Lu Han is a Master of Philosophy candidate at the University of Sydney. Her research focuses on trustworthy and privacy-preserving personalization of large language models. She studies how generative models can adapt to individual users, writers, or domains while preserving private data, authorial style, and personalized preferences. Her work combines federated learning, parameter-efficient fine-tuning, representation learning, and evaluation of style retention, with the broader goal of building generative AI systems that are both personalized and reliable.
Distributed compUting, optimizAtion, and Learning (DUAL) group at USyd
Distributed compUting, optimizAtion, and Learning (DUAL) group at USyd