DUAL Distributed compUting, optimizAtion, and Learning (DUAL) group at USyd

Han Shu is a PhD Candidate at the University of Sydney whose research focuses on reinforcement learning and large language model (LLM) routing. His work aims to improve the decision-making capabilities of AI systems by combining adaptive control from reinforcement learning with efficient routing strategies for large-scale language models, enabling faster, more accurate, and context-aware responses.

In addition to his research, Han serves as a casual academic at the University of Sydney, teaching courses in predictive analytics, machine learning, and data mining. He has prior industry experience as a software engineer and research assistant, contributing to projects in distributed systems, deep learning, and intelligent systems. Han’s interdisciplinary background bridges machine learning, reinforcement learning, and AI system optimization.

Search for Han Shu's papers on the Research page