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 Bachelorā€™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 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.

šŸ”„ News

  • 2024.05: šŸŽ‰šŸŽ‰ Our paper ā€œImitation Learning from Purified Demonstrationsā€ is accepted by ICML 2024.
  • 2023.05: šŸŽ‰šŸŽ‰ Our paper ā€œLearning to Schedule in Diffusion Probabilistic Modelsā€ is accepted by KDD 2023.
  • 2022.12: šŸŽ‰šŸŽ‰ Our project ā€˜Robust Gait Control and Automatic Navigation for Quadruped Robotā€™ wins the *first* prize of China Graduate AI Innovation Competition (8/1174)
  • 2022.11: šŸŽ‰šŸŽ‰ Our paper ā€œUnlabeled Imperfect Demonstrations in Adversarial Imitation Learningā€ is accepted by AAAI 2023.

šŸ“ Publications

  • Yunke Wang, Chang Xu, Bo Du, Honglak Lee.Ā ā€œLearning to Weight Imperfect Demonstrationsā€, 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.Ā ā€œRobust Adversarial Imitation Learning via Adaptively-Selected Demonstrationsā€,Ā 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. ā€œUnlabeled Imperfect Demonstrations in Adversarial Imitation Learningā€, 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. ā€œLearning to Schedule in Diffusion Probabilistic Modelsā€, In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023. (CCF A, Core A*) [Paper]

  • Yunke Wang, Bo Du, Wenyuan Wang, Chang Xu. ā€œMulti-Tailed Vision Transformer for Efficient Inferenceā€, Neural Networks, 2024. (CCF B) [Paper]

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

  • Yunke Wang, Linwei Tao, Yutian Lin, Bo Du, Chang Xu. ā€œVisual Imitation Learning with Calibrated Contrastive Representationā€, Preprint, 2024. [Paper]

šŸŽ– 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.
  • 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).

šŸ“– 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.

šŸ’¬ Talks

  • 2023.06, ā€œImitation Learning from Imperfect Demonstrationsā€, at ā€œDiDiā€ Forum for Doctoral Students.
  • 2023.02, ā€œDynamic Neural Network in Vision Transformerā€ at the University of Sydney, Deep Learning Class.
  • 2021.10, ā€œDeep Reinforcement Learning in Autonomous Drivingā€ at In-Driving Co Ltd.
  • 2021.09, ā€œImitation Learning from Imperfect Demonstrationsā€ at Doctoral Innovation Forum on Artificial Intelligence in Central and Western China.

šŸ’» Academic Service

  • Conference Reviewer: NeurIPS, ICML, ICLR, KDD, CVPR, ICCV, ECCV, AAAI, IJCAI, ICPR.
  • Journal Reviewer: TPAMI, TKDE, TMM, TCSVT, Neural Networks, Neurocomputing.