paper-with-me

Papers

Enhancing Low-Rank Adaptation with Structured Nonlinear Transformations

2025-09-26 · Guanzhi Deng, Mingyang Liu, Dapeng Wu, Yinqiao Li, Linqi Song arxiv

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning method for large language models. However, its linear nature limits expressiveness. We propose LoRAN, a non-linear extension of LoRA that applies lightweight transformations to the low-rank updates. We further introduce Sinter, a sine-based activation that adds structured perturbations without increasing parameter count. Experiments across summarization and classification tasks show that LoRAN consistently improves over QLoRA. Ablation studies reveal that Sinter outperforms standard activations such as Sigmoid, ReLU, and Tanh, highlighting the importance of activation design in lowrank tuning.

📄 PDF Abstract BibTeX arXiv:2509.21870

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions

2026-04-12 · Wenhao Zhang, Lin Mu, Li Ni, Peiquan Jin 외 arxiv

Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models (LLMs), but its strictly linear structure fundamentally limits expressive capacity. The bilinear formulation of weig…

Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints

2026-06-30 · Shuai Yuan, Sudong Cai, Bingzhi Chen, Shuyuan Zheng 외 arxiv

Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transformer feed-forward networks. In gated FFNs, a low-rank residual can cha…

parameter-efficient fine-tuning

DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation

2025-03-23 · Massimo Bini, Leander Girrbach, Zeynep Akata

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 tas…

Image GenerationNatural Language Understanding

Mario at EXIST 2025: A Simple Gateway to Effective Multilingual Sexism Detection

2025-07-15 · Lin Tian, Johanne R. Trippas, Marian-Andrei Rizoiu arxiv

This paper presents our approach to EXIST 2025 Task 1, addressing text-based sexism detection in English and Spanish tweets through hierarchical Low-Rank Adaptation (LoRA) of Llama 3.1 8B. Our method introduces condition…

parameter-efficient fine-tuningCross-Lingual TransferBinary Classification

QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

2025-09-28 · Qian Chen, Linxin Yang, Akang Wang, Xiaodong Luo 외 arxiv

The combination of linear transformations and non-linear activation functions forms the foundation of most modern deep neural networks, enabling them to approximate highly complex functions. This paper explores the intro…

Image ClassificationText Classification