Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design
computer agents with intelligent capabilities such as understanding, reasoning, and learning …

We investigate the potential of learning visual representations using synthetic images
generated by text-to-image models. This is a natural question in the light of the excellent …

Deep learning has emerged as a powerful tool in various domains, revolutionising machine
learning research. However, one persistent challenge is the scarcity of labelled training …

The success of language Transformers is primarily attributed to the pretext task of masked
language modeling (MLM), where texts are first tokenized into semantically meaningful …

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE),
for self-supervised representation pretraining. We pretrain an encoder by making predictions …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

Visual recognition is recently learned via either supervised learning on human-annotated
image-label data or language-image contrastive learning with webly-crawled image-text …

In recent years, neural architecture-based recommender systems have achieved
tremendous success, but they still fall short of expectation when dealing with highly sparse …

Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …