AI RESEARCH

Curvature-Guided LoRA: Steering in the pretrained NTK subspace

arXiv CS.LG

ArXi:2603.29824v1 Announce Type: new Parameter-efficient fine-tuning methods such as LoRA enable efficient adaptation of large pretrained models but often fall short of full fine-tuning performance. Existing approaches focus on aligning parameter updates, which only indirectly control model predictions. In this work, we