GV
Gaël Varoquaux
cs.LGstat.MLcs.CVcs.AIneuroscienceq-bio.NCmachine learningModels, Neurologicalstat.MEAlgorithms
On Valency
published · living versionsW_hqyhj9g7·v1 · currentpublished
The NumPy array: a structure for efficient numerical computation
with Stefan Van Der Walt, S. Chris Colbert
1 version
W_dwtmxhph·v1published
Preprints & journals
204 papers in the corpus · 2005–2026The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks2610.23322v1 · Julie Alberge, Gael Varoquaux, Judith Ab'ecassis2026 · 0 citationsarXiv
SurvICL: a Foundation Model for in-context Survival Analysis2610.22242v1 · Julie Alberge, Linus Bleistein, Judith Ab'ecassis et al.2026 · 0 citationsarXiv
TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings2610.17065v1 · F'elix Lefebvre, David Holzmuller, Gioia Blayer et al.2026 · 0 citationsarXiv
Immunometabolic endotypes define distinct clinical trajectories in type 2 diabetes.42641605 · Vuong, Bao Tran, Delépine, Chloé M, Ratter-Rieck, Jacqueline M et al.2026 · 0 citationsCell metabolism. 2026;38(10):2018-2035.e6
Beyond IID: How General Are Tabular Foundation Models, Really?2606.30410v1 · Lennart Purucker, Andrej Tschalzev, Nick Erickson et al.2026 · 1 citationarXiv
Analysis of the challenges in ensuring robust and effective clinical evaluation of AI-based digital medical devices.42712384 · Boulet, Sandrine, Thévenet, Vincent, Abecassis, Judith et al.2026 · 0 citationsBMJ digital health & AI. 2026;2(1):e000043
Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well2606.12552v1 · C'elestin Eve, Gael Varoquaux, Thomas Moreau2026 · 0 citationsarXiv
Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference2606.03332v1 · Roman Plaud, Alexandre Perez-Lebel, Antoine Saillenfest et al.2026 · 0 citationsarXiv
STRABLE: Benchmarking Tabular Machine Learning with Strings2605.12292v2 · Gioia Blayer, Myung Jun Kim, F'elix Lefebvre et al.2026 · 0 citationsarXiv
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image2605.10616v2 · Alan Arazi, Eilam Shapira, Shoham Grunblat et al.2026 · 0 citationsarXiv
Innovative Clinical Trial Approach for Evaluating Digital Medical Devices Under European Fast-Track Regulatory Frameworks.42086335 · Ursino, Moreno, Boulet, Sandrine, Collignon, Corinne et al.2026 · 1 citationStatistics in medicine. 2026;45(10-12):e70572
International AI Safety Report 20262602.21012v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2026 · 3 citationsarXiv
TabICLv2: A better, faster, scalable, and open tabular foundation model2602.11139v2 · Jingang Qu, David Holzmuller, Gael Varoquaux et al.2026 · 2 citationsarXiv
On the calibration of survival models with competing risks2602.00194v1 · Julie Alberge, Tristan Haugomat (DREES), Gael Varoquaux et al.2026 · 0 citationsInternational Conference on Artificial Intelligence and Statistics (AISTATS) 2026, May 2026, Tanger, Morocco
Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance.41391983 · Van Calster, Ben, Collins, Gary S, Vickers, Andrew J et al.2025 · 110 citationsThe Lancet. Digital health. 2025;7(12):100916
International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management2511.19863v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2025 · 2 citationsarXiv
Large Language Models as Search Engines: Societal Challenges2512.08946v1 · Zacchary Sadeddine, Winston Maxwell, Gael Varoquaux et al.2025 · 0 citationsSIGIR Forum 2025
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications2510.13653v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2025 · 3 citationsarXiv
Incidence of death and amputation in patients with a first diabetic foot ulcer: results from the CODIA cohort.40915494 · Julla, Jean-Baptiste, Jolivet, Théo, Estellat, Candice et al.2025 · 4 citationsDiabetes & metabolism. 2025;51(6):101700
Beyond Quantification: Navigating Uncertainty in Professional AI Systems2509.03271v1 · Sylvie Delacroix, Diana Robinson, Umang Bhatt et al.2025 · 11 citationsRSS Data Science (2025)
Advancing science- and evidence-based AI policy.40743343 · Bommasani, Rishi, Arora, Sanjeev, Chayes, Jennifer et al.2025 · 22 citationsScience (New York, N.Y.). 2025;389(6759):459-461
Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning2507.00965v3 · F'elix Lefebvre, Gael Varoquaux2025 · 1 citationarXiv
Query-Level Uncertainty in Large Language Models2506.09669v4 · Lihu Chen, Gerard de Melo, Fabian M. Suchanek et al.2025 · 0 citationsarXiv
Table Foundation Models: on knowledge pre-training for tabular learning2505.14415v2 · Myung Jun Kim, F'elix Lefebvre, Gaetan Brison et al.2025 · 0 citationsarXiv
Confidence intervals for performance estimates in brain MRI segmentation.40367699 · El Jurdi, Rosana, Varoquaux, Gaël, Colliot, Olivier2025 · 9 citationsMedical image analysis. 2025;103:103565
