Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique to address the massive memory and computation overhead. Existing quantization paradigms fall short as they are oblivious to two critical forms of heterogeneity: the inherent discrepancy between vision and language tokens, and the non-uniform contribution of different experts. To bridge this gap, we propose Visual Expert Quantization (VEQ), a dual-aware quantization framework designed to simultaneously accommodate cross-modal differences and heterogeneity between experts. Specifically, VEQ incorporates 1)Modality-expert-aware Quantization, which utilizes expert activation frequency to prioritize error minimization for pivotal experts, and 2)Modality-affinity-aware Quantization, which constructs an enhanced Hessian matrix by integrating token-expert affinity with modality information to guide the calibration process. Extensive experiments across diverse benchmarks verify that VEQ consistently outperforms state-of-the-art baselines. Specifically, under the W3A16 configuration, our method achieves significant average accuracy gains of 2.04\% on Kimi-VL and 3.09\% on Qwen3-VL compared to the previous SOTA quantization methods, demonstrating superior robustness across various multimodal tasks. Our code will be available at https://github.com/guangshuoqin/VEQ.
MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Zhongguancun Academy（中关村学院）
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
School of Software, Tsinghua University, Beijing, China（清华大学软件学院，北京，中国）；TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China（天津大学计算机科学与技术学院，中国）；School of New Media and Communication, Tianjin University, China（天津大学新媒体与传播学院，中国）
MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
Fudan University（复旦大学）；Shanghai Innovation Institut（上海创新研究院）；University of Southern California（南加州大学）；Huawei Technologies Co., Ltd（华为技术有限公司）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Institute of Digital Twin, EIT（宁波空间智能与数字衍生关键实验室，数字孪生研究院，EIT）
Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models
China University of Petroleum (Beijing)（中国石油大学（北京））；Hainan Institute of China University of Petroleum (Beijing)（中国石油大学（北京）海南学院）；South China Normal University（华南师范大学）
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；YUKUN Intelligent World（宇琨智能世界）
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）
ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding
International Digital Economy Academy（国际数字经济学院）；Tsinghua University（清华大学）；Peking University（北京大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
IMA-MoE: An Interpretable Modality-Aware Mixture-of-Experts Framework for Characterizing the Neurobiological Signatures of Binge Eating Disorder
Department of Biomedical Engineering, New Jersey Institute of Technology（新泽西理工学院生物医学工程系）；College of Engineering, Northeastern University（东北大学工程学院）；Department of Psychiatry, Icahn School of Medicine at Mount Sinai（辛克尔医学中心精神科部门）；School of Computing, University of Georgia（佐治亚大学计算机科学学院）
LLMs Can Evolve Continually on Modality for X-Modal Reasoning
Dalian University of Technology（大连理工大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology（香港科技大学）
Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging
Technical University of Munich (TUM)（慕尼黑工业大学）；TUM University Hospital（慕尼黑工业大学附属医院）；Hasso Plattner Institute for Digital Engineering（哈索·普拉特纳数字工程研究所）；University of Potsdam（波茨坦大学）；Imperial College London（伦敦帝国理工学院）
Flexible Multimodal Neuroimaging Fusion for Alzheimer's Disease Progression Prediction
Department of Computer Science and Engineering（计算机科学与工程系）；Department of Biomedical Informatics（生物医学信息学系）；Department of Neurology（神经病学系）；Translational Data Analytics Institute（转化数据分析研究所）
DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis
Department of Systems Engineering, Stevens Institute of Technology（史蒂文斯理工学院系统工程系）；Department of Neurosurgery, Robert Wood Johnson Medical School, Rutgers University（罗格斯大学罗伯特·伍德·约翰逊医学院神经外科）
VLT: A Vision-Language-Time Series Multimodal Foundation Model for Industrial Intelligence
School of Automation Science and Electrical Engineering, Beihang University（北京航空航天大学自动化科学与电气工程学院）；Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）；State Key Laboratory of Intelligent Manufacturing System Technology（智能制造系统技术国家重点实验室）；School of Computer Science and Artificial Intelligence, Zhengzhou University（郑州大学计算机科学与人工智能学院）
Northwestern University（西北大学）；Northwestern University Feinberg School of Medicine（西北大学费恩伯格医学院）；Simpson Querrey Lung Institute for Translational Science（辛普森奎雷转化科学肺研究所）
Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing
School of Computer Science, Peking University（北京大学计算机科学学院）；MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室）；National Key Laboratory for Multimedia Information Processing, Peking University（北京大学国家多媒体信息处理重点实验室）
BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Great Bay University（大湾区大学）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室）；Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）
EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
School of iOPEN, Northwestern Polytechnical University（iOPEN学院，西北工业大学）；The First Affiliated Hospital of Sun Yat-Sen University（中山大学附属第一医院）；College of Mechanical Engineering, Tongji University（同济大学机械工程学院）
Large sparsely-activated models have obtained excellent performance in multiple domains. However, such models are typically trained on a single modality at a time. We present the Language-Image MoE, LIMoE, a sparse mixture of experts model capable of multimodal learning. LIMoE accepts both images and text simultaneously, while being trained using a contrastive loss. MoEs are a natural fit for a multimodal backbone, since expert layers can learn an appropriate partitioning of modalities. However, new challenges arise; in particular, training stability and balanced expert utilization, for which …
MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion
Beijing University of Posts and Telecommunications（北京邮电大学）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Communication University of China（中国传媒大学）
The University of Edinburgh（爱丁堡大学）；Imperial College, London（伦敦帝国学院）；University of Surrey（萨里大学）；Queen Mary University of London（伦敦玛丽女王大学）；Microsoft Research, Cambridge（微软研究院剑桥分部）
