Junjie Zhao

About

Junjie Zhao is a researcher at the forefront of control theory and machine learning integration, with a primary focus on model predictive control (MPC) and deep learning architectures. His most notable contribution is the development of a Transformer-based explicit model predictive control framework that introduces a variable prediction horizon—a significant advancement over traditional fixed-horizon methods. This work, published in 2026, has already garnered 3 citations, signaling early impact in the field. By leveraging the attention mechanism of Transformers, Zhao’s approach enhances the adaptability and computational efficiency of MPC systems, enabling real-time decision-making in complex, dynamic environments such as autonomous driving and robotics. His research bridges the gap between classical control theory and modern AI, offering scalable solutions for nonlinear systems. Zhao’s work is particularly relevant for students and engineers seeking to apply state-of-the-art sequence modeling to control challenges, and his innovative use of variable horizons promises to inspire further exploration in adaptive, learning-based control strategies.

Research Focus

Key Achievements

Top Papers

1. 1
   Transformer-based explicit model predictive control with variable prediction horizon

   3 citations · 2026

Key Collaborators

Contact & Links