Yiwei Lu is an assistant professor at the School of Engineering Design and Teaching Innovation of the University of Ottawa. He obtained his PhD in computer science from the University of Waterloo and was a Vector Institute researcher. His research focuses on trustworthy AI and machine learning, addressing fundamental challenges in AI safety with particular emphasis on understanding how training data impacts model behaviour. He works on building comprehensive, trustworthy machine learning pipelines and on developing rigorous technical frameworks for AI auditing and governance. His research has been published at prestigious machine learning and computer vision venues, including NeurIPS, ICML, ICLR, AAAI, TMLR, and ECCV.