AI Paper Atlas

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

Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning

Lingfeng He, De Cheng, Huaijie Wang, Xi Yang, Nannan Wang, Xinbo Gao

ICML 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 general-subspace LoRA branch to single-branch LoRA (ablation)sequential LoRA · ImageNetR/ImageNetA, 10 and 20 sessionsALast: 72.09 -> 79.19 (10S-ImageNetR)Improved
add isolated-subspace LoRA branch to single-branch LoRA (ablation)sequential LoRA · ImageNetR/ImageNetA, 10 and 20 sessionsALast: 72.09 -> 79.22 (10S-ImageNetR)Improved
combine general and isolated branches (ablation)LoDA · ImageNetR/ImageNetA, 10 and 20 sessionsALast: 79.22 -> 81.05 (10S-ImageNetR)Improved
add Gradient-Aligned Optimization (GAO) (ablation)LoDA dual-branch · ImageNetR/ImageNetA, 10 and 20 sessionsALast: 81.05 -> 81.93 (10S-ImageNetR)Improved
build isolated subspace by maximizing new-to-old relative energy instead of null space (InfLoRA) (ablation)LoRAI · 10S-ImageNetRALast: 75.15 -> 79.22Improved
build isolated subspace by relative energy maximization instead of null space (InfLoRA) (ablation)LoRAI · 10S-ImageNetAALast: 57.10 -> 59.89Improved
use relative energy maximization instead of random orthogonal bases (ablation)LoRAI · 10S-ImageNetRALast: 68.23 -> 79.22Improved
use closed-form rescaling instead of CoMA merging for general branch (ablation)LoRAG · 10S-ImageNetRALast: 78.39 -> 79.19Improved
use per-unit closed-form rescaling instead of simple averaging (ablation)LoRAG · 10S-ImageNetRALast: 78.43 -> 79.19Improved
raise rescaling lambda from 3.0 to 10.0 (ablation)closed-form rescaling · 10S-ImageNetR / 10S-ImageNetAALast: 79.19 -> 78.96 (ImageNetR); 59.62 -> 59.75 (ImageNetA)No clear effect
add classifier alignment (feature replay) to LoDALoDA · 10S-ImageNetAALast: 62.59 -> 66.71Improved
add classifier alignment (feature replay) to LoDALoDA · 10S-CIFAR100ALast: 90.47 -> 92.15Improved

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