# AVERY: Intent-Driven Adaptive VLM Split Computing via Embodied Self-Awareness for Efficient Disaster Response Systems

arXiv: https://arxiv.org/abs/2511.18151 · HTML: https://mlsanity.com/paper/2511.18151/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 22 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Simple but Effective: CLIP Embeddings for Embodied AI](https://mlsanity.com/paper/2111.09888/) (2021)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model](https://mlsanity.com/paper/2503.18278/) (2025)
- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing](https://mlsanity.com/paper/2201.02693/) (2022)
- [Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations](https://mlsanity.com/paper/2502.11007/) (2025)
- [Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency](https://mlsanity.com/paper/2311.05739/) (2023)
- [Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2302.00875/) (2023)
- [A Multi-task Supervised Compression Model for Split Computing](https://mlsanity.com/paper/2501.01420/) (2025)
- [ACCESS-AV: Adaptive Communication-Computation Codesign for Sustainable Autonomous Vehicle Localization in Smart Factories](https://mlsanity.com/paper/2507.20399/) (2025)
- [MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference](https://mlsanity.com/paper/2509.16995/) (2025)
- [Analysis and design of model predictive control frameworks for dynamic operation -- An overview](https://mlsanity.com/paper/2307.03004/) (2023)
- [Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models](https://mlsanity.com/paper/2412.06458/) (2024)
- [T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization](https://mlsanity.com/paper/2511.13676/) (2025)
- [Model predictive altitude and velocity control in ergodic potential field directed multi-UAV search](https://mlsanity.com/paper/2401.02899/) (2024)
- [edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer](https://mlsanity.com/paper/2508.12638/) (2025)
- [Distributed Split Computing Using Diffusive Metrics for UAV Swarms](https://mlsanity.com/paper/2503.16146/) (2025)
- [S2M3: Split-and-Share Multi-Modal Models for Distributed Multi-Task Inference on the Edge](https://mlsanity.com/paper/2508.04271/) (2025)
- [DroneFL: Federated Learning for Multi-UAV Visual Target Tracking](https://mlsanity.com/paper/2509.21523/) (2025)

## Built on by (most cited first, 4 of 4)

- [AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge](https://mlsanity.com/paper/2602.13476/) (2026)
- [RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA Models](https://mlsanity.com/paper/2603.07949/) (2026)
- [FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge](https://mlsanity.com/paper/2608.15410/) (2026)
- [FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception](https://mlsanity.com/paper/2609.30629/) (2026)

## Abstract (arXiv)

Unmanned Aerial Vehicles (UAVs) in disaster response require complex, queryable intelligence that onboard 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, unstable networks endemic to disaster zones. We present AVERY, an intent-driven adaptive split computing framework for efficient VLM deployment on resource-constrained platforms. AVERY is motivated by the observation that operator intent must be treated as a first-class system objective, since missions such as broad situational monitoring and precise, spatially grounded investigation require different semantic products, latency targets, and resource allocations. To reflect this, AVERY advances split computing beyond traditional depth-wise partitioning through a functional, cognitive-inspired dual-stream split: a high-frequency, low-resolution Context stream for real-time awareness, and a low-frequency, high-fidelity Insight stream for deep analysis. This design enables a hierarchical split strategy: computation is first separated by function, then partitioned depth-wise across edge and cloud when the Insight stream is required. A lightweight, self-aware onboard controller monitors network conditions and operator intent to select from pre-trained compression models, navigating the accuracy-throughput trade-off at runtime. Evaluated using LISA-7B in an edge-cloud setting under fluctuating network conditions, AVERY achieves 11.2% higher accuracy than raw image compression, 93.98% lower energy consumption than full-edge execution, and average accuracy within 0.75% of the static High-Accuracy baseline during dynamic adaptation. Overall, AVERY enhances mission efficiency and enables real-time, queryable intelligence in dynamic disaster environments.