mlsanityData to 14 Oct 2026

Multilingual Vision-Language Models, A Survey

arXiv 2509.22123 ↗First posted 26 Sep 2025cs.CLcited by 1

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language neutrality (consistent cross-lingual representations) and cultural awareness (adaptation to cultural contexts). Current training methods favor neutrality through contrastive learning, while cultural awareness depends on diverse data. Two-thirds of evaluation benchmarks use translation-based approaches prioritizing semantic consistency, though recent work incorporates culturally grounded content. We find discrepancies in cross-lingual capabilities and gaps between training objectives and evaluation goals.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 132 of its 182 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

132 of 182 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs21 May
  2. 2024Maya: An Instruction Finetuned Multilingual Multimodal Model10 Dec
  3. 2024All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages25 Nov
  4. 2024WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines16 Oct
  5. 2024Benchmarking Vision Language Models for Cultural Understanding15 Jul
  6. 2024PaliGemma: A versatile 3B VLM for transfer10 Jul
  7. 2024Vision-Language Models under Cultural and Inclusive Considerations8 Jul
  8. 2024M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks4 Jul
  9. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark10 Jun
  10. 2024EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models15 Mar
  11. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct
  12. 2023mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs13 Jul
5 more
  1. 2023Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages29 Jun
  2. 2022Improving the Cross-Lingual Generalisation in Visual Question Answering7 Sep
  3. 2022Write and Paint: Generative Vision-Language Models are Unified Modal Learners15 Jun
  4. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts3 Nov
  5. 2021SimVLM: Simple Visual Language Model Pretraining with Weak Supervision24 Aug

Other references · 115

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  5. 2020Language Models are Few-Shot Learnerscited by 32,419
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  7. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  8. 2022Training language models to follow instructions with human feedbackcited by 15,971
  9. 2024The Llama 3 Herd of Modelscited by 14,715
  10. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  11. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  12. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
38 more
  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  9. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  10. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  11. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  12. 2015VQA: Visual Question Answeringcited by 2,506
  13. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  14. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  15. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  16. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  17. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  18. 2025Gemma 3 Technical Reportcited by 1,824
  19. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  20. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  21. 2019Root Mean Square Layer Normalizationcited by 1,480
  22. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  23. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  24. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  25. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  26. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  27. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,188
  28. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  29. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 968
  30. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  31. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  32. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 915
  33. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 856
  34. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  35. 2016Language Modeling with Gated Convolutional Networkscited by 702
  36. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
  37. 2021ImageNet-21K Pretraining for the Massescited by 613
  38. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 556

50 most cited of 115 All 115 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025jina-vlm: Small Multilingual Vision Language Modelcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
  2. 2025TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
  3. 2024See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
  4. 2024From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models
  5. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  6. 2025Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
  7. 2025Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation
  8. 2025Behind Maya: Building a Multilingual Vision Language Model