KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval
Visual Document Retrieval (VDR) directly matches text queries against document images, preserving visual and structural information that may be lost during text extraction. However, existing VDR models and training resources remain predominantly English-centric, while many high-performing systems rely on massive backbones or storage-intensive multi-vector representations. To address these limitations, we introduce KoVRE: Korean Visual Document Retrieval Embedding, a single-vector retriever for Korean visual documents, alongside a comprehensive training recipe. We train the model on 708,729 Korean and English query-page pairs using positive-aware hard-negative mining and conduct controlled...
| Authors | Yongbin Choi, Gyuho Shim, Youngjoon Jang |
|---|---|
| Primary category | cs.AI |
| Published | 2 August 2026 |
| Last updated at source | 2 August 2026 |
Connected in the knowledge graph
- whybe-choi/kovreModel · cited by
- whybe-choi/en-vdr-hnDataset · cited by
Models and datasets referencing this paper
- whybe-choi/en-vdr-hnDataset
- whybe-choi/kovreModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.