Guangyu Sun

I am a second-year Ph.D. student with Prof. Chen Chen at the University of Central Florida. I earned my Master of Science of Computer Science at the University of Rochester, advised by Prof. Chenliang Xu. Before my graduate education, I earned my Bachelor's Degree in Computer Science at the University of Missouri, advised by Prof. Dong Xu, and my Bachelor's Degree in Computer Science and Technology at Shandong University. My research interests include Federated Learning, Generative AI, Multi-modality Learning, and Efficient Fine-tuning.

Email  /  Google Scholar  /  Github  /  LinkedIn  /  CV

profile photo
News
Publications

Towards Multi-modal Transformers in Federated Learning
Guangyu Sun, Matias Mendieta, Chen Chen
[Paper]

Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
Matias Mendieta, Guangyu Sun, Chen Chen
[Paper]

FedPerfix

FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning
Guangyu Sun, Matias Mendieta, Jun Luo, Shandong Wu, Chen Chen.
2023 IEEE/CVF International Conference on Computer Vision. ICCV 2023.
[Paper][Code]

Conquering the Communication Constraints to Enable Large Pre-Trained Models in Federated Learning
Guangyu Sun, Matias Mendieta, Taojiannan Yang, Chen Chen
[Paper]

Anomaly Crossing: New Horizons for Video Anomaly Detection as Cross-domain Few-shot Learning
Guangyu Sun*, Zhang Liu*, Lianggong Wen, Jing Shi, Chenliang Xu
[Paper] [Code]

Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
Ming Liu*, Dongpeng Liu*, Guangyu Sun, Yi Zhao, Duolin Wang, Fangxing Liu, Xiang Fang, Qing He, Dong Xu.
IEEE Industrial Electronics Magazine
[Paper]

Assessing environmental oil spill based on fluorescence images of water samples and deep learning
Dongpeng Liu, Ming Liu, Guangyu Sun, Zhiqian Zhou, Duolin Wang, Fei He, Jiaxin Li, Ryan Gettler, Eric Brunson, Jeffery Steevens, Dong Xu
Journal of Environmental informatics
[Paper]


Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.