Tom Dupre la Tour

Researcher, OpenAI

Joined

April 2020

Names

Tom Dupre la Tour (Preferred)

Emails

****@berkeley.edu (Confirmed)

****@gmail.com (Confirmed)

****@openai.com (Confirmed)

Personal Links

Career & Education History

Researcher

OpenAI (openai.com)

2023 – Present

Postdoc

University of California Berkeley (berkeley.edu)

2019 – 2023

PhD student

Télécom ParisTech (telecom-paristech.fr)

2015 – 2018

Advisors, Relations & Conflicts

Postdoc Advisor

Jack Gallant

2019 – 2023

PhD Advisor

Alexandre Gramfort

2015 – 2018

Expertise

No areas of expertise listed

Publications

Persona Features Control Emergent Misalignment
Miles Wang, Tom Dupre la Tour, Olivia Watkins, Aleksandar Makelov, Ryan Andrew Chi, Samuel Miserendino, Jeffrey George Wang, Achyuta Rajaram, Johannes Heidecke, Tejal Patwardhan, Daniel P Mossing
- ICLR 2026 Poster
- Readers: Everyone
Scaling and evaluating sparse autoencoders
Leo Gao, Tom Dupre la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu
- ICLR 2025 Oral
- Readers: Everyone
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Thomas Moreau, Mathurin Massias, Alexandre Gramfort, Pierre Ablin, Pierre-Antoine Bannier, Benjamin Charlier, Mathieu Dagréou, Tom Dupre la Tour, Ghislain Durif, Cássio Fraga Dantas, Quentin Klopfenstein, Johan Larsson, En Lai, Tanguy Lefort, Benoît Malézieux, Badr Moufad, Binh Nguyen, Alain Rakotomamonjy, Zaccharie Ramzi, Joseph Salmon et al. (1 additional authors not shown)
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
A finer mapping of convolutional neural network layers to the visual cortex
Tom Dupre la Tour, Michael Lu, Michael Eickenberg, Jack L. Gallant
- Published: 02 Nov 2021, Last Modified: 05 May 2023
- SVRHM 2021 Poster
- Readers: Everyone
Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals.
Tom Dupré la Tour, Thomas Moreau, Mainak Jas, Alexandre Gramfort
- 2018 (modified: 09 Nov 2022)
- NeurIPS2018
- Readers: Everyone
Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals.
Tom Dupré la Tour, Thomas Moreau, Mainak Jas, Alexandre Gramfort
- 2018 (modified: 09 Nov 2022)
- CoRR2018
- Readers: Everyone
Driver Estimation in Non-Linear Autoregressive Models.
Tom Dupré la Tour, Yves Grenier, Alexandre Gramfort
- 2018 (modified: 09 Nov 2022)
- ICASSP2018
- Readers: Everyone
Nonlinear models for neurophysiological time series. (Modèles non linéaires pour les séries temporelles neurophysiologiques).
Tom Dupré la Tour
- 2018 (modified: 09 Nov 2022)
- undefined2018
- Readers: Everyone
Non-linear auto-regressive models for cross-frequency coupling in neural time series.
Tom Dupré la Tour, Lucille Tallot, Laetitia Grabot, Valérie Doyère, Virginie van Wassenhove, Yves Grenier, Alexandre Gramfort
- 2017 (modified: 09 Nov 2022)
- PLoS Computational Biology2017
- Readers: Everyone
Learning the Morphology of Brain Signals Using Alpha-Stable Convolutional Sparse Coding.
Mainak Jas, Tom Dupré la Tour, Umut Simsekli, Alexandre Gramfort
- 2017 (modified: 09 Nov 2022)
- NIPS2017
- Readers: Everyone

View all 11 publications

Co-Authors

View all 48 co-authors