How Claude’s Computer Use Update Unlocks Full Desktop Automations

Anthropic’s Claude Code Computer Use preview lets Mac Pro and Max users control apps, browsers, and spreadsheets through the ...
IEEE

G-TADS: GUI Task-Ability Decoupling Strategy for High-Adaptability Multimodal Intelligent Agents

Abstract: Graphical User Interface (GUI) automation aims to help users interact with devices efficiently, and the integration of open-source multimodal large language models (MLLMs) with GUI agents ...
IEEE

An Intelligent Digital Microfluidic Biochip System with GUI and Deep Learning-Based Automation

Abstract: This paper introduces an intelligent digital microfluidic biochip (DMFB) system that integrates deep learning for automated droplet manipulation with an intuitive interface for manual ...
GitHub

AFRAgent: An Adaptive Feature Renormalization Based High Resolution Aware GUI Agent

AFRAgent is a state-of-the-art multimodal architecture for smartphone GUI automation that achieves superior performance while being less than one-fourth the size of its nearest competitor. Built on ...
GitHub

An example test automation framework built with Java, Junit5, Spring, WebTestClient, & Playwright

Countercheck has a couple of intended uses: 🏃‍ ️ A hit-the-ground-running drop-in solution for people needing a Java-based test automation framework ⚙️ An example of how a framework can be structured ...