UCSC-VLAA/ViLBench download history

UCSC-VLAA/ViLBench is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 53 times (22 in the last 7 days), and 1,081 times in total. It ranks #177,952 among datasets by monthly downloads.

Benchmark Data for ViLBench: A Suite for Vision-Language Process Reward Modeling arXiv | Project Page There are 600 data collected from 5 existing vision-language tasks

Open UCSC-VLAA/ViLBench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.