視覺文件檢索邁向多語言：Hugging Face 推出 VDR-2B-multilingual 模型
Original: Visual Document Retrieval Goes Multilingual
Hugging Face has recently released a new Visual Document Retrieval (VDR) model — **VDR-2B-multilingual**. This technology marks a formal…
Hugging Face 發表全新的 VDR-2B-multilingual 模型，專為視覺文件檢索（VDR）設計。傳統檢索依賴繁瑣的 OCR 步驟，而該模型能直接將文件頁面視為圖像進行向量化，保留排版、圖表與插圖資訊。本次更新重點在於擴展至多語言支持（包含中英日韓等），大幅提升跨國企業與多語系文檔的檢索效率與準確度。
Hugging Face has recently released a new Visual Document Retrieval (VDR) model — **VDR-2B-multilingual**. This technology marks a formal transition in document retrieval from the traditional "text-based" approach to a "multimodal vision-based" one, with full support for multilingual environments.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.