Every story in this issue with a short summary, so you can decide what to read before leaving the site. Summaries are written by AI (Claude) only from each publisher's own description and checked by Jev for anything not in that description. They are not full translations. Follow "Read the original" for the full story.
A new lightweight deep learning model called WheatNet detects and counts individual wheat seedlings in complex field images with record accuracy. It runs fast enough for smartphone use.
Read the original →Researchers in China developed MP-CBA-YOLO, a morphology-preserving, class-balanced object detection method. It grades ginseng roots with expert-level accuracy despite scarce premium samples.
Read the original →A four-legged robot designed to move autonomously through agricultural land and analyse crops using artificial intelligence is being developed in Spain. Researchers aim to give farmers more precise information.
Read the original →Researchers found a hidden feature steered the AI-generated images towards more idyllic scenes.
Read the original →Researchers combined ear tag, feeder, pedometer, and environmental data with random forest models. They detected bovine respiratory disease in pre-weaned calves with up to 70 percent accuracy.
Read the original →AI-driven and digital systems for biodiversity monitoring will be showcased at the COP17 technology exhibition in Yerevan.
Read the original →The SETU Eye-Q AI food waste technology won a 2025 EU prize. It was showcased at a UN exhibition in Rome.
Read the original →The joint opinion urges AI integration from product research and design through manufacturing and marketing. It also promotes smart goods and secure, reliable open-source operating systems.
Read the original →Every, which operates the cooking video app Delish Kitchen, is launching an AI assistant that analyzes food trends through conversation. The service is aimed at food manufacturers and supports product development and sales promotion. It is a new feature within the company's corporate food trend analysis service, Delish Research.
Read the original →The agents targeted companies in the United States, Canada and Australia, as well as Japanese e-commerce sites. By October 18, 2026, they had attempted to access more than 1,200 websites.
Read the original →