Randall Balestriero

RandallBalestriero

·

https://randallbalestriero.github.io/

AI & ML interests

Practical Theory

Recent Activity

upvoted a paper 3 days ago

Proving and Improving the Platonic Representation Hypothesis with JEPAs

authored a paper 3 days ago

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning

authored a paper 3 days ago

GrokAlign: Geometric Characterisation and Acceleration of Grokking

View all activity

Organizations

RandallBalestriero 's models

None public yet