The Primacy of Magnitude in Low-Rank Adaptation

NeurIPSSpotlight2025

Authors: Zicheng Zhang, Haoran Li, Yifeng Zhang, Guoqiang Gong, Jiaxing Wang, Junxing Hu, pengzhang liu, Qixia Jiang
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Low-Rank Adaptation (LoRA) offers a parameter-efficient paradigm for tuning large models…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

efficient

← All NeurIPS 2025 Spotlight papers · Browse the whole archive