AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models

Xingkui Zhu, Dingkang Liang, Cheng Chen, Daoxin Zhang, lv Hanxiang, Zhe Xu, Yao Hu, Xiang Bai

CVPR 2026 · Architectures and efficiency › Mixture of experts · approach: Sparse MoE as regularization and attention

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 dense FFN with Nexus Layer (same FLOPs)ViT-S · ImageNet-1K valTop-1 accuracy (%): 78.8 -> 81.2Improved
use Nexus instead of SoftMoEViT-S · ImageNet-1K valTop-1 accuracy (%): 80.8 -> 81.2, FLOPs 5.4G -> 4.3GImproved
use Nexus instead of Memory+ViT-S · ImageNet-1K valTop-1 accuracy (%): 79.3 -> 81.2Improved
use Nexus instead of SoftMoEConvNeXt-S · ImageNet-1K valTop-1 accuracy (%): 83.9 -> 83.9No clear effect
use Nexus instead of denseConvNeXt-B · ImageNet-1K valTop-1 accuracy (%): 83.8 -> 84.5Improved
add Memory+ layersConvNeXt-B · ImageNet-1K valTop-1 accuracy (%): 83.8 -> 83.8No clear effect
use Nexus instead of denseViT-S Mask R-CNN · COCO val2017APbbox: 40.2 -> 42.7Improved
use Nexus instead of denseViT-S · ADE20KmIoU (%): 44.6 -> 45.8Improved
use unified routing instead of Product Key routing in memory layers (ablation)ViT-S · ImageNet-1K valTop-1 accuracy (%): 79.4 -> 80.1Improved
use unified routing instead of Expert Choice routing over memory values (ablation)ViT-S · ImageNet-1K valFLOPs (G): 59.9 -> 4.2 (EC runs out of memory)Improved
add expert units to a memory-only layer under fixed parameter budget (ablation)Nexus · ImageNet-1K valTop-1 accuracy (%): 80.1 -> 81.2Improved
use a hybrid memory/expert allocation instead of expert-only (ablation)Nexus · ImageNet-1K valTop-1 accuracy (%): 80.8 -> 81.2, expert-only costs over 1.2x computeImproved

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