Cover Image

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Ye, Meng, Yuan, Sun, Zewen, Ji, Kangye, Tang, Chen, Fan, Jiajun, Ma, Xinzhu, Xia, Shutao, Wang, Zhi, Zhu, Wenwu
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

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference
by: Li, Ye, et al.
Published: (2024)

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
by: Li, Ye, et al.
Published: (2026)

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration
by: Li, Ye, et al.
Published: (2025)

Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
by: Ji, Kangye, et al.
Published: (2026)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
by: Sun, Haojun, et al.
Published: (2024)

One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
by: Tang, Zuojin, et al.
Published: (2026)

EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance
by: Li, Yingxin, 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)

JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
by: Miao, Shangchen, et al.
Published: (2026)

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
by: Wang, Hanzhen, et al.
Published: (2025)

Retraining-free Model Quantization via One-Shot Weight-Coupling Learning
by: Tang, Chen, et al.
Published: (2024)

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

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
by: Ni, Chaojun, et al.
Published: (2025)

Test-time Sparsity for Extreme Fast Action Diffusion
by: Ji, Kangye, et al.
Published: (2026)

VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
by: Li, Wenhao, et al.
Published: (2026)

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning
by: Cao, Jiajun, et al.
Published: (2025)

FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
by: Xu, Xiaoxu, et al.
Published: (2026)

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
by: Wang, Ruiheng, et al.
Published: (2026)

Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered
by: Jabbour, Jason, et al.
Published: (2025)

EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
by: Cao, Jiajun, et al.
Published: (2026)

A Pragmatic VLA Foundation Model
by: Wu, Wei, et al.
Published: (2026)

Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning
by: Liu, Yijun, et al.
Published: (2025)

Block-wise Adaptive Caching for Accelerating Diffusion Policy
by: Ji, Kangye, et al.
Published: (2025)

World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
by: Liu, Xiaokang, et al.
Published: (2026)

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
by: Song, Wenxuan, et al.
Published: (2026)

TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
by: Liu, Jiahang, et al.
Published: (2025)

GraSP-VLA: Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies
by: Neau, Maëlic, et al.
Published: (2025)

Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild
by: Luo, Hao, et al.
Published: (2026)

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

Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
by: Li, Wenhao, et al.
Published: (2026)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
by: Chen, Lei, et al.
Published: (2024)

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

WorldVLA: Towards Autoregressive Action World Model
by: Cen, Jun, et al.
Published: (2025)

2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
by: Zheng, Zihao, et al.
Published: (2026)

RedVLA: Physical Red Teaming for Vision-Language-Action Models
by: Zhang, Yuhao, et al.
Published: (2026)

DPPA: Pruning Method for Large Language Model to Model Merging
by: Zhu, Yaochen, et al.
Published: (2024)

Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
by: Gao, Juntao, et al.
Published: (2025)

VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
by: Ye, Angen, et al.
Published: (2025)

VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
by: Zhao, Yongsheng, et al.
Published: (2025)

DroneVLA: VLA based Aerial Manipulation
by: Mehboob, Fawad, et al.
Published: (2026)