Dr. Yangyang Shu | Low-supervised Learning | Best Researcher Award

Associate Lecturer at University of New South Wales, Australia

Yangyang Shu is a computer science researcher specializing in machine learning and artificial intelligence, with a current appointment as Associate Lecturer at the University of New South Wales (UNSW). His research spans self-supervised learning, domain adaptation, privileged information, and their applications in areas like fine-grained visual recognition and music understanding. With a strong academic background from institutions in China and Australia, he has published extensively in top-tier venues (CVPR, IJCAI, ECCV) and actively contributes to peer review for A* conferences and journals. Yangyang is also skilled in symbolic music generation and performance modeling, especially in the context of large language models.

Publication Profile 

Scopus

Educational Background 🎓

• Ph.D. in Engineering & Information Technology
  University of Technology Sydney (UTS), Australia
  Duration: July 2018 – November 2021
  Supervisor: Prof. Guandong Xu

• M.Sc. in Computer Science
  University of Science and Technology of China (USTC)
  Duration: September 2015 – July 2018
  Supervisor: Prof. Shangfei Wang

• B.Sc. in Computer Science
  Anhui University (AHU)
  Duration: September 2011 – July 2015

Professional Experience 💼

• Associate Lecturer
  University of New South Wales (UNSW), School of Systems and Computing
  March 2025 – Present
  Supervisor: Prof. Roland Göcke

• Research Fellow
  University of Adelaide, Australian Institute for Machine Learning (AIML)
  December 2021 – December 2024
  Supervisor: A/Prof. Lingqiao Liu

• Academic Supervision
  Unofficially supervised 1 PhD student, 3 master’s students, and 2 undergraduates at USTC, UTS, Adelaide, and UNSW.

• Teaching Experience

  • ZEIT 2103 – Data Structures and Representation, 2025 Semester 1

  • ZEIT 1112 – Introduction to Programming, 2025 Semester 2

Research Interests 🔬

• Core Areas:

  • Machine Learning (Self/Semi-Supervised Learning)

  • Unsupervised Domain Adaptation

  • Learning with Privileged Information

  • Multi-task Learning and Fine-Grained Visual Recognition

  • Music Emotion Recognition and Aesthetic Assessment

• Recent Research Focus:

  • Rationale-Guided Learning: Developing regularizations based on prediction rationale to improve generalization and data efficiency.

  • Large Language Models for Music: Enhancing training, generation control, and inference for symbolic music generation models.

Awards and Honors🏆✨

• 🥇 National Scholarship, University of Science and Technology of China (14/150) – 2017

• 🏅 Outstanding Graduate, USTC – 2018 (17/150)

• 🎓 Excellent Graduate, Anhui Province – 2015 (2/391)

• 🧮 Second Prize, National College Student Mathematics Competition – 2014

Conclusion🌟

Yangyang Shu is an emerging leader in artificial intelligence research, particularly in areas intersecting machine learning theory and creative applications like music AI. His consistent contributions to high-impact venues, combined with interdisciplinary research and teaching experience across major institutions in China and Australia, mark him as a promising figure in the AI and computer vision communities. His pursuit of rationale-aware and efficient learning systems shows a clear vision for the next generation of interpretable and human-aligned AI technologies.

Publications 📚

1. 🎵 MuseBarControl
   Enhancing Fine-Grained Control in Symbolic Music Generation through Pre-Training and Counterfactual Loss
   Yangyang Shu, Haiming Xu, Ziqin Zhou, Anton van den Hengel, Lingqiao Liu
   📄 arXiv:2402.01157, 2024

   ---

2. 🧠 Unlocking the Potential of Pre-trained Vision Transformers
   for Few-Shot Semantic Segmentation through Relationship Descriptors
   Ziqin Zhou, Haiming Xu, Yangyang Shu, Lingqiao Liu
   🎯 CVPR 2024 (⭐ Core Rank A*)

   ---

3. ⚡ MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion
   Wei Hua, Chenlin Zhou, Jibin Wu, Yansong Chua, Yangyang Shu
   🤖 IJCAI 2025 (⭐ Core Rank A*)

   ---

4. 🧩 Learning Common Rationale to Improve Self-Supervised Representation
   for Fine-Grained Visual Recognition Problems
   Yangyang Shu, Anton van den Hengel, Lingqiao Liu
   🎯 CVPR 2023 (⭐ Core Rank A*)

   ---

5. 🔄 Source-Free Unsupervised Domain Adaptation
   with Hypothesis Consolidation of Prediction Rationale
   Yangyang Shu, Xiaofeng Cao, Qi Chen, Bowen Zhang, Ziqin Zhou, Anton van den Hengel, Lingqiao Liu
   📄 arXiv:2402.01157, 2024

   ---

6. 📉 Improving Fine-Grained Visual Recognition in Low Data Regimes
   Via Self-Boosting Attention Mechanism
   Yangyang Shu, Lingqiao Liu, Baosheng Yu, Haiming Xu
   🖼️ ECCV 2022 (⭐ Core Rank A*)

   ---

7. 🌇 Semi-Supervised Adversarial Learning
   for Attribute-Aware Photo Aesthetic Assessment
   Yangyang Shu, Qian Li, Lingqiao Liu, Guandong Xu
   📰 IEEE TMM 2021 (⭐ Core Rank A*)

   ---

8. 🎨 Privileged Multi-Task Learning for Attribute-Aware Aesthetic Assessment
   Yangyang Shu, Qian Li, Guandong Xu
   📘 Pattern Recognition (PR) 2022 (⭐ Core Rank A*)

   ---

9. ➕ V-SVR+: Support Vector Regression with Variational Privileged Information
   Yangyang Shu, Qian Li, Chang Xu, Shaowu Liu, Guandong Xu
   📰 IEEE TMM 2021 (⭐ Core Rank A*)

   ---

10. 🧪 Perf-AL: Performance Prediction for Configurable Software through Adversarial Learning
    Yangyang Shu, Yulei Sui, Hongyu Zhang, Guandong Xu
    🛠️ ESEM 2020, pp. 1–11 (⭐ Core Rank A)

    ---

11. 🖼️ Learning with Privileged Information for Photo Aesthetic Assessment
    Yangyang Shu, Qian Li, Shaowu Liu, Guandong Xu
    🧮 Neurocomputing 2020, Vol. 404, pp. 304–316 (⭐ Core Rank B)

    ---

12. 🎻 Emotion Recognition from Music Enhanced by Domain Knowledge
    Yangyang Shu, Guandong Xu
    🌊 PRICAI 2019, Fiji, pp. 121–134 (⭐ Core Rank B)

    ---

13. 🧠 Emotion Recognition through Integrating EEG and Peripheral Signals
    Yangyang Shu, Shangfei Wang
    🔊 ICASSP 2017, USA, pp. 2871–2875 (⭐ Core Rank B)

    ---