Image de couverture de livre

AsyMoE: Leveraging Modal Asymmetry for Enhanced Expert Specialization in Large Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Heng, Hu, Haichuan, Shen, Yaomin, Yu, Weihao, Yuan, Yilei, You, Haochen, Cheng, Guo, Zhang, Zijian, Gan, Lubin, Wei, Huihui, Zhang, Hao, Huang, Jin
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
par: Zhang, Heng, et autres
Publié: (2025)

H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space
par: Zhang, Heng, et autres
Publié: (2025)

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems
par: Zhang, Heng, et autres
Publié: (2025)

GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search
par: Zhang, Heng, et autres
Publié: (2025)

G2rammar: Bilingual Grammar Modeling for Enhanced Text-attributed Graph Learning
par: Zheng, Heng, et autres
Publié: (2025)

GraphShaper: Geometry-aware Alignment for Improving Transfer Learning in Text-Attributed Graphs
par: Zhang, Heng, et autres
Publié: (2025)

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
par: Zhang, Heng, et autres
Publié: (2025)

GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks
par: Zheng, Heng, et autres
Publié: (2025)

Empowering LLMs with Structural Role Inference for Zero-Shot Graph Learning
par: Zhang, Heng, et autres
Publié: (2025)

MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding
par: Chopra, Shivang, et autres
Publié: (2025)

SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs
par: Bo, Zi-Hao, et autres
Publié: (2026)

Combining Small‐Molecular Compounds With CAR T‐Cell Therapy: Novel Strategies for Enhanced Cancer Immunotherapy
par: Rangzi Yi, et autres
Publié: (2026)

UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling
par: Liu, Pingping, et autres
Publié: (2026)

MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts
par: Lou, Yuxuan, et autres
Publié: (2026)

Modality-Specialized Synergizers for Interleaved Vision-Language Generalists
par: Xu, Zhiyang, et autres
Publié: (2024)

MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
par: Wang, Dianyi, et autres
Publié: (2025)

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
par: Zhu, Peijun, et autres
Publié: (2025)

MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE
par: Zhang, Geng, et autres
Publié: (2025)

SD-MoE: Spectral Decomposition for Effective Expert Specialization
par: Huang, Ruijun, et autres
Publié: (2026)

Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap
par: Liu, Feilong
Publié: (2026)

MoVA: Adapting Mixture of Vision Experts to Multimodal Context
par: Zong, Zhuofan, et autres
Publié: (2024)

Advancing Expert Specialization for Better MoE
par: Guo, Hongcan, et autres
Publié: (2025)

ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference
par: Shen, Zixu, et autres
Publié: (2025)

VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models
par: Qin, Guangshuo, et autres
Publié: (2026)

ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis
par: Gan, Lubin, et autres
Publié: (2026)

Agent Manufacturing: Foundation-Model Agents as First-Class Industrial Entities
par: Zhang, Yilei
Publié: (2026)

Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
par: Bai, Jun, et autres
Publié: (2025)

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
par: Jiang, Songtao, et autres
Publié: (2024)

FinSentLLM: Multi-LLM and Structured Semantic Signals for Enhanced Financial Sentiment Forecasting
par: Zhang, Zijian, et autres
Publié: (2025)

LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting
par: Zhang, Lingzheng, et autres
Publié: (2024)

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
par: Wu, Tian, et autres
Publié: (2025)

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
par: Lin, Bin, et autres
Publié: (2024)

DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification
par: Wang, Yuhao, et autres
Publié: (2024)

RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation
par: Bi, Hanbo, et autres
Publié: (2025)

Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment
par: Gan, Lubin, et autres
Publié: (2025)

Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization
par: You, Haochen, et autres
Publié: (2026)

SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts
par: Liu, Jiaqi, et autres
Publié: (2025)

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
par: Han, Feng, et autres
Publié: (2026)

OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMs
par: Gao, Yuting, et autres
Publié: (2025)

Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training
par: Chen, Yangyi, et autres
Publié: (2025)