Transformers have achieved great success in many artificial intelligence fields, such as
natural language processing, computer vision, and audio processing. Therefore, it is natural …

Green artificial intelligence (AI) is more environmentally friendly and inclusive than
conventional AI, as it not only produces accurate results without increasing the …

Long-term time series forecasting is challenging since prediction accuracy tends to
decrease dramatically with the increasing horizon. Although Transformer-based methods …

Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Abstract We present CSWin Transformer, an efficient and effective Transformer-based
backbone for general-purpose vision tasks. A challenging issue in Transformer design is …

Abstract We present Multiscale Vision Transformers (MViT) for video and image recognition,
by connecting the seminal idea of multiscale feature hierarchies with transformer models …

We show that Transformer encoder architectures can be sped up, with limited accuracy
costs, by replacing the self-attention sublayers with simple linear transformations that" mix" …

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 …

Astounding results from Transformer models on natural language tasks have intrigued the
vision community to study their application to computer vision problems. Among their salient …

In recent advancements in high-fidelity image generation Denoising Diffusion Probabilistic
Models (DDPMs) have emerged as a key player. However their application at high …