Seongryong Oh
Papers
1
Total Citations
9
H-Index
1
About
Seongryong Oh is a leading researcher at the intersection of autonomous systems and efficient deep learning, with a focus on enabling real-time, continuous intelligence on resource-constrained edge devices. His work directly addresses the critical bottleneck of deploying deep neural network (DNN) video analytics in autonomous platforms like self-driving vehicles, unmanned aerial vehicles (UAVs), and security robots, where computational power and battery life are severely limited. Oh’s major contribution, the DACAPO system (2024, 9 citations), introduces a novel framework for accelerating continuous learning in these environments, allowing autonomous systems to adapt and improve their performance over time without overwhelming their hardware. This work is pivotal for moving beyond static, pre-trained models to truly intelligent, self-improving agents. By tackling the fundamental trade-off between model accuracy and operational efficiency, Oh’s research is shaping the future of edge AI, making it possible for robots and drones to learn and react in real-time. His work stands as a key achievement in the push toward fully autonomous, long-duration operations in the wild.
Research Focus
Key Achievements
Top Papers
- 1