mlsanityData to 7 Oct 2026

Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality

arXiv 2505.02466 ↗First posted 5 May 2025cs.IRcited by 30

Not on the map. Why?

Abstract (arXiv)

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, serving as a baseline for future research.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 21.

30 papers.

Sort:

By area:

  1. 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 183
  2. 2026OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesiscited by 32
  3. 2025RaDeR: Reasoning-aware Dense Retrieval Modelscited by 27
  4. 2025Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Modelcited by 24
  5. 2025Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMscited by 17
  6. 2026AgentIR: Reasoning-Aware Retrieval for Deep Research Agentscited by 13
  7. 2026e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddingscited by 12
  8. 2025Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Videocited by 10
  9. 2025SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehensioncited by 8
  10. 2026Multi-Vector Index Compression in Any Modalitycited by 8
  11. 2025Distillation versus Contrastive Learning: How to Train Your Rerankerscited by 6
  12. 2026Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detectioncited by 5
18 more
  1. 2025Hedonic Neurons: A Mechanistic Mapping of Latent Coalitions in Transformer MLPscited by 1
  2. 2025Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generationcited by 1
  3. 2026RoutIR: Fast Serving of Retrieval Pipelines for Retrieval-Augmented Generationcited by 1
  4. 2026RANKVIDEO: Reasoning Reranking for Text-to-Video Retrievalcited by 1
  5. 2026Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coveragecited by 1
  6. 2026Findings of the MAGMaR 2026 Shared Taskcited by 1
  7. 2026MVEB: Massive Video Embedding Benchmarkcited by 1
  8. 2026Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budgetcited by 1
  9. 2026ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrievalcited by 0
  10. 2026MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generationcited by 0
  11. 2026Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerabilitycited by 0
  12. 2026VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corporacited by 0
  13. 2026Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priorscited by 0
  14. 2026Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generationcited by 0
  15. 2026Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embeddingcited by 0
  16. 2026Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankerscited by 0
  17. 2026Omni-Interactive Universal Embeddercited by 0
  18. 2026MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videoscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG
  2. 2025Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
  3. 2025RzenEmbed: Towards Comprehensive Multimodal Retrieval
  4. 2025Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems
  5. 2025DocMMIR: A Framework for Document Multi-modal Information Retrieval
  6. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
  7. 2024MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs
  8. 2025VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding