PhD
Chair of Data Analytics and Machine Learning at TUM
Informatik 26
Department of Computer Science
Boltzmannstr. 3
85748 Garching
Biosketch
Amine is a PhD student at the Technical University of Munich working with Prof. Stephan Günnemann. He is broadly interested in the foundations of AI and machine learning and their real-world applications. His current research aims to develop reliable generative models for complex domains, ranging from biological systems to interlinked business data. Amine holds a Bachelor’s degree in Electrical Engineering and a Master’s degree in Robotics & AI. He has been part of the relAI family since 2022.
relAI Research
Generative Models for Structured Data
My research focuses on developing generative models for structured data, including tables, graphs, and databases. In my earlier work, I explored applications in biology, developing a diffusion-based approach for protein docking [1] and a latent diffusion model for molecular graph generation [2]. More recently, I developed a diffusion model for relational databases that represents databases as graphs and combines ideas from random graph generation and diffusion models to efficiently generate synthetic relational databases with millions of rows [3]. Currently, I am working on tabular foundation generative models that can generate tables across different schemas and learn previously unseen distributions from limited examples. I am particularly interested in the real-world application and deployment of these models.
Publications
https://arxiv.org/abs/2304.03889
https://arxiv.org/abs/2406.10513
https://arxiv.org/abs/2505.16527