Picture for Austin Wen

Austin Wen

Accelerating the Low-Rank Decomposed Models

Add code
Jul 24, 2024
Viaarxiv icon

Is 3D Convolution with 5D Tensors Really Necessary for Video Analysis?

Add code
Jul 23, 2024
Viaarxiv icon

SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection

Add code
Jan 27, 2024
Viaarxiv icon

SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling

Add code
Nov 25, 2023
Viaarxiv icon

GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values

Add code
Nov 06, 2023
Viaarxiv icon

Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition

Add code
Sep 21, 2023
Viaarxiv icon