paper-with-me

Papers

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation

2026-03-23 · Donald Shenaj, Federico Errica, Antonio Carta arxiv

Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA$^2$, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.

📄 PDF Abstract BibTeX arXiv:2603.21884

Code (0)

등록된 구현이 없습니다.

Tasks

Personalized Image Generation

Similar Papers 제목 키워드 기반

GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning

2024-12-12 · Abdessalam Ed-dib, Zhanibek Datbayev, Amine Mohamed Aboussalah

Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a tra…

Post-Optimization Adaptive Rank Allocation for LoRA

2026-04-30 · Vishnuprasadh Kumaravelu, Sunil Gupta, P. K. Srijith arxiv

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregar…

parameter-efficient fine-tuning

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

2025-06-17 · Hengyuan Zhang, Xinrong Chen, Yingmin Qiu, Xiao Liang 외

Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. However, their performance is limited by th…

Bilevel OptimizationMixture-of-Expertsparameter-efficient fine-tuning

TLoRA: Task-aware Low Rank Adaptation of Large Language Models

2026-04-20 · Weicheng Lin, Yi Zhang, Jiawei Dang, Liang-Jie Zhang arxiv

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely influenced by the allocation of ranks and scaling factors, as well a…

parameter-efficient fine-tuningNatural Language UnderstandingCode Generation

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

2026-05-08 · Ionut-Vlad Modoranu, Mher Safaryan, Dan Alistarh arxiv

With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to deployment. While Low-Rank Adaptation (LoRA) has become the standard for p…

parameter-efficient fine-tuning