Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference

2026-07-13

AI Summary

This work addresses the high inference latency of existing Vision-Language-Action (VLA) models, which stems from temporal redundancy in both visual encoding and diffusion-based policy generation, hindering real-time deployment. The authors propose the first VLA framework that jointly optimizes temporal redundancy across perception and action generation: dynamically updating only visual tokens corresponding to changing image regions at the perception stage, and compressing the diffusion sampling process into an efficient two-step generation at the policy stage, accompanied by an efficiency-oriented training mechanism. Evaluated on Libero, RobotWin, and real robotic platforms, the method achieves over 2× inference speedup while maintaining task success rates as high as 98%.

Abstract

Vision-Language-Action (VLA) models exhibit strong generalization for robotic manipulation, yet their high inference latency limits real time deployment. We identify two primary sources of temporal redundancy in existing VLA pipelines: repeated visual encoding of highly similar consecutive frames and multi step iterative sampling in diffusion based policies. To address this, we propose a system level acceleration strategy that reduces computation in both perception and action generation. On the perception side, we incrementally update only tokens corresponding to dynamic scene regions instead of re-encoding entire frames. On the policy side, we compress diffusion sampling into a compact 2-step schedule through efficiency oriented training while preserving action precision. Experiments on Libero, RobotWin, and Real Robot Platforms demonstrate over 2 times speedup while maintaining high performance, achieving up to 98% success rate on general manipulation benchmarks. Our codes will be released on Github.

Problem

• Temporal Redundancy
• Vision-Language-Action
• Inference Latency
• Real-time Deployment
• Robotic Manipulation

Innovation

• temporal redundancy reduction
• incremental visual encoding
• diffusion policy compression
• vision-language-action models
• efficient robotic inference