# Maya: An Instruction Finetuned Multilingual Multimodal Model

arXiv: https://arxiv.org/abs/2412.07112 · HTML: https://mlsanity.com/paper/2412.07112/

## Key facts

- Cited by 15 papers 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.
- First posted on arXiv 10 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Built on by (most cited first, 15 of 15)

- [Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia](https://mlsanity.com/paper/2503.07920/) (2025)
- [AIN: The Arabic INclusive Large Multimodal Model](https://mlsanity.com/paper/2502.00094/) (2025)
- [IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs](https://mlsanity.com/paper/2511.04727/) (2025)
- [JEEM: Vision-Language Understanding in Four Arabic Dialects](https://mlsanity.com/paper/2503.21910/) (2025)
- [OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA](https://mlsanity.com/paper/2510.06371/) (2025)
- [CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset](https://mlsanity.com/paper/2507.22752/) (2025)
- [Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model](https://mlsanity.com/paper/2501.05122/) (2025)
- [NeoBabel: A Multilingual Open Tower for Visual Generation](https://mlsanity.com/paper/2507.06137/) (2025)
- [Anthropogenic Regional Adaptation in Multimodal Vision-Language Model](https://mlsanity.com/paper/2604.11490/) (2026)
- [Multilingual Vision-Language Models, A Survey](https://mlsanity.com/paper/2509.22123/) (2025)
- [M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG](https://mlsanity.com/paper/2512.05959/) (2025)
- [Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models](https://mlsanity.com/paper/2512.14926/) (2025)
- [Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text](https://mlsanity.com/paper/2601.10096/) (2026)
- [Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages](https://mlsanity.com/paper/2605.17152/) (2026)
- [Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models](https://mlsanity.com/paper/2606.03793/) (2026)

## 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.