Skip to content
Preprint

Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference

Sep 2026 · 1 citation · 30 references
Computer Science

TL;DR

Text-Vision Synergistic Token Caching (TVCache), a training-free framework for efficient VLA inference that filters attention heads based on text-vision information focus to improve task-relevant and physically consistent visual grounding, and introduces a reuse-layer selection mechanism guided by text-vision entropy differences to avoid caching unstable representations and improve cache resource allocation.

Abstract

Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive. Token caching provides a training-free, plug-and-play acceleration alternative. However, existing VLA caching does not fully exploit a key inductive bias of VLA models: text-vision synergy, wherein textual semantics guide the precise visual grounding of task-relevant regions. In particular, existing designs insufficiently account for head-wise reliability in attention aggregation and layer-wise stability in cache reuse. To address this, we propose Text-Vision Synergistic Token Caching (TVCache), a training-free framework for efficient VLA inference. TVCache filters attention heads based on text-vision information focus to improve task-relevant and physically consistent visual grounding. Concurrently, we introduce a reuse-layer selection mechanism guided by text-vision entropy differences to avoid caching unstable representations and improve cache resource allocation. Extensive experiments across four representative VLA models, two simulation benchmarks, and real-world robotic tasks demonstrate the effectiveness and generality of TVCache. At matched token-retention ratios, TVCache consistently improves task success over existing VLA caching with comparable computational cost. On OpenVLA-OFT, it improves average success by up to 14.5 percentage points over VLA-Cache at 12.5% retention while reducing FLOPs by 2.45x relative to full-token inference.

View source

Similar papers

Preprint Oct 2026

VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models

Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but incur high computational costs from processing long token sequences at every control step, limiting real-time deployment. Visual token pruning offers a direct solution, as visual patches dominate the input sequence and contain consi...

Owen Du, Yang Yue, Jie Zhang et al. · 0 citations
Preprint Nov 2026

T3R: Training-Free Two-Stage Token Refinement Towards Efficient and Robust VLA Models

Vision-Language-Action (VLA) models enable end-to-end robot control, but inference is increasingly expensive. Each decision processes hundreds of visual tokens, often across multiple cameras, leading to substantial computation while allowing irrelevant background content to distract action prediction under distribution...

M. Hassan, Zhen-Yang Chen, Zheng-Zhang-Yu Wang et al. · 0 citations
Preprint Oct 2026

FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action Models

Vision-Language-Action (VLA) models present a promising paradigm for general-purpose robot manipulation, but closed-loop deployment is often limited by inference efficiency: at each timestep, high-resolution, often multi-view images are encoded into hundreds of visual tokens that dominate transformer computation and la...

Jiu-Yi Xu, Cheng-Yuan Qian, Zheng-Zhong Tu et al. · 0 citations
Book Open access Nov 2026

DATP: Training-Free Depth-Aware Token Pruning for Vision-Language Models

The massive redundancy of visual tokens in Vision-Language Models (VLMs) creates a critical computational bottleneck during large language model (LLM) prefill. Recent training-free pruning methods provide plug-and-play acceleration, yet their pruning decisions often rely on limited visual states or delayed in-LLM signa...

Qing-Xin Liu, Jin-Zhi Liao, Xiang Zhao · 0 citations
#small language model Preprint Sep 2026

SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models

Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but aggressive compression can sharply degrade performance, often attributed to irreversible loss of task-relevant visual information. We show...

Ahmadreza Jeddi, En-Ming Zhang, Jasper Gerigk et al. · 0 citations

TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning

TReVS is proposed, a training-free framework that combines textual relevance with vision-encoder saliency for pre-LLM pruning and leverages high-variance attention heads to remove task-irrelevant tokens at shallow-to-intermediate layers of the LLM.

Jing Wang, Zhi-Ping Wu, Dong-Dong Ren et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.