Long Kiu Chung
Papers
1
Total Citations
5
H-Index
1
About
Long Kiu Chung is an emerging researcher working at the intersection of machine learning, formal verification, and safe robotics. His work focuses on the critical challenge of deploying neural networks in safety-sensitive environments, particularly in human-robot interaction scenarios where constraint violations can have serious real-world consequences. His most notable contribution, "Constrained Feedforward Neural Network Training via Reachability Analysis" (2021), addresses a fundamental open problem in the field: how to train neural networks that provably satisfy safety constraints. By leveraging reachability analysis — a formal verification technique traditionally used in control theory — Chung developed a principled framework that bridges the gap between the expressive power of neural networks and the rigorous safety guarantees required in robotics applications. This work has garnered 5 citations since its publication, reflecting growing interest from both the machine learning and robotics communities in trustworthy AI systems. Chung's research represents an important step toward making neural network-based controllers viable in real-world, safety-critical deployments, and positions him as a promising contributor to the rapidly expanding field of safe and certifiable artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1