AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training

Szymon Płotka, Gizem Mert, Pedro R. A. S. Bassi, Wenxuan Li, Zongwei Zhou, Anna M Marcinkiewicz, Wiktoria Romańczyk, Jarosław B Ćwikła, Łukasz Struski, Ewa Szczurek, Jacek Tabor, Arkadiusz Sitek

NeurIPS 2026 · Architectures and efficiency › Mixture of experts · approach: Sparse MoE as regularization and attention · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an anatomy-activated mixture-of-experts architecture for 3D medical vision-language pre-training, routing volumetric patches with organ-level anatomical context rather than isolated local features.

Problem

Medical 3D vision-language pre-training uses anatomy-agnostic encoders that apply uniform dense parameterization to all volumetric patches, and existing MoE routers gate on isolated local features without anatomical context.

Approach

Anatomy-activated MoE routing for 3D medical VLP so that expert selection is conditioned on organ/anatomical context instead of only local patch features; the abstract is truncated so exact mechanism is not fully stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add anatomy-activated MoE routing (ablation)SegMamba · AMOS-CTDSC (%): 85.5 -> 87.5Improved
add anatomy-activated MoE routing (ablation)SegMamba · AMOS-CTHD95 (mm): 17.3 -> 7.6Improved
add OQMSP organ-query alignment after A2MoE (ablation)A2MoE SegMamba · AMOS-MRIDSC (%): 78.5 -> 82.3Improved
add OQMSP organ-query alignment after A2MoE (ablation)A2MoE SegMamba · AMOS-CTHD95 (mm): 7.6 -> 6.2Improved
add OQMSP organ-query alignment after A2MoE (ablation)A2MoE SegMamba · GEPAR3DHD95 (mm): 7.9 -> 8.1Hurt
add histogram embedding to router (ablation)MoE router · AMOS-CTDSC (%): 86.0 -> 87.0Improved
add class-to-expert affinity prior to router (ablation)MoE router with histogram · AMOS-CTHD95 (mm): 12.0 -> 7.6Improved
add affinity prior and histogram (ablation)MoE router · AMOS-MRIDSC (%): 77.4 -> 78.5Improved
use [16,16,16,16] experts instead of [8,8,8,8] (ablation)A2MoE · PANORAMAmDSC (%): 75.1 -> 78.2Improved
use [16,16,16,16] experts instead of [4,4,4,4] (ablation)A2MoE · AMOS-CTmDSC (%): 87.5 -> 86.9Hurt
use pyramid expert allocation [4,8,16,32] (ablation)A2MoE · multiple datasetsmDSC (%): 77.4 vs 78.2 (PANORAMA); 86.1 vs 86.2 (GEPAR3D)Mixed

Limitations

Experimental setup

Builds on: mixture-of-experts

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