Yangyang Shu
Scholar

Yangyang Shu

Google Scholar ID: TpdRFZIAAAAJ
Associate Lecturer, University of New South Wales
Computer VisionMachine Learning
Citations & Impact
All-time
Citations
238
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • Published several papers, including 'MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion' (IJCAI 2025), 'Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors' (CVPR 2024), 'MuseBarControl: Enhancing Fine-Grained Control in Symbolic Music Generation through Pre-Training and Counterfactual Loss' (arXiv:2402.01157, 2024), and more.
Research Experience
  • Currently an Associate Lecturer in the School of Systems and Computing at the University of New South Wales (UNSW), Australia. Previously worked as a Research Fellow at the Australian Institute for Machine Learning (AIML) at the University of Adelaide, advised by Prof. Lingqiao Liu.
Education
  • Received an M.S. degree in Computer Science from the University of Science and Technology of China in 2018, advised by Prof. Shangfei Wang. Completed a Ph.D. in Data Science and Machine Intelligence Lab and the Faculty of Engineering and Information Technology at the University of Technology Sydney in 2021, advised by Prof. Guandong Xu.
Background
  • Research interests lie in machine learning, computer vision, multimedia, privileged information, and related applications in artificial intelligence, including multi-task learning, fine-grained recognition, music emotion, music composition, and photo aesthetics. Recently, the major research topics are about rationale-guided machine learning and large language models.
Miscellany
  • Deeply passionate about techniques that can enhance the training and deployment of large language models, with a particular focus on music large language models. Interests include developing improved training methodologies, advanced strategies for better generation control, and optimizing inference times.
Co-authors
0 total
Co-authors: 0 (list not available)