Flammarion, Nicolas

64 publications

ICLR 2025 Does Refusal Training in LLMs Generalize to the past Tense? Maksym Andriushchenko, Nicolas Flammarion

JMLR 2025 Early Alignment in Two-Layer Networks Training Is a Two-Edged Sword Etienne Boursier, Nicolas Flammarion

ICLR 2025 Is In-Context Learning Sufficient for Instruction Following in LLMs? Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

ICLR 2025 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

COLT 2025 Learning Algorithms in the Limit Hristo Papazov, Nicolas Flammarion

ICML 2025 Learning In-Context $n$-Grams with Transformers: Sub-$n$-Grams Are Near-Stationary Points Aditya Varre, Gizem Yüce, Nicolas Flammarion

ICML 2025 Learning Parametric Distributions from Samples and Preferences Marc Jourdan, Gizem Yüce, Nicolas Flammarion

ICLR 2025 Long-Context Linear System Identification Oğuz Kaan Yüksel, Mathieu Even, Nicolas Flammarion

NeurIPS 2025 OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents Thomas Kuntz, Agatha Duzan, Hao Zhao, Francesco Croce, J Zico Kolter, Nicolas Flammarion, Maksym Andriushchenko

AISTATS 2025 On the Sample Complexity of Next-Token Prediction Oğuz Kaan Yüksel, Nicolas Flammarion

ICLR 2025 Selective Induction Heads: How Transformers Select Causal Structures in Context Francesco D'Angelo, Francesco Croce, Nicolas Flammarion

ICML 2025 Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks Etienne Boursier, Nicolas Flammarion

NeurIPSW 2024 Does Refusal Training in LLMs Generalize to the past Tense? Maksym Andriushchenko, Nicolas Flammarion

NeurIPSW 2024 Does Refusal Training in LLMs Generalize to the past Tense? Maksym Andriushchenko, Nicolas Flammarion

ICLR 2024 First-Order ANIL Provably Learns Representations Despite Overparametrisation Oğuz Kaan Yüksel, Etienne Boursier, Nicolas Flammarion

NeurIPS 2024 Implicit Bias of Mirror Flow on Separable Data Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion

NeurIPSW 2024 Is In-Context Learning Sufficient for Instruction Following in LLMs? Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

NeurIPS 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong

ICMLW 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong

ICMLW 2024 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

AISTATS 2024 Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks Hristo Papazov, Scott Pesme, Nicolas Flammarion

ICML 2024 Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion

NeurIPS 2024 SGD vs GD: Rank Deficiency in Linear Networks Aditya Varre, Margarita Sagitova, Nicolas Flammarion

ICMLW 2024 SGD vs GD: Rank Deficiency in Linear Networks Aditya Varre, Margarita Sagitova, Nicolas Flammarion

NeurIPS 2024 Why Do We Need Weight Decay in Modern Deep Learning? Francesco D'Angelo, Maksym Andriushchenko, Aditya Varre, Nicolas Flammarion

NeurIPS 2023 (S)GD over Diagonal Linear Networks: Implicit Bias, Large Stepsizes and Edge of Stability Mathieu Even, Scott Pesme, Suriya Gunasekar, Nicolas Flammarion

ICML 2023 A Modern Look at the Relationship Between Sharpness and Generalization Maksym Andriushchenko, Francesco Croce, Maximilian Müller, Matthias Hein, Nicolas Flammarion

NeurIPSW 2023 First-Order ANIL Provably Learns Representations Despite Overparametrisation Oğuz Yüksel, Etienne Boursier, Nicolas Flammarion

COLT 2023 Linearization Algorithms for Fully Composite Optimization Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion

TMLR 2023 On Adaptivity in Quantum Testing Omar Fawzi, Nicolas Flammarion, Aurélien Garivier, Aadil Oufkir

NeurIPS 2023 On the Spectral Bias of Two-Layer Linear Networks Aditya Vardhan Varre, Maria-Luiza Vladarean, Loucas Pillaud-Vivien, Nicolas Flammarion

NeurIPS 2023 Penalising the Biases in Norm Regularisation Enforces Sparsity Etienne Boursier, Nicolas Flammarion

COLT 2023 Quantum Channel Certification with Incoherent Measurements Omar Fawzi, Nicolas Flammarion, Aurélien Garivier, Aadil Oufkir

ICML 2023 SGD with Large Step Sizes Learns Sparse Features Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion

