Image de couverture de livre

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Apedo, Yvon, Poreba, Martyna, Szczepanski, Michal, Bouchafa, Samia
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions
par: Szczepanski, Michal, et autres
Publié: (2025)

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
par: Sassoon, Jordan, et autres
Publié: (2025)

Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
par: Galagain, Calvin, et autres
Publié: (2026)

TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
par: Li, Ao, et autres
Publié: (2025)

Object-Centric Vision Token Pruning for Vision Language Models
par: Li, Guangyuan, et autres
Publié: (2025)

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
par: Li, Kaiyuan, et autres
Publié: (2025)

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models
par: Meng, Yu, et autres
Publié: (2025)

Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
par: He, Jialuo, et autres
Publié: (2026)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
par: Lee, Dong-Jae, et autres
Publié: (2026)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
par: Son, Jaemin, et autres
Publié: (2025)

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

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models
par: Zhang, Pu, et autres
Publié: (2025)

ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
par: Sha, Lin, et autres
Publié: (2026)

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
par: Ma, Jie, et autres
Publié: (2026)

Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models
par: Góral, Gracjan, et autres
Publié: (2025)

FoPru: Focal Pruning for Efficient Large Vision-Language Models
par: Jiang, Lei, et autres
Publié: (2024)

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
par: Arif, Kazi Hasan Ibn, et autres
Publié: (2024)

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
par: Liu, Shengyuan, et autres
Publié: (2026)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
par: Zhang, Qizhe, et autres
Publié: (2025)

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference
par: Kang, Beomseok, et autres
Publié: (2026)

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
par: Huang, Mingzhe, et autres
Publié: (2026)

Exploring Token Pruning in Vision State Space Models
par: Zhan, Zheng, et autres
Publié: (2024)

PAS : Prelim Attention Score for Detecting Object Hallucinations in Large Vision--Language Models
par: Hoang-Xuan, Nhat, et autres
Publié: (2025)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
par: Liu, Jizhihui, et autres
Publié: (2025)

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

Token Pruning using a Lightweight Background Aware Vision Transformer
par: Sah, Sudhakar, et autres
Publié: (2024)

Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
par: Deniz, Omer Faruk, et autres
Publié: (2026)

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
par: Pei, Xiaohuan, et autres
Publié: (2024)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
par: He, Yefei, et autres
Publié: (2024)

HiPP-Prune: Hierarchical Preference-Conditioned Structured Pruning for Vision-Language Models
par: Bai, Lincen, 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)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
par: Zhang, Qizhe, et autres
Publié: (2024)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
par: Tang, Zicong, et autres
Publié: (2025)

HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
par: Zhang, Jusheng, et autres
Publié: (2025)

When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
par: Luo, Junwei, et autres
Publié: (2025)

VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models
par: Ji, Huawei, et autres
Publié: (2026)

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
par: Lin, Haokun, et autres
Publié: (2024)

Rethinking Token Reduction for Large Vision-Language Models
par: Wang, Yi, et autres
Publié: (2026)

Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers
par: Wen, Yuxin, et autres
Publié: (2024)

Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning
par: Qin, Wenda, et autres
Publié: (2025)