Papers
1
Total Citations
3
H-Index
1
About
Xingyu Cao is an emerging researcher working at the intersection of machine learning and control systems engineering, with a particular focus on model predictive control (MPC) and transformer-based architectures. Their most notable work, "Transformer-based explicit model predictive control with variable prediction horizon" (2026), represents a forward-thinking contribution to the field, demonstrating an innovative application of transformer neural networks to solve longstanding computational challenges in explicit MPC. By introducing variable prediction horizons into a transformer framework, Cao's research addresses the flexibility and scalability limitations that have historically constrained real-time MPC implementations, making advanced control strategies more accessible for complex dynamical systems. Although still in the early stages of accumulating citations — with 3 citations on this recent publication — the novelty of bridging deep learning architectures with formal control theory positions Cao as a researcher to watch in intelligent control systems. Their work is particularly relevant for students and practitioners interested in data-driven control, autonomous systems, and the growing convergence of modern AI techniques with classical engineering methodologies. As the field rapidly evolves, Cao's contributions offer a promising foundation for future advancements in adaptive and computationally efficient control design.
Research Focus
Key Achievements
Top Papers
- 1