1
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
LoRA新思路：在Fisher子空间中引导初始化，提升微调性能与稳定性。
arXiv:2605.01046v3 Announce Type: replace Abstract: LoRA adapts large language models (LLMs) by restricting updates to low-rank subspaces of pre-train…