Here are some of my recent projects:
Imagen and Imagen Video: High fidelity text-to-image and text-to-video synthesis with diffusion models.
3DiM: Image-to-3D generation with diffusion models.
Palette: Image-to-image translation with diffusion models.
WaveGrad: Efficient audio generation with diffusion models.
SimCLR: Simple and effective contrastive learning of visual representations without labels.
My work focuses on generative models.