Cover Image

HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Jingqi, Lu, Jingxi, Li, Chenghao, Sarkar, Sreetama, Beerel, Peter A.
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

RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
by: Xu, Jingqi, et al.
Published: (2025)

Block Selective Reprogramming for On-device Training of Vision Transformers
by: Sarkar, Sreetama, et al.
Published: (2024)

Linearizing Models for Efficient yet Robust Private Inference
by: Sarkar, Sreetama, et al.
Published: (2024)

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings
by: Xu, Jingqi, et al.
Published: (2025)

FixPix: Fixing Bad Pixels using Deep Learning
by: Sarkar, Sreetama, et al.
Published: (2023)

Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
by: Sarkar, Sreetama, et al.
Published: (2025)

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
by: Fang, Zhengyao, et al.
Published: (2026)

LoyalDiffusion: A Diffusion Model Guarding Against Data Replication
by: Li, Chenghao, et al.
Published: (2024)

MaskVD: Region Masking for Efficient Video Object Detection
by: Sarkar, Sreetama, et al.
Published: (2024)

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

Energy-Efficient & Real-Time Computer Vision with Intelligent Skipping via Reconfigurable CMOS Image Sensors
by: Kaiser, Md Abdullah-Al, et al.
Published: (2024)

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
by: Kim, Youngrae, et al.
Published: (2026)

Region Masking to Accelerate Video Processing on Neuromorphic Hardware
by: Sarkar, Sreetama, et al.
Published: (2025)

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

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
by: Zhu, Qihui, et al.
Published: (2026)

Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting
by: Xu, Jingqi, et al.
Published: (2025)

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement
by: Li, Chenghao, et al.
Published: (2023)

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
by: Zhang, Jianrui, et al.
Published: (2026)

Branch Landing: Bloom Filter-Based Source Authorization for Forward-Edge CFI on RISC-V
by: Wu, You, et al.
Published: (2026)

Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning
by: Qin, Wenda, et al.
Published: (2025)

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

Opto-ViT: Architecting a Near-Sensor Region of Interest-Aware Vision Transformer Accelerator with Silicon Photonics
by: Morsali, Mehrdad, et al.
Published: (2025)

Training Noise Token Pruning
by: Rao, Mingxing, et al.
Published: (2024)

VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models
by: Cheng, Jintao, et al.
Published: (2026)

IVRA: Improving Visual-Token Relations for Robot Action Policy with Training-Free Hint-Based Guidance
by: Park, Jongwoo, et al.
Published: (2026)

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)

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
by: Tan, Zhangyun, et al.
Published: (2026)

Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
by: Ye, Weihao, et al.
Published: (2024)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
by: Liu, Jingyu, et al.
Published: (2025)

Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
by: Choi, Dasol, et al.
Published: (2024)

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

Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance
by: Lee, Taehan, et al.
Published: (2025)

Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
by: Li, Jiaqi, et al.
Published: (2026)

Neural Network Training with Approximate Logarithmic Computations
by: Sanyal, Arnab, et al.
Published: (2019)

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
by: Li, Duo, et al.
Published: (2025)

Does Visual Token Pruning Improve Calibration? An Empirical Study on Confidence in MLLMs
by: Tan, Kaizhen
Published: (2026)

Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning
by: Choi, Minsik, et al.
Published: (2025)

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
by: Cao, Mingyu, et al.
Published: (2024)

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