Younmin Bae
Papers
1
Total Citations
4
H-Index
1
About
Younmin Bae is a researcher focused on efficient deep neural network (DNN) inference for edge computing, particularly in resource-constrained environments like robotics, autonomous agents, and IoT devices. Their most-cited work, "LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition" (2020, 4 citations), addresses the critical challenge of performing DNN inference on edge devices by proposing a novel parallelization strategy that minimizes communication overhead. This contribution is vital for enabling real-time, on-device AI in latency-sensitive applications where cloud reliance is impractical. Bae’s research bridges the gap between intensive computational demands and limited edge resources, advancing the practicality of deep learning in autonomous systems. While their citation count is still growing, this work lays a foundational framework for low-communication parallel inference, a key bottleneck in edge AI deployment. Bae’s efforts contribute to making intelligent, responsive edge devices more feasible, with potential impacts on autonomous navigation, smart sensors, and distributed AI systems. Their focus on communication efficiency distinguishes their approach in the broader field of efficient neural network inference.
Research Focus
Key Achievements
Top Papers
- 1