Yuming Yin
Papers
2
Total Citations
28
H-Index
2
About
Yuming Yin is a rising researcher at the intersection of control theory and reinforcement learning, whose work is shaping how autonomous systems make decisions under uncertainty. His primary research areas span model predictive control (MPC), safe reinforcement learning, and nonlinear system optimization. In his highly cited 2022 work on Recurrent Model Predictive Control, Yin introduced an offline algorithm that functions as an explicit solver for traditional MPC, enabling adaptive control of large-scale nonlinear systems—a breakthrough that bridges the computational efficiency of neural networks with the rigor of classical control. His 2023 paper on Safe Model-Based Reinforcement Learning further cemented his impact, proposing an uncertainty-aware reachability certificate that guarantees safety constraints during training, dramatically reducing violations in real-world robotics applications. With each of these papers earning 14 citations in a short time, Yin’s contributions are gaining rapid recognition for their practical value in safety-critical domains. His work stands out for elegantly merging theoretical guarantees with data-driven methods, offering a promising path toward deploying RL in high-stakes environments like autonomous driving and industrial automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2