Understanding and Enforcing Weight Disentanglement in Task Arithmetic

April 18, 2026 Β· Grace Period Β· πŸ› CVPR 2026

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Shangge Liu, Yuehan Yin, Lei Wang, Qi Fan, Yinghuan Shi, Wenbin Li, Yang Gao, Dacheng Tao arXiv ID 2604.17078 Category cs.AI: Artificial Intelligence Citations 0 Venue CVPR 2026
Abstract
Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of ``weight disentanglement" describes the ideal outcome of non-interfering task composition but does not reveal its underlying cause. Crucially, what intrinsic properties of the pre-trained model ($ΞΈ_0$) or the task vectors ($Ο„_t$) enable this disentanglement remains underexplored. In this paper, we introduce Task-Feature Specialization (TFS), a model's ability to allocate distinct internal features to different tasks, as the fundamental principle. We first prove that TFS is a sufficient condition for weight disentanglement. More importantly, we find that TFS also gives rise to an observable geometric consequence: weight vector orthogonality. This positions TFS as the common cause for both the desired functional outcome (disentanglement) and a measurable geometric property (orthogonality). This relationship provides the key insight for our method: since the abstract TFS property is intractable to enforce directly, we can instead promote weight disentanglement by shaping its concrete geometric consequence, orthogonality. Therefore, we propose OrthoReg, a simple and effective regularization method that actively enforces an internal orthogonal structure on weight updates ($Ξ”W$) that constitute $Ο„_t$ during fine-tuning. And we theoretically prove that OrthoReg promotes disentanglement. Extensive experiments demonstrate that OrthoReg consistently and significantly enhances the performance of various task arithmetic methods. Code is available at \href{https://github.com/RL-MIND/OrthoReg}{https://github.com/RL-MIND/OrthoReg}.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence