Recent years have seen a phenomenal rise in the performance and applications of
transformer neural networks. The family of transformer networks, including Bidirectional …

Large models based on the Transformer architecture play increasingly vital roles in artificial
intelligence, particularly within the realms of natural language processing (NLP) and …

Diffusion models have recently dominated image synthesis and other related generative
tasks. However, the iterative denoising process is expensive in computations at inference …

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …

Abstract Post-training quantization (PTQ), which only requires a tiny dataset for calibration
without end-to-end retraining, is a light and practical model compression technique …

Abstract Vision Transformers (ViTs) have achieved state-of-the-art performance on various
computer vision applications. However, these models have considerable storage and …

The complicated architecture and high training cost of vision transformers urge the
exploration of post-training quantization. However, the heavy-tailed distribution of vision …

The public model zoo containing enormous powerful pretrained model families (eg,
ResNet/DeiT) has reached an unprecedented scope than ever, which significantly …

Quantization scale and bit-width are the most important parameters when considering how
to quantize a neural network. Prior work focuses on optimizing quantization scales in a …

Abstract While Vision Transformers (ViTs) have undoubtedly made impressive strides in
computer vision (CV), their intricate network structures necessitate substantial computation …