Papers
1
Total Citations
2
H-Index
1
About
Gushu Li is a researcher advancing the frontiers of efficient video processing and runtime systems for modern AI workloads. His work addresses critical challenges in deploying convolutional neural networks (CNNs) on cloud-backed mobile platforms such as cell phones and robotics. Li’s most cited paper, “Palleon: A Runtime System for Efficient Video Processing toward Dynamic Class Skew,” tackles the tension between intensive energy demands and real-time performance in video analytics. By designing intelligent runtime mechanisms that adapt to shifting class distributions, his research enables systems to maintain high accuracy while significantly reducing computational overhead. This contribution is vital for scalable, energy-efficient AI deployment in dynamic environments. With his work laying groundwork for next-generation mobile and edge computing, Gushu Li is shaping how video processing systems balance performance, power, and practicality in the age of deep learning.
Research Focus
Key Achievements
Top Papers
- 1