AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding

Bonan Zhang, Shiyu Dong, Quan Tran, Katharina Gschwind, Shuqi Yang, Sijia Chen, Adel Ahmadyan, Seungwhan Moon, Lu Zhang, Ahmed Kirmani, Babak Damavandi, Anuj Kumar

ECCV 2026 · Architectures and efficiency › Mixture of experts · approach: Expert routing and specialization · 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
replace dense MLP with fine-grained MoE (ViT-B/32) (ablation)CLIP vision encoder · Zero-shot avg classification (B/32, 12.8B samples)avg accuracy: 55.8 -> 63.2Improved
use fine-grained MoE instead of conventional MoE (ViT-B/32) (ablation)MoE-ViE · Zero-shot avg classification (B/32, 12.8B samples)avg accuracy: 59.9 -> 63.2Improved
use fine-grained MoE instead of conventional MoE (ViT-L/16) (ablation)MoE-ViE · Zero-shot avg classification (L/16, 12.8B samples)avg accuracy: 78.5 -> 79.6Improved
z-score magnitude-aware bias update instead of sign update in loss-free balancing (ablation)MoE-ViE-B/32 · Load balancing ablation (MoE-ViE-B/32)avg classification: 62.6 -> 63.2Improved
loss-free balancing instead of importance/load auxiliary loss (ablation)MoE-ViE-B/32 · Load balancing ablation (MoE-ViE-B/32)avg classification: 59.9 -> 62.6Improved
add one shared expert (ablation)MoE-ViE-B/32 · Shared experts ablation (MoE-ViE-B/32)avg classification: 62.1 -> 63.2Improved
increase shared experts from 1 to 4 (ablation)MoE-ViE-B/32 · Shared experts ablation (MoE-ViE-B/32)avg classification: 63.2 -> 62.5Hurt
vary shared expert weight lambda from 0.01 to 10 (ablation)MoE-ViE-B/32 · Weight of shared expertsavg classification: 62.9 - 63.2No clear effect
increase top-k from 8 to 16 (ablation)MoE-ViE-B/32 · Top-k ablation (MoE-ViE-B/32)avg classification: 63.2 -> 63.1No clear effect
reduce top-k from 8 to 4 (ablation)MoE-ViE-B/32 · Top-k ablation (MoE-ViE-B/32)avg classification: 63.2 -> 62.4Hurt
make experts finer (width 1/4 vs full width) (ablation)MoE-ViE-B/32 · Expert width ablation (MoE-ViE-B/32)avg classification: 59.9 -> 63.2Improved
make experts finer still (1/8 width vs 1/4) (ablation)MoE-ViE-B/32 · Expert width ablation (MoE-ViE-B/32)avg classification: 63.2 -> 62.8No clear effect

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