Connectionists: PhD position - Self-Supervised Representation Learning and Low-Rank Tensor Models

[Ricardo Borsoi]

The SiMul team (https://cran-simul.github.io <https://cran-simul.github.io/>) at the University of Lorraine is offering a fully funded PhD position on the theoretical foundations of self-supervised learning, focusing on representation stability, interpretability, and efficiency.
Despite their success, self-supervised approaches and foundation models still lack a thorough theoretical understanding. This project aims to bridge that gap by exploring connections between AI models and low-rank tensor decompositions, providing a rigorous mathematical framework to address key questions:

When are learned representations interpretable and stable?
How do models perform on heterogeneous data (e.g., federated or personalized learning)?
Can smaller, energy-efficient models achieve strong performance on specialized tasks?
Position Details

Location: Nancy, France
Funding: Fully funded
Candidate Profile: Master’s degree (or equivalent) in applied mathematics or an AI-related field. A strong mathematical background is required.
More details: https://cran-simul.github.io/assets/jobs/sujetThese_LENTILLE_2025.pdf <https://cran-simul.github.io/assets/jobs/sujetThese_LENTILLE_2025.pdf>
How to Apply

Interested candidates should send their application to David Brie, Ricardo Borsoi, and Konstantin Usevich (david.brie at univ-lorraine.fr <mailto:david.brie at univ-lorraine.fr>, ricardo.borsoi at univ-lorraine.fr <mailto:ricardo.borsoi at univ-lorraine.fr>, konstantin.usevich at univ-lorraine.fr <mailto:konstantin.usevich at univ-lorraine.fr>) with:

An academic CV
A short explanation of research interests and motivation for this position
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20250327/5cc5c6a3/attachment.html>