AVERY: Adaptive VLM Split Computing through Embodied Self-Awareness for Efficient Disaster Response Systems

• URL: http://arxiv.org/abs/2511.18151v1
• Date: Sat, 22 Nov 2025 18:42:04 GMT
• Title: AVERY: Adaptive VLM Split Computing through Embodied Self-Awareness for Efficient Disaster Response Systems
• Authors: Rajat Bhattacharjya, Sing-Yao Wu, Hyunwoo Oh, Chaewon Nam, Suyeon Koo, Mohsen Imani, Elaheh Bozorgzadeh, Nikil Dutt,
• Abstract summary: Unmanned Aerial Vehicles (UAVs) in disaster response require complex, queryable intelligence that on-board CNNs cannot provide.<n>We present AVERY, a framework that enables VLM deployment through adaptive split computing.
• Score: 6.294240680169978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unmanned Aerial Vehicles (UAVs) in disaster response require complex, queryable intelligence that on-board CNNs cannot provide. While Vision-Language Models (VLMs) offer this semantic reasoning, their high resource demands make on-device deployment infeasible, and naive cloud offloading fails under the low-bandwidth networks common in disaster zones. We present AVERY, a framework that enables VLM deployment through adaptive split computing. We advance the split computing paradigm beyond traditional depth-wise partitioning by introducing a functional, cognitive-inspired dual-stream split that separates the VLM into a high-frequency, low-resolution "context stream" for real-time awareness and a low-frequency, high-fidelity "insight stream" for deep analysis. A lightweight, self-aware on-board controller manages this architecture, monitoring network conditions and operator intent to dynamically select from pre-trained compression models, navigating the fundamental accuracy-throughput trade-off. Evaluated using the VLM LISA-7B across an edge-cloud scenario under fluctuating network conditions, AVERY consistently outperforms static configurations, achieving 11.2% higher accuracy than raw image compression and 93.98% lower energy consumption compared to full-edge execution, thereby enhancing mission efficiency and enabling real-time, queryable intelligence on resource-constrained platforms in dynamic environments.

Related papers

• AIVD: Adaptive Edge-Cloud Collaboration for Accurate and Efficient Industrial Visual Detection [15.419663374345845]
  This paper proposes the AIVD framework, which achieves unified precise localization and high-quality semantic generation.<n>To enhance the cloud MLLM's robustness against edge cropped-box noise and scenario variations, we design an efficient fine-tuning strategy.<n>To maintain high throughput and low latency across heterogeneous edge devices and dynamic network conditions, we propose a heterogeneous resource-aware dynamic scheduling algorithm.
  arXiv  Detail & Related papers  (2026-01-08T08:56:07Z)
• Hierarchical Task Offloading and Trajectory Optimization in Low-Altitude Intelligent Networks Via Auction and Diffusion-based MARL [37.79695337425523]
  Low-altitude intelligent networks (LAINs) can support mission-critical applications such as disaster response, environmental monitoring, and real-time sensing.<n>These systems face key challenges, including energy-constrained UAVs, task arrivals, and heterogeneous computing resources.<n>We propose an integrated air-ground collaborative network and formulate a time-dependent integer nonlinear programming problem that jointly optimize UAV trajectory planning and task offloading decisions.
  arXiv  Detail & Related papers  (2025-12-05T08:14:45Z)
• Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimization [61.55616421408666]
  Low-Altitude Economy Networks (LAENets) have enabled a variety of applications, including aerial surveillance, environmental sensing, and semantic data collection.<n> onboard vision (VLMs) offer inference for real-time inference but limited onboard dynamic network conditions.<n>We propose a UAV-enabled LAENet system that improves communication efficiency under dynamic LAENet conditions.
  arXiv  Detail & Related papers  (2025-10-11T05:11:21Z)
• Hierarchical Task Offloading for UAV-Assisted Vehicular Edge Computing via Deep Reinforcement Learning [11.695622067301128]
  We propose a dual-layer UAV-assisted edge computing architecture based on partial offloading.<n>The proposed architecture enables efficient integration and coordination of heterogeneous resources.<n>We show that the proposed approach outperforms several baselines in task completion rate, system efficiency, and convergence speed.
  arXiv  Detail & Related papers  (2025-07-08T07:10:52Z)
• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models [21.42353501209045]
  Vision-Language-Action (VLA) models demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands.<n>We introduce EfficientVLA, a structured and training-free inference acceleration framework.<n>We apply our method to a standard VLA model CogACT, yielding a 1.93X inference speedup and reduces FLOPs to 28.9%, with only a 0.6% success rate drop in the SIMPLER benchmark.
  arXiv  Detail & Related papers  (2025-06-11T18:34:57Z)
• Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum Systems [9.820223170841219]
  Service Level Objectives (SLOs) in large-scale architectures are challenging due to their heterogeneous nature and varying service requirements.<n>We present a benchmark of Active Inference -- an emerging method from neuroscience -- against three established reinforcement learning algorithms.<n>We find that Active Inference is a promising approach for ensuring SLO compliance in DCCS, offering lower memory usage, stable CPU utilization, and fast convergence.
  arXiv  Detail & Related papers  (2025-03-05T08:56:26Z)
• Network Resource Optimization for ML-Based UAV Condition Monitoring with Vibration Analysis [54.550658461477106]
  Condition Monitoring (CM) uses Machine Learning (ML) models to identify abnormal and adverse conditions.<n>This work explores the optimization of network resources for ML-based UAV CM frameworks.<n>By leveraging dimensionality reduction techniques, there is a 99.9% reduction in network resource consumption.
  arXiv  Detail & Related papers  (2025-02-21T14:36:12Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation [12.511829774226113]
  We propose an ultra-lightweight (1M) visual-inertial odometry (VIO) network capable of test-time adaptation (TTA) based on visual-inertial consistency. It achieves 36X smaller network size than state-of-the-art with a minute increase in error -- 1% on the KITTI dataset.
  arXiv  Detail & Related papers  (2024-09-19T22:24:14Z)
• Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning [55.08287089554127]
  Open Radio Access Network systems, with their base stations (vBSs), offer operators the benefits of increased flexibility, reduced costs, vendor diversity, and interoperability.<n>We propose an online learning algorithm that balances the effective throughput and vBS energy consumption, even under unforeseeable and "challenging'' environments.<n>We prove the proposed solutions achieve sub-linear regret, providing zero average optimality gap even in challenging environments.
  arXiv  Detail & Related papers  (2023-09-04T17:30:21Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)

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.