AI Paper Atlas

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

Compensating Distribution Drifts in Continual Learning with Pre-trained Vision Transformers

Xuan Rao, Simian Xu, Zheng Li, Bo Zhao, Derong Liu, Mingming Ha, Cesare Alippi

AAAI 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Synthetic data and merging for CLIP · 2 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 SLDC (weak-nonlinear α2) drift compensation to sequential fine-tuning (ablation)SeqFT · CUB-200 (MoCo-V3)Last-Acc: 64.40 -> 78.98Improved
use weak-nonlinear operator instead of linear operator (ablation)SLDC · Cars-196 (MoCo-V3)Last-Acc: 61.01 -> 77.53Improved
use weak-nonlinear SLDC instead of fully nonlinear MLP compensation (ablation)SLDC · Cars-196 (Sup-21K)Last-Acc: +6.52%Improved
add feature distillation to sequential fine-tuning (ablation)SeqFT · CUB-200 (Sup-21K)Last-Acc: 76.57 -> 86.75Improved
combine distillation with linear SLDC (ablation)α1-SLDC · CUB-200 (MoCo-V3)Last-Acc: 70.42 -> 80.55Improved
linear α1-SLDC without ADE or distillation on Sup-21K (ablation)SeqFT · CUB-200 and Cars-196 (Sup-21K)Last-Acc: 76.57 -> 71.49; 54.53 -> 46.78Hurt
add auxiliary data enrichment (ADE) to linear SLDC (ablation)α1-SLDC · Cars-196 (Sup-21K)Last-Acc: 46.78 -> 73.01Improved
add MLP-based compensation (MLPDC) to distilled sequential fine-tuning (ablation)SeqKD · CUB-200 (Sup-21K)Last-Acc: 86.75 -> 75.76Hurt
vary regularization coefficient γα2 over 0.1 to 2.0 (ablation)α2-SLDC · MoCo-V3 with distillationaccuracyNo clear effect
add ADE samples (larger sample size) (ablation)SLDC · CUB-200 vs ImageNet-RaccuracyMixed
lower temperature αtemp below 1.0 when ADE is used (ablation)α1-SLDC · Cars-196 and CUB-200 (MoCo-V3, distillation)accuracyMixed
extend to 20-task sequences (ablation)SLDC variants · MoCo-V3 20 tasksaccuracyImproved

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