Binhang Yuan

Binhang Yuan is an Assistant Professor at the Department of Computer Science and Engineering (CSE), the Hong Kong University of Science and Technology (HKUST). His research interests include data management systems for machine learning, distributed and decentralized machine learning systems. He received his Ph.D. and master's degrees from Rice University and his bachelor's degree from Fudan University. Before joining HKUST, he was a Postdoc at the Swiss Federal Institute of Technology Zurich (ETH Zurich). His work has been recognized with the Best Paper Honorable Mention Award at VLDB and Research Highlight Award in SIGMOD.

Binhang Yuan is a researcher focused on ML systems, with a particular emphasis on optimizing large language models (LLMs) for efficient inference and training. His work explores techniques such as contextual sparsity, generative inference over heterogeneous environments, and distributed learning frameworks for foundation models. Yuan has developed systems like FlexGen and HexGen to enhance throughput and reduce resource requirements for LLM deployment. His research also extends to healthcare IoT and federated learning, aiming to improve scalability and privacy in distributed machine learning. Additionally, he has contributed to the design of distributed systems for reinforcement learning and time series classification.