| 2025 | ICLR | Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling. | David Grangier, Simin Fan, Skyler Seto, Pierre Ablin |
| 2025 | ICLR | The AdEMAMix Optimizer: Better, Faster, Older. | Matteo Pagliardini, Pierre Ablin, David Grangier |
| 2025 | ICLR | Theory, Analysis, and Best Practices for Sigmoid Self-Attention. | Jason Ramapuram, Federico Danieli, Eeshan Gunesh Dhekane, Floris Weers, Dan Busbridge, Pierre Ablin, Tatiana Likhomanenko, Jagrit Digani, Zijin Gu, Amitis Shidani, Russell Webb |
| 2025 | ICML | Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging. | Pierre Ablin, Angelos Katharopoulos, Skyler Seto, David Grangier |
| 2025 | ICML | Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection. | Louis Bthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi, Pierre Ablin |
| 2025 | ICML | Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency. | Michael Kirchhof, James Thornton, Louis Bthune, Pierre Ablin, Eugne Ndiaye, Marco Cuturi |
| 2024 | AISTATS | A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization. | Mathieu Dagrou, Thomas Moreau, Samuel Vaiter, Pierre Ablin |
| 2024 | AISTATS | Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization. | Zhenzhang Ye, Gabriel Peyr, Daniel Cremers, Pierre Ablin |
| 2024 | ICML | How Smooth Is Attention? | Valrie Castin, Pierre Ablin, Gabriel Peyr |
| 2024 | ICML | Careful with that Scalpel: Improving Gradient Surgery with an EMA. | Yu-Guan Hsieh, James Thornton, Eugne Ndiaye, Michal Klein, Marco Cuturi, Pierre Ablin |
| 2024 | ICML | Optimization without Retraction on the Random Generalized Stiefel Manifold. | Simon Vary, Pierre Ablin, Bin Gao, Pierre-Antoine Absil |
| 2023 | ICML | Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps. | Marco Cuturi, Michal Klein, Pierre Ablin |
| 2022 | AISTATS | Fast and accurate optimization on the orthogonal manifold without retraction. | Pierre Ablin, Gabriel Peyr |
| 2022 | AISTATS | Sinkformers: Transformers with Doubly Stochastic Attention. | Michael E. Sander, Pierre Ablin, Mathieu Blondel, Gabriel Peyr |
| 2021 | ICML | Kernel Stein Discrepancy Descent. | Anna Korba, Pierre-Cyril Aubin-Frankowski, Szymon Majewski, Pierre Ablin |
| 2021 | ICML | Momentum Residual Neural Networks. | Michael E. Sander, Pierre Ablin, Mathieu Blondel, Gabriel Peyr |
| 2020 | ICML | Super-efficiency of automatic differentiation for functions defined as a minimum. | Pierre Ablin, Gabriel Peyr, Thomas Moreau |
| 2019 | AISTATS | Stochastic algorithms with descent guarantees for ICA. | Pierre Ablin, Alexandre Gramfort, Jean-Franois Cardoso, Francis R. Bach |
| 2019 | ESANN | Beyond Pham's algorithm for joint diagonalization. | Pierre Ablin, Jean-Franois Cardoso, Alexandre Gramfort |
| 2019 | ICASSP | A Quasi-Newton Algorithm on the Orthogonal Manifold for NMF with Transform Learning. | Pierre Ablin, Dylan Fagot, Herwig Wendt, Alexandre Gramfort, Cdric Fvotte |
| 2018 | ICASSP | Faster ICA Under Orthogonal Constraint. | Pierre Ablin, Jean-Franois Cardoso, Alexandre Gramfort |
| 2015 | MICCAI | Detecting Myocardial Infarction Using Medial Surfaces - LV Statistical Modelling Challenge: Myocardial Infarction. | Pierre Ablin, Kaleem Siddiqi |