---
license: apache-2.0
task_categories:
- image-text-to-text
---

This repository contains the data for [LOVA3: Learning to Visual Question Answering, Asking and Assessment](https://huggingface.co/papers/2405.14974). 
LOVA3 is a framework designed to equip MLLMs with the capabilities to answer, ask, and assess questions in the context of images.

Code: https://github.com/showlab/LOVA3

## 🎓 Citation

If you find LOVA3 useful, please cite using this BibTeX:

```bibtex
@inproceedings{
    zhao2024lova,
    title={{LOVA}3: Learning to Visual Question Answering, Asking and Assessment},
    author={Hengyuan Zhao and Pan Zhou and Difei Gao and Zechen Bai and Mike Zheng Shou},
    booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
    year={2024},
    url={https://openreview.net/forum?id=vIOKLMl6wu}
}
```