Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909978295533568 |
|---|---|
| author | Yang, Enneng Shen, Li Guo, Guibing Wang, Xingwei Cao, Xiaochun Zhang, Jie Tao, Dacheng |
| author_facet | Yang, Enneng Shen, Li Guo, Guibing Wang, Xingwei Cao, Xiaochun Zhang, Jie Tao, Dacheng |
| contents | Model merging is an efficient empowerment technique in the machine learning community that does not require the collection of raw training data and does not require expensive computation. As model merging becomes increasingly prevalent across various fields, it is crucial to understand the available model merging techniques comprehensively. However, there is a significant gap in the literature regarding a systematic and thorough review of these techniques. This survey provides a comprehensive overview of model merging methods and theories, their applications in various domains and settings, and future research directions. Specifically, we first propose a new taxonomic approach that exhaustively discusses existing model merging methods. Secondly, we discuss the application of model merging techniques in large language models, multimodal large language models, and more than ten machine learning subfields, including continual learning, multi-task learning, few-shot learning, etc. Finally, we highlight the remaining challenges of model merging and discuss future research directions. A comprehensive list of papers about model merging is available at https://github.com/EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07666 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities Yang, Enneng Shen, Li Guo, Guibing Wang, Xingwei Cao, Xiaochun Zhang, Jie Tao, Dacheng Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Model merging is an efficient empowerment technique in the machine learning community that does not require the collection of raw training data and does not require expensive computation. As model merging becomes increasingly prevalent across various fields, it is crucial to understand the available model merging techniques comprehensively. However, there is a significant gap in the literature regarding a systematic and thorough review of these techniques. This survey provides a comprehensive overview of model merging methods and theories, their applications in various domains and settings, and future research directions. Specifically, we first propose a new taxonomic approach that exhaustively discusses existing model merging methods. Secondly, we discuss the application of model merging techniques in large language models, multimodal large language models, and more than ten machine learning subfields, including continual learning, multi-task learning, few-shot learning, etc. Finally, we highlight the remaining challenges of model merging and discuss future research directions. A comprehensive list of papers about model merging is available at https://github.com/EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications. |
| title | Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities |
| topic | Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.07666 |