Heterogeneous medical image data motivate domain-specialized diffusion experts, but expert specialization alone does not determine how their predictions should be combined during sampling. Learning a global router is particularly challenging when the server has limited, potentially unrepresentative images. We study two router-learning strategies for a fixed expert pool. Server-Only learns input- and timestep-dependent expert assignments from server images with component labels. Anchor-Delta (AD) uses the same images and frozen experts to obtain additional evidence from denoising losses. It distills targets that combine this evidence with the current router's assignments, while a proxy gate controls a subsequent refinement step. Component labels describe data origin; expert losses measure empirical prediction performance. We evaluate these distinct signals through routing analyses and paired medical image generation. An AD-trained router improves generation metrics over Server-Only in a heterogeneous four-domain setting, and a separate server-data study shows gains in held-out routing over a corrected-routing comparator. Additional paired evaluations show that the effect of inference-time evidence mixing varies across benchmarks. These findings establish server-data availability and expert performance as distinct considerations in learning routers for multi-domain diffusion models.
Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock
Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model
School of Software Technology, Zhejiang University(浙江大学软件学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Electronic and Information, Shanghai Dianji University(上海电机学院电子信息学院)
Stable Routing for Mixture-of-Experts in Class-Incremental Learning
State Key Laboratory of Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);School of Artificial Intelligence, Nanjing University(南京大学人工智能学院)
GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving
School of Automotive Studies, Tongji University(汽车学院,同济大学);School of Electronics and Information Engineering, Control Science and Engineering Department, Tongji University(电子信息学院,控制科学与工程系,同济大学)
Robust Mixture-of-Expert Training for Convolutional Neural Networks
Michigan State University(密歇根州立大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);The University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);MIT(麻省理工学院);Harvard University(哈佛大学);UC Santa Barbara(加州大学圣巴巴拉分校);Carnegie Mellon University(卡内基梅隆大学);UIUC(伊利诺伊大学厄巴纳-香槟分校);IBM Research(IBM研究院)
Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models
The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province, Xidian University, China(陕西省智能人机交互与可穿戴技术重点实验室,西安电子科技大学);Warren Alpert Medical School, Brown University, USA(布朗大学沃伦·阿尔珀特医学院);National University of Singapore, Singapore(新加坡国立大学)
Intelligent Communication Mixture-of-Experts Boosted-Medical Image Segmentation Foundation Model
College of Optoelectronics Engineering, Chongqing University, Chongqing, China;Center of Digital Dentistry, Peking University School;Hospital of Stomatology \& NHC Key Laboratory of Digital Stomatology, Beijing, China
Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
Faculty of Mathematics, Informatics, and Mechanics, University of Warsaw(华沙大学数学、信息学与力学系);Faculty of Mathematics and Computer Science, Jagiellonian University(雅盖隆大学数学与计算机科学系);Institute of AI for Health, Helmholtz Munich(海德堡医学院人工智能与健康研究所);Faculty of Electronics and Information Technology, Warsaw University of Technology(华沙理工大学电子与信息技术系);NASK - National Research Institute(国家研究 institute);Faculty of Radiology, Massachusetts General Hospital(麻省总医院放射学系);Department of Radiology, Harvard Medical School(哈佛医学院放射学系)