Fengze Li

I hold a Ph.D from the University of Liverpool, advised by Dr. Jieming Ma, Dr. Zhongbei Tian (University of Birmingham) and Dr. Hai-Ning Liang (HKUST, GZ).

My general research focuses on industrial intelligence. In detail, I explore the application and optimization of 3D vision and LLMs across various domains, including photovoltaics (PV), medical imaging and robotics.

Before Ph.D, I had the honor to work with Dr. Jize Yan and Dr. Jie Zhang (University of Bath) at University of Southampton. I've also interned at DJI, Deloitte, and worked as a research assistant at JITRI with Dr. Ji Ge (University of Toronto). Currently, I am at Baidu's ACG LLMs group.

Google Scholar  /  LinkedIn  

profile photo

Selected Publications

CountingFruit: Language-Guided 3D Fruit Counting with Semantic Gaussian Splatting
Fengze Li, Yangle Liu, Jieming Ma, Hai-Ning Liang, Yaochun Shen, Huangxiang Li, Zhijing Wu
arXiv preprint arXiv:2506.01109, 2025
3D-PV: Enhancing PV Power Prediction by Modeling Spatial Uncertainty Under Dynamic Shading Conditions
Fengze Li, Dou Hong, Jieming Ma*, Zhongbei Tian, Hai-Ning Liang
Expert Systems With Applications (SCI Q1 TOP), 2025
A Comprehensive Survey of Specularity Detection: State-of-the-Art Techniques and Breakthroughs
Fengze Li, Jieming Ma*, Zhijing Wu, Zhongbei Tian, Hai-Ning Liang
Artificial Intelligence Review (SCI Q1 TOP), 2025
Temporal environment informed photovoltaic performance prediction framework with multi-spatial attention LSTM
Douhong, Fengze Li, Jieming Ma*, Ka Lok Man, Huiqing Wen, Prudence Wong
Solar Energy (SCI Q2 TOP), 2025
Real-Time Dynamic Scene Representation for Endoscopic Images with 4D Gaussian Splatting
Fengze Li, Jishuai He, Jieming Ma*, Hai-Ning Liang, Zhijing Wu
IEEE International Symposium on Biomedical Imaging (ISBI), 2025, Houston, USA, Poster/Live Demo Session
SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
Fengze Li, Yue Wang, Yangle Liu, Ming Huang, Dou Hong, Jieming Ma*
IEEE International Conference on Big Data and Artificial Intelligence (BDAI), Suzhou, China, 2025, Oral Session
Mirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model
Fengze Li, Jieming Ma*, Zhongbei Tian, Ji Ge, Hai-Ning Liang, Tianxi Wen
IEEE International Conference on Frontiers of Signal Processing (ICFSP), Paris, France, 2022, Oral Session

Industry

Baidu
LLMs Algorithm Development--Baidu AI Cloud Group (ACG)
May. 2025 - Present
JITRI - Jiangsu Industrial Technology Research Institute
Research Scientist Intern
May. 2021 - Jan. 2022
DJI
Software Engineer Intern
Jan. 2018 - Mar. 2018
Deloitte
Software Engineer Intern
Dec. 2017 - Jan. 2018

Education

University of Liverpool
Ph.D. in Computer Science
2021 - 2025
University of Southampton
M.Sc. in Computer Science
2019 - 2020
Shenzhen University
B.Eng. in Computer Science
2015 - 2019