Yunke Wang

Yunke Wang

PostDoc@USYD

I am a postdoctoral researcher at the School of Computer Science, University of Sydney (USYD), advised by Prof. Chang Xu. I obtained my Ph.D. degree at the School of Computer Science, Wuhan University (WHU) in June 2024, under the supervision of Prof. Bo Du and Prof. Chang Xu. Before that, I received my Bachelor’s degree in computer science from Wuhan University in June 2019. I was a visiting research student at the University of Sydney (USYD) from 2022 to 2023.

My research interests lie in reinforcement learning/imitation learning and their applications in robotics. Specifically, imitation learning and its applications in computer vision fields. Specifically, I want to make imitation learning more practical in real-world tasks by exploring how to leverage imperfect and visual demonstrations effectively. In addition, I closely follow the latest developments in generative models and LLMs.

📢 Feel free to reach out if you are seeking research collaboration in the field of robotics/generative models/VLM.

🔥 News

  • 2025.01: 🎉🎉 Our paper “CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V” is accepted by NAACL Findings 2025.
  • 2024.12: 📢📢 Call for Papers: Welcome to contribute papers to our Workshop on Sustainable AI for the Future Web at The Web Conference 2025 that will be held in Sydney 28 April - 2 May 2025.
  • 2024.12: 🎉🎉 Our paper “WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration” is accepted by AAAI 2025.
  • 2024.05: 🎉🎉 Our paper “Imitation Learning from Purified Demonstrations” is accepted by ICML 2024.
  • 2023.05: 🎉🎉 Our paper “Learning to Schedule in Diffusion Probabilistic Models” is accepted by KDD 2023.
  • 2022.12: 🎉🎉 Our project ‘Robust Gait Control and Automatic Navigation for Quadruped Robot’ wins the *first* prize of China Graduate AI Innovation Competition (8/1174)
  • 2022.11: 🎉🎉 Our paper “Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning” is accepted by AAAI 2023.

📝 Selected Publications

  • Yunke Wang, Chang Xu, Bo Du, Honglak Lee. “Learning to Weight Imperfect Demonstrations”, In Proceedings of the 38th International Conference on Machine Learning (ICML), 2021. (CCF A, Core A*) [Paper] [Supp] [Code] [Code_Atari]

  • Yunke Wang, Chang Xu, Bo Du. “Robust Adversarial Imitation Learning via Adaptively-Selected Demonstrations”, In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021. (CCF A, Core A*) [Paper] [Supp] [Code]

  • Yunke Wang, Bo Du, Chang Xu. “Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning”, In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023. (CCF A, Core A*) [Paper] [Supp] [Code]

  • Yunke Wang, Xiyu Wang, Anh-Dung Dinh, Bo Du, Chang Xu. “Learning to Schedule in Diffusion Probabilistic Models”, In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023. (CCF A, Core A*) [Paper]

  • Yunke Wang, Minjing Dong, Yukun Zhao, Bo Du, Chang Xu. “Imitation Learning from Purified Demonstrations”, In Proceedings of the 41st International Conference on Machine Learning (ICML), 2024. (CCF A, Core A*) [Paper] [Code]

  • Yunke Wang, Bo Du, Wenyuan Wang, Chang Xu. “Multi-Tailed Vision Transformer for Efficient Inference”, Neural Networks, 2024. (CCF B) [Paper]

  • Yunke Wang, Linwei Tao, Yutian Lin, Bo Du, Chang Xu. “Visual Imitation Learning with Calibrated Contrastive Representation”, Preprint, 2024. [Paper]

  • Yunke Wang, Yanxi Li, Chang Xu. “AI Scaling: From Up to Down and Out”, Preprint, 2025. [Paper]

🎖 Honors and Awards

  • 2024.06 Outstanding Graduates, Wuhan University.
  • 2023.11 Academic Innovation Scholarship, Wuhan University.
  • 2023.11 National Scholarship for Graduate Students, Ministry of Education. (1%)
  • 2023.06 KDD-23 Student Travel Award, KDD.
  • 2023.01 AAAI-23 Student Scholarship, AAAI.
  • 2022.12 First Prize Winner of China Graduate AI Innovation Competition. (8/1174)
  • 2021.10 Yisheng Ph.D. Scholarship, Wuhan University.
  • 2018.08 Second Prize Winner of Chinese Collegiate Computing Competition.
  • 2018.08 First Prize Winner of Chinese Collegiate Internet of Things Design Competition (TI CUP) (Central South Region).

📖 Educations

  • 2019.09 - 2024.06, Ph.D. in Artificial Intelligence, Wuhan University (WHU), Wuhan, China.
  • 2015.09 - 2019.06, Bachelor of Engineering in Computer Science, Wuhan University (WHU), Wuhan, China.

💬 Invited Talks

  • 2024.11, “Policy Learning in Diffusion Models”, at the University of Queensland, Brisbane City Campus, International Workshop on Weakly Supervised Learning 2024.
  • 2023.06, “Imitation Learning from Imperfect Demonstrations”, at “DiDi” Forum for Doctoral Students.
  • 2023.02, “Dynamic Neural Network in Vision Transformer” at the University of Sydney, Deep Learning Class.
  • 2021.10, “Deep Reinforcement Learning in Autonomous Driving” at In-Driving Co Ltd.
  • 2021.09, “Imitation Learning from Imperfect Demonstrations” at Doctoral Innovation Forum on Artificial Intelligence in Central and Western China.

🫶🏼 Academic Service

  • Workshop Organizer / Program Chair: The Workshop on Sustainable AI for the Future Web (WSAI) on The Web Conference 2025.
  • Conference Reviewer: NeurIPS, ICML, ICLR, KDD, MM, CVPR, ICCV, ECCV, AAAI, IJCAI, IROS, ICPR.
  • Journal Reviewer: TPAMI, TKDE, TMM, TCSVT, Neural Networks, Neurocomputing.
  • Guest Lecturer: USYD GenAI Summer School 2024.