Michal Golovanevsky, PhD

Hello, I’m Michal Golovanevsky. I’m a Postdoctoral Research Fellow in the AI in Medicine program at Mass General Brigham and Harvard Medical School. My education spans applied mathematics, computer science, and AI, and I focus on developing reliable and interpretable multimodal learning systems for real-world healthcare settings.

My current research explores how vision-language models reason and how they can be made more transparent and dependable for clinical use. In my PhD at Brown University, I designed new attention mechanisms and mechanistic interpretability approaches to better understand the inner workings of multimodal deep learning systems, with applications in healthcare.

I’m motivated by building trustworthy AI systems that translate complex model behavior into clear, actionable insights that support safer and more effective healthcare technologies.