Efficient Multimodal Large Language Models: A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908780110807040 |
|---|---|
| author | Jin, Yizhang Li, Jian Liu, Yexin Gu, Tianjun Wu, Kai Jiang, Zhengkai He, Muyang Zhao, Bo Tan, Xin Gan, Zhenye Wang, Yabiao Wang, Chengjie Ma, Lizhuang |
| author_facet | Jin, Yizhang Li, Jian Liu, Yexin Gu, Tianjun Wu, Kai Jiang, Zhengkai He, Muyang Zhao, Bo Tan, Xin Gan, Zhenye Wang, Yabiao Wang, Chengjie Ma, Lizhuang |
| contents | In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry. Thus, studying efficient and lightweight MLLMs has enormous potential, especially in edge computing scenarios. In this survey, we provide a comprehensive and systematic review of the current state of efficient MLLMs. Specifically, we summarize the timeline of representative efficient MLLMs, research state of efficient structures and strategies, and the applications. Finally, we discuss the limitations of current efficient MLLM research and promising future directions. Please refer to our GitHub repository for more details: https://github.com/lijiannuist/Efficient-Multimodal-LLMs-Survey. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10739 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Multimodal Large Language Models: A Survey Jin, Yizhang Li, Jian Liu, Yexin Gu, Tianjun Wu, Kai Jiang, Zhengkai He, Muyang Zhao, Bo Tan, Xin Gan, Zhenye Wang, Yabiao Wang, Chengjie Ma, Lizhuang Computer Vision and Pattern Recognition Artificial Intelligence In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry. Thus, studying efficient and lightweight MLLMs has enormous potential, especially in edge computing scenarios. In this survey, we provide a comprehensive and systematic review of the current state of efficient MLLMs. Specifically, we summarize the timeline of representative efficient MLLMs, research state of efficient structures and strategies, and the applications. Finally, we discuss the limitations of current efficient MLLM research and promising future directions. Please refer to our GitHub repository for more details: https://github.com/lijiannuist/Efficient-Multimodal-LLMs-Survey. |
| title | Efficient Multimodal Large Language Models: A Survey |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2405.10739 |