IVC-liuyuan/training_m3diff download history

IVC-liuyuan/training_m3diff is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 9 times (3 in the last 7 days), and 64 times in total. It ranks #601,102 among datasets by monthly downloads.

M³Diff Instruction-Tuning Data This repository contains the instruction-tuning annotations used to train M³Diff, the model introduced in OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning (ICCV 2025). The dataset contains 896,015 question-answer records f

Open IVC-liuyuan/training_m3diff on Hugging Face

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