RhapsodyAI/MiniCPM-V-Embedding-preview
Feature Extraction
•
Updated
•
500
•
43
Awesome Visual Embedding
-
-
vidore/colidefics
Updated • 2 -
vidore/colpali
Updated • 33k • 370 -
Unifying Multimodal Retrieval via Document Screenshot Embedding
Paper • 2406.11251 • Published • 9 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 41 -
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
Paper • 2405.20204 • Published • 32 -
Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
Paper • 2406.02265 • Published • 6 -
Synthetic Multimodal Question Generation
Paper • 2407.02233 • Published • 1 -
RankCLIP: Ranking-Consistent Language-Image Pretraining
Paper • 2404.09387 • Published