# jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

arXiv: https://arxiv.org/abs/2412.08802 · HTML: https://mlsanity.com/paper/2412.08802/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://mlsanity.com/paper/2407.19669/) (2024)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)

## Built on by (most cited first, 30 of 37)

- [mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data](https://mlsanity.com/paper/2502.08468/) (2025)
- [MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation](https://mlsanity.com/paper/2502.04176/) (2025)
- [LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts](https://mlsanity.com/paper/2505.13928/) (2025)
- [MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval](https://mlsanity.com/paper/2510.09510/) (2025)
- [How far can we go with ImageNet for Text-to-Image generation?](https://mlsanity.com/paper/2502.21318/) (2025)
- [PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback](https://mlsanity.com/paper/2602.12127/) (2026)
- [One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image](https://mlsanity.com/paper/2504.02132/) (2025)
- [One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution](https://mlsanity.com/paper/2511.17138/) (2025)
- [jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers](https://mlsanity.com/paper/2605.08384/) (2026)
- [Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratings](https://mlsanity.com/paper/2503.06980/) (2025)
- [Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs](https://mlsanity.com/paper/2505.15075/) (2025)
- [On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey](https://mlsanity.com/paper/2507.20783/) (2025)
- [Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch](https://mlsanity.com/paper/2510.17858/) (2025)
- [Enhancing 3D Semantic Scene Completion with a Refinement Module](https://mlsanity.com/paper/2512.18363/) (2025)
- [MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents](https://mlsanity.com/paper/2603.05697/) (2026)
- [WebNavigator: Global Web Navigation via Interaction Graph Retrieval](https://mlsanity.com/paper/2603.20366/) (2026)
- [Towards Text-Image Interleaved Retrieval](https://mlsanity.com/paper/2502.12799/) (2025)
- [Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights](https://mlsanity.com/paper/2505.10043/) (2025)
- [UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval](https://mlsanity.com/paper/2508.04136/) (2025)
- [Illuminating Visual Identity in Universal Multimodal Embeddings](https://mlsanity.com/paper/2608.01794/) (2026)
- [MOHPER: Multi-objective Hyperparameter Optimization Framework for E-commerce Retrieval System](https://mlsanity.com/paper/2503.05227/) (2025)
- [PRISM: Product Retrieval In Shopping Carts using Hybrid Matching](https://mlsanity.com/paper/2509.14985/) (2025)
- [Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text](https://mlsanity.com/paper/2601.10096/) (2026)
- [RGB-Pointmap Pretraining for Unified 3D Scene Understanding](https://mlsanity.com/paper/2604.02546/) (2026)
- [HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2604.07220/) (2026)
- [MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset](https://mlsanity.com/paper/2605.21272/) (2026)
- [Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search](https://mlsanity.com/paper/2605.30917/) (2026)
- [One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling](https://mlsanity.com/paper/2606.08126/) (2026)
- [Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity](https://mlsanity.com/paper/2606.25343/) (2026)
- [ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP](https://mlsanity.com/paper/2606.26794/) (2026)

## Abstract (arXiv)

Contrastive Language-Image Pretraining (CLIP) has been widely used for crossmodal information retrieval and multimodal understanding tasks. However, CLIP models are mainly optimized for crossmodal vision-language tasks and underperform in single-mode text tasks. Moreover, these models are often trained on English datasets and therefore lack multilingual understanding. Additionally, from a visual understanding perspective, previous CLIP-based models exhibit insufficient understanding of visually rich documents. In this work, we propose jina-clip-v2, a contrastive vision-language model trained on text pairs, triplets and image-text pairs via a multi-task and multi-stage contrastive learning paradigm in order to support both text-only and crossmodal tasks. We employ a multilingual text encoder and expand the training dataset to include multilingual texts from 29 non-English languages, including Hindi, Chinese, German, French, and others, as well as images of visually rich documents. We evaluate the model's performance and show that jina-clip-v2 achieves notable improvements over state-of-the-art CLIP-based models in zero-shot text-only retrieval, semantic textual similarity, and crossmodal retrieval tasks in both English and multilingual settings. jina-clip-v2 also provides for flexibility in embedding dimensionality, enabling users to select the granularity of the representations. jina-clip-v2 is publicly available at https://huggingface.co/jinaai/jina-clip-v2.