arXiv Computer Vision
KoViDoRe: Korean Visual Document Retrieval
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 24
Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs
arXiv:2607. 20517v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) over heterogeneous PDF collections remains challenging due to multimodal content, domain-specific terminology, and the need for multi-hop reasoning across dispersed evidence.
Hugging Face Trending Papers
Aug 2
VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval
Visual document retrieval has recently become increasingly important in applications such as enterprise search, scientific literature discovery, and retrieval-augmented generation. These applications depend on efficiently identifying query-relevant pages across large collections of visually rich documents.
arXiv Computation and Language
Aug 25
L\"etzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents
arXiv:2608.21714v1 Announce Type: new Abstract: Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-l...
arXiv AI
Jun 4
Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)
arXiv:2606. 04240v1 Announce Type: cross Abstract: Retrieval over visually-rich documents, pages that interleave text with figures, tables, and charts, is essential for multimodal retrieval-augmented generation, yet most retrievers still discard the visual channel.
arXiv AI
Sep 2
MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval
MIDR (Multimodal Indexing for Document Retrieval) is a training‑free framework that enriches document indexes by converting rendered pages into verified textual fields with a multimodal LLM, then indexing those fields with BM25F and optionally fusing with dense retrieval. By shifting multimodal reasoning to index time, MIDR enables text‑centric serving while retaining multimodal evidence, achieving a 23.0% relative gain over BM25 on ViDoRe V3 and outperforming ColQwen2.5 on several domains with significantly smaller index memory and lower query latency.
arXiv Computation and Language
Aug 27
Recurrence Meets Transformers for Universal Multimodal Retrieval
The paper introduces ReT-2, a unified retrieval model that handles multimodal queries containing both images and text and searches across multimodal document collections. It employs a recurrent Transformer architecture with LSTM-inspired gating to integrate information across layers and modalities, capturing fine-grained visual and textual details. Evaluations on M2KR and M-BEIR benchmarks show state‑of‑the‑art performance, faster inference, and lower memory usage, and the model also boosts downstream tasks in retrieval‑augmented generation pipelines.