Cover Image

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Kexin, Xiao, Jing, Chen, Chaofeng, Min, Geyong, Zhu, Guibo, Wang, Jinqiao, Liao, Liang
Format:	Preprint
Published:	2026
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

ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
by: Sha, Lin, et al.
Published: (2026)

Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models
by: Zhan, Yufei, et al.
Published: (2024)

ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
by: Ye, Xubing, et al.
Published: (2024)

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

Similarity-Aware Token Pruning: Your VLM but Faster
by: Jeddi, Ahmadreza, et al.
Published: (2025)

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

A Benchmark for Crime Surveillance Video Analysis with Large Models
by: Chen, Haoran, et al.
Published: (2025)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
by: Liu, Jizhihui, et al.
Published: (2025)

VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation
by: Chen, Hanning, et al.
Published: (2024)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
by: Lee, Dong-Jae, et al.
Published: (2026)

Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance
by: Liang, Yuxuan, et al.
Published: (2025)

Dynamic Token Reduction during Generation for Vision Language Models
by: Liang, Xiaoyu, et al.
Published: (2025)

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

Topology-Aware Layer Pruning for Large Vision-Language Models
by: Zheng, Pengcheng, et al.
Published: (2026)

AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection
by: Gu, Zhaopeng, et al.
Published: (2025)

Attention Debiasing for Token Pruning in Vision Language Models
by: Zhao, Kai, et al.
Published: (2025)

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
by: Ma, Shilin, et al.
Published: (2026)

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
by: Gu, Zhaopeng, et al.
Published: (2024)

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
by: Zeng, Quan-Sheng, et al.
Published: (2025)

GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models
by: Pei, Ruiguang, et al.
Published: (2025)

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models
by: Zhang, Pu, et al.
Published: (2025)

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

Auto DragGAN: Editing the Generative Image Manifold in an Autoregressive Manner
by: Cai, Pengxiang, et al.
Published: (2024)

Towards Joint Quantization and Token Pruning of Vision-Language Models
by: Li, Xinqing, et al.
Published: (2026)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
by: Huang, Xiaohu, et al.
Published: (2024)

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

Object-Centric Vision Token Pruning for Vision Language Models
by: Li, Guangyuan, et al.
Published: (2025)

FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
by: Gu, Zhaopeng, et al.
Published: (2025)

TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understanding
by: Yang, Fan, et al.
Published: (2026)

AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance
by: Zhang, Weichen, et al.
Published: (2025)

BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model
by: Li, Haosheng, et al.
Published: (2026)

IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
by: Sun, Zhichao, et al.
Published: (2026)

Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models
by: He, Landi, et al.
Published: (2026)

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
by: Endo, Mark, et al.
Published: (2024)

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models
by: Liu, Yuchen, et al.
Published: (2025)

LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models
by: Takezoe, Rinyoichi, et al.
Published: (2026)

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

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
by: Meng, Yu, et al.
Published: (2025)

CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models
by: Cheng, Xinle, et al.
Published: (2025)

ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models
by: Kim, Youngeun, et al.
Published: (2025)