Ye XUE 薛烨

Tenure-track Associate Professor, Ph.D. Advisor School of Intelligent Systems Engineering Sun Yat-sen University Email: yokoyexue@gmail.com Personal Site: https://yokoxue.github.io/ GitHub Google Scholar

Introduction

I am currently a tenure-track 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 in the School of Data Science at 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.Eng. in Communication Engineering from Southeast University (Chien‑Shiung Wu Honor College, Advanced Class). My research spans sparse/efficient AI, physically grounded field world models, and AI for mathematical optimization.

Research

I work on sparse/efficient AI, World Models (I call it FieldMind） for electromagnetics/wireless, and learning-based optimization (L2O) for real-world communication and network decisions.

• World Models (WM) for Radio Environments
  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.

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

• Learning-based Optimization (L2O)
  Differentiable, learning-augmented solvers (RL/GNN/neural combinatorial optimization) operating on FWM for constrained decisions: site placement, beam/power/spectrum allocation, routing/formation planning. We pursue feasibility guarantees, learned warm-starts, fast cross-scenario adaptation, and edge/federated execution for real-time, certifiable decisions.

• Explainable artificial intelligence (XAI)
  Characterize generalizatioin bound and convergence properties of AI method using high-dimensional statistics and nonconvex optimization.

Recently, I have focused on building FieldMind (our FM 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

• Positions: Postdoc Fellow, PhD, Master, Research Assistants (rolling).

• Application: CV, transcripts, representative work (papers/code/demos/competitions); optional personal site or GitHub.

• Email subject: Apply-Name-Position-StartTime

Selected Recent Publications

1. Yiheng Wang*,Ye Xue†, Shutao Zhang, 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. Q1

2. Shutao Zhang, Ye Xue†, Zhiwei Tang, Hao Wang, Chao Shen, Qingjiang Shi, 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. Q1

3. Yeqing Qiu, Chengpiao Huang, Ye Xue†, Zhipeng Jiang, Qingjiang Shi, Dong Zhang, 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. Q2

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

5. Xinyu Qin, Shutao Zhang, Bingsheng Peng, Ye Xue#, Chao Shen, Qiliang Xie, Yuk Ngai Lee, Tsung-Hui Chang, “A Deep Learning Framework for Large-Scale Localized Statistical Channel Modeling,” accepted by the 2025 IEEE Global Communications Conference (GLOBECOM) Workshop.
6. Yiheng Wang, Shutao Zhang, Ye Xue#, Tsung-Hui Chang, “Multi-Modal Neural Radio Radiance Field for Localized Statistical Channel Modelling,” accepted by the 2025 IEEE Global Communications Conference (GLOBECOM) Workshop.

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

Funding

• NSFC Fund (62301334), 2024–2026, PI.
• National Key R&D Program of China (2023YFB2904800), 2023–2026, Sub-project PI.
• SRIBD Project (J00220230002), 2023–2024, PI.
• National Key R&D Program of China (2022YFA1003900), 2022–2027, Key member.
• Guangdong Major Project (2023B0303000001), 2023–2028, Core member.

Industrial Collaboration

• Huawei Innovation Lab (2024–2025): localized statistical channel modeling used in SRCON for wireless network optimization.
• China Mobile Hong Kong (2024–2025): EdgeAI–Wireless Digital Twin for environment-aware network optimization.
• Invited talks: Huawei RAN Research Dept. Meetup (2025); Huawei 2012 Lab (2023) in Huang Danian Chaspark.

Honors and Awards

• Specific Talent, Shenzhen “Pengcheng Peacock Program,” 2023.
• Postgraduate Studentship, Hong Kong University of Science and Technology (HKUST), 2017.
• First Prize, Excellent Undergraduate Thesis of Jiangsu Province, 2017 (one of 5 awardees across SEU).
• Baosteel Scholarship, 2016.
• Microsoft Research Asia Young Scholar Award, 2015 (one of 32 awardees across Mainland China).
• RoboCup Kidsize, National Level, 2nd Place, 2015.