AAAI 2026technical0 citations

Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT

Da Chang, Peng Xue, Yu Li, Yongxiang Liu, Pengxiang Xu, Shixun Zhang

Abstract

Parameter-Efficient Fine-Tuning (PEFT) methods are crucial for adapting large pre-trained models. Among these, LoRA is considered a foundational approach. Building on this, the influential DoRA method enhances performance by decomposing weight updates into magnitude and direction. However, its underlying mechanism remains unclear, and it introduces significant computational overhead. In this work, we first identify that DoRA

BibTeX
@inproceedings{aaai2026_calibratingandro,
  title = {Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT},
  author = {Da Chang and Peng Xue and Yu Li and Yongxiang Liu and Pengxiang Xu and Shixun Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}
Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT · AAAI 2026