Yu Cheng

Yu Cheng is an Associate Professor in the Department of Computer Science at The Chinese University of Hong Kong. His research interests include Artificial Intelligence, Deep Learning, Machine Learning, and Computer Vision. Prof. Cheng joined the university in 2024 and is also the Chief Scientist at Kunlun Wanwei Technology and Skywork AI. He has held significant roles at Microsoft Research Redmond and Minimax, contributing to the development of several GenAI models. He serves as a Senior Area Chair for NeurIPS and ICML and as an Action Editor for Transactions on Machine Learning Research and ACM Transactions on Intelligent Systems and Technology. His work has been recognized with several awards, including the IEEE 2024 SPS Young Author Best Paper Award and the Outstanding Paper Award in NeurIPS 2023.

Yu Cheng is a professor at the Chinese University of Hong Kong, specializing in Deep Generative Models, Multimodal Learning, and Efficient/sparse Architectures. Their research focuses on advancing representation learning through multimodal data integration, enhancing generative models for image-text understanding, and developing efficient neural network architectures for model compression and acceleration. Key contributions include work on adversarial training, parameter-efficient fine-tuning, and robustness evaluation of language models. Cheng's publications explore topics such as model compression, domain adaptation, and trustworthiness assessment in large-scale AI systems, emphasizing practical applications in natural language processing and computer vision.