D. studies, I also spent one year as a visiting student at the Southern University of Science and Technology, supervised by Prof. Fang Kong. Prior to this, I received my Master’s degree in Information and Communication Engineering from Sun Yat-sen University in 2023, and my Bachelor’s degree in Information and Interaction Design from South China University of Technology in 2020.

My research broadly focuses on developing efficient, trustworthy, and generalizable machine learning algorithms for communication and networked systems. In particular, I am interested in leveraging machine learning theory to understand and improve learning, optimization, and decision-making in distributed and resource-constrained environments.

My current research interests include:

• Efficient Training and Inference: Distributed machine learning, progressive training, MoE training, and edge collaborative inference.
• Online Learning and Reinforcement Learning: Robust multi-armed bandits and provably sample-efficient reinforcement learning.
• Wireless Communications and Networking: AI for communications, wireless sensing, and localization.

🔥 News

• [Jun. 2026] One paper was accepted by UAI 2026!
• [Feb. 2026] One paper was accepted by Neural Networks!
• [Jan. 2026] One paper was accepted by ICLR 2026!

Experience

• Research Intern, Noah’s Ark Lab, Huawei Technologies Ltd.
  Time: Jan. 2026 – July 2026
  Mentor: Dr. Yu Pan
  Project: Research on Expert Specialization in Large-Scale Pre-trained MoE Models.

• Visiting Student, Department of Statistics and Data Science, Southern University of Science and Technology.
  Time: Nov. 2024 – Sept. 2025
  Supervisor: Prof. Fang Kong
  Project: Research on Trustworthy Online Learning Algorithms for Multi-Agent Systems.

Publications

• [UAI '26] Federated Combinatorial Causal Bandits with Heterogeneous Causal Influences
  Zheshun Wu, Wei Chen, Zenglin Xu, and Fang Kong.
  Conference on Uncertainty in Artificial Intelligence (UAI), 2026.
• [NN '26] Enhancing Progressive Ensemble Learning via Normalized Extra-Gradient Initialization
  Zheshun Wu, Yu Pan, Dun Zeng, Zenglin Xu, Qifan Wang, and Jie Liu.
  Neural Networks, 2026.
• [ICLR '26] Bandit Learning in Matching Markets Robust to Adversarial Corruptions
  Zheshun Wu, Jinhang Zuo, Zenglin Xu, and Fang Kong.
  The 14th International Conference on Learning Representations (ICLR), 2026.
• [TCCN '25] Online Optimization for Learning to Communicate over Time-correlated Channels
  Zheshun Wu, Junfan Li, Zenglin Xu, Sumei Sun, and Jie Liu.
  IEEE Transactions on Cognitive Communications and Networking (TCCN), 2025.
• [NeurIPS '24] On the Necessity of Collaboration for Online Model Selection with Decentralized Data
  Junfan Li, Zheshun Wu, Zenglin Xu, and Irwin King.
  Advances in Neural Information Processing Systems (NeurIPS), 2024.
• [TNNLS '24] Advocating for the Silent: Enhancing Federated Generalization for Non-Participating Clients
  Zheshun Wu, Zenglin Xu, Dun Zeng, Qifan Wang, and Jie Liu.
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024.
• [TVT '24] Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks
  Zheshun Wu, Zenglin Xu, Dun Zeng, Junfan Li, and Jie Liu.
  IEEE Transactions on Vehicular Technology (TVT), 2024.
• [SPL '24] Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channels
  Zheshun Wu, Zenglin Xu, Hongfang Yu, and Jie Liu.
  IEEE Signal Processing Letters (SPL), 2024.
• [TNSM '23] Joint Scheduling and Robust Aggregation for Federated Localization over Unreliable Wireless D2D Networks
  Zheshun Wu, Xiaoping Wu, and Yunliang Long.
  IEEE Transactions on Network and Service Management (TNSM), 2023.
• [SENSJ '22] Prediction Based Semi-supervised Online Personalized Federated Learning for Indoor Localization
  Zheshun Wu, Xiaoping Wu, and Yunliang Long.
  IEEE Sensors Journal, 2022.
• [ComL '22] Multi-level Federated Graph Learning and Self-attention Based Personalized Wi-Fi Indoor Fingerprint Localization
  Zheshun Wu, Xiaoping Wu, and Yunliang Long.
  IEEE Communications Letters (ComL), 2022.