This monograph surveys vision-language pre-training (VLP) methods for multimodal
intelligence that have been developed in the last few years. We group these approaches …

The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

Is vision good enough for language? Recent advancements in multimodal models primarily
stem from the powerful reasoning abilities of large language models (LLMs). However the …

The recent wave of large-scale text-to-image diffusion models has dramatically increased
our text-based image generation abilities. These models can generate realistic images for a …

In the last year alone, a surge of new benchmarks to measure $\textit {compositional} $
understanding of vision-language models have permeated the machine learning ecosystem …

Despite the success of large vision and language models (VLMs) in many downstream
applications, it is unclear how well they encode the compositional relationships between …

The stunning qualitative improvement of text-to-image models has led to their widespread
attention and adoption. However, we lack a comprehensive quantitative understanding of …

Large-scale diffusion models have achieved state-of-the-art results on text-to-image
synthesis (T2I) tasks. Despite their ability to generate high-quality yet creative images, we …

Understanding and reasoning about spatial relationships is crucial for Visual Question
Answering (VQA) and robotics. Vision Language Models (VLMs) have shown impressive …

A fundamental characteristic common to both human vision and natural language is their
compositional nature. Yet, despite the performance gains contributed by large vision and …