AI Paper Atlas

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

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective

Jingren Liu, Zhong Ji, Yunlong Yu, Jiale Cao, Yanwei Pang, Jungong Han, Xuelong Li

TPAMI 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 12 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
add knowledge retention (KR) to S2 (ablation)S2 adapter · CIFAR-100 (IN21K)incremental accuracy (%): 85.14 -> 91.29Improved
add knowledge retention (KR) to S1 (ablation)S1 adapter · CIFAR-100 (IN21K)incremental accuracy (%): 83.22 -> 84.61Improved
add knowledge retention (KR) to S1+S2+Hybrid (ablation)NTK-CL · CIFAR-100 (IN21K)incremental accuracy (%): 89.18 -> 91.89Improved
add knowledge retention (KR) to S1+S2+Hybrid (ablation)NTK-CL · ImageNet-R (IN21K)incremental accuracy (%): 75.94 -> 80.91Improved
use hybrid adaptation instead of S1 only (ablation)single-branch adapter · CIFAR-100 (IN21K)incremental accuracy (%): 83.22 -> 86.75Improved
add task-feature dissimilarity loss (ablation)NTK-CL with KR · CIFAR-100 (IN21K)incremental accuracy (%): 91.89 -> 92.83Improved
add orthogonality loss (ablation)NTK-CL with KR · CIFAR-100 (IN21K)incremental accuracy (%): 91.89 -> 92.39Improved
add regularization loss (ablation)NTK-CL with KR · CIFAR-100 (IN21K)incremental accuracy (%): 91.89 -> 92.16Improved
add regularization loss to full constraints (ablation)NTK-CL · CIFAR-100 (IN21K)incremental accuracy (%): 93.06 -> 93.76Improved
add regularization loss to full constraints (ablation)NTK-CL · ImageNet-R (IN21K)incremental accuracy (%): 82.50 -> 82.77Improved
NTK-CL versus best baseline on ImageNet-ANTK-CL · ImageNet-A (IN21K)incremental accuracy (%): 64.35 -> 66.56Improved
NTK-CL versus OVOR on DomainNetNTK-CL · DomainNet (IN21K)incremental accuracy (%): 75.80 -> 73.70Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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