Multi-Task Model Merging via Adaptive Weight Disentanglement

Model merging has recently gained attention as an economical and scalable approach to incorporate task-specific weights from various tasks into a unified multi-task model. For example, in Task Arithmetic (TA), adding the fine-tuned weights of different tasks can enhance the model's performance...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Xiong, Feng, Cheng, Runxi, Chen, Wang, Zhang, Zhanqiu, Guo, Yiwen, Yuan, Chun, Xu, Ruifeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!