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

arXiv:2609.34319 · cs.CV, cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Benchmark — 13× in this paper · explained in 2 episodes
• Grounding — 10× in this paper · explained in 3 episodes
• Visual Grounding — 9× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Pruning — 5× in this paper · explained in 4 episodes
• Quantization — 5× in this paper · explained in 12 episodes
• VLA Models — 5× in this paper · explained in 3 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Ablation — 3× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• Training-Free Framework — 3× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Attention Entropy — 2× in this paper · explained in 2 episodes
• KV cache — 2× in this paper · explained in 3 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• KV cache reuse — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• OpenVLA: An Open-Source Vision-Language-Action Model
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
• VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
• SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
• How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
• DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
• QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
• CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding
• DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Evaluating Real-World Robot Manipulation Policies in Simulation
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
• Similarity-Aware Token Pruning: Your VLM but Faster
• Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models