Kyle Zheng

Papers

Total Citations

H-Index

About

Kyle Zheng is a researcher at the forefront of distributed systems and machine learning, with a focus on the edge-to-cloud continuum. His most-cited work, "AutoLearn: Learning in the Edge to Cloud Continuum" (2023), introduces a framework that optimizes machine learning model deployment across heterogeneous devices, balancing latency, bandwidth, and computational constraints. This contribution addresses a critical challenge in real-time AI applications, enabling efficient inference at the network edge while leveraging cloud resources for complex training tasks. With 4 citations in a nascent field, Zheng's work is gaining traction among practitioners building scalable, low-latency systems. His research also explores the integration of cloud computing, robotics, and autonomous systems, emphasizing hands-on experimentation through NSF-supported testbeds. By bridging theoretical foundations with practical deployment strategies, Zheng is shaping the next generation of intelligent, distributed infrastructures. His ongoing projects aim to democratize access to edge AI, making autonomous systems more responsive and resource-efficient. For students and researchers, Zheng's work offers a blueprint for tackling the complexities of modern, decentralized computing environments.