profile pic

Zehong Lin

Research Assistant Professor

Department of Electronic and Computer Engineering (ECE)
The Hong Kong University of Science and Technology (HKUST)

Address: Room 3112A, Academic Building, HKUST
Email: eezhlin@ust.hk
[Google Scholar] [GitHub]

About Me

I am currently a VPRDO 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 neural data representation and compression, generative AI and foundation models, and edge AI systems.

Research Interests

  • Neural Data Representation and Compression

  • Generative AI and Foundation Models

  • Distributed Learning and Optimization

  • O-RAN and Edge AI Systems

News

  • New [01/2025] Paper “GI-GS: Global illumination decomposition on Gaussian splatting for inverse rendering” was accepted by ICLR 2025. [Paper] [Code] [Project Page] (Acceptance Rate: 32.08%)

  • 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)] (Acceptance Rate: 18.7%)

  • 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 [10/2024] Paper “EVA-Gaussian: 3D Gaussian-based real-time human novel view synthesis under diverse camera settings” was submitted. [Paper][Code][Project Page]

  • New [10/2024] Paper “MEGA: Memory-efficient 4D Gaussian splatting for dynamic scenes” was submitted. [Paper][Code][Project Page]

  • New [09/2024] Paper “WirelessAgent: Large language model agents for intelligent wireless networks” was submitted. [Paper][Wechat Official Accounts Article (Chinese)]

  • 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)] (Acceptance Rate: 27.9%)

  • [06/2024] Paper “WirelessLLM: Empowering large language models towards wireless intelligence” was accepted by the Journal of Communications and Information Networks. [Paper][Video][Wechat Official Accounts Article (Chinese)]

  • [05/2024] Paper “Understanding and improving model averaging in federated learning on heterogeneous data” was accepted by IEEE Transactions on Mobile Computing (TMC). [Paper][Code][Wechat Official Accounts Article (Chinese)]

  • [03/2024] Paper “FedCiR: Client-invariant representation learning for federated non-IID features” was accepted by IEEE Transactions on Mobile Computing (TMC). [Paper]

  • [03/2024] We will organize the 2nd IEEE Hong Kong 6G Wireless Summit (IEEE HK6GWS 2024) on 11-12 September 2024.

  • [01/2024] Paper “Spatial-aware latent initialization for controllable image generation” was submitted. [Paper]

  • [12/2023] Paper “Large language models empowered autonomous edge AI for connected intelligence” was accepted by IEEE Communications Magazine. [Paper][Wechat Official Accounts Article (Chinese)]

  • [11/2023] Paper “Channel and gradient-importance aware device scheduling for over-the-air federated learning” was accepted by IEEE Transactions on Wireless Communications (TWC). [Paper]

  • [09/2023] Paper “Probabilistic scheduling for over-the-air federated learning,” was accepted by the 2023 IEEE 23rd International Conference on Communication Technology (ICCT). [Paper]

  • [08/2023] We will organize the 1st IEEE Hong Kong 6G Wireless Summit (IEEE HK6GWS 2023) on 13-14 September 2023.

  • [07/2023] Paper “A survey of what to share in federated learning: Perspectives on model utility, privacy leakage, and communication efficiency” was submitted. [Paper][Wechat Official Accounts Article (Chinese)]

  • [03/2023] Paper “CFLIT: Coexisting federated learning and information transfer” was accepted by IEEE Transactions on Wireless Communications (TWC). [Paper]

  • [10/2022] I joined the Department of ECE at HKUST.

  • [08/2022] I passed my Ph.D. thesis defense.