Multimodal Large Language Models (MLLMs) combine the natural language understanding and generation capabilities of LLMs with perception skills in modalities such as image and audio, representing a key advancement in contemporary AI. This chapter presents the main fundamentals of MLLMs and emblematic models. Practical techniques for preprocessing, prompt engineering, and building multimodal pipelines with LangChain and LangGraph are also explored. For further practical study, supplementary material is publicly available online: https://github.com/neemiasbsilva/MLLMs-Teoria-e-Pratica. Finally, the chapter discusses the challenges and highlights promising trends.
@article{arxiv.2602.12302,
title = {Grandes Modelos de Linguagem Multimodais (MLLMs): Da Teoria \`a Pr\'atica},
author = {Neemias da Silva and Júlio C. W. Scholz and John Harrison and Marina Borges and Paulo Ávila and Frances A Santos and Myriam Delgado and Rodrigo Minetto and Thiago H Silva},
journal= {arXiv preprint arXiv:2602.12302},
year = {2026}
}
Comments
in Portuguese language. Accepted book chapter - Webmedia 2025