| 2026 | COLT | Space-Efficient Language Generation in the Limit. | Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov, Miltiadis Stouras, Ola Svensson |
| 2025 | AISTATS | On the Sample Complexity of Next-Token Prediction. | Oguz Kaan Yksel, Nicolas Flammarion |
| 2025 | COLT | Learning Algorithms in the Limit. | Hristo Papazov, Nicolas Flammarion |
| 2025 | ICLR | Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks. | Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion |
| 2025 | ICLR | Does Refusal Training in LLMs Generalize to the Past Tense? | Maksym Andriushchenko, Nicolas Flammarion |
| 2025 | ICLR | Selective induction Heads: How Transformers Select Causal Structures in Context. | Francesco D'Angelo, Francesco Croce, Nicolas Flammarion |
| 2025 | ICLR | Long-Context Linear System Identification. | Oguz Kaan Yksel, Mathieu Even, Nicolas Flammarion |
| 2025 | ICLR | Is In-Context Learning Sufficient for Instruction Following in LLMs? | Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion |
| 2025 | ICML | Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks. | Etienne Boursier, Nicolas Flammarion |
| 2025 | ICML | Learning Parametric Distributions from Samples and Preferences. | Marc Jourdan, Gizem Yce, Nicolas Flammarion |
| 2025 | ICML | Learning In-context n-grams with Transformers: Sub-n-grams Are Near-Stationary Points. | Aditya Varre, Gizem Yce, Nicolas Flammarion |
| 2024 | AISTATS | Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks. | Hristo Papazov, Scott Pesme, Nicolas Flammarion |
| 2024 | ICLR | First-order ANIL provably learns representations despite overparametrisation. | Oguz Kaan Yksel, Etienne Boursier, Nicolas Flammarion |
| 2024 | ICML | Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning. | Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion |
| 2023 | COLT | Quantum Channel Certification with Incoherent Measurements. | Omar Fawzi, Nicolas Flammarion, Aurlien Garivier, Aadil Oufkir |
| 2023 | COLT | Linearization Algorithms for Fully Composite Optimization. | Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion |
| 2023 | ICML | A Modern Look at the Relationship between Sharpness and Generalization. | Maksym Andriushchenko, Francesco Croce, Maximilian Mller, Matthias Hein, Nicolas Flammarion |
| 2023 | ICML | SGD with Large Step Sizes Learns Sparse Features. | Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion |
| 2022 | AAAI | Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks. | Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein |
| 2022 | COLT | Trace norm regularization for multi-task learning with scarce data. | Etienne Boursier, Mikhail Konobeev, Nicolas Flammarion |
| 2022 | COLT | Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation. | Loucas Pillaud-Vivien, Julien Reygner, Nicolas Flammarion |
| 2022 | COLT | Accelerated SGD for Non-Strongly-Convex Least Squares. | Aditya Varre, Nicolas Flammarion |
| 2022 | CVPR | ARIA: Adversarially Robust Image Attribution for Content Provenance. | Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings, Tu Bui, Nicolas Flammarion, John P. Collomosse |
| 2022 | ICML | Towards Understanding Sharpness-Aware Minimization. | Maksym Andriushchenko, Nicolas Flammarion |
| 2022 | UAI | On the effectiveness of adversarial training against common corruptions. | Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion |
| 2020 | ECCV | Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search. | Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein |
| 2020 | ICML | On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent. | Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion |
| 2019 | COLT | Fast Mean Estimation with Sub-Gaussian Rates. | Yeshwanth Cherapanamjeri, Nicolas Flammarion, Peter L. Bartlett |
| 2018 | COLT | Averaging Stochastic Gradient Descent on Riemannian Manifolds. | Nilesh Tripuraneni, Nicolas Flammarion, Francis R. Bach, Michael I. Jordan |
| 2018 | ICML | On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo. | Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan |
| 2017 | COLT | Stochastic Composite Least-Squares Regression with Convergence Rate $O(1/n)$. | Nicolas Flammarion, Francis R. Bach |
| 2015 | COLT | From Averaging to Acceleration, There is Only a Step-size. | Nicolas Flammarion, Francis R. Bach |