GitHub

️ MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents

We are happy to release MMBench-GUI, a hierarchical, multi-platform benchmark framework and toolbox, to evaluate GUI agents. MMBench-GUI is comprising four evaluation levels: GUI Content Understanding ...
IEEE

Power Cycling Testing for Power Semiconductor Switches: Methods, Standards, Limitations, and Outlooks

Abstract: Reliability is a critical performance metric for power semiconductor switches and power electronic systems. Yet guidance on how to test and quantify that reliability is fragmented in the ...
IEEE

Supply Chain Stress Testing for Tariff Shocks and Trade Conflicts: Methods, Models, and Reciprocal Influence of Operations and Economics

Abstract: This article is induced by novel decision-making settings entailed in supply chains in the wake of the global tariff crisis in spring 2025. Their context and scope differ from traditional ...
NPR

Teachers are using software to see if students used AI. What happens when it's wrong?

Ailsa Ostovitz has been accused of using AI on three assignments in two different classes this school year. "It's mentally exhausting because it's like I know this is my work," says Ostovitz, 17. "I ...
GitHub

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

Current GUI grounding approaches rely heavily on large-scale pixel-level annotations and training-time optimization, which are expensive, inflexible, and difficult to scale to new domains. we observe ...