Category Archives: External Primers

Any-to-Any Generation via Composable Diffusion

The paper presents Composable Diffusion (CoDi), a novel generative model capable of generating any combination of output modalities, such as language, image, video, or audio, from any combination of input modalities. Unlike existing generative AI systems, CoDi can generate multiple modalities in parallel and its input is not limited to a subset of modalities like text or image.

What is Data Science?

Communications of the ACM March Cover

Data science is emerging fast and a single definition of it has not yet been reached. In this blog, we presented six facets of data science, each highlighting a different perspective of the field. This multifaceted nature of data science may partially explain the difficulties associated with the efforts to define it.