The Revolution of Multimodal Large Language Models: A Survey

TL;DR

This survey reviews recent advances in Multimodal Large Language Models (MLLMs), focusing on their architectures, training, and applications across various visual and textual tasks, highlighting current challenges and future directions.

Contribution

It provides a comprehensive overview of recent MLLMs, analyzing their design choices, training strategies, and performance across multiple tasks and benchmarks.

Findings

MLLMs demonstrate strong performance in visual grounding and image editing.

Current models face challenges in computational efficiency and domain adaptation.

Benchmark comparisons reveal gaps in multimodal understanding and generation capabilities.

Abstract

Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal Large Language Models (MLLMs). These models can seamlessly integrate visual and textual modalities, while providing a dialogue-based interface and instruction-following capabilities. In this paper, we provide a comprehensive review of recent visual-based MLLMs, analyzing their architectural choices, multimodal alignment strategies, and training techniques. We also conduct a detailed analysis of these models across a wide range of tasks, including visual grounding, image generation and editing, visual understanding, and domain-specific applications. Additionally, we compile and describe training datasets and evaluation benchmarks, conducting comparisons among existing models in terms of performance and computational requirements. Overall, this survey offers a comprehensive overview of the current state of the art, laying the groundwork for future MLLMs.