MMPB
Datasets
All datasets matching “MMPB”MMPB
🌐 Project & Link
Official project page: https://aidaslab.github.io/MMPB/
Hugging Face dataset: 🤗 stackadd/MMPB
Paper (arXiv): “MMPB: It’s Time for Multi-Modal Personalization”
📘 Dataset Card for MMPB: Multi-Modal Personalization Benchmark
MMPB is the first large-scale benchmark designed to evaluate Vision-Language Models (VLMs) on personalization — their ability to understand, remember, and adapt to user-specific multimodal information.
It contains 10,000… See the full description on the dataset page: https://huggingface.co/datasets/snu-aidas/MMPB.MMPB-clean
MMPB-Clean
MMPB-Clean is a cleaned train/test release of the MMPB personalized multimodal benchmark.
It contains visual question answering examples for preference reasoning and identity recognition.
Dataset Structure
data/train.csv.gz: training split.
data/test.csv.gz: test split.
images/: source images referenced by the image_path column.
injection/: profile/injection images referenced by injection_image_1 ... injection_image_5.
The image paths in the CSV files… See the full description on the dataset page: https://huggingface.co/datasets/12123bskbc/MMPB-clean.