Tobías I. Liaudat

Researcher, IRFU/DEDIP, CEA

Joined

February 2024

Names

Tobías I. Liaudat (Preferred)

Tobias Liaudat

Emails

****@gmail.com (Confirmed)

****@cea.fr

Personal Links

Homepage

Google Scholar

ORCID

Career & Education History

Researcher

IRFU/DEDIP, CEA (cea.fr)

2024 – Present

Postdoc

Computer Science, University College London, University of London (ucl.ac.uk)

2022 – 2023

PhD student

IRFU/DAP, CEA (cea.fr)

2019 – 2022

Advisors, Relations & Conflicts

Postdoc Advisee

Tom Sprunck

2025 – Present

PhD Advisee

Sammy Nasser Sharief

2025 – 2028

Postdoc Advisor

Jason McEwen

2022 – 2023

Postdoc Advisor

Marcelo Pereyra

2022 – 2023

Postdoc Advisor

Marta Betcke

2022 – 2023

PhD Advisor

Jean-Luc Starck

2019 – 2022

PhD Advisor

PhD Advisor

2019 – 2022

Expertise

Inverse problems

Present

Computational imaging

Present

Bayesian models and methods

Present

Publications

Generative modelling for mass-mapping with fast uncertainty quantification
Tobías I. Liaudat, Jessica Whitney, Jason McEwen, Matthijs Mars, Matthew Alexander Price
- Monthly Notices of the Royal Astronomical Society, Volume 542, Issue 3, September 2025
- Readers: Everyone
Scalable Bayesian uncertainty quantification with data-driven priors for radio interferometric imaging
Tobías I. Liaudat, Matthijs Mars, Matthew Alexander Price, Marta Betcke, Marcelo Pereyra, Jason McEwen
- RAS Techniques and Instruments, Volume 3, Issue 1, January 2024
- Readers: Everyone
Rethinking data-driven point spread function modeling with a differentiable optical model
Tobías I. Liaudat, Jean-Luc Starck, Martin Kilbinger, Pierre-Antoine Frugier
- Inverse Problems, IOP journal
- Readers: Everyone
Uncertainty quantification for fast reconstruction methods using augmented equivariant bootstrap: Application to radio interferometry
Tobías I. Liaudat, Mostafa Cherif, Jonathan Kern, Christophe Kervazo, Jerome Bobin
- Machine Learning and the Physical Sciences Workshop, NeurIPS 2024
- Readers: Everyone
Deep unfolding of MCMC kernels: scalable, modular & explainable GANs for high-dimensional posterior sampling
Tobías I. Liaudat, Jonathan Spence, Konstantinos C. Zygalakis, Marcelo Pereyra
- arxiv
- Readers: Everyone
Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements
Tobías I. Liaudat, Tom Sprunck, Marcelo Pereyra
- arxiv
- Readers: Everyone
Proximal Nested Sampling with Data-Driven Priors for Physical Scientists
Tobías I. Liaudat, Jason McEwen, Matthew Alexander Price, Xiaohao Cai, Marcelo Pereyra
- Proceedings of The 42nd International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering
- Readers: Everyone

Tobías I. Liaudat

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Generative modelling for mass-mapping with fast uncertainty quantification

Scalable Bayesian uncertainty quantification with data-driven priors for radio interferometric imaging

Rethinking data-driven point spread function modeling with a differentiable optical model

Uncertainty quantification for fast reconstruction methods using augmented equivariant bootstrap: Application to radio interferometry

Deep unfolding of MCMC kernels: scalable, modular & explainable GANs for high-dimensional posterior sampling

Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements

Proximal Nested Sampling with Data-Driven Priors for Physical Scientists

Co-Authors