Cover Image

Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Szczepanski, Michal, Poreba, Martyna, Haroun, Karim
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
by: Apedo, Yvon, et al.
Published: (2026)

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
by: Sassoon, Jordan, et al.
Published: (2025)

Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
by: Galagain, Calvin, et al.
Published: (2026)

Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents
by: Xu, Zhou, et al.
Published: (2026)

Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers
by: Maisonnave, Lucas, et al.
Published: (2025)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
by: Jin, Xinqi, et al.
Published: (2025)

How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
by: Huang, YiJie, et al.
Published: (2026)

Where Do You Go? Pedestrian Trajectory Prediction using Scene Features
by: Rezaei, Mohammad Ali, et al.
Published: (2025)

ToDo: Token Downsampling for Efficient Generation of High-Resolution Images
by: Smith, Ethan, et al.
Published: (2024)

Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
by: Shabtay, Nimrod, et al.
Published: (2026)

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent
by: Li, Jiaao, et al.
Published: (2025)

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

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

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
by: Li, Yueying, et al.
Published: (2026)

TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
by: Shaulov, Ariel, et al.
Published: (2026)

What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph
by: Jiang, Yutao, et al.
Published: (2025)

Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models
by: Son, Jaemin, et al.
Published: (2025)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
by: Li, Geng, et al.
Published: (2026)

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
by: Chien, Tzu-Chun, et al.
Published: (2025)

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

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
by: Liu, Shengyuan, et al.
Published: (2026)

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

IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs
by: Tan, Yifan, et al.
Published: (2026)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
by: Zhang, Qizhe, et al.
Published: (2025)

Token Pruning using a Lightweight Background Aware Vision Transformer
by: Sah, Sudhakar, et al.
Published: (2024)

Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification
by: Yang, Zi, et al.
Published: (2024)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
by: Qu, Liao, et al.
Published: (2024)

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization
by: Li, Kaiyuan, et al.
Published: (2025)

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

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
by: Liu, Ziyan, et al.
Published: (2025)

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
by: Sun, Fengyuan, et al.
Published: (2025)

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

Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
by: He, Jialuo, et al.
Published: (2026)

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
by: Arif, Kazi Hasan Ibn, et al.
Published: (2024)

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models
by: Chi, Tien-Yu, et al.
Published: (2025)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
by: Ma, Jie, et al.
Published: (2026)

Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
by: Jung, Chaeyoung, et al.
Published: (2026)

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling
by: Ju, Shaobo, et al.
Published: (2026)

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
by: Alvar, Saeed Ranjbar, et al.
Published: (2025)