Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricultural decision support remains poorly understood. We benchmark a diverse set of open-source and closed-source VLMs on 27 agricultural image classification datasets from the AgML collection...

Semantically consistent cross-domain image translation facilitates the generation of training data by transferring labels across different domains. However, existing generative models struggle with object-level accuracy when translating images between domains...

Accurate plant segmentation in thermal imagery remains a significant challenge for high throughput field phenotyping, particularly in outdoor environments where low contrast between plants and weeds and frequent occlusions hinder performance...