Image de couverture de livre

FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xia, Guoyang, Ding, Yifeng, Li, Fengfa, Ren, Lei, Chen, Wei, Feng, Fangxiang, Wang, Xiaojie
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SMAR: Soft Modality-Aware Routing Strategy for MoE-based Multimodal Large Language Models Preserving Language Capabilities
par: Xia, Guoyang, et autres
Publié: (2025)

MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts
par: Yu, Haofei, et autres
Publié: (2023)

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
par: Ouyang, Haojie, et autres
Publié: (2025)

FastVID: Dynamic Density Pruning for Fast Video Large Language Models
par: Shen, Leqi, et autres
Publié: (2025)

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
par: Wang, Xinhao, et autres
Publié: (2026)

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
par: Wen, Zichen, et autres
Publié: (2025)

Lngram: N-gram Conditional Memory in Latent Space
par: Zheng, Yunao, et autres
Publié: (2026)

DiffHarmony: Latent Diffusion Model Meets Image Harmonization
par: Zhou, Pengfei, et autres
Publié: (2024)

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
par: Cao, Jianjian, et autres
Publié: (2024)

Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
par: Zhang, Dingkun, et autres
Publié: (2026)

MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
par: Huang, Yushi, et autres
Publié: (2025)

Concept Conductor: Orchestrating Multiple Personalized Concepts in Text-to-Image Synthesis
par: Yao, Zebin, et autres
Publié: (2024)

Route Experts by Sequence, not by Token
par: Wen, Tiansheng, et autres
Publié: (2025)

FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
par: Yao, Zebin, et autres
Publié: (2025)

Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models
par: Wu, Qiong, et autres
Publié: (2024)

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
par: Wang, Yahong, et autres
Publié: (2026)

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
par: Lee, Jaewoo, et autres
Publié: (2025)

Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
par: Ye, Weihao, et autres
Publié: (2024)

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
par: Le, Qi, et autres
Publié: (2025)

HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
par: Guo, Yansong, et autres
Publié: (2026)

MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts
par: Zeng, Zinan, et autres
Publié: (2024)

Saliency-driven Dynamic Token Pruning for Large Language Models
par: Tao, Yao, et autres
Publié: (2025)

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
par: He, Peize, et autres
Publié: (2026)

TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
par: Yang, Cheng, et autres
Publié: (2025)

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
par: Alvar, Saeed Ranjbar, et autres
Publié: (2025)

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
par: Zhao, Shiyu, et autres
Publié: (2024)

FastAV: Efficient Token Pruning for Audio-Visual Large Language Model Inference
par: Jung, Chaeyoung, et autres
Publié: (2026)

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
par: Ma, Kexin, et autres
Publié: (2026)

Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
par: Oncescu, Costin-Andrei, et autres
Publié: (2025)

Accelerating Matrix Factorization by Dynamic Pruning for Fast Recommendation
par: Wu, Yining, et autres
Publié: (2024)

TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models
par: Zhang, Hao, et autres
Publié: (2025)

How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
par: Chen, Wei, et autres
Publié: (2026)

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
par: Liu, Haozhe, et autres
Publié: (2025)

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models
par: Liang, Xun, et autres
Publié: (2025)

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
par: Zhu, Qihui, et autres
Publié: (2026)

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
par: Wu, Qiong, et autres
Publié: (2024)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
par: Liu, Zheyuan, et autres
Publié: (2025)

ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning
par: Gao, Shangqian, et autres
Publié: (2025)

DynaMMo: Dynamic Model Merging for Efficient Class Incremental Learning for Medical Images
par: Qazi, Mohammad Areeb, et autres
Publié: (2024)

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
par: Sun, Fengyuan, et autres
Publié: (2025)