Papers
1
Total Citations
5
H-Index
1
About
Quentin Cappart is a rising leader at the intersection of artificial intelligence and combinatorial optimization, with a particular focus on integrating graph neural networks and reinforcement learning to solve complex, real-world decision-making problems. His most cited work, "Graph neural networks and deep reinforcement learning for simultaneous beam orientation and trajectory optimization of Cyberknife" (2021, 5 citations), exemplifies his ability to apply cutting-edge AI techniques to critical challenges in medical physics—specifically, reducing treatment time in robotic radiosurgery without compromising dose quality. Cappart’s broader research spans constraint programming, learning-based search heuristics, and the development of neural architectures that can reason over structured data. He has made notable contributions to the NeurIPS and AAAI communities, where his work on combining deep learning with exact optimization methods has been recognized for its novelty and practical impact. By bridging the gap between symbolic reasoning and data-driven learning, Cappart is helping to define a new generation of hybrid AI systems, making him a compelling figure for students and researchers interested in the future of automated decision-making.
Research Focus
Key Achievements
Top Papers
- 1