Clément Lalanne
Assistant Professor (MCF) @ University of Toulouse, associate to Institute of Mathematics of Toulouse.
AI co-chair @ ANITI.
My work focuses on Machine Learning, Trustworthy AI, Statistics and Optimization.
Contact :
✉ clement.lalanne@math.univ-toulouse.fr
☎ +33 5 61 55 76 52
Click in the box to add points: a small neural network learns to separate ● from ✕ by gradient descent.
News
- July 2026 Had a wonderful time at ICML 2026 in Seoul, South Korea, where I presented our article Token-Efficient Change Detection in LLM APIs together with Timothée Chauvin, Erwan Le Merrer and Jean-Michel Loubes (joint work also with François Taïani and Gilles Tredan). It was a stimulating and inspiring week, full of great talks and rich discussions, and it was a real pleasure to reconnect with the community and meet so many brilliant people.
- June 2026 It was great to talk about change detection in LLMs at TSE! Thanks to the organizers Adrien Blanchet and Julien Chhor. Slides available in .pdf and .key formats.
- June 2026 New preprint : Minimax Private Estimation of Smooth Optimal-Transport Maps (Clément Lalanne, David Rodríguez-Vítores, Franck Iutzeler, Jean-Michel Loubes).
- May 2026 Our article Token-Efficient Change Detection in LLM APIs (Timothée Chauvin, Clément Lalanne, Erwan Le Merrer, Jean-Michel Loubes, François Taïani, Gilles Tredan) just got accepted to ICML ! See you in Seoul :)
- February 2026 New preprint : Token-Efficient Change Detection in LLM APIs (Timothée Chauvin, Clément Lalanne, Erwan Le Merrer, Jean-Michel Loubes, François Taïani, Gilles Tredan). We show that LLM change detection exhibits a sharp low-temperature phase transition, and leverage this phenomenon to build a token-efficient method that reduces API costs by up to 30x.
- January 2026 I was delighted to be invited to speak in the session "Theory, Data, Models: What Foundations for AI?" during the ANITI Days 2026. Many thanks to Edouard Pauwels and Nicholas Asher for their invitation. It was a little intimidating to speak alongside David Donoho, Emiliano Lorini, and Rufin VanRullen, but everything went smoothly in the end. For anyone interested, the slides are available in .pdf and .key formats.
- 📰 News Archive
Publications
This publication list is automatically fetched and formatted from my HAL profile. In case of errors or omissions, please refer to my Google Scholar profile.
Loading publications...
Teaching
- Assymptotic Statistics (M2 RI Toulouse University / ISAE Supaero) : Course 2026-2027.
- Mathematics of Machine Learning (M2 MAPI3 Toulouse University) : Course 2026-2027, Projects 2026-2027.
- 📰 Teaching Archive
Curriculum
- 2024-Today : Assistant Professor (MCF) in Applied Mathematics at University of Toulouse and Institute of Mathematics of Toulouse
- 2023-2024 : Postdoc @ Toulouse School of Economics (Toulouse Capitole University) with Jérôme Bolte and Sébastien Gadat
- 2020-2023 : PhD in Computer Science @ ENS Lyon under the supervision of Aurélien Garivier and Rémi Gribonval among the Inria OCKHAM team
- 2023 : I successfully defended my PhD thesis in computer science titled "On the tradeoffs of statistical learning with privacy" on October 4th 2023. You may find the manuscript here, and the slides here
- 2023 : Laureate of the Agrégation Externe de Mathématiques
- 2020-2023 : Teacher Assistant @ ENS Lyon. Topics : Machine Learning, Optimization, Data Bases and Data Mining, Competitive Programming, System Programming
- 2016-2020 : Undergrad @ ENS Ulm; Civil Servant student (Normalien) in Computer Science (major) and Mathematics (minor)
- 2020 : M.S. (Diplôme de l'ENS) in Computer Science with a minor in Mathematics from ENS Ulm
- 2019 : M.S. in Applied Mathematics, MVA from ENS Paris-Saclay
- 2019 : Internship : Nystagmus waveform extraction using convolutional dictionary learning with detrending, supervised by Nicolas Vayatis, Laurent Oudre and Thomas Moreau, CMLA
- 2018 : Internship : Storage-optimal continuous optimization, supervised by Volkan Cevher, EPFL in LIONS team
- 2017 : Internship : De-anonymization and privacy: Study of a random graph model, supervised by Florian Simatos, DISC of ISAE Supaero
- 2013-2016 : CPGE MP* @ Lycée Louis-Le-Grand & MPSI/MP @ Lycée Louis Barthou