Abstract: Multimodal vision-language models (VLMs) continue to achieve ever-improving scores on chart understanding benchmarks. Yet, we find that this progress does not fully capture the breadth of ...

The encoding shelves are grouped into positional channels \(e.g. x, y\), mark channels \(e.g. size, color, shape, detail, text\), and facet channels \(e.g. row ...

Researchers today have access to an unprecedented amount of data. The challenge is to benefit from this abundance without being overwhelmed. Data visualization for efficient exploration and effective ...

When working with high-dimensional data, it may be tempting to choose a three-dimensional (3D) spatial visualization over a two-dimensional (2D) 'flat' representation because it allows us an ...