Zehong Lin

Assistant Professor

School of Data Science
Lingnan University
Hong Kong SAR

Email: zehonglin@ln.edu.hk
[Google Scholar]

Openings

I am looking for self-motivated Ph.D. students (Fall 2026) with strong backgrounds in machine learning, wireless communications, computer vision, and mathematical optimization. If you are interested in joining my group, please get in touch with me via email with your resume, transcripts, and sample publications (if any).

About Me

I am an Assistant Professor at the School of Data Science, Lingnan University (LU). Before that, I was a Research Assistant Professor at the Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology (HKUST). I received my Ph.D. degree in Information Engineering from The Chinese University of Hong Kong (CUHK) in 2022, and my B.Eng. degree in Information Engineering from South China University of Technology (SCUT) in 2017. My research interests include spatial perception and immersive communications, GenAI for communications, distributed and federated learning, and edge AI systems.

Research Interests

• Spatial Perception and Immersive Communications

• GenAI for Communications

• Edge AI Systems

• Distributed and Federated Learning

News

• New [11/2025] Paper “Neural representation for wireless radiation field reconstruction: A 3D Gaussian splatting approach” was accepted by IEEE Transactions on Wireless Communications (TWC). [Paper] [Code] [Wechat Official Accounts Article (Chinese)]

• New [11/2025] Paper “LumiTex: Towards high-fidelity PBR texture generation with illumination context” was submitted. [Paper][Code][Project Page]

• New [11/2025] Paper “Feed-forward 3D Gaussian splatting compression with long-context modeling” was submitted. [Paper]

• New [11/2025] Paper “RemedyGS: Defend 3D Gaussian splatting against computation cost attacks” was submitted. [Paper]

• New [09/2025] Paper “Forge4D: Feed-forward 4D human reconstruction and interpolation from uncalibrated sparse-view videos” was submitted. [Paper][Code][Project Page]

• New [07/2025] Paper “EVA-Gaussian: 3D Gaussian-based real-time human novel view synthesis under diverse camera settings” was accepted by the 1st International Workshop on End-to-End 3D Learning (E2E3D) at ICCV 2025. [Paper][Code][Project Page]

• New [06/2025] Paper “MEGA: Memory-efficient 4D Gaussian splatting for dynamic scenes” was accepted by ICCV 2025. (Highlight) [Paper][Code][Project Page]

• New [05/2025] We will organize the 3rd IEEE Hong Kong 6G Wireless Summit (IEEE HK6GWS 2025) on 11-12 September 2025.

• New [05/2025] Paper “WirelessAgent: Large language model agents for intelligent wireless networks” was submitted. [Paper][Wechat Official Accounts Article (Chinese)]

• New [01/2025] Paper “GI-GS: Global illumination decomposition on Gaussian splatting for inverse rendering” was accepted by ICLR 2025. [Paper] [Code] [Project Page] [Wechat Official Accounts Article (Chinese)]

• New [12/2024] Paper “WRF-GS: Wireless radiation field reconstruction with 3D Gaussian splatting” was accepted by INFOCOM 2025. [Paper] [Code] [Wechat Official Accounts Article (Chinese)]

• New [11/2024] Paper “Dynamics-aware Gaussian splatting streaming towards fast on-the-fly training for 4D reconstruction” was submitted. [Paper][Code][Project Page][Video]

• New [07/2024] Paper “Bidirectional stereo image compression with cross-dimensional entropy model” was accepted by ECCV 2024. [Paper][Code][Video] [Wechat Official Accounts Article (Chinese)]