We study the capabilities of speech processing systems trained simply to...
Text embeddings are useful features in many applications such as semanti...
We show how to derive state-of-the-art unsupervised neural machine
trans...
Recently, there have been breakthroughs in computer vision ("CV") models...
We introduce Codex, a GPT language model fine-tuned on publicly availabl...
State-of-the-art computer vision systems are trained to predict a fixed ...
Text-to-image generation has traditionally focused on finding better mod...
We identify empirical scaling laws for the cross-entropy loss in four
do...
As language models become more powerful, training and evaluation are
inc...
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...
We study empirical scaling laws for language model performance on the
cr...
Reward learning enables the application of reinforcement learning (RL) t...
Large language models have a range of beneficial uses: they can assist i...
Transformers are powerful sequence models, but require time and memory t...
We present Optimal Transport GAN (OT-GAN), a variant of generative
adver...
We explore the properties of byte-level recurrent language models. When ...
We present a variety of new architectural features and training procedur...