M3DR: Towards Universal Multilingual Multimodal Document Retrieval

TL;DR

M3DR introduces a multilingual multimodal document retrieval framework that leverages synthetic data and contrastive training to achieve state-of-the-art cross-lingual and cross-modal retrieval across diverse languages and scripts.

Contribution

The paper presents M3DR, a novel framework that generalizes across languages, architectures, and retrieval paradigms, significantly improving multilingual multimodal document retrieval performance.

Findings

Achieves ~150% relative improvements on cross-lingual retrieval tasks.

Demonstrates consistent performance across 22 typologically diverse languages.

Introduces a comprehensive multilingual retrieval benchmark.

Abstract

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual contexts. In this work, we present M3DR (Multilingual Multimodal Document Retrieval), a framework designed to bridge this gap across languages, enabling applicability across diverse linguistic and cultural contexts. M3DR leverages synthetic multilingual document data and generalizes across different vision-language architectures and model sizes, enabling robust cross-lingual and cross-modal alignment. Using contrastive training, our models learn unified representations for text and document images that transfer effectively across languages. We validate this capability on 22 typologically diverse languages, demonstrating consistent performance and adaptability across linguistic and script variations. We further introduce a comprehensive benchmark that captures real-world multilingual scenarios, evaluating models under monolingual, multilingual, and mixed-language settings. M3DR generalizes across both single dense vector and ColBERT-style token-level multi-vector retrieval paradigms. Our models, NetraEmbed and ColNetraEmbed achieve state-of-the-art performance with ~150% relative improvements on cross-lingual retrieval.