GuangYuan Yu
Papers
1
Total Citations
3
H-Index
1
About
GuangYuan Yu is a researcher at the forefront of advanced control systems, specializing in model predictive control (MPC) and its integration with deep learning architectures. His most-cited work, "Transformer-based explicit model predictive control with variable prediction horizon" (2026), introduces a novel framework that leverages transformer neural networks to enable real-time, adaptive control with dynamically adjustable prediction horizons—a significant departure from traditional fixed-horizon MPC. This contribution addresses critical computational bottlenecks in explicit MPC, making it viable for complex, fast-changing environments such as autonomous systems and robotics. With 3 citations in its early publication stage, the paper signals growing interest in bridging transformer models and control theory. Yu’s research not only advances the theoretical foundations of learning-based control but also offers practical pathways for deploying intelligent controllers in resource-constrained settings. His work exemplifies the convergence of machine learning and classical control, positioning him as an emerging voice in the next generation of adaptive, data-driven automation.
Research Focus
Key Achievements
Top Papers
- 1