Story
arxiv_cs_lg · Nov 10, 2026 · paper
Source brief
A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)
arxiv.orgNov 10, 2026
original source linked
In brief
Low-rank adaptation (LoRA) is the de facto method for parameter-efficient fine-tuning of large neural networks, achieving strong task adaptation with minimal trainable parameters and low optimization cost. Beyond this efficiency, practitioners have observed two striking propertie