Théo Uscidda

PhD student, Computer Science, Institut Polytechnique de Paris

Joined

January 2023

Names

Théo Uscidda (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Computer Science, Institut Polytechnique de Paris (polytechnique.fr)

2021 – 2026

Advisors, Relations & Conflicts

Visiting PhD Advisor

2023 – 2025

PhD Advisor

2021 – 2025

Expertise

Generative Modeling

,

Representational Learning

,

Optimal Transport

2021 – 2025

Publications

Disentangled Representation Learning with the Gromov-Monge Gap
Théo Uscidda, Luca Eyring, Karsten Roth, Fabian J Theis, Zeynep Akata, marco cuturi
- ICLR 2025 Poster
- Readers: Everyone
Disentangled Representation Learning through Geometry Preservation with the Gromov-Monge Gap
Théo Uscidda, Luca Eyring, Karsten Roth, Fabian J Theis, Zeynep Akata, marco cuturi
- 2nd SPIGM @ ICML Poster
- Readers: Everyone
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics
Dominik Klein, Théo Uscidda, Fabian J Theis, marco cuturi
- NeurIPS 2024 poster
- Readers: Everyone
Mirror and Preconditioned Gradient Descent in Wasserstein Space
Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, Anna Korba
- NeurIPS 2024 spotlight
- Readers: Everyone
Generative Entropic Neural Optimal Transport To Map Within and Across Space
Dominik Klein, Théo Uscidda, Fabian J Theis, marco cuturi
- Submitted to ICLR 2024
- Readers: Everyone
Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
Luca Eyring, Dominik Klein, Théo Uscidda, Giovanni Palla, Niki Kilbertus, Zeynep Akata, Fabian J Theis
- ICLR 2024 poster
- Readers: Everyone
The Monge Gap: A Regularizer to Learn All Transport Maps
Théo Uscidda, Marco Cuturi
- 30 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
The Monge Gap: A Regularizer to Learn All Transport Maps
Théo Uscidda, marco cuturi
- ICML 2023 Poster
- Readers: Everyone

Co-Authors