Cover Image

Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Yujie, Fan, Jiahan, Guo, Jiyu, Zhen, Ruichen, Shao, Rui, Su, Xiu, Xie, Zeke, Yang, Shuo
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuning
by: Zhou, Jianyi, et al.
Published: (2026)

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

DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference
by: Li, Yuquan, et al.
Published: (2026)

FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching
by: Zheng, Zihao, et al.
Published: (2026)

Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
by: Liang, Yuanchang, et al.
Published: (2026)

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
by: Zhong, Yifan, et al.
Published: (2025)

FAST: Efficient Action Tokenization for Vision-Language-Action Models
by: Pertsch, Karl, et al.
Published: (2025)

APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation
by: Zhang, Daoxuan, et al.
Published: (2026)

Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models
by: Ye, Yifan, et al.
Published: (2025)

PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
by: Guo, Xinyu, et al.
Published: (2026)

From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
by: Lin, Yihan, et al.
Published: (2026)

UnderwaterVLA: Dual-brain Vision-Language-Action architecture for Autonomous Underwater Navigation
by: Wang, Zhangyuan, et al.
Published: (2025)

VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness
by: Zheng, Zihao, et al.
Published: (2026)

ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models
by: Wang, Yiru, et al.
Published: (2026)

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
by: Wang, Hao, et al.
Published: (2026)

AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models
by: Li, Xiaoqi, et al.
Published: (2026)

Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
by: Li, Pengteng, et al.
Published: (2026)

ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
by: Dai, Yuntao, et al.
Published: (2025)

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

RetoVLA: Reusing Register Tokens for Spatial Reasoning in Vision-Language-Action Models
by: Koo, Jiyeon, et al.
Published: (2025)

RL Token: Bootstrapping Online RL with Vision-Language-Action Models
by: Xu, Charles, et al.
Published: (2026)

CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
by: Li, Wei, et al.
Published: (2025)

Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
by: Zhang, Yang, et al.
Published: (2025)

AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment
by: Kong, Weijie, et al.
Published: (2026)

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
by: Zhang, Yichi, et al.
Published: (2026)

VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
by: Wang, Zixuan, et al.
Published: (2026)

Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories
by: Yang, Rushuai, et al.
Published: (2025)

Dexbotic: Open-Source Vision-Language-Action Toolbox
by: Xie, Bin, et al.
Published: (2025)

Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
by: Shao, Rui, et al.
Published: (2025)

Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
by: Niu, Haochen, et al.
Published: (2026)

VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation
by: Zhang, Chaofan, et al.
Published: (2025)

SG-VLA: Learning Spatially-Grounded Vision-Language-Action Models for Mobile Manipulation
by: Tu, Ruisen, et al.
Published: (2026)

ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal
by: Shao, Shuo, et al.
Published: (2026)

StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
by: Deng, Shengliang, et al.
Published: (2025)

History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation
by: Wang, Qitong, et al.
Published: (2026)

Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
by: Zheng, Meng, et al.
Published: (2026)

Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning
by: Peng, Zhenghao "Mark", et al.
Published: (2025)

RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
by: Zang, Hongzhi, et al.
Published: (2025)

Adaptive Capacity Allocation for Vision Language Action Fine-tuning
by: Kim, Donghoon, et al.
Published: (2026)

AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulation
by: Zhu, Juan, et al.
Published: (2026)