面向边缘网络的视觉-语言模型：全面综述
Vision-Language Models for Edge Networks: A Comprehensive Survey
AI总结：
该综述聚焦边缘网络场景下的视觉大语言模型（VLMs），梳理了模型压缩、专用硬件等优化技术与高效训练方法，分析部署挑战与隐私问题，介绍多领域应用并给出未来研究方向，助力资源受限场景下的VLMs落地。
摘要：
视觉大语言模型（Vision Large Language Models, VLMs）将视觉理解与自然语言处理相结合，可实现图像字幕生成、视觉问答、视频分析等任务。尽管VLMs在自动驾驶、智能监控、医疗健康等领域展现出出色能力，但受算力、内存、能耗限制，其在资源受限的边缘设备上部署仍面临挑战。本综述探讨了面向边缘环境优化VLMs的最新进展，重点关注模型压缩技术，包括剪枝、量化、知识蒸馏，以及提升效率的专用硬件方案。我们详细讨论了高效训练与微调方法、边缘部署挑战及隐私考量。此外，我们还探讨了轻量级VLMs在医疗健康、环境监测、自治系统中的多样应用，阐明其日益增长的影响力。通过梳理关键设计策略、当前挑战并给出未来方向建议，本综述旨在推动VLMs实际部署的相关研究，最终让先进AI在资源受限场景中落地可用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
