Ye XUE 薛烨

Ye XUE 薛烨

Ye Xue
Associate Professor, Ph.D. Advisor

School of Intelligent Systems Engineering
Sun Yat-sen University, Shenzhen, China
Email: xuey57@mail.sysu.edu.cn

Wireless World Model 3DGS / NeRF Channel Modeling L2O Efficient AI

Google Scholar GitHub Publications Group

Introduction

I am an associate professor at the School of Intelligent Systems Engineering, Sun Yat-sen University (SYSU). Before joining SYSU, I was a research scientist at the Shenzhen Research Institute of Big Data and an adjunct assistant professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen. I received my Ph.D. in Electronic and Computer Engineering from the Hong Kong University of Science and Technology (HKUST), and my B.S. in Communication Engineering from Southeast University (Chien-Shiung Wu Honor College, Advanced Class).

My research spans sparse/efficient AI, the physically grounded wireless world model, and AI for mathematical optimization.

Education

Professional Experience

Research

I work on sparse/efficient AI, the wireless world model (we call ours FieldMind), and learning-based optimization (L2O) for real-world communication and network decisions.

Wireless World Model (WWM) 3DGSNeRF

Physically grounded, data-driven models of radio/EM environments that fuse geometry and materials (BIM, point clouds, maps), contextual signals (vision/language, IMU, GNSS), and RF measurements (sweeps/arrays). We combine neural representations (3DGS/NeRF variants, diffusion/energy models, GNNs, neural operators such as FNO/DeepONet/GNO) with PDE and boundary consistency, constitutive relations, and structured sparsity/low-rank priors. The models support editable inversion, uncertainty quantification, and active re-measurement for localized statistical channel modeling and environment-aware communication.

Learning-based Optimization (L2O) GNNRL

Differentiable, learning-augmented solvers (RL/GNN/neural combinatorial optimization) operating on the wireless world model (WWM) for constrained decisions: UAV sensing plans, site placement, beam/power/spectrum allocation, and routing/formation planning. We pursue feasibility guarantees, learned warm-starts, fast cross-scenario adaptation, and edge/federated execution for real-time, certifiable decisions.

Sparse and Efficient AI CompressionFPGA

Structured sparsity, low-rank, and tensorization across data/features/models/gradients with unified compression and distillation for edge–cloud collaboration and federated training. HW/SW co-acceleration (CPU/GPU/FPGA) enables reliable on-device deployment in wireless applications.

Explainable AI (XAI) Theory

Characterizing the generalization bounds and convergence properties of AI methods using high-dimensional statistics and nonconvex optimization.

Recently, I have focused on building FieldMind (our wireless-world-model instantiation), which couples physics-informed field representations with algorithm–system co-design (C++/CUDA/FPGA; edge/federated) to map structural sparsity into solvers and hardware, delivering end-to-end speed/energy gains and rapid replanning.

Current Openings

We recruit Postdoc Fellows / Ph.D. / Master / Research Assistants / Interns with strengths in MATH (optimization, probability, geometry), AI (deep/graph/generative modeling, 3DGS/NeRF, neural operators), or SYSTEMS (C++/CUDA/FPGA, robotics, UAV, wireless). We value curiosity, hands-on ability, reproducibility, and cross-disciplinary collaboration.

Selected Recent Publications

  1. Wireless WM3DGSY. Xue, Y. Wang, X. Shao, Q. Yan, S. Zhang, and T.-H. Chang, “Point-Cloud-Assistant Localized Statistical Channel Prediction by Tangent Gaussian Splatting,” IEEE Transactions on Wireless Communications, vol. 25, pp. 17816–17830, 2026. doi: 10.1109/TWC.2026.3696997 · [Project Page]

  2. Wireless WMChannel ModelingXinyu Qin, Qi Yan, Shutao Zhang, Bingsheng Peng, Ye Xue†, and Tsung-Hui Chang, “A Measurement Report Data-Driven Framework for Localized Statistical Channel Modeling,” IEEE Transactions on Mobile Computing, 2026. doi: 10.1109/TMC.2026.3667749

  3. Wireless WMRadiance FieldBingsheng Peng, Shutao Zhang, Xi Zheng, Xinyu Qin, Ye Xue†, and Tsung-Hui Chang, “RF-LSCM: Pushing Radiance Fields to Multi-Domain Localized Statistical Channel Modeling for Cellular Network Optimization,” IEEE Transactions on Mobile Computing, accepted Mar. 2026.

  4. Wireless WM3DGSYiheng Wang, Ye Xue†, Shutao Zhang, and Tsung-Hui Chang, “RadCloudSplat: Scatterer-Driven 3D Gaussian Splatting with Point-Cloud Priors for Radiomap Extrapolation,” IEEE INFOCOM 2026. [Project Page]

  5. L2OXuanhao Pan*, Chenguang Wang*, Chaolong Ying, Ye Xue, and Tianshu Yu, “Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP Solvers,” ICLR 2026.

  6. L2OYeqing Qiu, Ye Xue†, Akang Wang, Yiheng Wang, Qingjiang Shi, and Zhi-Quan Luo, “ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-k-Cut Problems,” International Conference on Machine Learning (ICML 2025).

  7. Wireless WMChannel ModelingYiheng Wang*, Ye Xue*†, Shutao Zhang, and Tsung-Hui Chang, “GNN-based Structured Bayesian Inference for Multi-grid Localized Statistical Channel Modeling,” IEEE Transactions on Wireless Communications, 2025. doi: 10.1109/TWC.2025.3547705

  8. L2OGenerativeShutao Zhang, Ye Xue†, Zhiwei Tang, Hao Wang, Chao Shen, Qingjiang Shi, and Tsung-Hui Chang, “Robust Network Optimization by Deep Generative Models and Stochastic Optimization,” IEEE Transactions on Wireless Communications, 2025. doi: 10.1109/TWC.2025.3551316

  9. L2OYeqing Qiu, Chengpiao Huang, Ye Xue†, Zhipeng Jiang, Qingjiang Shi, Dong Zhang, and Zhi-Quan Luo, “Relaxation-free Min-k-partition for PCI Assignment in 5G Networks,” IEEE Transactions on Signal Processing, 2025. doi: 10.1109/TSP.2025.3604409

  10. L2OYeqing Qiu, Ye Xue†, Zhipeng Jiang, and Qingjiang Shi, “Relaxed Gradient Projection for PCI Assignment in 5G Network,” The 14th IEEE/CIC International Conference on Communications in China (ICCC 2025).

  11. Wireless WMChannel ModelingXinyu Qin, Shutao Zhang, Bingsheng Peng, Ye Xue†, Chao Shen, Qiliang Xie, Yuk Ngai Lee, and Tsung-Hui Chang, “A Deep Learning Framework for Large-Scale Localized Statistical Channel Modeling,” IEEE GLOBECOM 2025 Workshop.

  12. Wireless WMMultimodalYiheng Wang, Shutao Zhang, Ye Xue†, and Tsung-Hui Chang, “Multi-Modal Neural Radio Radiance Field for Localized Statistical Channel Modelling,” IEEE GLOBECOM 2025 Workshop.

[* equal contribution, † corresponding author]   Full list of publications.

Funding

Industrial Collaboration (Selected)

Invited Talks

Honors and Awards

Academic Service