Youngsok Kim

Papers

Total Citations

H-Index

About

Youngsok Kim is a leading researcher in computer vision and real-time AI systems, with a primary focus on efficient deep neural network architectures for autonomous and edge computing environments. His most influential work, "Real-Time Object Detection System with Multi-Path Neural Networks" (2020, 58 citations), addresses a critical challenge in deploying high-accuracy DNNs under strict latency constraints for applications like autonomous vehicles, drones, and security robots. Kim’s key contribution lies in designing multi-path neural network frameworks that balance detection precision with computational speed, enabling reliable object detection in dynamic, time-sensitive scenarios. This work has been widely cited by researchers developing lightweight models for embedded systems and real-time perception pipelines. Beyond this flagship paper, Kim’s broader research explores the intersection of model efficiency, sensor fusion, and robust performance in uncontrolled environments. His achievements are particularly notable for bridging the gap between theoretical advances in deep learning and practical deployment in safety-critical autonomous systems. For students and researchers, Kim’s work offers a compelling blueprint for building AI that is both powerful and fast enough to operate in the real world.