longlian/VPBench download history

longlian/VPBench is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 156 times (55 in the last 7 days), and 10,736 times in total. It ranks #81,775 among datasets by monthly downloads.

VPBench: Visually Prompted Benchmarks Are Surprisingly Fragile Project Page | Paper | GitHub VPBench is a benchmark designed to evaluate the robustness of Vision-Language Models (VLMs) to visual prompting. As detailed in the paper "Visually Prompted Benchmarks Are Surprisingly Fragile", e

Open longlian/VPBench on Hugging Face

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