AI Paper Atlas

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

PLAN: Proactive Low-Rank Allocation for Continual Learning

Xiequn Wang, Zhan Zhuang, Yu Zhang

ICCV 2025 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 6 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 basis selection mechanism for A_t (ablation)PLAN · ImageNet-R (N=20)Acc: 68.35 -> 71.06Improved
add perturbation-based min-max optimization of B_t (ablation)PLAN · ImageNet-R (N=20)Acc: 70.65 -> 71.06Improved
add selection mechanism (ablation)PLAN · ImageNet-R (N=5)Acc: 75.97 -> 77.79Improved
add perturbation optimization (ablation)PLAN · ImageNet-R (N=10)Acc: 74.97 -> 75.25Improved
add both components over Inc-LoRA (ablation)Inc-LoRA · ImageNet-R (N=20)Acc: 52.12 -> 71.06Improved
use standard basis instead of random orthogonal basis (ablation)PLAN · CIFAR-100Acc: 81.21 -> 87.54Improved
use standard basis instead of LoRA-GA basis (ablation)PLAN · CIFAR-100Acc: 84.30 -> 87.54Improved
use p=2 instead of p=1 (ablation)PLAN · CIFAR-100Acc: 80.32 -> 87.54Improved
use p=2 instead of p=infinity (ablation)PLAN · CIFAR-100Acc: 79.94 -> 87.54Improved
set rho=0.01 instead of 0.1 (ablation)PLAN · ImageNet-R (N=5)Acc: 75.23 -> 77.79Improved
set rho=0.01 instead of 0.001 (ablation)PLAN · ImageNet-R (N=5)Acc: 76.38 -> 77.79Improved
PLAN vs InfLoRA with iBOT pretraining on ImageNet-R N=20PLAN · ImageNet-R N=20 (iBOT-1k)Acc: 78.11 -> 78.39Mixed

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