mlsanityData to 7 Oct 2026

Maya: An Instruction Finetuned Multilingual Multimodal Model

arXiv 2412.07112 ↗First posted 10 Dec 2024cs.CV cs.CLcited by 15

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

Abstract (arXiv)

The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) 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 15 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. First posted on arXiv 10 Dec 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 4.

15 papers.

Sort:

By area:

  1. 2025AIN: The Arabic INclusive Large Multimodal Modelcited by 8
  2. 2025Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asiacited by 8
  3. 2025JEEM: Vision-Language Understanding in Four Arabic Dialectscited by 7
  4. 2025IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMscited by 7
  5. 2025OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QAcited by 5
  6. 2025CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Datasetcited by 4
  7. 2025Centurio: On Drivers of Multilingual Ability of Large Vision-Language Modelcited by 3
  8. 2025NeoBabel: A Multilingual Open Tower for Visual Generationcited by 2
  9. 2026Anthropogenic Regional Adaptation in Multimodal Vision-Language Modelcited by 2
  10. 2025Multilingual Vision-Language Models, A Surveycited by 1
  11. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAGcited by 1
  12. 2025Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Modelscited by 0
3 more
  1. 2026Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Textcited by 0
  2. 2026Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languagescited by 0
  3. 2026Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Behind Maya: Building a Multilingual Vision Language Model
  2. 2024Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models
  3. 2024Why do LLaVA Vision-Language Models Reply to Images in English?
  4. 2024EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models
  5. 2025Rethinking Multilingual Vision-Language Translation: Dataset, Evaluation, and Adaptation
  6. 2026"Inctelegi Romanecste?'' A Recipe for Romanian Vision-Language Models
  7. 2026Multilingual Training and Evaluation Resources for Vision-Language Models
  8. 2024M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks