We release Code Llama, a family of large language models for code based ...
Recent work has shown that it is possible to resynthesize high-quality s...
We tackle the task of conditional music generation. We introduce MusicGe...
In recent years, image generation has shown a great leap in performance,...
Speech language models (SpeechLMs) process and generate acoustic data on...
Backpropagation, which uses the chain rule, is the de-facto standard
alg...
Generalization bounds which assess the difference between the true risk ...
Self-supervised representations have been extensively studied for
discri...
Contemporary predictive models are hard to interpret as their deep nets
...
Recent innovations in self-supervised representation learning have led t...
Self-supervised pre-trained features have consistently delivered state-o...
Large speech emotion recognition datasets are hard to obtain, and small
...
The success of deep neural nets heavily relies on their ability to encod...
Machine learning advances in the last decade have relied significantly o...
Deep learning algorithms have shown promising results in visual question...
Many recent datasets contain a variety of different data modalities, for...