Papers
4
Total Citations
50
H-Index
2
About
Peipei Zhou is a multidisciplinary researcher whose work spans hardware-software co-design, edge computing, and materials discovery, with a particular focus on enabling intelligent systems to operate efficiently in real-world environments. Her most impactful contributions center on on-device machine learning, where she has pioneered techniques for training deep neural networks directly on resource-constrained hardware such as FPGAs, rather than relying solely on cloud-based pipelines. Her paper "EF-Train" (2022, 23 citations) demonstrated how CNNs can be efficiently trained at the edge through data reshaping, enabling autonomous systems like robots and UAVs to adapt dynamically to new environments. Complementing this, her work on weakly supervised temporal action localization pushes the boundaries of on-device video understanding. Zhou has also made notable contributions to connected autonomous driving, addressing critical sensor fusion latency challenges in edge-assisted perception systems. Remarkably, her research extends into materials science, with her highly cited microfluidics work (2020, 24 citations) leveraging high-throughput screening to accelerate novel material discovery. This breadth reflects Zhou's distinctive ability to bridge physical and computational domains, making her a uniquely versatile voice in modern engineering research.
Research Focus
Key Achievements
Top Papers
- 1Microfluidic High-Throughput Platforms for Discovery of Novel Materials24 citations · 2020
- 2
- 3
- 4