FF
François Fleuret
cs.LGcs.CVstat.MLcs.AIcs.CLAlgorithmscond-mat.stat-mechArtificial Intelligenceastro-ph.IMcs.DS
On Valency
published · living versionsW_t6szp3tn·v1 · currentpublished
Gaussian Distillation of Flow Policies
with Youssef Saied, Ziyad Sheebaelhamd, Claire Vernade
1 version
Preprints & journals
87 papers in the corpus · 2000–2026MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities2607.25948v1 · Mingqiao Ye, Zhaochong An, Zhitong Gao et al.2026 · 0 citationsarXiv
The Free Transformer2510.17558v1 · Francois Fleuret2025 · 0 citationsarXiv
CWM: An Open-Weights LLM for Research on Code Generation with World Models2510.02387v1 · FAIR CodeGen team, Jade Copet, Quentin Carbonneaux et al.2025 · 0 citationsarXiv
Solvation free energies from neural thermodynamic integration.40130791 · Máté, Bálint, Fleuret, François, Bereau, Tristan2025 · 6 citationsThe Journal of chemical physics. 2025;162(12)
End-to-End Optimal Detector Design with Mutual Information Surrogates2503.14342v1 · Kinga Anna Wozniak, Stephen Mulligan, Jan Kieseler et al.2025 · 1 citationarXiv
Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners2502.20339v1 · Daniele Paliotta, Junxiong Wang, Matteo Pagliardini et al.2025 · 0 citationsarXiv
Leveraging the true depth of LLMs2502.02790v3 · Ram'on Calvo Gonz'alez, Daniele Paliotta, Matteo Pagliardini et al.2025 · 0 citationsarXiv
Neural Thermodynamic Integration: Free Energies from Energy-Based Diffusion Models.39503734 · Máté, Bálint, Fleuret, François, Bereau, Tristan2024 · 12 citationsThe journal of physical chemistry letters. 2024;15(45):11395-11404
LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging2410.17146v2 · Ke Wang, Nikolaos Dimitriadis, Alessandro Favero et al.2024 · 1 citationarXiv
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences2407.08056v2 · Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret2024 · 1 citationarXiv
Efficient World Models with Context-Aware Tokenization2406.19320v1 · Vincent Micheli, Eloi Alonso, Francois Fleuret2024 · 1 citationarXiv
Localizing Task Information for Improved Model Merging and Compression2405.07813v1 · Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez et al.2024 · 1 citationarXiv
{\sigma}-GPTs: A New Approach to Autoregressive Models2404.09562v2 · Arnaud Pannatier, Evann Courdier, Francois Fleuret2024 · 3 citationsarXiv
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging2402.02622v2 · Matteo Pagliardini, Amirkeivan Mohtashami, Francois Fleuret et al.2024 · 1 citationarXiv
Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows2401.00828v4 · B'alint M'at'e, Francois Fleuret2024 · 1 citationarXiv
DeepEMD: A Transformer-based Fast Estimation of the Earth Mover's Distance2311.09998v1 · Atul Kumar Sinha, Francois Fleuret2023 · 7 citationsarXiv
PAUMER: Patch Pausing Transformer for Semantic Segmentation2311.00586v1 · Evann Courdier, Prabhu Teja Sivaprasad, Francois Fleuret2023 · 3 citationsarXiv
Faster Causal Attention Over Large Sequences Through Sparse Flash Attention2306.01160v1 · Matteo Pagliardini, Daniele Paliotta, Martin Jaggi et al.2023 · 6 citationsarXiv
SequeL: A Continual Learning Library in PyTorch and JAX2304.10857v1 · Nikolaos Dimitriadis, Francois Fleuret, Pascal Frossard2023 · 1 citationarXiv
Graph Neural Networks Go Forward-Forward2302.05282v1 · Daniele Paliotta, Mathieu Alain, B'alint M'at'e et al.2023 · 4 citationsarXiv
Learning Interpolations between Boltzmann Densities2301.07388v5 · B'alint M'at'e, Francois Fleuret2023 · 5 citationsarXiv
ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields2211.11704v2 · Mohammad Mahdi Johari, Camilla Carta, Francois Fleuret2022 · 253 citationsarXiv
Deformations of Boltzmann Distributions2210.13772v3 · B'alint M'at'e, Francois Fleuret2022 · 0 citationsarXiv
Inference from Real-World Sparse Measurements2210.11269v7 · Arnaud Pannatier, Kyle Matoba, Francois Fleuret2022 · 0 citationsarXiv
