AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm

Xiao Fan, Jingyan Jiang, Zhaoru Chen, Fanding Huang, Xiao Chen, Qinting Jiang, Bowen Zhang, Xing Tang, Zhi Wang

AAAI 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 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 load balancing loss (ablation)MoETTA · Average over 3 settingsaccuracy (%): 21.28 -> 66.20Improved
add sample-wise router (ablation)MoETTA · Average over 3 settingsaccuracy (%): 27.42 -> 66.20Improved
add MoE-LayerNorm module (ablation)MoETTA · Average over 3 settingsaccuracy (%): 22.42 -> 66.20Improved
add layer-wise router (ablation)MoETTA · Average over 3 settingsaccuracy (%): 19.89 -> 66.20Improved
add gradient flow from entropy loss to router (ablation)MoETTA · Average over 3 settingsaccuracy (%): 63.96 -> 66.20Improved
add entropy re-weighting (ablation)MoETTA · Average over 3 settingsaccuracy (%): 61.72 -> 66.20Improved
add sample selection (ablation)MoETTA · Average over 3 settingsaccuracy (%): 62.89 -> 66.20Improved
add sample selection (ablation)MoETTA · Potpourri+accuracy (%): 57.61 -> 66.21Improved
add sample selection (ablation)MoETTA · Classical mixed shiftsaccuracy (%): 67.04 -> 67.25No clear effect
replace best baseline MGTTA with MoETTAMoETTA vs MGTTA · Potpourri (ViT-B/16)accuracy (%): 62.98 -> 65.12Improved
scale backbone to ViT-L/16, MoETTA vs EATAMoETTA · Potpourri (ViT-L/16)accuracy (%): 64.6 -> 64.4Hurt
use MoETTA instead of EATA on ViT-L/16MoETTA vs EATA · Classical mixed shifts (ViT-L/16)accuracy (%): 66.6 -> 68.8Improved

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