Tevatron 2.0: Unified Document Retrieval Toolkit Across Scale, Language, And Modality

Abstract

Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created new opportunities for multimodal retrieval. In response, we have updated the Tevatron toolkit, introducing a unified pipeline that enables researchers to explore retriever models at different scales, across multiple languages, and with various modalities. This demo paper highlights the toolkit's key features, bridging academia and industry by supporting efficient training, inference, and evaluation of neural retrievers. We showcase a unified dense retriever achieving strong multilingual and multimodal effectiveness, and conduct a cross-modality zero-shot study to demonstrate its research potential. Alongside, we release OmniEmbed, to the best of our knowledge, the first embedding model that unifies text, image document, video, and audio retrieval, ser

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyma2025tevatron

Related papers

• Tevatron: An Efficient And Flexible Toolkit For Dense Retrieval (2022)9.03
• Magmar Shared Task System Description: Video Retrieval With Omniembed (2025)0.00
• Recurrence Meets Transformers For Universal Multimodal Retrieval (2025)2.41
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• Universal Vision-language Dense Retrieval: Learning A Unified Representation Space For Multi-modal Retrieval (2022)3.45
• Unifier: A Unified Retriever For Large-scale Retrieval (2022)7.50
• M3DR: Towards Universal Multilingual Multimodal Document Retrieval (2025)0.00
• Mm-embed: Universal Multimodal Retrieval With Multimodal Llms (2024)0.00