Cover Image

Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lei, Lei, Gu, Jie, Ma, Xiaokang, Tang, Chu, Chen, Jingmin, Xu, Tong
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

Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model
by: Ji, Bokai, et al.
Published: (2025)

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
by: Yao, Linli, et al.
Published: (2024)

Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
by: Li, Mingxing, et al.
Published: (2025)

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models
by: Liu, Juntao, et al.
Published: (2025)

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

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

PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models
by: Huang, Mouxiao, et al.
Published: (2025)

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos
by: Li, Can, et al.
Published: (2026)

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

Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning
by: Cao, Qinglong, et al.
Published: (2026)

A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment
by: Wu, Tianhe, et al.
Published: (2024)

Vision-centric Token Compression in Large Language Model
by: Xing, Ling, et al.
Published: (2025)

Gaussian Sequences with Multi-Scale Dynamics for 4D Reconstruction from Monocular Casual Videos
by: Li, Can, et al.
Published: (2026)

Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
by: Peng, Tianfan, et al.
Published: (2025)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models
by: Ma, Kexin, et al.
Published: (2026)

TokenPacker: Efficient Visual Projector for Multimodal LLM
by: Li, Wentong, et al.
Published: (2024)

An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks
by: Liu, Lei, et al.
Published: (2025)

Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning
by: Xu, Hai-Ming, et al.
Published: (2024)

Scaling Mesh Generation via Compressive Tokenization
by: Weng, Haohan, et al.
Published: (2024)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
by: Wang, Yiyu, et al.
Published: (2025)

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

LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models
by: Hu, Qingqiao, et al.
Published: (2025)

Introducing Visual Perception Token into Multimodal Large Language Model
by: Yu, Runpeng, et al.
Published: (2025)

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling
by: Song, Jiafei, et al.
Published: (2026)

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

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression
by: Tong, Bo, et al.
Published: (2024)

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
by: Lan, Xiaohan, et al.
Published: (2024)

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
by: Hu, Lianyu, et al.
Published: (2025)

Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models
by: Yu, Gaotong, et al.
Published: (2024)

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

InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models
by: Wang, Haomin, et al.
Published: (2025)

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
by: Zhong, Weihong, et al.
Published: (2024)

Can Multimodal Large Language Models Understand Spatial Relations?
by: Liu, Jingping, et al.
Published: (2025)

Enhancing Explainability in Multimodal Large Language Models Using Ontological Context
by: Amara, Jihen, et al.
Published: (2024)

Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models
by: Yang, Zhongyu, et al.
Published: (2025)

MedSeg-R: Reasoning Segmentation in Medical Images with Multimodal Large Language Models
by: Huang, Yu, et al.
Published: (2025)

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
by: Lee, Jaewoo, et al.
Published: (2025)

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models
by: Zhang, Zhifang, et al.
Published: (2025)

Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information
by: Chen, Yi, et al.
Published: (2024)