mlsanityData to 14 Oct 2026

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval

arXiv 2506.18902 ↗First posted 23 Jun 2025cs.AI cs.CL cs.IRcited by 76

Not on the map. Why?

Abstract (arXiv)

We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-vector and multi-vector embeddings in the late interaction style. The model incorporates task-specific Low-Rank Adaptation (LoRA) adapters to optimize performance across diverse retrieval scenarios, including query-document retrieval, semantic text similarity, and code search. Comprehensive evaluations demonstrate that jina-embeddings-v4 achieves state-of-the-art performance on both single-modal and cross-modal retrieval tasks, with particular strength in processing visually rich content such as tables, charts, diagrams, and mixed-media formats. To facilitate evaluation of this capability, we also introduce Jina-VDR, a novel benchmark specifically designed for visually rich image retrieval.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 36 of its 57 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

36 of 57 references.

References · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  9. 2021Measuring Coding Challenge Competence With APPScited by 902
  10. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 766
  11. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  12. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 654
24 more
  1. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 561
  2. 2019PlotQA: Reasoning over Scientific Plotscited by 321
  3. 2023Improving Text Embeddings with Large Language Modelscited by 303
  4. 2022Matryoshka Representation Learningcited by 282
  5. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 247
  6. 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMscited by 234
  7. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 195
  8. 2024GME: Improving Universal Multimodal Retrieval by Multimodal LLMscited by 170
  9. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  10. 2024E5-V: Universal Embeddings with Multimodal Large Language Modelscited by 126
  11. 2025MMTEB: Massive Multilingual Text Embedding Benchmarkcited by 125
  12. 2024Unifying Multimodal Retrieval via Document Screenshot Embeddingcited by 110
  13. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 104
  14. 2022Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Datasetcited by 100
  15. 2024CoIR: A Comprehensive Benchmark for Code Information Retrieval Modelscited by 60
  16. 2024Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Modelscited by 57
  17. 2024LongEmbed: Extending Embedding Models for Long Context Retrievalcited by 48
  18. 2024Jina CLIP: Your CLIP Model Is Also Your Text Retrievercited by 46
  19. 2024CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Rerankingcited by 37
  20. 2024CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrievalcited by 34
  21. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  22. 2024CAMEL-Bench: A Comprehensive Arabic LMM Benchmarkcited by 17
  23. 2025MIEB: Massive Image Embedding Benchmarkcited by 15
  24. 2023MPMQA: Multimodal Question Answering on Product Manualscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 18; 2026: 58.

76 papers.

Sort:

By area:

  1. 2025Scaling Language-Centric Omnimodal Representation Learningcited by 22
  2. 2026jina-embeddings-v5-text: Task-Targeted Embedding Distillationcited by 22
  3. 2025DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruningcited by 20
  4. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 20
  5. 2025Efficient Code Embeddings from Code Generation Modelscited by 13
  6. 2025Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimizationcited by 12
  7. 2025VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generationcited by 10
  8. 2026Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrievalcited by 10
  9. 2026Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Frameworkcited by 10
  10. 2026Multi-Vector Index Compression in Any Modalitycited by 10
  11. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  12. 2026Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrievalcited by 8
38 more
  1. 2026CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embeddingcited by 7
  2. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 7
  3. 2026CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Codingcited by 7
  4. 2025TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistantcited by 6
  5. 2026Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrievalcited by 6
  6. 2025Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?cited by 5
  7. 2025Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systemscited by 5
  8. 2026ReinPool: Reinforcement Learning Pooling Multi-Vector Embeddings for Retrieval Systemcited by 5
  9. 2026OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understandingcited by 5
  10. 2026Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representationscited by 4
  11. 2026Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generationcited by 4
  12. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  13. 2025M3DR: Towards Universal Multilingual Multimodal Document Retrievalcited by 3
  14. 2026WebNavigator: Global Web Navigation via Interaction Graph Retrievalcited by 3
  15. 2026Retrieval Needs Multivectors: An Exponential Separationcited by 3
  16. 2026MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Modelscited by 3
  17. 2025Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Surveycited by 2
  18. 2026SynthAgent: A Multi-Agent LLM Framework for Realistic Patient Simulation -- A Case Study in Obesity with Mental Health Comorbiditiescited by 2
  19. 2026IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answeringcited by 2
  20. 2026MINER: Mining Multimodal Internal Representation for Efficient Retrievalcited by 2
  21. 2026MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Frameworkcited by 2
  22. 2026MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localizationcited by 2
  23. 2026SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactionscited by 2
  24. 2025HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Taskscited by 1
  25. 2025Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understandingcited by 1
  26. 2025Cross-modal Retrieval Models for Stripped Binary Analysiscited by 1
  27. 2026LEMUR: Learned Multi-Vector Retrievalcited by 1
  28. 2026UrbanGraphEmbeddings: Learning and Evaluating Spatially Grounded Multimodal Embeddings for Urban Sciencecited by 1
  29. 2026Non-Parametric Structural Priors for Geometry Theorem Predictioncited by 1
  30. 2026MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrievalcited by 1
  31. 2026Document-as-Image Representations Fall Short for Scientific Retrievalcited by 1
  32. 2026RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corporacited by 1
  33. 2026Xetrieval: Mechanistically Explaining Dense Retrievalcited by 1
  34. 2026LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinementcited by 1
  35. 2026Illuminating Visual Identity in Universal Multimodal Embeddingscited by 1
  36. 2026EigenLI: Spectral Approximations to Late Interactioncited by 1
  37. 2025Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrievalcited by 0
  38. 2025VLSP 2025 MLQA-TSR Challenge: Vietnamese Multimodal Legal Question Answering on Traffic Sign Regulationcited by 0

50 most cited of 76 All 76 (JSON)