We present Phenaki, a model capable of realistic video synthesis given a sequence of
textual prompts. Generating videos from text is particularly challenging due to the …

Generating temporally coherent high fidelity video is an important milestone in generative
modeling research. We make progress towards this milestone by proposing a diffusion …

Video prediction is a challenging task. The quality of video frames from current state-of-the-
art (SOTA) generative models tends to be poor and generalization beyond the training data …

We present a framework for video modeling based on denoising diffusion probabilistic
models that produces long-duration video completions in a variety of realistic environments …

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 …

Denoising diffusion probabilistic models are a promising new class of generative models
that mark a milestone in high-quality image generation. This paper showcases their ability to …

Autonomous driving promises transformative improvements to transportation, but building
systems capable of safely navigating the unstructured complexity of real-world scenarios …

The ability to predict future visual observations conditioned on past observations and motor
commands can enable embodied agents to plan solutions to a variety of tasks in complex …

Recent unsupervised pre-training methods have shown to be effective on language and
vision domains by learning useful representations for multiple downstream tasks. In this …

We introduce the first work to explore web-scale diffusion models for robotics. DALL-E-Bot
enables a robot to rearrange objects in a scene, by first inferring a text description of those …