Wuxin Yu
Papers
1
Total Citations
7
H-Index
1
About
Wuxin Yu is a leading researcher at the forefront of efficient deep learning, with a primary focus on model lightweighting and optimization acceleration for computer vision. His most influential work centers on Vision Transformers (ViTs), where he has made pivotal contributions to making these powerful yet computationally intensive models viable for real-world deployment on mobile and embedded devices. In his highly cited 2022 review, Yu systematically surveyed and categorized the latest lightweighting and acceleration methods for ViTs, providing a crucial roadmap for the field. This comprehensive analysis has garnered 7 citations, establishing it as a foundational reference for researchers working to bridge the gap between state-of-the-art performance and practical efficiency. Yu’s research directly addresses critical challenges in smart home, smart medical, and autonomous driving technologies, where real-time inference on resource-constrained hardware is essential. By synthesizing and advancing techniques such as pruning, quantization, and knowledge distillation for transformer architectures, he is enabling the next generation of intelligent, on-device applications that require both accuracy and speed.
Research Focus
Key Achievements
Top Papers
- 1