Md Kamrul Islam

About Me

I am an AI Research Engineer with two years of experience across research and industry, specializing in large language models, information extraction, deep learning, and medical imaging. I hold an Erasmus Mundus Joint Master’s degree in Big Data Management and Analytics (BDMA), completed across CentraleSupélec, Universitat Politecnica de Catalunya, and Universite Libre de Bruxelles. During my master’s thesis, supervised by Dr. Tiphaine Henry, and Prof. Sami Souihi, I worked on large language models for cybersecurity-related tasks. I previously earned a Bachelor’s of Engineering degree in Software Engineering from Sichuan University, China with distinction, where my undergraduate thesis, supervised by Prof. Jie Chen, focused on deep learning for medical imaging. When I’m not reading papers or running experiments, I enjoy practicing new languages or playing tennis.

Interested in collaborating on a publication or exchanging research ideas? I would be glad to connect.

mdkamrul.islam@student-cs.fr / mdkamrul.islam@hotmail.com

Research Highlights

My academic and research experiences reflect this exploration:

• Master’s thesis (LLMs + security requirements extraction): Developed a hybrid LLM + rule-based framework for security annotations in business process models, improving quality while reducing manual effort.
  Submission update: Submitted to the 24th International Conference on Business Process Management (BPM 2026) and currently under review.
  Availability: Preprint, code, and dataset are temporarily private to preserve anonymous review.
• Graduate research (medical imaging): Developed unsupervised deep clustering frameworks based on group-equivariant CNNs to improve representation learning and cluster separability while reducing reliance on data augmentation. See project: Unsupervised chest X-ray clustering with group-equivariant convolutions.
• Undergraduate thesis (deep learning in healthcare): Designed and trained CNN architectures for multi-class tumor classification from brain MRI scans, with a focus on preprocessing, evaluation metrics, and robustness. See project: Brain Tumor Detection and Classification Using Convolutional Neural Networks.

Expertise

• Core ML & AI: Python, PyTorch, Deep Learning, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG)
• Data & Systems: Big data systems, distributed data pipelines, data engineering, data mining
• Domains: AI in healthcare, medical imaging, security-aware business process modeling, knowledge graphs

Research Interests

I am broadly interested in: