Momin Ahmad Khan

I am a fifth-year PhD student at UMass Amherst, advised by Professor Fatima Anwar. My research spans the security and robustness of distributed AI systems, large language models (LLMs), and vision-language models (VLMs). I’ve worked on designing attacks and defenses for Federated Learning (FL), identifying pitfalls in robustness evaluations, and improving prompt learning through more reliable and interpretable optimization techniques.

Recently, I completed my second internship at Nokia Bell Labs, where I focused on mechanistic interpretability for embodied AI agents—probing perception-action loops using sparse autoencoders and grounded representations. In my first internship at Bell Labs, I developed agentic LLM systems for model selection and code generation, and built a smart meeting assistant integrating LLMs, VLMs, and hardware. I’m currently exploring techniques like DPO and GRPO to enhance grounding and alignment in VLMs and multi-agent settings.

Before joining UMass, I completed my undergraduate studies in Electrical Engineering at the School of Electrical Engineering and Computer Science at the National University of Sciences and Technology in 2021. I graduated with a gold medal for best thesis project and a silver medal for the second-highest GPA in my batch.

Besides work, I am learning to play the guitar. I love to travel alone, and I have started a photography page to document my adventures. I enjoy cooking and continue to try out new recipes. But most of all, I love playing Dota 2, and I am in the top 10% of players globally!