Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval
Paper
• 2602.03992 • Published
• 1
Vision-Language Retrieval Papers
-
-
M3DR: Towards Universal Multilingual Multimodal Document Retrieval
Paper • 2512.03514 • Published • 9 -
ModernVBERT: Towards Smaller Visual Document Retrievers
Paper • 2510.01149 • Published • 33 -
Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model
Paper • 2507.05513 • Published • 1 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 51 -
Unifying Multimodal Retrieval via Document Screenshot Embedding
Paper • 2406.11251 • Published • 11