LoRA vs Full Fine-tuning: An Illusion of Equivalence
Paper • 2410.21228 • Published • 3
Lora
-
-
Artificial Entanglement in the Fine-Tuning of Large Language Models
Paper • 2601.06788 • Published • 5 -
DiffoRA: Enabling Parameter-Efficient LLM Fine-Tuning via Differential Low-Rank Matrix Adaptation
Paper • 2502.08905 • Published -
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
Paper • 2502.01235 • Published • 1 -
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
Paper • 2502.13533 • Published • 13 -
Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
Paper • 2602.04998 • Published • 6 -
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Paper • 2310.20624 • Published • 13