Greetings!

I am Md Nahidul Islam, a Ph.D. student in Computer Science at the University of Memphis, advised by Dr. Myounggyu Won. My research focuses on trustworthy autonomous driving, particularly interactive motion planning, trajectory forecasting, conformal risk certification, counterfactual evaluation, and model compression for safe robotics.

My work sits at the intersection of machine learning and safety-critical decision-making. I develop methods that aim to provide reliability guarantees for autonomous systems as they are actually deployed, rather than only evaluating predictors in isolation.

In May 2026, I earned my M.S. en route with the thesis “BucketKD: A Safety-Aware Bucket-Based Knowledge Distillation Framework for End-to-End Motion Planning,” which studies how to compress autonomous-driving planners while preserving safety-relevant trajectory behavior. I currently have manuscripts under review at NeurIPS 2026, IROS 2026, and CoRL 2026, and our work on detecting stealthy anomalies was published at IEEE MILCOM 2025.

Before joining the University of Memphis, I worked as an Assistant Director at Bangladesh Bank, the Central Bank of Bangladesh, and as a Software Engineer at Binate Solutions Ltd. I was also a Research Assistant at Bangladesh University of Engineering and Technology (BUET) under Dr. Muhammad Abdullah Adnan, where I contributed to publications at IEEE CCNC, IEEE MILCOM, ICASSP, NAACL, and LREC.

I am actively seeking Summer 2027 research internships in autonomous driving, motion planning, trajectory forecasting, and trustworthy machine learning. If you are recruiting in these areas, I would be glad to hear from you. Please reach me at mislam19@memphis.edu.