Text-to-image synthesis has recently seen significant progress thanks to large pretrained
language models, large-scale training data, and the introduction of scalable model families …

We introduce a new paradigm for generative modeling built on Continuous Normalizing
Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present …

Background Medicine is inherently multimodal, requiring the simultaneous interpretation
and integration of insights between many data modalities spanning text, imaging, genomics …

Model-based reinforcement learning methods often use learning only for the purpose of
estimating an approximate dynamics model, offloading the rest of the decision-making work …

We present DreamBooth3D, an approach to personalize text-to-3D generative models from
as few as 3-6 casually captured images of a subject. Our approach combines recent …

We present a diffusion-based model for 3D-aware generative novel view synthesis from as
few as a single input image. Our model samples from the distribution of possible renderings …

We present Stable Video Diffusion-a latent video diffusion model for high-resolution, state-of-
the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained …

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

Despite the stunning ability to generate high-quality images by recent text-to-image models,
current approaches often struggle to effectively compose objects with different attributes and …

Three billion years of evolution has produced a tremendous diversity of protein molecules,
but the full potential of proteins is likely to be much greater. Accessing this potential has …