-
Analyzing Llama-3 weights via RMT
Using random matrix theory to analyze Llama-3.2 weights
-
Implicit gradients and Dirichlet uncertainty
-
Turning your diffusion model into a classifier
A simple implementation on 2D points
-
Road to modern SSL Part 1, Ensembles, crops and augmentations
Learning modern SSL, one piece at a time
-
An introduction to Slot Attention
Going over the basics of Slot Attention, and covering some recent literature in the area