MIN-Merging: Merge the Important Neurons for Model Merging
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909869433421824 |
|---|---|
| author | Liang, Yunfei |
| author_facet | Liang, Yunfei |
| contents | Recent advances in deep learning have led to a surge of open-source models across diverse domains. While model merging offers a promising way to combine their strengths, existing approaches often suffer from parameter conflicts that degrade performance on domain-specific tasks. We propose MIN-Merging, a router-based framework that selectively merges the most important neurons to reduce such conflicts. Extensive experiments on Computer Vision(CV) and Natural Language Processing(NLP) benchmarks show that MIN-Merging achieves consistent gains on in-domain tasks while retaining the generalization ability of pretrained models on out-of-domain tasks. These results highlight its effectiveness as a practical solution to the parameter conflict problem in model merging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17890 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIN-Merging: Merge the Important Neurons for Model Merging Liang, Yunfei Machine Learning Artificial Intelligence Recent advances in deep learning have led to a surge of open-source models across diverse domains. While model merging offers a promising way to combine their strengths, existing approaches often suffer from parameter conflicts that degrade performance on domain-specific tasks. We propose MIN-Merging, a router-based framework that selectively merges the most important neurons to reduce such conflicts. Extensive experiments on Computer Vision(CV) and Natural Language Processing(NLP) benchmarks show that MIN-Merging achieves consistent gains on in-domain tasks while retaining the generalization ability of pretrained models on out-of-domain tasks. These results highlight its effectiveness as a practical solution to the parameter conflict problem in model merging. |
| title | MIN-Merging: Merge the Important Neurons for Model Merging |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.17890 |