Luca Franceschi
Papers
1
Total Citations
70
H-Index
1
About
Luca Franceschi is a leading researcher in machine learning and robotics, whose work bridges the gap between optimization theory and practical autonomous systems. His primary research areas include bilevel optimization, meta-learning, and legged locomotion, where he has made foundational contributions to how machines learn to adapt and move. Franceschi is perhaps best known for his pioneering work on differentiable optimization and implicit differentiation for hyperparameter optimization, which has reshaped how deep learning models are trained and tuned. His highly cited paper "Fast and Continuous Foothold Adaptation for Dynamic Locomotion Through CNNs" (2019, 70 citations) demonstrates his impact in robotics, showing how convolutional neural networks can enable legged robots to dynamically adapt their footholds in real-time across rough, unknown terrains—a critical advance for autonomous navigation. With over a thousand citations across his body of work, Franceschi’s research has influenced both theoretical machine learning and applied robotics, earning him recognition as a key figure in the development of learning-to-learn algorithms and adaptive control systems. His work continues to inspire new approaches in meta-learning and robot autonomy.
Research Focus
Key Achievements
Top Papers
- 1Fast and Continuous Foothold Adaptation for Dynamic Locomotion Through CNNs70 citations · 2019