AI Paper Atlas

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

Learning Adaptive and Expandable Mixture Model for Continual Learning

Fei Ye, YongCheng Zhong, Qihe Liu, Adrian G. Bors, JingLing Sun, Jinyu Guo, ShiJie Zhou

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 prediction calibration process (PCP) (ablation)AEMM (mse) · MTIL 3 task orders (TIN/CD/RESISC45), mean over ordersAverage accuracy: 89.65 -> 90.15Improved
add representation calibration process (RCP) (ablation)AEMM (mse) · MTIL 3 task orders (TIN/CD/RESISC45), mean over ordersAverage accuracy: 89.77 -> 90.15Improved
add PCP (ablation)AEMM (mse) · MTIL 3 task orders (TIN/CD/RESISC45), mean over ordersLast accuracy: 89.56 -> 90.03Improved
add RCP (ablation)AEMM (mse) · MTIL 3 task orders (TIN/CD/RESISC45), mean over ordersLast accuracy: 89.56 -> 90.03Improved
add PCP (ablation)AEMM (mse) · MTIL TIN-CD-RESISC45 orderAverage accuracy: 86.35 -> 86.91Improved
add RCP (ablation)AEMM (mse) · MTIL TIN-CD-RESISC45 orderAverage accuracy: 86.19 -> 86.91Improved
add PCP (ablation)AEMM (mse) · MTIL CD-RESISC45-TIN orderAverage accuracy: 93.74 -> 94.29Improved
add RCP (ablation)AEMM (mse) · MTIL CD-RESISC45-TIN orderAverage accuracy: 94.18 -> 94.29Improved
use MSE instead of MMD for representation calibrationAEMM · MTIL (7 datasets), Total AvgAverage accuracy: 87.60 -> 87.77No clear effect
use AEMM dual-representation expandable model instead of strongest baseline CLS-ERAEMM (mse) · MTIL (7 datasets), Total AvgAverage accuracy: 81.00 -> 87.77Improved
increase PCP coefficient (ablation)AEMM (RCP=0) · MTIL (7 datasets)Average accuracy: peaking at 87.58%Improved
increase RCP coefficient beyond 0.3 (ablation)AEMM (PCP=0) · MTIL (7 datasets)Average accuracyHurt

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