Hyojong Kim
Papers
1
Total Citations
4
H-Index
1
About
Hyojong Kim’s research lies at the intersection of efficient deep learning, edge computing, and embedded systems, with a focus on enabling real-time neural network inference on resource-constrained devices. His most cited work, “LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition” (2020), tackles the critical bottleneck of communication overhead in distributed inference—a key challenge for robots, autonomous agents, and IoT devices. By proposing a novel parallelization strategy that minimizes data exchange between computing nodes, Kim’s method significantly accelerates DNN inference while preserving accuracy, making it highly relevant for latency-sensitive edge applications. Though early in his career, his contributions address a fundamental tension between the computational demands of deep learning and the limited resources of edge hardware. With 4 citations to date, his work is gaining traction among researchers seeking practical solutions for deploying AI in real-world, low-power environments. Kim’s research promises to bridge the gap between cutting-edge neural architectures and the constraints of mobile and embedded platforms, positioning him as an emerging voice in efficient AI systems.
Research Focus
Key Achievements
Top Papers
- 1