In an era defined by the explosive growth of data and rapid technological advancements, Multimodal Large Language Models (MLLMs) stand at the forefront of artificial intelligence (AI) systems. Designed to seamlessly integrate diverse data types-including text, images, videos, audio, and physiological sequences-MLLMs address the complexities of real-world applications far beyond the capabilities of single-modality systems. In this paper, we systematically sort out the applications of MLLM in multimodal tasks such as natural language, vision, and audio. We also provide a comparative analysis of the focus of different MLLMs in the tasks, and provide insights into the shortcomings of current MLLMs, and suggest potential directions for future research. Through these discussions, this paper hopes to provide valuable insights for the further development and application of MLLM.
@article{arxiv.2408.01319,
title = {A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks},
author = {Jiaqi Wang and Hanqi Jiang and Yiheng Liu and Chong Ma and Xu Zhang and Yi Pan and Mengyuan Liu and Peiran Gu and Sichen Xia and Wenjun Li and Yutong Zhang and Zihao Wu and Zhengliang Liu and Tianyang Zhong and Bao Ge and Tuo Zhang and Ning Qiang and Xintao Hu and Xi Jiang and Xin Zhang and Wei Zhang and Dinggang Shen and Tianming Liu and Shu Zhang},
journal= {arXiv preprint arXiv:2408.01319},
year = {2024}
}