Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and compute-heavy. The tutorial offers an overview of this emerging research area for multilingual multimodality across text, speech, and vision under limited data/compute budgets, synthesizing foundations, recent multilingual models (PALO, Maya), speech-text LLMs. We cover low-cost data creation/curation; adapter stacks for tri-modal alignment; culture-aware evaluation beyond English and hands on resources for fine-tuning a compact multilingual VLM and wiring a speech->text->LLM pipeline. The content will be delivered as an interactive half-day tutorial, designed for researchers and practitioners working on multilingual, multimodal AI in low-resource language settings.
@article{arxiv.2605.17152,
title = {Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages},
author = {Firoj Alam and Shammur Absar Chowdhury and Enamul Hoque Prince},
journal= {arXiv preprint arXiv:2605.17152},
year = {2026}
}
Comments
Multimodal Foundation Models, Large Language Models, Native, Multilingual, Language Diversity, Low-resources-language