aimagelab/ReT-M2KR
Preview
•
Updated
•
301
ReT
Models and data for ReT: Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval [CVPR 2025]
-
-
aimagelab/ReT-CLIP-ViT-L-14
Visual Document Retrieval • 0.5B • Updated • 91 -
aimagelab/ReT-OpenCLIP-ViT-H-14
Visual Document Retrieval • 1B • Updated • 3 -
aimagelab/ReT-OpenCLIP-ViT-G-14
Visual Document Retrieval • 3B • Updated • 3 • 1 -
Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
Paper • 2503.01980 • Published