ChartMuseum is a chart question answering benchmark designed to evaluate reasoning capabilities of large vision-language models (LVLMs) over real-world chart images. The benchmark consists of 1162 ...

Abstract: Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models ...

Abstract: Visual target navigation is a critical capability for autonomous robots operating in unknown environments, particularly in human-robot interaction scenarios. While classical and ...

A Nigerian Visual Artist, Yele Akin-Johnson is at the forefront of global digital culture by re-imagining African visual language in a global digital economy. Akin-Johnson is working at the porous ...

Keeping a visual journal can turn everyday moments into a creative practice and a clearer mind 🖊️📓. It captures feelings and ideas with color, shape, and lines—sometimes louder than words. Start ...

In the field of cognitive neuroscience, understanding how humans process and integrate information from different sensory modalities is a crucial topic. Attention mechanisms play a vital role in this ...