AI RESEARCH
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
arXiv CS.CL
•
ArXi:2605.17152v1 Announce Type: new 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.