We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer
ViT for images of different complexity. A-ViT achieves this by automatically reducing the …

Pruning is an effective way to reduce the huge inference cost of Transformer models.
However, prior work on pruning Transformers requires retraining the models. This can add …

Recent work in natural language processing (NLP) has yielded appealing results from
scaling model parameters and training data; however, using only scale to improve …

Recent advances in state-of-the-art DNN architecture design have been moving toward
Transformer models. These models achieve superior accuracy across a wide range of …

In recent years, larger and deeper models are springing up and continuously pushing state-
of-the-art (SOTA) results across various fields like natural language processing (NLP) and …

Pre-trained Transformer-based models have achieved state-of-the-art performance for
various Natural Language Processing (NLP) tasks. However, these models often have …

The Transformer has been an indispensable staple in deep learning. However, for real-life
applications, it is very challenging to deploy efficient Transformers due to the immense …

Transformer is a deep learning language model widely used for natural language
processing (NLP) services in datacenters. Among transformer models, Generative …

Large language models (LLMs) have revolutionized natural language processing with their
exceptional capabilities. However, deploying LLMs on resource-constrained edge devices …

Attention-based neural networks have become pervasive in many AI tasks. Despite their
excellent algorithmic performance, the use of the attention mechanism and feedforward …