Randall Balestriero

A new method enhances positive sample generation in self-supervised learning.

Examining grokking in deep learning and its implications for performance.

This study examines the challenges of reconstruction learning in machine learning for perception tasks.

Streamlined approaches to self-supervised learning enhance performance and accessibility.

A new framework for evaluating vision-language models effectively.

A look at deep learning models and their geometric properties.

Linking geographic entities in historical maps using advanced techniques.