paper-with-me

홈 › Papers

SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules

2024-03-18 · Xiangyu Chen, Jing Liu, Ye Wang, Pu, Wang, Matthew Brand, Guanghui Wang, Toshiaki Koike-Akino

Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision. This paper proposes a generalized framework called SuperLoRA that unifies and extends different LoRA variants, which can be realized under different hyper-parameter settings. Introducing grouping, folding, shuffling, projecting, and tensor factoring, SuperLoRA offers high flexibility compared with other LoRA variants and demonstrates superior performance for transfer learning tasks especially in the extremely few-parameter regimes.

📄 PDF Abstract BibTeX arXiv:2403.11887

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights

2026-02-19 · Kasun Dewage, Marianna Pensky, Suranadi De Silva, Shankadeep Mondal arxiv

We introduce CRAFT (Cross-layer Rank Adaptation via Frozen Tucker), a parameter-efficient fine-tuning (PEFT) method that applies Tucker tensor decomposition to pre-trained attention weight matrices stacked across transfo…

parameter-efficient fine-tuning

Less is More: Resource-Efficient Low-Rank Adaptation

2025-11-30 · Chunlin Tian, Xuyang Wei, Huanrong Liu, Zhijiang Guo 외 arxiv

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), but it still incurs notable overhead and suffers from parameter interference in complex datas…

parameter-efficient fine-tuningImage Generation

TAP-SLF: Parameter-Efficient Adaptation of Vision Foundation Models for Multi-Task Ultrasound Image Analysis

2026-02-28 · Hui Wan, Libin Lan arxiv

Executing multiple tasks simultaneously in medical image analysis, including segmentation, classification, detection, and regression, often introduces significant challenges regarding model generalizability and the optim…

parameter-efficient fine-tuning

A Unified Multi-Task Semantic Communication System with Domain Adaptation

2022-06-01 · Guangyi Zhang, Qiyu Hu, Zhijin Qin, Yunlong Cai 외

The task-oriented semantic communication systems have achieved significant performance gain, however, the paradigm that employs a model for a specific task might be limited, since the system has to be updated once the ta…

Domain AdaptationSemantic Communication

KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation

2026-06-15 · Mao-Lin Luo, Yi-Lin Zhang, Zi-Hao Zhou, Yankun Hong 외 arxiv

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plastic…

Visual Question AnsweringImage ClassificationContinual Learning