False Promises in Medical Imaging AI? Assessing Validity of Outperformance Claims2505.04720v2 · Evangelia Christodoulou, Annika Reinke, Pascaline Andre et al.2025 · 2 citationsarXiv
From Prediction to Prescription: Machine Learning and Causal Inference for the Heterogeneous Treatment Effect.40203240 · Abécassis, Judith, Dumas, Élise, Alberge, Julie et al.2025 · 20 citationsAnnual review of biomedical data science. 2025;8(1):381-404
Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration2503.18025v1 · Alexandre Perez-Lebel, Gael Varoquaux, Sanmi Koyejo et al.2025 · 0 citationsProceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS) 2025, Mai Khao, Thailand. PMLR: Volume 258
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data2502.05564v2 · Jingang Qu, David Holzmuller, Gael Varoquaux et al.2025 · 9 citationsarXiv
Step-by-step causal analysis of EHRs to ground decision-making.39899627 · Doutreligne, Matthieu, Struja, Tristan, Abecassis, Judith et al.2026 · 10 citationsPLOS digital health. 2025;4(2):e0000721
International AI Safety Report2501.17805v1 · Yoshua Bengio, Soren Mindermann, Daniel Privitera et al.2025 · 16 citationsarXiv
How to select predictive models for decision-making or causal inference.40117179 · Doutreligne, Matthieu, Varoquaux, Gaël2025 · 5 citationsGigaScience. 2025;14
Performance evaluation of predictive AI models to support medical decisions: Overview and guidance2412.10288v1 · Ben Van Calster, Gary S. Collins, Andrew J. Vickers et al.2024 · 15 citationsarXiv
International Scientific Report on the Safety of Advanced AI (Interim Report)2412.05282v2 · Yoshua Bengio, Soren Mindermann, Daniel Privitera et al.2024 · 9 citationsarXiv
Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing Risks2410.16765v1 · Julie Alberge (SODA), Vincent Maladiere, Olivier Grisel et al.2024 · 2 citationsarXiv
Confidence intervals uncovered: Are we ready for real-world medical imaging AI?2409.17763v2 · Evangelia Christodoulou, Annika Reinke, Rola Houhou et al.2024 · 12 citationsarXiv
Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI2409.14160v2 · Gael Varoquaux, Alexandra Sasha Luccioni, Meredith Whittaker2024 · 36 citationsarXiv
What is the Role of Small Models in the LLM Era: A Survey2409.06857v9 · Lihu Chen, Gael Varoquaux2024 · 10 citationsarXiv
Imputation for prediction: beware of diminishing returns2407.19804v2 · Marine Le Morvan (SODA), Gael Varoquaux (SODA)2024 · 3 citationsarXiv
Teaching Models To Survive: Proper Scoring Rule and Stochastic Optimization with Competing Risks2406.14085v1 · Julie Alberge (SODA), Vincent Maladiere, Olivier Grisel et al.2024 · 0 citationsarXiv
Individual Brain Charting dataset extension, third release for movie watching and retinotopy data.38839770 · Pinho, Ana Luísa, Richard, Hugo, Ponce, Ana Fernanda et al.2024 · 9 citationsScientific data. 2024;11(1):590
The past, present, and future of the brain imaging data structure (BIDS).39308505 · Poldrack, Russell A, Markiewicz, Christopher J, Appelhoff, Stefan et al.2026 · 60 citationsImaging neuroscience (Cambridge, Mass.). 2024;2:1-19
CARTE: Pretraining and Transfer for Tabular Learning2402.16785v2 · Myung Jun Kim, L'eo Grinsztajn, Gael Varoquaux2024 · 2 citationsarXiv
Understanding metric-related pitfalls in image analysis validation.36945687 · Reinke, Annika, Tizabi, Minu D, Baumgartner, Michael et al.2025 · 233 citationsArXiv. 2024
Retrieve, Merge, Predict: Augmenting Tables with Data Lakes2402.06282v7 · Riccardo Cappuzzo, Aimee Coelho, Felix Lefebvre et al.2024 · 0 citationsarXiv
Reconfidencing LLMs from the Grouping Loss Perspective2402.04957v3 · Lihu Chen, Alexandre Perez-Lebel, Fabian M. Suchanek et al.2024 · 3 citationsarXiv
Metrics reloaded: recommendations for image analysis validation.38347141 · Maier-Hein, Lena, Reinke, Annika, Godau, Patrick et al.2024 · 539 citationsNature methods. 2024;21(2):195-212
Causal Inference Methods for Combining Randomized Trials and Observational Studies: A Review.41059256 · Colnet, Bénédicte, Mayer, Imke, Chen, Guanhua et al.2025 · 127 citationsStatistical science : a review journal of the Institute of Mathematical Statistics. 2024;39(1):165-191
Learning High-Quality and General-Purpose Phrase Representations2401.10407v2 · Lihu Chen, Gael Varoquaux, Fabian M. Suchanek2024 · 2 citationsarXiv
The Past, Present, and Future of the Brain Imaging Data Structure (BIDS).37744469 · Poldrack, Russell A, Markiewicz, Christopher J, Appelhoff, Stefan et al.2026 · 0 citationsArXiv. 2024
Career total: 491 works. 204 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.