AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation

Lujun Li, Cheng Lin, Dezhi Li, You-Liang Huang, Wei Li, Tianyu Wu, Jie Zou, Wei Xue, Sirui Han, Yike Guo

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use AwSVD for outer LoRA init instead of random (ablation)NoRA · GSM8Kaccuracy: 66.4 -> 69.4Improved
use AwSVD instead of plain SVD for outer init (ablation)NoRA · GSM8Kaccuracy: 69.1 -> 69.4Improved
use AwSVD instead of plain SVD for outer init (ablation)NoRA · MATHaccuracy: 18.9 -> 19.1Improved
use Gaussian inner init instead of uniform/zero (ablation)NoRA · GSM8Kaccuracy: 68.3 -> 69.4Improved
use Gaussian inner init instead of diag(Sigma) (ablation)NoRA · GSM8Kaccuracy: 68.9 -> 69.4Improved
use serial LoRA instead of parallel LoRA (ablation)NoRA · GSM8Kaccuracy: 66.4 -> 69.4Improved
use serial LoRA instead of adapter (ablation)NoRA · GSM8Kaccuracy: 68.0 -> 69.4Improved
place inner LoRA at wa only instead of wa and wb (ablation)NoRA · GSM8Kaccuracy: 68.9 -> 69.4Improved
place inner LoRA at wa instead of wb (ablation)NoRA · GSM8Kaccuracy: 68.4 -> 69.4Improved
increase inner rank r' from 8 to 64 at outer rank 64 (ablation)NoRA · MATHaccuracy: 17.10 -> 19.48Improved
increase inner rank r' from 8 to 64 at outer rank 128 (ablation)NoRA · MATHaccuracy: 17.80 -> 19.83Improved
use NoRA instead of LoRA-XS (r=128)LLaVA-1.5-7B · TextVQAaccuracy: 54.36 -> 58.70Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy