In recent years, foundation models (FMs) such as large language models (LLMs) and latent
diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This …

In this paper we put forward a new approach to music captioning, the task of automatically
generating natural language descriptions for songs. These descriptions are useful both for …

When learning representations from large corpora of language data, the overwhelming
strategy is to interpret that data as a collection of IID samples to be modeled in isolation from …