microsoft/VISION_LANGUAGE download history
microsoft/VISION_LANGUAGE is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 416 times (151 in the last 7 days), and 9,513 times in total. It ranks #38,227 among datasets by monthly downloads.
A key question for understanding multimodal vs. language capabilities of models is what is the relative strength of the spatial reasoning and understanding in each modality, as spatial understanding is expected to be a strength for multimodality? To test this we created a procedurally generatable, s