Name: MLn Club (ML Reading Group) #2: LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
Start: 2026-05-25T19:00:00.000-04:00
End: 2026-05-25T21:00:00.000-04:00
Location: Pittsburgh, PA

We meet weekly on Sundays in person to talk about ML papers! Optional quiet reading from 7 pm, discussion starts 8 pm. Come and join the discussion! Open to all. Website: https://czhs.github.io/mln/

MLn Reading Club

Week 2: LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

Most self-supervised learning methods work by carefully balancing instability. Remove stop-gradients, momentum encoders, or augmentation tricks, and they collapse. We’ve gotten strong results, but not a clean understanding of 

LeJEPA pushes in the opposite direction: instead of stabilizing training with heuristics, it builds a system where 

The core idea is simple but sharp: learn representations by 

, while designing the objective so that trivial solutions (e.g., constant embeddings) are provably suboptimal. This removes the need for asymmetric updates used in methods like BYOL or contrastive negatives from SimCLR.

Discussion at 20:00, (optional) quiet reading from 19:00.