research
∙
11/22/2022
Interpreting Neural Networks through the Polytope Lens
Mechanistic interpretability aims to explain what a neural network has l...
share
research
∙
10/28/2021
Scatterbrain: Unifying Sparse and Low-rank Attention Approximation
Recent advances in efficient Transformers have exploited either the spar...
research
∙
05/12/2019
