Summary
Jingwei Zhang is a PhD-level computer vision researcher and Research Assistant at Stony Brook University with 11 years of experience building efficient architectures for giga-pixel image and video processing. His work centers on Mamba-style models and CUDA designs that enable end-to-end training of ultra-high-resolution imagery within GPU memory, alongside efficient fine-tuning techniques such as visual prompt tuning. He has broad foundations in self-supervised learning, segmentation foundational models, and sampling strategies, and is actively extending this expertise into vision–language models and their compact architectures. Prior work at the Institute of Computing Technology involved algorithm development for bioinformatics, reflecting a strong algorithmic background beyond vision. Based in Brookhaven, NY, he combines deep academic rigor with practical system-level GPU engineering to push large-scale visual modeling into more efficient, deployable forms.
10 years of coding experience
2 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Chinese Academy of Sciences
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Shandong University
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Stony Brook University