Tutorial Delivered at LREC-2026

🎉 Tutorial Delivered at LREC 2026

We are happy to share that we organized our half-day tutorial at LREC 2026:

Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages

• Date: 12 May 2026
• Time: 14:00–18:00 CET
• Tutorial page: https://mm-llms-in-the-wild.github.io

🧭 Overview

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), and speech–text LLMs.

We cover:

• Low-cost data creation and curation for multilingual multimodal settings
• Adapter stacks for tri-modal alignment (text, speech, vision)
• Culture-aware evaluation beyond English
• Hands-on resources for fine-tuning a compact multilingual VLM and wiring a speech → text → LLM pipeline

The content was delivered as an interactive half-day tutorial, designed for researchers and practitioners working on multilingual, multimodal AI in low-resource language settings.

🔗 Resources

• 📄 Paper: https://arxiv.org/abs/2605.17152
• 🖥 Slides: https://mm-llms-in-the-wild.github.io/content
• 📚 Reading list: https://mm-llms-in-the-wild.github.io/reading_list

Thanks to everyone who joined and contributed to the discussion on building inclusive, multilingual, and multimodal AI for low-resource languages.