Papers
1
Total Citations
2
H-Index
1
About
Yuke Wang is a researcher whose work sits at the intersection of computer systems and machine learning, with a particular focus on efficient video processing and runtime optimization. His most notable contribution is the development of **Palleon**, a runtime system designed to address the critical challenge of dynamic class skew in real-time video analytics. While convolutional neural networks have enabled high-accuracy video processing on cloud-backed mobile platforms—from cell phones to robotics—these systems often struggle with the tension between computational intensity and energy efficiency. Wang’s Palleon tackles this head-on by intelligently managing resource allocation and classification workloads as video content shifts unpredictably. Though early in its citation impact (2 citations as of 2021), this work represents a foundational step toward making CNN-based video processing practical for energy-constrained, real-world deployments. Wang’s research is particularly relevant for students and engineers building scalable, responsive mobile and robotic vision systems, as it bridges the gap between theoretical model accuracy and the messy realities of dynamic, resource-limited environments. His work signals a promising trajectory in systems for AI.
Research Focus
Key Achievements
Top Papers
- 1