Generative Modeling

Data Generation in AI through Transport and Denoising – EchoCem Challenge featured image
Image Segmentation

Data Generation in AI through Transport and Denoising – EchoCem Challenge

Segmentation of ultrasonic well imagery using transport and denoising architectures. Ranked 1st on both public and private leaderboards in the Collège de France EchoCem challenge.

Thomas Gravier
•
Read more
Learning Gradients of Convex Functions with Monotone Gradient Networks featured image
Optimal Transport

Learning Gradients of Convex Functions with Monotone Gradient Networks

Study and implementation of Monotone Gradient Networks (MGN) for learning gradients of convex functions, optimal transport, and generative modeling on high-dimensional data.

Thomas Gravier
•
Read more