AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting

Hao Chen, Han Tao, Guo Song, Jie Zhang, Yonghan Dong, Yunlong Yu, Lei Bai

ICCV 2025 · Architectures and efficiency › Mixture of experts · approach: Expert routing and specialization · 3 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 plain MoE with VA-MoE (channel-adaptive experts) (ablation)ViT+MoE · ERA5 1.5deg Z500 120hRMSE: 356.02 -> 302.13Improved
replace ViT with VA-MoE (ablation)ViT · ERA5 1.5deg Z500 120hRMSE: 517.81 -> 302.13Improved
replace light MoE with VA-MoE (ablation)ViT+MoE (light) · ERA5 1.5deg Z500 120hRMSE: 405.73 -> 302.13Improved
replace ViT with VA-MoE (ablation)ViT · ERA5 1.5deg T500 120hRMSE: 2.40 -> 1.59Improved
incremental training of surface variables, 1979-2020 data, half iterationsVA-MoE · ERA5 0.25deg U10 120hRMSE: 2.25 -> 2.33Hurt
incremental training of surface variables, 1979-2020 data, half iterationsVA-MoE · ERA5 0.25deg T2M 120hRMSE: 1.42 -> 1.45Hurt
reduce incremental data to 2000-2020 and quarter of iterationsVA-MoE (IL) · ERA5 0.25deg MSL 120hRMSE: 281.6 -> 304.7Hurt
reduce incremental data to 2000-2020 and quarter of iterationsVA-MoE (IL) · ERA5 0.25deg T2M 120hRMSE: 1.45 -> 1.57Hurt
add incremental training of surface variables after upper-air trainingVA-MoE · ERA5 0.25deg Z500 120hRMSE: 295.52 -> 292.63Improved
add incremental training of surface variables after upper-air trainingVA-MoE · ERA5 1.5deg Z500 120hRMSE: 302.13 -> 301.41No clear effect
add incremental training of surface variables after upper-air trainingVA-MoE · ERA5 0.25deg V500 72hRMSE: 3.04 -> 3.51Hurt

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