AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

SeeDNorm: Self-Rescaled Dynamic Normalization

Wenrui Cai, Defa Zhu, Siyuan Qiao, Qingjie Liu, Qiyang Min

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch

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 RMSNorm with SeeDNormOLMoE-1.3B · c4_en-validationloss: 2.922 -> 2.900Improved
replace RMSNorm with SeeDNormOLMoE-7B · c4_en-validationloss: 2.644 -> 2.631Improved
replace RMSNorm with SeeDNormOLMo2-550M · c4_en-validationloss: 3.011 -> 3.008No clear effect
replace RMSNorm with SeeDNormOLMo2-1B · ARC-Easyaccuracy: 68.7 -> 70.0Improved
replace normalization with DyTOLMoE-1.3B · c4_en-validationloss: 2.922 -> 2.968Hurt
use SeeDNorm instead of LayerNormViT-B · ImageNet-1KAcc@1: 82.3 -> 82.7Improved
use unbounded activation (GeLU, Swish) for sigma (ablation)SeeDNorm OLMoE-1.3B · trainingconvergenceHurt
tanh vs other bounded activations (sigmoid, hardtanh) (ablation)SeeDNorm OLMoE-1.3B · training losslossImproved
initialize alpha to 10 instead of 1 (ablation)SeeDNorm · c4_en-validationloss: 2.900 -> 3.154Hurt
make alpha a vector rather than scalar (ablation)SeeDNorm · c4_en-validationloss: 2.909 -> 2.900Improved
use dot product instead of element-wise product of beta and x (ablation)SeeDNorm · c4_en-validationloss: 2.909 -> 2.900Improved
use multi-head SeeDNorm instead of single head (ablation)SeeDNorm ViT-B · ImageNet-1KAcc@1: fail to converge -> 82.7Improved

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