Deep learning (DL) is revolutionizing evidence-based decision-making techniques that can
be applied across various sectors. Specifically, it possesses the ability to utilize two or more …

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Inference from large autoregressive models like Transformers is slow-decoding K tokens
takes K serial runs of the model. In this work we introduce speculative decoding-an …

The quadratic computation complexity of self-attention has been a persistent challenge
when applying Transformer models to vision tasks. Linear attention, on the other hand, offers …

This paper presents SimMIM, a simple framework for masked image modeling. We have
simplified recently proposed relevant approaches, without the need for special designs …

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 …

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head
self-attention (MHSA) among them. Complete leverage of these image tokens brings …

Multimodal data collected from the real world are often imperfect due to missing modalities.
Therefore multimodal models that are robust against modal-incomplete data are highly …

Rotated object detection aims to identify and locate objects in images with arbitrary
orientation. In this scenario, the oriented directions of objects vary considerably across …

The performance of video prediction has been greatly boosted by advanced deep neural
networks. However, most of the current methods suffer from large model sizes and require …