Non classé

36 Hi! PARIS Papers Accepted at NeurIPS 2025

We are proud to highlight the strong presence of its researchers at NeurIPS 2025, one of the world’s leading conferences in artificial intelligence and machine learning.

This year, 36 papers from Hi! PARIS affiliated researchers have been accepted, reflecting both the depth and diversity of the Center’s scientific contributions. Their work spans fundamental advances and applied research, covering areas such as optimization, variational inference, diffusion models, causal inference, graph neural networks, multimodal AI, and algorithmic fairness.

Beyond theoretical progress, these papers address real-world challenges in domains including cybersecurity, finance, healthcare, and robotics. Many of them result from cross-institutional collaborations within the Hi! PARIS ecosystem, bringing together expertise from HEC Paris, Institut Polytechnique de Paris schools, Inria, and CNRS.

This collective achievement once again highlights Hi! PARIS’s mission to advance AI research at the intersection of science, business, and society.

Congratulations to our researchers!

Here is a list of papers accepted at NeurIPS 2025 that include at least one author affiliated with Hi! PARIS:

Title Hi! PARIS Authors All Authors
Learning with Equality Constraints Luiz Chamon Aneesh Barthakur, Luiz Chamon
Learning (Approximately) Equivariant Networks via Constrained Optimization Luiz Chamon Andrei Manolache, Luiz Chamon, Mathias Niepert
msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML Emmanuel Baccelli Zhaolan Huang, Emmanuel Baccelli
Least squares variational inference Nicolas Chopin Yvann Le Fay, Nicolas Chopin, Simon Barthelmé
Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means Stephan Clémençon Anna van Elst, Igor Colin, Stephan Clémençon
Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures Marco Cuturi, Nina Vesseron Nina Vesseron, Louis Béthune, Marco Cuturi
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss Marco Cuturi Pau Rodriguez, Michal Klein, Eleonora Gualdoni, Valentino Maiorca, Arno Blaas, Luca Zappella, Marco Cuturi, Xavier Suau
Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds Arnak Dalalyan Vahan Arsenyan, Elen Vardanyan, Arnak Dalalyan
Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning Gael Varoquaux Félix Lefebvre, Gael Varoquaux
Tight analyses of first-order methods with error feedback Aymeric Dieuleveut Daniel Berg Thomsen, Adrien Taylor, Aymeric Dieuleveut
Valid Selection among Conformal Sets Aymeric Dieuleveut Mahmoud Hegazy, Liviu Aolaritei, Michael Jordan, Aymeric Dieuleveut
Why Popular MOEAs are Popular: Proven Advantages in Approximating the Pareto Front Benjamin Doerr Mingfeng Li, Qiang Zhang, Weijie Zheng, Benjamin Doerr
Continuous Simplicial Neural Networks Aref Einizade Aref Einizade, Dorina Thanou, Fragkiskos Malliaros, Jhony H. Giraldo
Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs Rémi Flamary Sonia Mazelet, Rémi Flamary, Bertrand Thirion
The quest for the GRAph Level autoEncoder (GRALE) Florence d'Alché-Buc, Rémi Flamary, Charlotte Laclau Paul Krzakala, Gabriel Melo, Charlotte Laclau, Florence d'Alché-Buc, Rémi Flamary
Torch-Uncertainty: Deep Learning Uncertainty Quantification Gianni Franchi Adrien Lafage, Olivier Laurent, Firas Gabetni, Gianni Franchi
Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity Gianni Franchi, Antoine Manzanera Mouïn Ben Ammar, David Brellmann, Arturo Mendoza, Antoine Manzanera, Gianni Franchi
Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems Josselin Garnier Lorenzo Baldassari, Josselin Garnier, Knut Solna, Maarten V. de Hoop
Exponential Convergence Guarantees for Iterative Markovian Fitting Alain Durmus, Marta Gentiloni Silveri Marta Gentiloni Silveri, Giovanni Conforti, Alain Durmus
Thresholds for sensitive optimality and Blackwell optimality in stochastic games Julien Grand-Clément Stephane Gaubert, Julien Grand-Clément, Ricardo Katz
Active Seriation Yann Issartel James Cheshire, Yann Issartel
T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning Vicky Kalogeiton, Steve Oudot Julie Mordacq, David Loiseaux, Vicky Kalogeiton, Steve Oudot
Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion Anna Korba Adrien Vacher, Omar Chehab, Anna Korba
Variational Inference with Mixtures of Isotropic Gaussians Anna Korba Marguerite Petit-Talamon, Marc Lambert, Anna Korba
From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling Arthur Leclaire Marien Renaud, Valentin De Bortoli, Arthur Leclaire, Nicolas Papadakis
GuideFlow3D: Optimization-Guided Flow For Appearance Transfer Vincent Lepetit Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit, Iro Armeni
Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression Vincent Lepetit Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit
The Price of Opportunity Fairness in Matroid Allocation Problems Patrick Loiseau, Vianney Perchet Rémi Castera, Felipe Garrido-Lucero, Patrick Loiseau, Simon Mauras, Mathieu Molina, Vianney Perchet
Enhancing Graph Classification Robustness with Singular Pooling Johannes Lutzeyer Sofiane Ennadir, Oleg Smirnov, Yassine ABB
Statistical inference for Linear Stochastic Approximation with Markovian Noise Eric Moulines Sergey Samsonov, Marina Sheshukova, Eric Moulines, Alexey Naumov
Self-Supervised Learning of Graph Representations for Network Intrusion Detection Pavlo Mozharovskyi, Van-Tam Nguyen Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen
Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization Vianney Perchet Marius Potfer, Vianney Perchet
Stable Matching with Ties: Approximation Ratios and Learning Vianney Perchet Shiyun Lin, Simon Mauras, Nadav Merlis, Vianney Perchet
Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data Loucas Pillaud-Vivien Léo Dana, Loucas Pillaud-Vivien, Francis Bach
Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing Enzo Tartaglione Massimiliano Ciranni, Vito Paolo Pastore, Roberto Di Via, Enzo Tartaglione, Francesca Odone, Vittorio Murino
Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment Michalis Vazirgiannis Xiao Fei, Michail Chatzianastasis, Sarah Carneiro, Hadi Abdine, Lawrence Petalidis, Michalis Vazirgiannis