BaiqiL/NaturalBench download history

BaiqiL/NaturalBench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,289 times (299 in the last 7 days), and 20,056 times in total. It ranks #15,991 among datasets by monthly downloads.

(NeurIPS24) NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples Baiqi Li1*, Zhiqiu Lin1*, Wenxuan Peng1*, Jean de Dieu Nyandwi1*, Daniel Jiang1, Zixian Ma2, Simran Khanuja1, Ranjay Krishna2†, Graham Neubig1†, Deva Ramanan1†. 1Carnegie Mellon University, 2U

Open BaiqiL/NaturalBench on Hugging Face

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