mlsanityData to 7 Oct 2026

Behind Maya: Building a Multilingual Vision Language Model

arXiv 2505.08910 ↗First posted 13 May 2025cs.CV cs.CLcited by 3

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

Abstract (arXiv)

In recent times, we have seen a rapid development of large Vision-Language Models (VLMs). They have shown impressive results on academic benchmarks, primarily in widely spoken languages but lack performance on low-resource languages and varied cultural contexts. To address these limitations, we introduce Maya, an open-source Multilingual VLM. Our contributions are: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; and 2) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 28 of its 37 references that are in the map. First posted on arXiv 13 May 2025.

Builds on

28 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Why do LLaVA Vision-Language Models Reply to Images in English?2 Jul
  2. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark10 Jun
  3. 2023Kosmos-2: Grounding Multimodal Large Language Models to the World26 Jun
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learning29 Apr

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  10. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  11. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  12. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
12 more
  1. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  2. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  3. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  4. 2024LoRA+: Efficient Low Rank Adaptation of Large Modelscited by 365
  5. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  6. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  7. 2024MM1: Methods, Analysis & Insights from Multimodal LLM Pre-trainingcited by 230
  8. 2024Aya 23: Open Weight Releases to Further Multilingual Progresscited by 121
  9. 2023Kosmos-G: Generating Images in Context with Multimodal Large Language Modelscited by 105
  10. 2022Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Datasetcited by 100
  11. 2024Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languagescited by 63
  12. 2024PALO: A Polyglot Large Multimodal Model for 5B Peoplecited by 34

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMscited by 7
  2. 2025NeoBabel: A Multilingual Open Tower for Visual Generationcited by 2
  3. 2025Seeing Straight: Document Orientation Detection for Efficient OCRcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Maya: An Instruction Finetuned Multilingual Multimodal Model
  2. 2024Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models
  3. 2025Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
  4. 2024An Introduction to Vision-Language Modeling
  5. 2026"Inctelegi Romanecste?'' A Recipe for Romanian Vision-Language Models
  6. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  7. 2026Multilingual Training and Evaluation Resources for Vision-Language Models
  8. 2024Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions