Gang Wu
PhD Candidate
Harbin, Heilongjiang, China
Summary
👤
Senior🎓
Top SchoolGang Wu is a PhD candidate in Computer Science at Harbin Institute of Technology specializing in low-level computer vision and representation learning, with nine years of experience in research and development. He has a strong track record as first author on papers in IEEE TIP, AAAI, ACM MM, and other top venues, developing novel methods for image super-resolution, multi-task restoration, and lightweight architectures. His work blends convolutional and transformer designs, explores 1×1 convolution–based efficiency, and introduces task-agnostic contrastive learning and uncertainty regularization for all-in-one restoration. He has contributed to broader topics including domain generalization, contrastive learning, and federated learning, with co-authored papers at ECCV, ICLR, and ICML. Based in Harbin and supervised by Prof. Junjun Jiang, he brings both theoretical rigor and practical efficiency focus to visual representation problems. An underrated strength is his ability to distill complex multi-task objectives into compact, deployable models suitable for resource-constrained scenarios.
9 years of coding experience
Bachelor, Computer Science, Top 1%, Bachelor, Computer Science, Top 1% at Soochow University博士, Computer Science, 博士, Computer Science at 哈工大
Github Skills (29)
pytorch10
diffusion-models10
stable-diffusion10
diffusers10
text2image10
audio10
deep-learning10
image-generation10
flux10
visual-question-answering10
jax10
foundation9
flax9
openmmlab9
computer-vision8
Programming languages (3)
Github contributions (5)
Aitical/spider_demo
Sep 2017 - Jun 2018
Contributions:19 commits, 18 pushes, 1 branch in 8 months
Aitical/PCL-SISR
Mar 2022 - Jul 2022
Contributions:8 commits, 15 pushes, 1 branch in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.