AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

SAME: Sparse and Anchored Model Editing for Heterogeneous Incremental Learning under Limited Data

Zixuan Duan, Zeyu Zhang, Fengyuan Lu, Shaofeng Zhang, Wenbin Li, Qi Fan, Yang Gao

CVPR 2026 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory

Read the paper

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 new knowledge injection (closed-form key-value fit) (ablation)continual fine-tune · MTIL HIL Split-2 5-shotaverage accuracy: 46.0 -> 59.9Improved
add parameter anchor (ablation)SAME (NKI) · MTIL HIL Split-2 5-shotaverage accuracy: 59.9 -> 65.3Improved
add knowledge anchor (ablation)SAME (NKI+PA) · MTIL HIL Split-2 5-shotaverage accuracy: 65.3 -> 65.5Improved
add sparse fine-tuning (ablation)SAME (NKI+PA+KA) · MTIL HIL Split-2 5-shotaverage accuracy: 65.5 -> 66.0Improved
use Fisher-based mask instead of random mask (ablation)SAME sparse FT · MTIL HIL Split-2 5-shotaverage accuracy: 66.0 -> 65.3Hurt
raise sparsity ratio from 30% to 40% (ablation)SAME · MTIL HIL Split-2 5-shotaverage accuracy: 66.0 -> 60.9Hurt
lower sparsity ratio from 30% to 20% (ablation)SAME · MTIL HIL Split-2 5-shotaverage accuracy: 66.0 -> 65.6Hurt
change lambda_p from 300 to 200 or 400 (ablation)SAME · MTIL HIL Split-2 5-shotaverage accuracy: 66.0 -> 65.8No clear effect
SAME vs best model fusion baseline (TIES-Merging)SAME · MTIL HIL Split-2 5-shotaverage accuracy: 61.7 -> 66.0Improved
SAME vs best continual learning baseline (MoE-Adapter)SAME · MTIL HIL Split-2 5-shotaverage accuracy: 59.2 -> 66.0Improved
SAME vs best continual learning baseline in Split-3 (MoE-Adapter)SAME · MTIL HIL Split-3 5-shotaverage accuracy: 56.9 -> 61.4Improved

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