AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

MuonSSM: Orthogonalizing State Space Models for Sequence Modeling

Thai Khanh Nguyen, Vo Ngoc Bich Uyen, Thieu Vo, Tan Minh Nguyen, Cuong Pham

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 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
add MuonSSM (momentum + Newton-Schulz) to MambaMamba 170M · zero-shot common-sense avg (FineWeb-Edu)avg accuracy: 42.13 -> 44.23Improved
add MuonSSM to LongHornLongHorn 170M · LAMBADAperplexity: 96.80 -> 80.98Improved
add MuonSSM to LongHornLongHorn 170M · S-NIAH-PK 8Kaccuracy: 20.0 -> 39.3Improved
add MuonSSM to Gated DeltaNetGated DeltaNet 170M · S-NIAH-PK 8Kaccuracy: 25.7 -> 44.5Improved
add MuonSSM to LongHornLongHorn 170M · S-NIAH-UUID 8Kaccuracy: 19.3 -> 28.6 (Mamba+Muon improves, LongHorn 2K 46.4 -> 52.9)Mixed
add MuonSSM to LongHornLongHorn 170M · S-NIAH-PK 2Kaccuracy: 67.9 -> 66.7Hurt
add MuonSSM to MambaVision-Tiny backbonesMamba · ImageNet-1KTop-1: 81.08 -> 81.19Improved
add MuonSSM to MambaMambaVision-Tiny Mamba · ImageNet-ATop-1: 20.57 -> 20.50No clear effect
add MuonSSM to LongHornMambaVision-Tiny LongHorn · ADE20KmIoU: 44.2 -> 45.7Improved
add MuonSSM to Gated DeltaNetGated DeltaNet · MMActaccuracy: 66.39 -> 66.61No clear effect
add MuonSSM to MambaMamba · UESTC-MMEA-CLaccuracy: 87.74 -> 91.62Improved
double state dimension of Mamba instead of using Muon (ablation)Mamba · MMActaccuracy: 71.47 -> 72.52 (Muon: 74.65)Improved

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