Software tool can detect hidden errors in complex tissue analyses

A new software tool, ovrlpy, improves quality control in spatial transcriptomics, a key technology in biomedical research. Developed by the Berlin Institute of Health at Charité (BIH) in international ...
Blue Headlineq

You’re Trusting AI Agents That Make Decisions You Can’t Explain

AI agents make decisions you can’t explain. AgentXRay reveals how black-box AI workflows can be reconstructed—and why trust is at risk.
Microsoft

A one-prompt attack that breaks LLM safety alignment

As LLMs and diffusion models power more applications, their safety alignment becomes critical. Our research shows that even minimal downstream fine‑tuning can weaken safeguards, raising a key question ...
IEEE

Using Graph Neural Networks in Reinforcement Learning With Application to Monte Carlo Simulations in Power System Reliability Analysis

Abstract: This paper presents a novel method for power system reliability studies that combines graph neural networks with reinforcement learning. Monte Carlo methods are the backbone of probabilistic ...
IEEE

Accelerating Reliability Analysis for Aging and Self-Heating using Machine Learning

Abstract: The relentless drive for advanced technologies, fueled by the demands of AI and safety-critical applications, has intensified the focus on transistor aginga pivotal concern that undermines ...