Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

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 cost of vision-and-language pre-training has become increasingly prohibitive due to
end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and …

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of
training on large amounts of noisy image-text data, without relying on expensive accurate …

We launch EVA, a vision-centric foundation model to explore the limits of visual
representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained …

We present ImageBind, an approach to learn a joint embedding across six different
modalities-images, text, audio, depth, thermal, and IMU data. We show that all combinations …

Abstract We present the Pathways [1] Autoregressive Text-to-Image (Parti) model, which
generates high-fidelity photorealistic images and supports content-rich synthesis involving …

The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

We present Imagen, a text-to-image diffusion model with an unprecedented degree of
photorealism and a deep level of language understanding. Imagen builds on the power of …

Scaling up neural networks has led to remarkable performance across a wide range of
tasks. Moreover, performance often follows reliable scaling laws as a function of training set …