AI Paper Atlas

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

Sparse Tuning Enhances Plasticity in PTM-based Continual Learning

Huan Zhang, Shenghua Fan, Shuyu Dong, Yujin Zheng, Dingwen Wang, Fan Lyu

AAAI 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 0 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 MIST pre-adaptationSimpleCIL · Cars-196A_T: 27.8 -> 43.5Improved
add MIST pre-adaptationL2P · Cars-196A_T: 39.6 -> 52.7Improved
add MIST pre-adaptationRanPAC · ImageNet-RA_T: 77.9 -> 81.0Improved
add MIST pre-adaptationSLCA · Cars-196A_T: 67.7 -> 74.6Improved
add MIST pre-adaptationSimpleCIL · ImageNet-RA_T: 54.3 -> 72.2Improved
replace MI-based selection with full fine-tuning pre-adaptation (ablation)RanPAC · ImageNet-RA_T: 77.9 -> 36.7Hurt
replace MI-based selection with random or L2 selection (ablation)RanPAC · Cars-196A_T: 74.6 -> 10.9 (Rand)Hurt
add MI loss to MI-based sparse selection (ablation)RanPAC + MS · Cars-196A_T: 66.2 -> 72.1Improved
add gradient dropout to MS+ML (ablation)RanPAC · ImageNet-RA_T: 76.7 -> 81.0Improved
use MI-based selection instead of gradient-magnitude selection (both with MI loss and dropout) (ablation)RanPAC · Cars-196A_T: 42.0 -> 76.4Improved
add MISTRanPAC · CIFAR-100A_T: 90.8 -> 92.4Improved

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