arXiv · cs.AI · Gaurab Wagle, Bishal Adhikari, Jiajia Li, Xiaolei Huang, Dong Chen · 9 小时前模型评分37
PlantVLM-Edge：面向设备端作物健康诊断的量化视觉语言模型
PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis
导读
PlantVLM-Edge 提出一套可完全在资源受限边缘设备上运行的量化视觉语言模型框架，用于对话式作物健康诊断。该框架在 NVIDIA Jetson AGX Orin 上验证了 Qwen3-VL-2B 与 LLaVA-1.5-7B 两种模型、四种量化方案，其中 4-bit AWQ 在两个诊断领域均保留 98.6% 的全精度回答质量，并将 2B 主干权重内存减少 49%。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：embodied-ai，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：农业
事件类型：研究发布
证据摘录
- “This paper presents PlantVLM-Edge, a quantized vision-language framework for conversational crop health diagnosis that can run entirely on resource-constrained edge devices.”
- “Eight-bit quantization affects answer quality minimally relative to the full-precision model, and 4-bit activation-aware weight quantization (AWQ) retains 98.6% of full-precision answer quality on both domains while reducing the weight memory of the 2B backbone by 49%.”
- “In its most compact form, PlantVLM-Edge requires 2.01 GiB of weight memory, returns its first token in about 0.12 s, and completes a 64-token diagnostic response in 0.78 s.”
来源：arXiv · cs.AI · arxiv.org