neulab/CulturalGround
This repository provides the official resources for EMNLP 2025 Paper Grounding Multilingual Multimodal LLMs With Cultural Knowledge
This project helps researchers and developers improve how large language models understand global cultures. It provides a dataset of 30 million visual question-answering pairs across 42 countries and 39 languages, and a fine-tuned model called CulturalPangea. Users can input images and questions about cultural entities to get more accurate, culturally-aware answers from the model.
No commits in the last 6 months.
Use this if you are building or evaluating multilingual, multimodal AI models and need them to accurately recognize and respond to culturally specific entities from diverse global backgrounds.
Not ideal if your primary focus is on general vision-language tasks without a specific emphasis on diverse cultural understanding.
Stars
12
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/neulab/CulturalGround"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
adambielski/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
Papers, code and datasets about deep learning and multi-modal learning for video analysis
KaiyangZhou/pytorch-vsumm-reinforce
Unsupervised video summarization with deep reinforcement learning (AAAI'18)