---
library_name: transformers
license: apache-2.0
datasets:
- aimagelab/ReT-M2KR
base_model:
- openai/clip-vit-large-patch14
pipeline_tag: visual-document-retrieval
---

# Model Card: ReT-2

Official implementation of ReT-2: Recurrence Meets Transformers for Universal Multimodal Retrieval.

This model features visual and textual backbones based on [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14). 
<br>The backbones have been fine-tuned on the M-BEIR dataset. 


### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/aimagelab/ReT-2
- **Paper:** [Recurrence Meets Transformers for Universal Multimodal Retrieval](https://arxiv.org/abs/2509.08897)


### Training Data
[TIGER-Lab/M-BEIR](https://huggingface.co/datasets/TIGER-Lab/M-BEIR)


## Citation
```
@article{caffagni2025recurrencemeetstransformers,
      title={{Recurrence Meets Transformers for Universal Multimodal Retrieval}}, 
      author={Davide Caffagni and Sara Sarto and Marcella Cornia and Lorenzo Baraldi and Rita Cucchiara},
      journal={arXiv preprint arXiv:2509.08897},
      year={2025}
}
```