AI Paper Atlas

Research map / Continual learning / Online and replay-based

FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning

Hongwei Yan, Guanglong Sun, Kanglei Zhou, Qian Li, Liyuan Wang, Yi Zhong

ICLR 2026 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 2 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 REAR analytic random-expanded router to prompt experts (ablation)FlyPrompt · CIFAR-100 Si-Blurry (Sup-21K)A_auc: 80.75 -> 81.90 (no EMA); 82.17 -> 83.24 (with EMA)Improved
add REAR router (ablation)FlyPrompt (Sup-21K/1K) · CIFAR-100A_auc: 72.51 -> 78.48Improved
add EMA temporal-ensemble heads (ablation)FlyPrompt · CIFAR-100 Si-Blurry (Sup-21K)A_auc: 81.90 -> 83.24Improved
add EMA heads to single-prompt baseline without REAR (ablation)single prompt · CIFAR-100 Si-Blurry (Sup-21K)A_auc: 71.33 -> 71.69No clear effect
add prompt experts (multi-prompt across tasks) (ablation)FlyPrompt · CIFAR-100 Si-Blurry (Sup-21K)A_auc: 71.33 -> 80.75Improved
replace expert routing with RanPAC analytic classifier (ablation)FlyPrompt · CIFAR-100 Si-Blurry (Sup-21K)A_auc: 83.24 -> 69.91Hurt
plug REAR into DualPrompt (ablation)DualPrompt · CIFAR-100 (Sup-21K)A_auc: 76.04 -> 80.63Improved
plug REAR into MVP (ablation)MVP · CIFAR-100 (Sup-21K)A_auc: 67.74 -> 67.44No clear effect
plug TE2 into MVP (ablation)MVP · CIFAR-100 (Sup-21K)A_auc: 67.74 -> 68.91Improved
use two EMA heads (0.9, 0.99) instead of online head only (ablation)FlyPrompt · CIFAR-100A_auc: 81.90 -> 83.24Improved
use a single slow EMA head 0.999 (ablation)FlyPrompt · CIFAR-100A_auc: 81.90 -> 81.80No clear effect
use SoftMax + element-wise max instead of mean ensemble (ablation)FlyPrompt · CIFAR-100A_auc: 81.34 -> 83.24Improved

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