NeurIPS 2023 Saddle-to-Saddle Dynamics in Diagonal Linear Networks Scott Pesme, Nicolas Flammarion

NeurIPS 2023 Sharpness-Aware Minimization Leads to Low-Rank Features Maksym Andriushchenko, Dara Bahri, Hossein Mobahi, Nicolas Flammarion

NeurIPS 2023 Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings Klim Kireev, Maksym Andriushchenko, Carmela Troncoso, Nicolas Flammarion

NeurIPSW 2023 Why Do We Need Weight Decay for Overparameterized Deep Networks? Francesco D'Angelo, Aditya Varre, Maksym Andriushchenko, Nicolas Flammarion

CVPRW 2022 ARIA: Adversarially Robust Image Attribution for Content Provenance Maksym Andriushchenko, Xiaoyang Rebecca Li, Geoffrey Oxholm, Thomas Gittings, Tu Bui, Nicolas Flammarion, John P. Collomosse

COLT 2022 Accelerated SGD for Non-Strongly-Convex Least Squares Aditya Varre, Nicolas Flammarion

JMLR 2022 An Efficient Sampling Algorithm for Non-Smooth Composite Potentials Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright, Peter L. Bartlett

NeurIPS 2022 Gradient Flow Dynamics of Shallow ReLU Networks for Square Loss and Orthogonal Inputs Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion

COLT 2022 Label Noise (stochastic) Gradient Descent Implicitly Solves the Lasso for Quadratic Parametrisation Loucas Pillaud Vivien, Julien Reygner, Nicolas Flammarion

UAI 2022 On the Effectiveness of Adversarial Training Against Common Corruptions Klim Kireev, Maksym Andriushchenko, Nicolas Flammarion

AAAI 2022 Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein

ICML 2022 Towards Understanding Sharpness-Aware Minimization Maksym Andriushchenko, Nicolas Flammarion

COLT 2022 Trace Norm Regularization for Multi-Task Learning with Scarce Data Etienne Boursier, Mikhail Konobeev, Nicolas Flammarion

NeurIPS 2021 Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms Mathieu Even, Raphaël Berthier, Francis R. Bach, Nicolas Flammarion, Hadrien Hendrikx, Pierre Gaillard, Laurent Massoulié, Adrien Taylor

NeurIPS 2021 Implicit Bias of SGD for Diagonal Linear Networks: A Provable Benefit of Stochasticity Scott Pesme, Loucas Pillaud-Vivien, Nicolas Flammarion

NeurIPS 2021 Last Iterate Convergence of SGD for Least-Squares in the Interpolation Regime. Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion

NeurIPS 2021 Sequential Algorithms for Testing Closeness of Distributions Aadil Oufkir, Omar Fawzi, Nicolas Flammarion, Aurélien Garivier

ICML 2020 On Convergence-Diagnostic Based Step Sizes for Stochastic Gradient Descent Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion

NeurIPS 2020 Online Robust Regression via SGD on the L1 Loss Scott Pesme, Nicolas Flammarion

ECCV 2020 Square Attack: A Query-Efficient Black-Box Adversarial Attack via Random Search Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein

NeurIPS 2020 Understanding and Improving Fast Adversarial Training Maksym Andriushchenko, Nicolas Flammarion

NeurIPS 2019 Escaping from Saddle Points on Riemannian Manifolds Yue Sun, Nicolas Flammarion, Maryam Fazel

COLT 2019 Fast Mean Estimation with Sub-Gaussian Rates Yeshwanth Cherapanamjeri, Nicolas Flammarion, Peter L. Bartlett

COLT 2018 Averaging Stochastic Gradient Descent on Riemannian Manifolds Nilesh Tripuraneni, Nicolas Flammarion, Francis R. Bach, Michael I. Jordan

NeurIPS 2018 Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L Bartlett, Michael I Jordan

ICML 2018 On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo Niladri Chatterji, Nicolas Flammarion, Yian Ma, Peter Bartlett, Michael Jordan

JMLR 2017 Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression Aymeric Dieuleveut, Nicolas Flammarion, Francis Bach

JMLR 2017 Robust Discriminative Clustering with Sparse Regularizers Nicolas Flammarion, Balamurugan Palaniappan, Francis Bach

COLT 2017 Stochastic Composite Least-Squares Regression with Convergence Rate $O(1/n)$ Nicolas Flammarion, Francis Bach

COLT 2015 From Averaging to Acceleration, There Is Only a Step-Size Nicolas Flammarion, Francis R. Bach