I am a Ph.D. student at PCNI Lab of the School of Electronics, Peking University, supervised by Prof. Xiang Cheng. I also work closely with Prof. Shijian Gao from HKUST-GZ. Before that, I obtained my bachelor’s degree in the School of Information and Communication Engineering from the University of Electronic Science and Technology of China (UESTC) in 2025.

My research interests include AI-empowered wireless system design and adaptive convolution. Specifically, I have recently focused on the wireless physical layer (PHY) design enabled by foundation models.

Publications

Working Paper

1. Xuanyu Liu, Shijian Gao, Boxun Liu, Xiang Cheng, and Liuqing Yang, “WiFo-CF: Wireless Foundation Model for CSI Feedback” [arXiv]
2. Boxun Liu, Xuanyu Liu, Shijian Gao, Xiang Cheng, and Liuqing Yang, “Foundation Model for Intelligent Wireless Communications,” Science Advances, submitted for publication, 2025. [arXiv]
3. Xiang Cheng, Boxun Liu, Xuanyu Liu, and Xuesong Cai, “Large Wireless Foundation Models: Stronger over Bigger,” IEEE Wireless Communications Magazine, submitted for publication, 2026.

Journals

1. Xiang Cheng, Boxun Liu, Xuanyu Liu, Ensong Liu, and Ziwei Huang, “Foundation Model Empowered Synesthesia of Machines (SoM): AI-native Intelligent Multi-Modal Sensing-Communication Integration”, IEEE Transactions on Network Science and Engineering, Jul. 2025. [arXiv] [Code] First to propose the paradigm of foundation-model-empowered Machine Synesthesia (SoM).
2. Xuanyu Liu, Shijian Gao, Boxun Liu, Xiang Cheng, and Liuqing Yang, “LLM4WM: Adapting LLM for Wireless Multi-Tasking”, IEEE Transactions on Machine Learning in Communications and Networking, vol. 3, pp. 835-847, July. 2025. [Paper][arXiv][Code] Selected as the Most Popular Document Top 5 of TMLCN: August 2025-now
3. Boxun Liu, Shijian Gao, Xuanyu Liu, Xiang Cheng, and Liuqing Yang, “WiFo: Wireless Foundation Model for Channel Prediction,” SCIENCE CHINA Information Sciences, vol. 68, no. 6, p. 162302, May. 2025. [Paper][arXiv] [Code] The first wireless foundation model to address time-frequency channel prediction tasks in a one-for-all manner.
4. Boxun Liu, Xuanyu Liu, Shijian Gao, Xiang Cheng, and Liuqing Yang, “LLM4CP: Adapting Large Language Models for Channel Prediction,” Journal of Communications and Information Networks, vol. 9, no. 2, pp. 113-125, Jun. 2024. [Paper][Code] [Interpretation] The first attempt to adapt pre-trained LLM for channel prediction.
   • Selected in Incentive Plan for Scientific and Technological Papers in the Field of Information and Communication China (only 9 in 2024) [中国通信学会-2024年度信息通信领域科技论文激励计划]
   • Selected as the Most Popular Document of JCIN: August 2024-now
   • JCIN 2025 Best Paper award

Conferences

None

Honors and Awards

• 2025.06 Outstanding Graduation Project (Thesis), UESTC
• 2025.06 Certificate of Honorary Research, UESTC
• 2025.06 Outstanding Graduate of Sichuan Province
• 2024.12 National Encouragement Scholarship (Undergraduate)
• 2024.05 Meritorious Winner, Mathematical Contest in Modeling (MCM), USA
• 2023.12 National Scholarship (Undergraduate)
• 2022.12 National Scholarship (Undergraduate)

Academic Service

Technical Reviewers

• IEEE Journal on Selected Areas in Communications
• IEEE Transactions on Intelligent Transportation Systems
• IEEE Wireless Communications Letters
• Science China Information Sciences
• Journal of Communications and Information Networks