I am a master’s student pursuing an MPhil in Data Intensive Science at the University of Cambridge. My interests lie in computer vision, machine learning, and, particularly, in building efficient deep learning models. Previously, I studied Mathematics at the University of Edinburgh, where I had the privilege of working with Prof. ChengJia Wang on medical-related deep learning methods. In my free time, I enjoy competing on Kaggle, reading Chinese fiction novels, and sometimes reading interesting papers on arXiv....
This works is a wrapping up project that conclude all the paper on LoRA that I have read to develop [SeLoRA](https://arxiv.org/abs/2408.07196v1). Note that although the variants might not be comprehensive and it cut off around march 2024, I hope this would give you an idea of what is LoRA, and what have already been accompolished in this. Low Rank Adaptation Low Rank Adaptation (LoRA), a line of research under Parameter efficient Fine-Tuning (PEFT) methods, was initially designed for Large Language Models (LLMs), but has later been popularized by the Stable Diffusion community due to its fascinating ability of efficiently learning a style from only a few images....