RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA models

2026-03-09

AI Summary

Existing edge-cloud collaborative inference methods for Vision-Language-Action (VLA) models are highly susceptible to visual noise and overlook step-level redundancy inherent in embodied tasks, thereby compromising the physical continuity of generated actions. To address these limitations, this work proposes RAPID, a novel framework that, for the first time, explicitly models step-level redundancy in embodied tasks and introduces a noise-resilient, continuity-preserving edge-cloud partitioning mechanism. By jointly leveraging environmental and task-specific features, RAPID dynamically optimizes redundancy-aware inference partitioning strategies. This approach achieves up to 1.73× inference acceleration with only 5%–7% additional overhead, significantly enhancing both computational efficiency and action coherence in embodied reasoning.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Embodied AI
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Vision Language Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) inference offers an effective fix by easing edge-device computing pressure to meet real-time needs. However, existing ECC frameworks are suboptimal for VLA models due to two challenges: (1) Mainstream environment-oriented edge-cloud partitioning methods are susceptible to interference from visual noise; (2) Existing edge-cloud partitioning methods overlook the step-wise redundancy unique to embodied tasks, thereby disrupting the physical continuity of motion. To address these issues, we propose a novel ECC inference framework, termed RAPID. Specifically, we developed an implementation tailored to the proposed framework. Experiments demonstrate this achieves a speedup of up to 1.73x with only 5%~7% overhead.

Problem

• Vision Language Action
• Edge-Cloud Collaborative inference
• visual noise
• step-wise redundancy
• physical continuity

Innovation

• edge-cloud collaborative inference
• VLA models
• step-wise redundancy
• partitioning optimization
• embodied intelligence