الباحثون

Shao-Hua Sun

المنشورات 2

نسخة أولية وصول مفتوح

A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic

Model merging aims to build a multi-task model cheaply by combining the weights of individual task-specific models. To perform well across multiple tasks, most existing merging methods use an additional dataset to find the coefficients for the best linear combination of task-specific weight updates. However, we identif …

المؤلفون المشاركون