Picture for Matthew Leavitt

Matthew Leavitt

On the special role of class-selective neurons in early training

Add code
May 27, 2023
Viaarxiv icon

Knowledge Distillation for Efficient Sequences of Training Runs

Add code
Mar 11, 2023
Viaarxiv icon

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

Add code
Mar 19, 2021
Figure 1 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Figure 2 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Figure 3 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Figure 4 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Viaarxiv icon