jankin123/SIF-50K download history

jankin123/SIF-50K is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 63 times (42 in the last 7 days), and 2,026 times in total. It ranks #157,534 among datasets by monthly downloads.

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning This repository contains the SIF-50K dataset, introduced in the paper SIFThinker: Spatially-Aware Image Focus for Visual Reasoning. SIFThinker is a spatially-aware "think-with-images" framework that enables attention correct

Open jankin123/SIF-50K on Hugging Face

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