Youcheng Sun
Papers
5
Total Citations
79
H-Index
3
About
Youcheng Sun is a leading researcher at the intersection of artificial intelligence, software engineering, and formal verification, with a primary focus on ensuring the safety and reliability of learning-enabled systems. His work is centered on two key areas: robustness-oriented testing for deep learning (DL) systems and the formal verification of neural network-enabled state estimation for robotics. Sun’s most impactful contribution is the development of **RobOT (Robustness-Oriented Testing)**, a pioneering framework that applies software engineering techniques—such as fuzzing and guided search—to systematically uncover adversarial examples, or "bugs," in DL systems. This work, published in 2021, has garnered over 63 citations, reflecting its significant influence on the field of DL quality assurance. Additionally, Sun has made notable strides in the formal verification of learning-enabled state estimation systems (LE-SESs), which are critical for robotics applications like localization using Bayes filters. His 2020 paper on this topic is among the first to address verification challenges in such systems, emphasizing robustness and resilience properties. With a growing citation record and a focus on bridging formal methods with practical AI safety, Sun’s research is shaping how we build trustworthy, verifiable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1RobOT: Robustness-Oriented Testing for Deep Learning Systems63 citations · 2021
- 2
- 3RobOT: Robustness-Oriented Testing for Deep Learning Systems4 citations · 2021
- 4
- 5