Yuezhangjoslin/spatialuncertain download history

Yuezhangjoslin/spatialuncertain is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 828 times (136 in the last 7 days), and 3,707 times in total. It ranks #22,254 among datasets by monthly downloads.

SpatialUncertain A controlled 3D benchmark evaluating whether Vision-Language Models (VLMs) know when not to answer spatial reasoning questions under occlusion and perspective ambiguity. Companion to the paper Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (an

Open Yuezhangjoslin/spatialuncertain on Hugging Face

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