Cover Image

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Ziyan, Chen, Yeqiu, Cai, Hongyi, Lin, Tao, Yang, Shuo, Liu, Zheng, Zhao, Bo
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

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

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
by: Lin, Tao, et al.
Published: (2025)

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning
by: Cao, Jiajun, 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)

SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
by: Zhou, Zewei, et al.
Published: (2026)

S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
by: Lin, Weihao, et al.
Published: (2024)

Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning
by: Tong, Enwei, et al.
Published: (2026)

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

Bridging the Gap between Human Motion and Action Semantics via Kinematic Phrases
by: Liu, Xinpeng, et al.
Published: (2023)

Efficient Token Pruning for LLaDA-V
by: Wan, Zhewen, et al.
Published: (2026)

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
by: Gu, Chenyang, et al.
Published: (2026)

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
by: Tan, Xudong, et al.
Published: (2025)

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

When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
by: Wang, Yahong, et al.
Published: (2025)

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces
by: E, Shaojun, et al.
Published: (2025)

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

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
by: Bagrov, Natan, et al.
Published: (2025)

TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts
by: Zhang, Hao, et al.
Published: (2025)

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

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
by: Wang, Yating, et al.
Published: (2025)

GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation
by: Zhang, Weiming, et al.
Published: (2024)

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

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
by: Xu, Siyu, et al.
Published: (2025)

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

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

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
by: Li, Ye, et al.
Published: (2025)

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

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
by: Lou, Haoran, et al.
Published: (2025)

GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation
by: Zhang, Weiming, et al.
Published: (2024)

TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression
by: Zeng, Sen, et al.
Published: (2026)

TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models
by: Zhang, Hao, et al.
Published: (2025)

GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation
by: Wang, Haonan, et al.
Published: (2024)

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
by: Wang, Yuqing, et al.
Published: (2025)

Dialogue Director: Bridging the Gap in Dialogue Visualization for Multimodal Storytelling
by: Zhang, Min, et al.
Published: (2024)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
by: Zhang, Yuan, et al.
Published: (2024)

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

SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
by: Fang, Hengyu, et al.
Published: (2025)

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
by: Guo, Hang, et al.
Published: (2025)

SFTok: Bridging the Performance Gap in Discrete Tokenizers
by: Rao, Qihang, et al.
Published: (2025)

DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
by: Yuan, Tianyuan, et al.
Published: (2025)