mlsanityData to 7 Oct 2026

Vision-Language Models for Edge Networks: A Comprehensive Survey

arXiv 2502.07855 ↗First posted 11 Feb 2025cs.CV cs.AI cs.CLcited by 29

On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency

Abstract (arXiv)

Vision Large Language Models (VLMs) combine visual understanding with natural language processing, enabling tasks like image captioning, visual question answering, and video analysis. While VLMs show impressive capabilities across domains such as autonomous vehicles, smart surveillance, and healthcare, their deployment on resource-constrained edge devices remains challenging due to processing power, memory, and energy limitations. This survey explores recent advancements in optimizing VLMs for edge environments, focusing on model compression techniques, including pruning, quantization, knowledge distillation, and specialized hardware solutions that enhance efficiency. We provide a detailed discussion of efficient training and fine-tuning methods, edge deployment challenges, and privacy considerations. Additionally, we discuss the diverse applications of lightweight VLMs across healthcare, environmental monitoring, and autonomous systems, illustrating their growing impact. By highlighting key design strategies, current challenges, and offering recommendations for future directions, this survey aims to inspire further research into the practical deployment of VLMs, ultimately making advanced AI accessible in resource-limited settings.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 113 of its 205 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

113 of 205 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities7 Mar
  2. 2022EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning14 Oct

Other references · 111

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020Language Models are Few-Shot Learnerscited by 32,199
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  7. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  8. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  9. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  10. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  12. 2017Squeeze-and-Excitation Networkscited by 4,763
38 more
  1. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2019Advances and Open Problems in Federated Learningcited by 3,021
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  8. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  9. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  12. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  13. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  14. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  15. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  16. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  17. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  18. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  19. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  20. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  21. 2023A Survey on Multimodal Large Language Modelscited by 898
  22. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  23. 2020AdapterFusion: Non-Destructive Task Composition for Transfer Learningcited by 780
  24. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  25. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  26. 2017Federated Multi-Task Learningcited by 669
  27. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  28. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  29. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  30. 2017Large Batch Training of Convolutional Networkscited by 529
  31. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  32. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 420
  33. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  34. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  35. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 319
  36. 2018Slimmable Neural Networkscited by 301
  37. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 288
  38. 2024ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Modelscited by 204

50 most cited of 111 All 111 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 18.

29 papers.

Sort:

By area:

  1. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  2. 2025Object Detection with Multimodal Large Vision-Language Models: An In-depth Reviewcited by 14
  3. 2025Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Artcited by 13
  4. 2025Masking Teacher and Reinforcing Student for Distilling Vision-Language Modelscited by 6
  5. 2025Limits and Gains of Test-Time Scaling in Vision-Language Reasoningcited by 5
  6. 2025ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Modelscited by 4
  7. 2025Focus: A Streaming Concentration Architecture for Efficient Vision-Language Modelscited by 3
  8. 2025Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimizationcited by 2
  9. 2026ZAYA1-VL-8B Technical Reportcited by 2
  10. 2026MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarioscited by 2
  11. 2025From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Roboticscited by 1
  12. 2025Collaborative Edge-to-Server Inference for Vision-Language Modelscited by 1
17 more
  1. 2026Vision-Language Models on the Edge for Real-Time Robotic Perceptioncited by 1
  2. 2026Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Modelscited by 1
  3. 2026One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMscited by 1
  4. 2026Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deploymentcited by 1
  5. 2025Hierarchy-Aware Fine-Tuning of Vision-Language Modelscited by 0
  6. 2026Lightweight Transformer Architectures for Edge Devices in Real-Time Applicationscited by 0
  7. 2026Synthesizing the Kill Chain: A Zero-Shot Framework for Target Verification and Tactical Reasoning on the Edgecited by 0
  8. 2026Efficient Few-Shot Learning for Edge AI via Knowledge Distillation on MobileViTcited by 0
  9. 2026Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmarkcited by 0
  10. 2026Integration of Object Detection and Small VLMs for Construction Safety Hazard Identificationcited by 0
  11. 2026Efficient Semantic Image Communication for Traffic Monitoring at the Edgecited by 0
  12. 2026LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Modelscited by 0
  13. 2026PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajectory Predictioncited by 0
  14. 2026Zamba2-VL Technical Reportcited by 0
  15. 2026TrustCLIP: Learning Private Visual Features via Adversarial Reconstructioncited by 0
  16. 2026AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoringcited by 0
  17. 2026TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous Drivingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Efficient Vision-Language Models
  2. 2026Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models
  3. 2026Empirical Recipes for Efficient and Compact Vision-Language Models
  4. 2025A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
  5. 2026LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge
  6. 2025Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers
  7. 2025edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer
  8. 2026INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference