Yiqi Zhao

Papers

Total Citations

H-Index

About

Yiqi Zhao is a rising researcher at the forefront of safe autonomy, whose work bridges formal verification, control theory, and statistical learning. Their most-cited survey, "Formal Verification and Control with Conformal Prediction" (2024, 2 citations), offers a timely synthesis of how conformal prediction—a powerful statistical tool for uncertainty quantification—can provide practical, rigorous safety guarantees for learning-enabled autonomous systems (LEASs). This contribution is especially vital as autonomous vehicles, drones, and robotics increasingly rely on black-box neural networks, where traditional verification methods fall short. Zhao’s research addresses a critical gap: ensuring that these systems operate reliably under real-world uncertainty, without sacrificing performance. By unifying formal methods with data-driven uncertainty quantification, Zhao is helping to chart a path toward certifiably safe AI in high-stakes applications. Their work is already influencing the next generation of control engineers and verification specialists, offering a blueprint for how to integrate statistical guarantees into the design of autonomous systems. As the field of safe AI accelerates, Yiqi Zhao stands out as a key voice in making autonomy both intelligent and trustworthy.