Jonathan Kuck

Papers

Total Citations

H-Index

About

Jonathan Kuck is a researcher at the forefront of safe and reliable machine learning, with a primary focus on developing sample-efficient safety assurances for high-stakes robotics and autonomous systems. His major contribution lies in pioneering the application of conformal prediction—a statistical framework for uncertainty quantification—to create early warning systems that can detect imminent unsafe situations with minimal data. This work directly addresses the critical challenge of deploying machine learning models in real-world environments where failures can have catastrophic consequences. Kuck’s most cited paper, "Sample-Efficient Safety Assurances Using Conformal Prediction" (2022), has garnered 25 citations, establishing a foundational approach that balances rigorous safety guarantees with practical data efficiency. By enabling models to provide reliable alerts before corrective action is needed, his research bridges the gap between theoretical robustness and real-world deployment. Kuck’s contributions are particularly notable for their potential to transform how we trust and verify AI in autonomous vehicles, drones, and medical robotics, making him a key voice in the growing field of safe AI.