Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization

• URL: http://arxiv.org/abs/2608.00569v1
• Date: Sat, 01 Aug 2026 10:11:59 GMT
• Title: Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization
• Abstract summary: We introduce CloudEdgeVLA, a cloud-edge policy that treats temporal misalignment as a representation-learning problem.<n>A lightweight edge head combines the latest available cloud feature with current local vision.<n>CloudEdgeVLA retains 63.8--78.0% success with a 40-step uniform-delay window.
• Score: 6.831202558046453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying billion-parameter Vision-Language-Action (VLA) policies on mobile robots creates a systems conflict: semantic reasoning benefits from cloud GPUs, whereas closed-loop control must respond locally despite network delay and jitter. Existing hierarchical and asynchronous policies improve throughput, but their slow-path representations can still arrive stale or require explicit scheduling and delay cues. We introduce CloudEdgeVLA, a cloud-edge policy that treats temporal misalignment as a representation-learning problem. A cloud VLA encodes delayed observations into slowly varying task features, while a lightweight edge head combines the latest available cloud feature with current local vision. During training, current and randomly delayed frames are paired with the same current action target in fresh and stale paths. This objective encourages the cloud representation to preserve task-level information while the edge path supplies state-sensitive corrections. Across four LIBERO suites, CloudEdgeVLA retains 63.8--78.0% success with a 40-step uniform-delay window, whereas VLASH reaches at most 6.4% and the evaluated single-path baselines at most 3.0%. By removing blocking synchronization from the control loop, the design offers a practical route to scalable VLA deployment in which cloud models can grow while edge computation remains lightweight and responsive.

Related papers

• Risk-Adaptive Edge--Cloud Visual Reasoning for Communication-Efficient Autonomous Driving [6.115137181728187]
  Cloud-hosted vision-language models (VLMs) offer greater contextual reasoning capabilities than smaller onboard models.<n>We present a risk-adaptive edge-cloud architecture in which onboard traffic assessment determines when cloud reasoning is requested.
  arXiv  Detail & Related papers  (2026-08-15T02:36:01Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference [0.8633013637160062]
  We present INAR-VL, a lightweight edge-cloud routing system for multimodal inference in a two-tier deployment.<n>We show that INAR-VL executes 36% of requests on the edge, reduces latency by 24%, lowers energy by 26%, and preserves 97% of cloud-level accuracy.
  arXiv  Detail & Related papers  (2026-05-13T12:44:10Z)
• Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models [0.3004066195320147]
  Vision-Language Models (VLMs) are challenging to deploy on resource-constrained embedded platforms.<n>Full offloading inference to the cloud is often impractical in bandwidth-limited environments.<n>We propose a progressive semantic communication framework for edge-cloud VLM inference.
  arXiv  Detail & Related papers  (2026-04-29T10:16:06Z)
• AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation [21.033021862213825]
  AsyncShield is a plug-and-play control framework for asynchronous navigation.<n>System uses a constrained Markov decision process to balance intent restoration fidelity and physical safety.<n>AsyncShield operates as a lightweight, plug-and-play module.
  arXiv  Detail & Related papers  (2026-04-27T06:20:15Z)
• Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation [6.709418204725671]
  Cloud robotics enables robots to offload high-dimensional motion planning and reasoning to remote servers.<n>For continuous manipulation tasks requiring high-frequency control, network latency and jitter can severely destabilize the system.<n>We propose Speculative Policy Orchestration (SPO), a latency-resilient cloud-edge framework.
  arXiv  Detail & Related papers  (2026-03-19T19:24:14Z)
• AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge [49.66156306240961]
  High latency breaks the control loop, rendering powerful models unsafe for real-time deployment.<n>We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution.<n>AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-13T21:31:19Z)
• InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models [49.08289742711585]
  We propose InfiniteVL, a linear-complexity VLM architecture that synergizes sliding window attention (SWA) with Gated DeltaNet.<n>We show that InfiniteVL achieves over 3.6times inference speedup while maintaining constant latency and memory footprint.<n>In streaming video understanding scenarios, it sustains a stable 24 FPS real-time prefill speed while preserving long-term memory cache.
  arXiv  Detail & Related papers  (2025-12-09T17:18:32Z)
• EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models [57.059991285047296]
  hybrid edge-cloud collaborative framework was recently proposed to realize fast inference and high-quality generation.<n>Excessive cloud denoising prolongs inference time, while insufficient steps cause semantic ambiguity, leading to inconsistency in edge model output.<n>We propose EC-Diff that accelerates cloud inference through gradient-based noise estimation.<n>Our method significantly enhances generation quality compared to edge inference, while achieving up to an average $2times$ speedup in inference compared to cloud inference.
  arXiv  Detail & Related papers  (2025-07-16T07:23:14Z)
• Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits [11.398891065175686]
  Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots.<n>LLMs can be deployed on-device, offering a cost-effective solution with reduced latency and improved privacy.<n>We propose a fast and cost-effective speculative edge-cloud decoding framework with a large target model on the server and a small draft model on the device.
  arXiv  Detail & Related papers  (2025-05-27T14:55:16Z)
• Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning [15.132585178169423]
  We introduce a novel solution called the Differentiable Center Sampling Network (DCS-Net)<n>It tackles the information leakage problem by incorporating both global feature reconstruction and local feature reconstruction as non-trivial proxy tasks.<n> Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models.
  arXiv  Detail & Related papers  (2024-02-03T08:58:23Z)
• Tailored Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud System [54.588242387136376]
  We introduce KaiS, a learning-based scheduling framework for edge-cloud systems. First, we design a coordinated multi-agent actor-critic algorithm to cater to decentralized request dispatch. Second, for diverse system scales and structures, we use graph neural networks to embed system state information. Third, we adopt a two-time-scale scheduling mechanism to harmonize request dispatch and service orchestration.
  arXiv  Detail & Related papers  (2021-01-17T03:45:25Z)
• Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision [68.35777836993212]
  We propose a Pseudo-LiDAR point cloud network to generate temporally and spatially high-quality point cloud sequences. By exploiting the scene flow between point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship.
  arXiv  Detail & Related papers  (2020-06-20T03:11:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.