AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge

Wonseon Lim, Jaesung Lee, Dae-Won Kim

CVPR 2026 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 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
replace random patch dropping (PD) with critical patch sampling (CPS) (ablation)CODA-Prompt with 0.5 patch reduction · ImageNet-R (reduction ratio 0.5)accuracy ACC_N: 45.32 -> 47.16Improved
add DPCT to PD (ablation)CODA-Prompt w/ PD · ImageNet-R (reduction ratio 0.5)accuracy ACC_N: 45.32 -> 47.96Improved
add DPCT to CPS (ablation)CODA-Prompt w/ CPS · ImageNet-R (reduction ratio 0.5)accuracy ACC_N: 47.16 -> 49.28Improved
add DPCT to CPS (ablation)CODA-Prompt w/ CPS · ImageNet-R (reduction ratio 0.5)training time per task: 1,389 s/task -> 1,126 s/taskImproved
add CPS and DPCT to CODA-PromptCODA-Prompt · ImageNet-R (reduction ratio 0.5)peak memory: 440 MB -> 253 MBImproved
add CPS and DPCT to CODA-PromptCODA-Prompt · ImageNet-R (reduction ratio 0.5)training time per task: 1,788 s/task -> 1,126 s/taskImproved
add CPS and DPCT to CODA-PromptCODA-Prompt · ImageNet-R (reduction ratio 0.5)accuracy ACC_N: 50.24 -> 49.28Hurt
lower sampling temperature in CPS (ablation)CPS-Prompt · CUB-200accuracyImproved
use moderate phase ratio lambda in 0.4-0.6 (ablation)CPS-Prompt · CUB-200accuracyImproved
use stochastic multinomial sampling instead of deterministic top-k (ablation)CPS-Prompt · CUB-200accuracyImproved
compare CPS-Prompt with C-PromptCPS-Prompt · CIFAR-100, ImageNet-R, CUB-200memory, time, energy: about 4.3x memory, 3.1x time, 3.3x energyImproved
compare CPS-Prompt with CODA-PromptCPS-Prompt · CIFAR-100, ImageNet-R, CUB-200memory, time, energy: about 1.6x less memory, 1.5x shorter time, 1.6x less energyImproved

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