Nassim Walha is a doctoral candidate in machine learning. His current research, in collaboration with the Data Analytics & Artificial Intelligence department at Siemens AG, focuses on uncertainty quantification and robustness in generative AI. During his studies, he joined various teams in academia and industry to work on topics related to machine learning and deep learning, both on the theoretical and practical side. His bachelor thesis focused on a mathematical proof of the double descent phenomenon, which explains why deep neural networks do not overfit despite being overparametrized. During his master studies, he joined Huawei Technologies to work on privacy in large language models. His master’s thesis on privacy-preserving text rewriting resulted in a paper at the Safe Generative AI workshop at NeurIPS 2024.