Summary
Erfan Hatefi is a research-focused PhD student and research associate with eight years of experience at the intersection of deep learning, explainable AI, and adversarial robustness. He contributed to high-impact XAI work at Fraunhofer HHI—applying Layer-wise Relevance Propagation and AttnLRP to prune CNNs and attribute Transformers—which resulted in publications at ECCV and ICML 2024. Currently based in Leipzig and pursuing doctoral research in multimodal machine learning, he combines strong mathematical intuition with practical systems skills, managing large-scale experiments on HPC clusters via Slurm and Apptainer. A former teaching assistant in algorithms and theory, he brings a pedagogical bent and a curiosity for building explanations from first principles, plus hands-on experience developing interactive PyTorch demos that make cutting-edge XAI accessible.
9 years of coding experience
3 years of employment as a software developer
Bachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at University of Kashan
Machine Learning Based on TensorFlow, Machine Learning Based on TensorFlow at Blue-White.co
Master of Science - MS Computer Science (Informatik), Master of Science - MS Computer Science (Informatik) at Technische Universität Berlin
Persian, English, German