Cover Image

EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Ze, Yang, Sen, Duan, Boqiang, Yang, Wankou, Wang, Jingdong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding
by: Dai, Ming, et al.
Published: (2025)

Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling
by: Feng, Ze, et al.
Published: (2025)

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
by: Li, Zheng, et al.
Published: (2024)

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
by: Cai, Yuxuan, et al.
Published: (2024)

Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
by: Sun, Haoyi, et al.
Published: (2026)

Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
by: Chen, Lin, et al.
Published: (2026)

A Survey of Token Compression for Efficient Multimodal Large Language Models
by: Shao, Kele, et al.
Published: (2025)

GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
by: Li, Yuqi, et al.
Published: (2026)

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
by: Zhang, Shaolei, et al.
Published: (2025)

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
by: Feng, Qianhan, et al.
Published: (2024)

CLIP-KD: An Empirical Study of CLIP Model Distillation
by: Yang, Chuanguang, et al.
Published: (2023)

Improving Generalized Visual Grounding with Instance-aware Joint Learning
by: Dai, Ming, et al.
Published: (2025)

Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
by: Liu, Ting, et al.
Published: (2024)

CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
by: Lee, Jungsoo, et al.
Published: (2025)

Object-level Geometric Structure Preserving for Natural Image Stitching
by: Cai, Wenxiao, et al.
Published: (2024)

SpatialBot: Precise Spatial Understanding with Vision Language Models
by: Cai, Wenxiao, et al.
Published: (2024)

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
by: Zhao, Shiyu, et al.
Published: (2024)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
by: Cao, Sihan, et al.
Published: (2026)

TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
by: Li, Ao, et al.
Published: (2025)

InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba
by: Wang, Yuhang, et al.
Published: (2025)

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
by: Luo, Junwei, et al.
Published: (2025)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
by: Tan, Xudong, et al.
Published: (2025)

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
by: Yang, Longrong, et al.
Published: (2024)

LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
by: Habib, Gousia, et al.
Published: (2023)

Grounding Everything in Tokens for Multimodal Large Language Models
by: Ren, Xiangxuan, et al.
Published: (2025)

Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities
by: Liu, Huan, et al.
Published: (2024)

KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling
by: Wang, Yu, et al.
Published: (2022)

TopKD: Top-scaled Knowledge Distillation
by: Wang, Qi, et al.
Published: (2025)

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
by: Wang, Xinhao, et al.
Published: (2026)

EA-KD: Entropy-based Adaptive Knowledge Distillation
by: Su, Chi-Ping, et al.
Published: (2023)

AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
by: Li, Yuqi, et al.
Published: (2025)

Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models
by: Luan, Bozhi, et al.
Published: (2025)

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
by: Wang, Yahong, et al.
Published: (2026)

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
by: Wang, Chao, et al.
Published: (2025)

LLAVADI: What Matters For Multimodal Large Language Models Distillation
by: Xu, Shilin, et al.
Published: (2024)

TokenCom: Vision-Language Model for Multimodal and Multitask Token Communications
by: Jiang, Feibo, et al.
Published: (2026)

ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
by: Ye, Wencheng, et al.
Published: (2025)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding
by: Fan, Rong, et al.
Published: (2026)

MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
by: Li, Yuqi, et al.
Published: (2025)