AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

Sparse Orthogonal Parameters Tuning for Continual Learning

Kun-Peng Ning, Hai-Jian Ke, Yuyang Liu, Jiayu Yao, Yonghong Tian, Yuan Li

IJCV 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 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 SoTU delta masking and merging instead of RanPACViT-B/16-IN21K · Cars196 (10 tasks)final accuracy: +3.7%Improved
use SoTU instead of RanPACViT-B/16-IN21K · ImageNet-A (10 tasks)final accuracy: +2.3%Improved
use SoTU instead of RanPACViT-B/16-IN21K · ImageNet-R (10 tasks)final accuracy: +1.6%Improved
use SoTU features without nonlinear projection instead of RanPAC featuresNCM classifier, buffer 10/cls · ImageNet-R (10 tasks, NCM feature space)final accuracy: 52.2% -> 67.9% (+12.7%)Improved
use SoTU features without nonlinear projection instead of RanPAC featuresNCM classifier, buffer 10/cls · CIFAR100 (10 tasks, NCM feature space)final accuracy: 75.4% -> 83.8% (+8.4%)Improved
use SoTU features without nonlinear projection instead of RanPAC featuresNCM classifier, buffer 10/cls · CUB200 (10 tasks, NCM feature space)final accuracy: 74.6% -> 78.8% (+4.2%)Improved
merge deltas with random masking (high sparsity) instead of low sparsity (ablation)SoTU delta merging · CIFAR10, CIFAR100, Tiny-ImageNetaccuracyImproved
randomly mask 80%-90% of delta parameters (ablation)single fine-tuned ViT · CIFAR10, CIFAR100, Tiny-ImageNetaccuracy: 80%~90% masking keeps competitive performanceNo clear effect
use larger ViT (ViT-L vs ViT-B vs ViT-S) for delta masking (ablation)delta masking · CIFAR10, CIFAR100, Tiny-ImageNetaccuracy: ViT-L tolerates most sparsity, then ViT-B, then ViT-SImproved
apply delta masking to ResNet50 instead of ViT (ablation)delta masking · CIFAR10, CIFAR100, Tiny-ImageNetaccuracyHurt
mask excessive delta parameters when merging (ablation)SoTU delta merging · CIFAR10, CIFAR100, Tiny-ImageNetaccuracyHurt
use masking rate p=0.7 (30% delta kept) instead of p=0.9 over 10 tasks (ablation)SoTU · CIFAR100 (10 tasks)accuracy: better in first 3 tasks, fails in following 7Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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