AI Paper Atlas

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

Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning

Heming Zou, Yunliang Zang, Wutong Xu, Xiangyang Ji

ICLR 2026 · 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
use sparse random projection instead of dense (ablation)Fly-CL (ViT-B/16) · CUB-200-2011 random projection timeseconds per task: 0.22 -> 0.08Improved
use GCV for ridge selection instead of explicit cross-validation (ablation)Fly-CL (ViT-B/16) · CUB-200-2011 ridge selection timeseconds per task: 7.34 -> 0.14Improved
use Cholesky factorization instead of LU decomposition for prototypes (ablation)Fly-CL (ViT-B/16) · CUB-200-2011 prototype timeseconds per task: 0.20 -> 0.10Improved
add top-k activation sparsity in similarity comparison (ablation)Fly-CL (ViT-B/16) · CUB-200-2011 similarity timeseconds per task: 0.21 -> 0.08Improved
add the random projection layer (ablation)Fly-CL (ViT-B/16) · CIFAR-100, CUB, VTAB accuracy curvesaverage accuracyImproved
add streaming ridge classification (ablation)Fly-CL (ViT-B/16) · CIFAR-100, CUB, VTAB accuracy curvesaverage accuracyImproved
add data normalization (ablation)Fly-CL (ViT-B/16) · CIFAR-100, CUB, VTAB accuracy curvesaverage accuracyImproved
increase projection dimension m (ablation)Fly-CL · CUB-200-2011accuracyImproved
replace F-OAL with Fly-CLF-OAL on ResNet-50 · VTAB overall accuracyoverall accuracy: 26.15 -> 94.00Improved
replace RanPAC with Fly-CLRanPAC (ViT-B/16) · CUB-200-2011 overall accuracyoverall accuracy: 92.67 -> 93.84Improved
replace RanPAC with Fly-CLRanPAC (ViT-B/16) · CIFAR-100 overall accuracyoverall accuracy: 94.21 -> 93.89Hurt
replace F-OAL with Fly-CLF-OAL (ViT-B/16) · CUB-200-2011 post-extraction timeseconds per task: 2.04 -> 0.35Improved

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