Publications

Preprints

• Adaptive Power Sampling for LLM Reasoning
  Bingnan Xiao, Chenhao Yang, Bingcong Li, Wei Ni, and Xin Wang.
  arXiv:2610.08563, 2026.
  [arXiv]
• Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach
  Xinyi Xu*, Bingnan Xiao*, Shuang Qin, Gang Feng, and Tony Q. S. Quek. (*Equal contribution)
  arXiv:2608.09742, 2026.
  [arXiv]
• Explainable AI for Next-Generation Wireless Physical Layer: Basics, State-of-the-Art, and Open Challenges
  Bingnan Xiao, Shuyan Hu, Xiaojing Chen, Zhiyuan Zhai, Bingcong Li, Wei Ni, Xin Wang, and Ekram Hossain.
  Submitted to IEEE Communications Surveys & Tutorials (SCI Q1 Top); arXiv:2606.24424, 2026.
  [arXiv]
• Agentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems
  Bingnan Xiao, Chenhao Yang, Wei Ni, Xin Wang, and Tony Q. S. Quek.
  Submitted to IEEE Transactions on Mobile Computing (CCF-A); arXiv:2606.24416, 2026.
  [arXiv]

Journal Papers

• Divergence-Based Adaptive Aggregation for Byzantine Robust Federated Learning
  Bingnan Xiao, Feng Zhu, Jingjing Zhang, Wei Ni, and Xin Wang.
  IEEE Transactions on Information Forensics and Security, 2026. (CCF-A)
  [arXiv]
• FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks
  Bingnan Xiao, Jingjing Zhang, Wei Ni, and Xin Wang.
  IEEE Transactions on Wireless Communications, 2025. (SCI Q1 Top)
  [paper] [arXiv]
• Over-the-Air Federated Learning: Status Quo, Open Challenges, and Future Directions
  Bingnan Xiao, Xichen Yu, Wei Ni, Xin Wang, and H. Vincent Poor.
  Fundamental Research, 2024.
  [paper] [arXiv]
• Optimal Adaptive Power Control for Over-The-Air Federated Edge Learning Under Fading Channels
  Xichen Yu, Bingnan Xiao, Wei Ni, and Xin Wang.
  IEEE Transactions on Communications, 2023. (SCI Q1 Top)
  [paper]

Conference Papers

• FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning
  Bingnan Xiao, Yuan Gao, Bingcong Li, Wei Ni, Xin Wang, and Tony Q. S. Quek.
  Accepted to the 40th Conference on Neural Information Processing Systems (NeurIPS 2026).
  [OpenReview] [arXiv]
• Federated Learning with Adjustable Learning Rates for Resource-Constrained Wireless Networks
  Bingnan Xiao, Jingjing Zhang, Wei Ni, and Xin Wang.
  Proceedings of the 10th IEEE International Conference on Computer and Communication Systems (ICCCS 2025). ★ Best Paper Award
  [paper]
• Optimal Power Control for Over-the-Air Federated Edge Learning Using Statistical Channel Knowledge
  Xichen Yu, Bingnan Xiao, Wei Ni, and Xin Wang.
  Proceedings of the 14th International Conference on Wireless Communications and Signal Processing (WCSP 2022).
  [paper]