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 …

Small data are often used in scientific and engineering research due to the presence of
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …

Conventional wisdom holds that autoregressive models for image generation are typically
accompanied by vector-quantized tokens. We observe that while a discrete-valued space …

While generative models produce high-quality images of concepts learned from a large-
scale database, a user often wishes to synthesize instantiations of their own concepts (for …

We introduce a novel sequential modeling approach which enables learning a Large Vision
Model (LVM) without making use of any linguistic data. To do this we define a common …

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 …

Autoencoder is an unsupervised learning model, which can automatically learn data
features from a large number of samples and can act as a dimensionality reduction method …

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

Abstract We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various
video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video …

Diffusion models currently achieve state-of-the-art performance for both conditional and
unconditional image generation. However, so far, image diffusion models do not support …