The Revolution of Multimodal Large Language Models: A Survey
This is an incremental survey that synthesizes existing research on MLLMs to inform future developments in multimodal AI.
This paper provides a comprehensive survey of Multimodal Large Language Models (MLLMs), analyzing their architectures, training techniques, and performance across various tasks such as visual grounding and image generation, while compiling datasets and benchmarks for comparison.
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.