Aavishkar Gautam

Hi! I’m Aavishkar Gautam, a Computer Science student at New York University Abu Dhabi with a minor in Applied Mathematics. I’m passionate about AI safety, machine learning security, and building innovative software solutions.

Research Interests

I’m currently working as a Research Assistant at the Haven Lab at NYUAD, focusing on AI safety research. I am researching frameworks to understand safety mechanisms specifically Refusal in Large Language Models (LLM) using Representation Engineering methodologies. I’m interested in understanding and improving the robustness of machine learning systems.

What I’m Working On

I’m currently co-authoring research on refusal mechanisms in frontier models and continuing to explore the intersection of AI safety and machine learning security.