中文
相关论文

相关论文: LoRA-MGPO: Mitigating Double Descent in Low-Rank A…

200 篇论文

Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models' scale and the diversity of tasks increase. Low-rank adaptation (LoRA) is based on the idea that the…

计算与语言 · 计算机科学 2025-05-27 Pengjie Ren , Chengshun Shi , Shiguang Wu , Mengqi Zhang , Zhaochun Ren , Maarten de Rijke , Zhumin Chen , Jiahuan Pei

Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific downstream tasks. However, the model trained based on LoRA…

计算与语言 · 计算机科学 2026-01-05 Yixing Xu , Chao Li , Xuanwu Yin , Spandan Tiwari , Dong Li , Ashish Sirasao , Emad Barsoum

Parameter-Efficient FineTuning (PEFT) methods have recently gained significant popularity thanks to the widespread availability of large-scale pretrained models. These methods allow for quick adaptation to downstream tasks with minimal…

机器学习 · 计算机科学 2025-05-20 Massimo Bini , Leander Girrbach , Zeynep Akata

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

计算与语言 · 计算机科学 2025-10-14 Bo Cheng , Xu Wang , Jinda Liu , Yi Chang , Yuan Wu

Low Rank Adaptation (LoRA) is a popular Parameter Efficient Fine Tuning (PEFT) method that effectively adapts large pre-trained models for downstream tasks. LoRA parameterizes model updates using low-rank matrices at each layer,…

计算与语言 · 计算机科学 2025-02-04 Ignacio Hounie , Charilaos Kanatsoulis , Arnuv Tandon , Alejandro Ribeiro

In recent years, Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) have significantly enhanced the adaptability of large-scale pre-trained models. Weight-Decomposed Low-Rank Adaptation (DoRA) improves upon LoRA…

计算与语言 · 计算机科学 2024-12-10 Qiushi Wang , Yuchen Fan , Junwei Bao , Hongfei Jiang , Yang Song

Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the learning capacity and…

机器学习 · 计算机科学 2026-02-09 Nghiem T. Diep , Hien Dang , Tuan Truong , Tan Dinh , Huy Nguyen , Nhat Ho

Parameter-efficient fine-tuning (PEFT) is a flexible and efficient method for adapting large language models (LLMs) to downstream tasks. Among these methods, weight-decomposed low-rank adaptation (DoRA) is a promising approach that…

机器学习 · 计算机科学 2025-08-05 Peijia Qin , Ruiyi Zhang , Pengtao Xie

The Parameter-Efficient Fine-Tuning (PEFT) methods have been extensively researched for large language models in downstream tasks. Among all the existing approaches, the Low-Rank Adaptation (LoRA) has gained popularity for its streamlined…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Tangyu Jiang , Haodi Wang , Chun Yuan

Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is computationally expensive and memory-intensive. Parameter-efficient fine-tuning (PEFT)…

计算与语言 · 计算机科学 2026-05-12 Longteng Zhang , Lin Zhang , Shaohuai Shi , Xiaowen Chu , Bo Li

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full…

机器学习 · 计算机科学 2026-05-21 Yongkang Liu , Xing Li , Mengjie Zhao , Shanru Zhang , Zijing Wang , Qian Li , Shi Feng , Feiliang Ren , Daling Wang , Hinrich Schütze

Parameter-Efficient Fine-Tuning (PEFT) has become an essential approach for adapting large-scale pre-trained models while reducing computational costs. Among PEFT methods, LoRA significantly reduces trainable parameters by decomposing…

计算与语言 · 计算机科学 2025-03-31 Jiancheng Zhao , Xingda Yu , Zhen Yang

Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant…

机器学习 · 计算机科学 2025-08-01 Zerui Tao , Yuhta Takida , Naoki Murata , Qibin Zhao , Yuki Mitsufuji

With the rapid development of Large Language Models (LLMs), Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant attention, which aims to achieve efficient fine-tuning of LLMs with fewer parameters. As a representative…

机器学习 · 计算机科学 2025-05-30 Dacao Zhang , Kun Zhang , Shimao Chu , Le Wu , Xin Li , Si Wei

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full…

计算与语言 · 计算机科学 2026-01-13 Yongkang Liu , Xing Li , Mengjie Zhao , Shanru Zhang , Zijing Wang , Qian Li , Shi Feng , Feiliang Ren , Daling Wang , Hinrich Schütze

Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to…

Among the widely used parameter-efficient fine-tuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference costs. However, there still often exists an accuracy gap between these…

The fine-tuning of Large Language Models (LLMs) is pivotal for achieving optimal performance across diverse downstream tasks. However, while full fine-tuning delivers superior results, it entails significant computational and resource…

计算与语言 · 计算机科学 2025-01-15 Yao Liang , Yuwei Wang , Yi Zeng

Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as training imbalance and the…

计算与语言 · 计算机科学 2024-10-31 Xujia Wang , Haiyan Zhao , Shuo Wang , Hanqing Wang , Zhiyuan Liu

Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challenging, particularly in resource-constrained environments.…

机器学习 · 计算机科学 2025-09-12 Hao Zhang , Bo Huang , Zhenjia Li , Xi Xiao , Hui Yi Leong , Zumeng Zhang , Xinwei Long , Tianyang Wang , Hao Xu
‹ 上一页 1 2 3 10 下一页 ›