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models2210.09759v2 · Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret2022 · 1 citationarXiv
Transformers are Sample-Efficient World Models2209.00588v2 · Vincent Micheli, Eloi Alonso, Francois Fleuret2022 · 25 citationsarXiv
Efficiently Training Low-Curvature Neural Networks2206.07144v3 · Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju et al.2022 · 0 citationsarXiv
Flowification: Everything is a Normalizing Flow2205.15209v3 · B'alint M'at'e, Samuel Klein, Tobias Golling et al.2022 · 2 citationsarXiv
HyperMixer: An MLP-based Low Cost Alternative to Transformers2203.03691v3 · Florian Mai, Arnaud Pannatier, Fabio Fehr et al.2022 · 15 citationsProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023
The Theoretical Expressiveness of Maxpooling2203.01016v1 · Kyle Matoba, Nikolaos Dimitriadis, Francois Fleuret2022 · 3 citationsarXiv
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned2202.10583v1 · Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas et al.2022 · 6 citationsarXiv
Borrowing from yourself: Faster future video segmentation with partial channel update2202.05748v2 · Evann Courdier, Francois Fleuret2022 · 2 citationsarXiv
SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics2202.05012v2 · Atul Kumar Sinha, Daniele Paliotta, B'alint M'at'e et al.2022 · 1 citationarXiv
Agree to Disagree: Diversity through Disagreement for Better Transferability2202.04414v2 · Matteo Pagliardini, Martin Jaggi, Francois Fleuret et al.2022 · 11 citationsarXiv
Efficient Wind Speed Nowcasting with GPU-Accelerated Nearest Neighbors Algorithm2112.10408v2 · Arnaud Pannatier, Ricardo Picatoste, Francois Fleuret2021 · 0 citationsarXiv
GeoNeRF: Generalizing NeRF with Geometry Priors2111.13539v2 · Mohammad Mahdi Johari, Yann Lepoittevin, Francois Fleuret2021 · 174 citationsarXiv
Test time Adaptation through Perturbation Robustness2110.10232v1 · Prabhu Teja Sivaprasad, Francois Fleuret2021 · 18 citationsarXiv
Speeding up PCA with priming2109.03709v3 · B'alint M'at'e, Francois Fleuret2021 · 0 citationsarXiv
Language Models are Few-Shot Butlers2104.07972v2 · Vincent Micheli, Francois Fleuret2021 · 16 citationsarXiv
Structural analysis of an all-purpose question answering model2104.06045v1 · Vincent Micheli, Quentin Heinrich, Francois Fleuret et al.2021 · 0 citationsarXiv
Unsupervised clustering of series using dynamic programming and neural processes2101.10983v1 · Karthigan Sinnathamby, Chang-Yu Hou, Lalitha Venkataramanan et al.2021 · 0 citationsarXiv
Unsupervised clustering of series using dynamic programming2101.09512v1 · Karthigan Sinnathamby, Chang-Yu Hou, Lalitha Venkataramanan et al.2021 · 0 citationsarXiv
On the importance of pre-training data volume for compact language models2010.03813v2 · Vincent Micheli, Martin d'Hoffschmidt, Francois Fleuret2020 · 38 citationsarXiv
Fast Transformers with Clustered Attention2007.04825v2 · Apoorv Vyas, Angelos Katharopoulos, Francois Fleuret2020 · 82 citationsarXiv
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention2006.16236v3 · Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas et al.2020 · 827 citationsarXiv
Taming GANs with Lookahead-Minmax2006.14567v3 · Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich et al.2020 · 7 citationsICLR 2021
Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability2006.09128v2 · Suraj Srinivas, Francois Fleuret2020 · 9 citationsarXiv
Real-Time Segmentation Networks should be Latency Aware2004.02574v2 · Evann Courdier, Francois Fleuret2020 · 7 citationsarXiv
Multi-task Reinforcement Learning with a Planning Quasi-Metric2002.03240v3 · Vincent Micheli, Karthigan Sinnathamby, Francois Fleuret2020 · 1 citationarXiv
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning1910.11758v4 · Prabhu Teja Sivaprasad (1, Florian Mai (1, Thijs Vogels et al.2019 · 29 citationsarXiv
Career total: 180 works. 87 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.