activity
20232025
most citedHow JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks

2 citations · 4 across the 8 of their papers we have counts for

collaborators
Showing 2023Show all

2 papers · 1 filter

cs.LG2023★ 1 cited

LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures

Vimal Thilak, Chen Huang, Omid Saremi +5

Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent…

cs.LG2023

Adaptivity and Modularity for Efficient Generalization Over Task Complexity

Samira Abnar, Omid Saremi, Laurent Dinh +8

Can transformers generalize efficiently on problems that require dealing with examples with different levels of difficulty? We introduce a new task tailored to assess generalizatio…