Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
Quentin Bertrand, Anne Gagneux, Mathurin Massias +1
Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand…
cs.LG2025
Convexity in ReLU Neural Networks: beyond ICNNs?
Anne Gagneux, Mathurin Massias, Emmanuel Soubies +1
Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to u…