Papers
2
Total Citations
7
H-Index
1
About
Yeseong Kim is a leading researcher at the intersection of energy-efficient machine learning and robotics, with a core focus on Hyperdimensional (HD) Computing. His work addresses critical challenges in deploying ML on resource-constrained platforms, where traditional deep neural networks are often impractical. Kim’s major contributions include pioneering HD Computing for real-world robotic control, as demonstrated in his highly regarded 2024 work, "Brain-Inspired Hyperdimensional Computing in the Wild," which introduced ReactHD—a lightweight symbolic learning framework for sensorimotor control of wheeled robots. This research tackles the dual challenges of efficiency and performance in energy-constrained scenarios. Most recently, Kim has advanced the field with "Hyperdimensional Computing-Based Federated Learning in Mobile Robots Through Synthetic Oversampling" (2025), proposing a novel framework that overcomes the computational and privacy limitations of conventional federated learning. By replacing deep neural networks with HD Computing, he enables privacy-preserving, collaborative learning on mobile robots. With his papers garnering early citations and establishing new paradigms, Kim is recognized as a key innovator in making machine learning viable for the next generation of autonomous, energy-aware systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2