today local_bar

Anne Gagneux

PhD student, Ecole Normale Supérieure de Lyon

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

#3701 · Quentin Bertrand, Anne Gagneux, Mathurin Massias, Rémi Emonet

We leverage the closed-form formulation of flow matching to understand its generalization