Jordan Lekeufack
Papers
1
Total Citations
15
H-Index
1
About
Jordan Lekeufack is a rising researcher at the intersection of machine learning, decision theory, and safe autonomous systems. His work focuses on developing rigorous frameworks that enable reliable decision-making even when predictive models are imperfect. In his highly influential 2024 paper, "Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions," Lekeufack introduces a novel framework that bridges conformal prediction with decision theory, providing formal guarantees for safety-critical applications such as robot planning with pedestrian predictions and autonomous manufacturing calibration. This work has already garnered 15 citations in its first year, signaling its rapid impact on the field. Lekeufack's contributions are particularly notable for addressing a fundamental challenge in deploying AI systems in the real world: how to make safe, autonomous decisions when machine learning predictions are inherently uncertain. His research promises to advance the reliability of autonomous systems across robotics, manufacturing, and beyond, making him a key voice in the growing dialogue around trustworthy AI.
Research Focus
Key Achievements
Top Papers
- 1