About me

I am currently a final-year PhD student at Sorbonne Université, ISIR (MLIA Team), under the supervision of Patrick Gallinari. My research focuses on deep learning methods for PDE solving, with a particular emphasis on operator learning and generalization for parametric PDEs and multi-physics problems. Current directions I am exploring include:

Recent News

Selected Publications

See Google Scholar for a complete list of my publications.

ECHO
ECHO: Efficient Generative Transformer Operators for Million-Point PDEs, Preprint, 2025.
Armand Kassaï Koupaï*, Lise Le Boudec*, Patrick Gallinari
ENMA
ENMA: Tokenwise Autoregression for Generative Neural PDE Operators, Spotlight, NeurIPS 2025.
Armand Kassaï Koupaï*, Lise Le Boudec*, Louis Serrano, Patrick Gallinari
Canopy Height Map
Zebra: In-Context and Generative Pretraining for Solving Parametric PDEs, Preprint, NeurIPS 2024.
Louis Serrano, Armand Kassaï Koupaï, Thomas X Wang, Pierre Erbacher, Patrick Gallinari
Canopy Height Map
GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning, NeurIPS 2024.
Armand Kassaï Koupaï, Jorge Misfut Benet, Yuan Yin, Jean-Noël Vittaut, Patrick Gallinari
Canopy Height Map
Operator Learning with Neural Fields: Tackling PDEs on General Geometries, NeurIPS 2023.
Louis Serrano, Lise Le Boudec*, Armand Kassaï Koupaï*, Thomas X Wang, Yuan Yin, Jean-Noël Vittaut, Patrick Gallinari