AI Paper Atlas

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

SABER: Continual Learning with Representation Conflict Management

Xuandi Luo, Huaidong Zhang, Yi Xie, Shengfeng He

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation

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 orthogonal initialization of A_t (ablation)LoRA baseline · ImageNet-R (T=10)A_last: 67.65 -> 72.39Improved
add subspace alignment (SA) (ablation)LoRA baseline · ImageNet-R (T=10)A_last: 67.65 -> 73.25Improved
add knowledge recomposition (KR) (ablation)LoRA baseline · ImageNet-R (T=10)A_last: 67.65 -> 74.08Improved
add knowledge balancing (KB) to KR (ablation)KR · ImageNet-R (T=10)A_last: 74.08 -> 75.11Improved
add SA to KR (ablation)KR · ImageNet-R (T=10)A_last: 74.08 -> 78.53Improved
add KB to SA+KR (full SABER) (ablation)SA+KR · ImageNet-R (T=10)A_last: 78.53 -> 80.30Improved
add SA+KR+KB at long sequence (ablation)LoRA baseline · ImageNet-R (T=20)A_last: 62.98 -> 77.77Improved
use dense mutually orthogonal A_t instead of random init (ablation)SABER · ImageNet-R (T=10)A_last: 2.76 -> 80.30Improved
use dense mutually orthogonal A_t instead of standard basis (ablation)SABER · ImageNet-R (T=10)A_last: 76.29 -> 80.30Improved
use dense mutually orthogonal A_t instead of intra-ortho init (ablation)SABER · ImageNet-R (T=10)A_avg: 76.10 -> 85.98Improved
vary common-knowledge ratio alpha within 0.5-0.8 (ablation)SABER · ImageNet-R (T=10)A_avg: accuracy drops by at most 0.63%No clear effect
set alpha=1.0 (no task-specific knowledge, SA only) (ablation)SABER · ImageNet-R (T=10)A_avgHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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