While recent work on text-conditional 3D object generation has shown
pro...
Contrastive models like CLIP have been shown to learn robust representat...
Diffusion models have recently been shown to generate high-quality synth...
We show that diffusion models can achieve image sample quality superior ...
Denoising diffusion probabilistic models (DDPM) are a class of generativ...
We identify empirical scaling laws for the cross-entropy loss in four
do...
Recent work has demonstrated substantial gains on many NLP tasks and
ben...
We introduce Jukebox, a model that generates music with singing in the r...
Flow-based generative models (Dinh et al., 2014) are conceptually attrac...
In this paper, we introduce a system called GamePad that can be used to
...
Deep reinforcement learning (RL) methods generally engage in exploratory...
Representation learning seeks to expose certain aspects of observed data...