# Multimodal Document Retrieval

ColNomic Embed Multimodal 7B is a state-of-the-art multi-vector multimodal embedding model, excelling in visual document retrieval tasks with support for multilingual and unified text-image encoding.

ReT is an innovative method supporting multimodal query and document retrieval, achieving fine-grained retrieval by integrating multi-level representations from visual and textual backbone networks.

ReT is an innovative method supporting multimodal query and document retrieval, achieving fine-grained retrieval by integrating multi-level representations from vision and text backbone networks.

ReT is an innovative method supporting multimodal query and document retrieval, achieving fine-grained retrieval by fusing multi-level representations from vision and text backbone networks.

A multilingual visual retrieval model based on Qwen2.5-VL-3B-Instruct and ColBERT strategy, supporting dynamic input image resolution and multilingual document retrieval.

A multilingual visual retrieval model based on Qwen2.5-VL-3B-Instruct and ColBERT strategy, supporting dynamic input image resolution and generating ColBERT-style multi-vector text and image representations.

A multilingual visual retrieval model based on Qwen2.5-VL-7B-Instruct using the ColBERT strategy, ranked first in the Vidore benchmark

A multilingual visual retriever based on Qwen2.5-VL-3B-Instruct with ColBERT strategy, excelling in Vidore benchmark tests

A visual retrieval model based on Qwen2.5-VL-3B-Instruct and ColBERT strategy, capable of generating multi-vector representations for text and images to enable efficient document retrieval.

A visual retrieval model based on Qwen2-VL-7B-Instruct using ColBERT strategy, focusing on efficient visual feature indexing for documents

A visual retrieval model based on Qwen2-VL-7B-Instruct and ColBERT strategy, supporting multi-vector text and image representation

ColPali is a vision-language model extended from PaliGemma-3B, capable of efficiently indexing documents through visual features and generating ColBERT-style multi-vector representations.

VisRAG is a retrieval-augmented generation (RAG) system based on vision-language models (VLM) that can directly embed documents as images, avoiding information loss caused by traditional text parsing.