Annonce


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

30 Novembre -0001


Catégorie : Postes Doctorant ;


The SiMul team (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

How to Apply

Interested candidates should send their application to David Brie, Ricardo Borsoi, and Konstantin Usevich (david.brie@univ-lorraine.frricardo.borsoi@univ-lorraine.frkonstantin.usevich@univ-lorraine.fr) with:

  • An academic CV
  • A short explanation of research interests and motivation for this position

Les commentaires sont clos.