aimagelab/ReT2-M2KR-ColBERT-CLIP-ViT-L

Model Card: ReT-2

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

This model features a visual backbone based on openai/clip-vit-large-patch14 and a textual backbone based on colbert-ir/colbertv2.0.
The backbones have been fine-tuned on the M2KR dataset.

Model Sources

• Repository: https://github.com/aimagelab/ReT-2
• Paper: Recurrence Meets Transformers for Universal Multimodal Retrieval

Training Data

aimagelab/ReT-M2KR

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}
}