Termsslug: visual-document-retrieval

Visual Document Retrieval

视觉文档检索

Retrieving relevant pages or snippets directly from document images.

Curated Intelligence

2 items · Page 1/1
Hugging Face BlogT1·Tools
68 pts
Sentence Transformers Adds Multimodal Fine-tuning Support

The Sentence Transformers library now supports training and fine-tuning multimodal embedding and reranker models across text, image, audio, and video. Using Qwen3-VL-Embedding as an example for Visual Document Retrieval, this update lowers the barrier to building customized multimodal RAG systems.

Hugging Face BlogT1·Open Source
68 pts
LlamaIndex Releases Multilingual Visual Document Retrieval Model

LlamaIndex has released and open-sourced vdr-2b-multi-v1, currently the best-performing multilingual embedding model for visual document retrieval. Trained on a newly released dataset of 500k high-quality samples—the largest open-source multilingual synthetic dataset for this task—it significantly enhances cross-language document understanding and retrieval capabilities.