I'm Binesh Sadanandan, a PhD student at the University of New Haven researching the robustness of medical Vision-Language Models. I write about AI, machine learning, mechanistic interpretability, and the challenges of deploying AI safely in healthcare.
My current work focuses on why medical VLMs give contradictory diagnoses when clinicians rephrase the same question, and what we can do about it. Read more on the About page, or find me at bineshkumar.me.