aimagelab/ReT2-M2KR-CLIP-ViT-B
Visual Document Retrieval • 0.2B • Updated • 10 • 1
ReT-2
Models and data for the paper "Recurrence Meets Transformers for Universal Multimodal Retrieval" (arXiv 2509.08897)
-
-
aimagelab/ReT2-M2KR-CLIP-ViT-L
Visual Document Retrieval • 0.4B • Updated • 1 -
aimagelab/ReT2-M2KR-SigLIP2-ViT-L
Visual Document Retrieval • 0.9B • Updated • 2 • 1 -
aimagelab/ReT2-M2KR-ColBERT-CLIP-ViT-L
Visual Document Retrieval • 0.4B • Updated • 5 -
aimagelab/ReT2-M2KR-ColBERT-SigLIP2-ViT-L
Visual Document Retrieval • 0.4B • Updated • 4 -
aimagelab/ReT2-M2KR-OpenCLIP-ViT-H
Visual Document Retrieval • 1B • Updated • 5 -
aimagelab/ReT2-MBEIR-CLIP-ViT-L
Visual Document Retrieval • 0.4B • Updated • 1 -
aimagelab/ReT2-MBEIR-SigLIP2-ViT-L
Visual Document Retrieval • 0.9B • Updated • 8 • 1 -
aimagelab/ReT-M2KR
Preview • Updated • 740 • 2 -
Recurrence Meets Transformers for Universal Multimodal Retrieval
Paper • 2509.08897 • Published