RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
NeurIPSSpotlight2025
TL;DR
As one of the state-of-the-art parameter-efficient fine-tuning~(PEFT) methods, Low-Rank Adaptation (LoRA) enables model optimization with reduced computational cost through trainable low-rank matrix…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
large language model language model optimization fine-tuning efficient
← All NeurIPS 2025 Spotlight papers · Browse the whole archive