الباحثون

Yongkang Liu

المنشورات 1

نسخة أولية وصول مفتوح

Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging

Zijing Wang, Yongkang Liu, Mingyang Wang وآخرون · 2026

Merging pretrained models has emerged as an effective approach for consolidating diverse capabilities into a single unified model. However, prevailing merging methods typically treat each task vector as an indivisible merging unit, overlooking the heterogeneous geometric changes encoded within it. This treatment can in …

المؤلفون المشاركون