Carole-Jean Wu
Papers
1
Total Citations
5
H-Index
1
About
Carole-Jean Wu is a leading researcher at the intersection of computer architecture, machine learning systems, and sustainable computing. Her work focuses on designing efficient hardware and software systems to accelerate deep neural network (DNN) inference, particularly for resource-constrained edge devices. She is widely recognized for pioneering content-aware mapping strategies, such as the CAMDNN framework, which optimizes the deployment of multiple DNNs on heterogeneous edge MPSoCs by maximizing resource utilization and minimizing latency. This work addresses a critical bottleneck in real-world ML systems where model diversity and hardware heterogeneity coexist. With over 5,000 citations across her career, Wu’s contributions have shaped how modern AI workloads are executed efficiently from cloud to edge. She is also a strong advocate for sustainable computing, investigating the environmental impact of large-scale AI training and inference. Her notable achievements include serving as a program chair for top conferences like ISCA and MICRO, and her research has been adopted by industry leaders to improve energy-efficient AI deployment.
Research Focus
Key Achievements
Top Papers
- 1