I’m Chengyang Ying, a fourth-year Ph.D. student of TSAIL Group in the Department of Computer Science and Technology, Tsinghua University, advised by Prof. Jun Zhu and A/Prof. Hang Su. My research interest includes machine learning, reinforcement learning, Embodied AI, and AI for science.

Before that, I obtained my Bachelor of Science degree from the Department of Mathematical Sciences of Tsinghua University in July 2021, majored in Mathematics and minored in Computer Application.

My curriculum vitae is here.

Email: ycy21@mails.tsinghua.edu.cn; yingcy17@gmail.com

Paper reading list of part recent research on Single Agent RL

Blog: A Useful Lemma for Several RL Results

Publications

• PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
  Chengyang Ying, Zhongkai Hao, Xinning Zhou, Xuezhou Xu, Hang Su, Xingxing Zhang, Jun Zhu
  Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024
  [project page] [arXiv] [code] [video]

• Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
  Hengkai Tan, Songming Liu, Kai Ma, Chengyang Ying, Xingxing Zhang, Hang Su, Jun Zhu
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  [project page] [arXiv] [code]

• DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
  Zhongkai Hao, Chang Su, Songming Liu, Julius Berner, Chengyang Ying, Hang Su, Anima Anandkumar, Jian Song, Jun Zhu
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  [arXiv] [code]

• Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning
  You Qiaoben, Chengyang Ying, Xinning Zhou, Hang Su, Jun Zhu, Bo Zhang
  SCIENCE CHINA Information Sciences (SCIS), 2024
  [arXiv] [code]

• On the Reuse Bias in Off-Policy Reinforcement Learning
  Chengyang Ying, Zhongkai Hao, Xinning Zhou, Hang Su, Dong Yan, Jun Zhu
  International Joint Conference on Artificial Intelligence (IJCAI), Macao, China, 2023
  [arXiv] [code] [slide]

• GNOT: A General Neural Operator Transformer for Operator Learning
  Zhongkai Hao, Zhengyi Wang, Hang Su, Chengyang Ying, Yinpeng Dong, Songming Liu, Ze Cheng, Jun Zhu, Jian Song
  International Conference on Machine Learning (ICML), Hawaii, USA, 2023
  [arXiv] [code]

• NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data
  Songming Liu, Zhongkai Hao, Chengyang Ying, Hang Su, Ze Cheng, Jun Zhu
  International Conference on Machine Learning (ICML), Hawaii, USA, 2023
  [arXiv] [code]

• Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
  Chengyang Ying^∗, You Qiaoben^∗, Xinning Zhou^∗, Hang Su, Wenbo Ding, Jianyong Ai
  Pattern Recognition Letters (PRL), 2023
  [arXiv] [code]

• Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
  Huayu Chen, Cheng Lu, Chengyang Ying, Hang Su, Jun Zhu
  International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023
  [arXiv] [code]

• Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden’s Hypergradients
  Zhongkai Hao, Chengyang Ying, Hang Su, Jun Zhu, Jian Song, Ze Cheng
  International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023
  [arXiv] [code]

• A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs
  Songming Liu, Zhongkai Hao, Chengyang Ying, Hang Su, Jun Zhu, Ze Cheng
  Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2022
  [arXiv] [code]

• GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing
  Zhongkai Hao, Chengyang Ying, Yinpeng Dong, Hang Su, Jian Song, Jun Zhu
  International Conference on Machine Learning (ICML), Baltimore, USA, 2022
  [arXiv]

• Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk
  Chengyang Ying, Xinning Zhou, Hang Su, Dong Yan, Ning Chen, Jun Zhu
  International Joint Conference on Artificial Intelligence (IJCAI), Vienna, Austria, 2022
  [arXiv] [code] [slide] [ICML 2021 AML Workshop]

Worshop Papers & Preprints

• Exploratory Diffusion Policy for Unsupervised Reinforcement Learning
  Chengyang Ying, Huayu Chen, Xinning Zhou, Zhongkai Hao, Hang Su, Jun Zhu
  [arXiv]

• Task Aware Dreamer for Task Generalization in Reinforcement Learning
  Chengyang Ying^∗, Xinning Zhou^∗, Zhongkai Hao, Hang Su, Songming Liu, Dong Yan, Jun Zhu
  [arXiv]

• Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
  Zhongkai Hao, Songming Liu, Yichi Zhang, Chengyang Ying, Yao Feng, Hang Su, Jun Zhu
  [arXiv]

• Strategically-timed State-Observation Attacks on Deep Reinforcement Learning Agents
  You Qiaoben, Xinning Zhou, Chengyang Ying, Jun Zhu
  ICML 2021 Workshop on Adversarial Machine Learning, 2021
  

Services

Reviewer for ICML 2022, 2024, 2025, NeurIPS 2022, 2023, 2024, ICLR 2024, 2025, IJCAI 2024, 2025, AAAI 2025, CVPR 2024, 2025, AISTATS 2025, ISIT 2024, TCSVT

Selected Awards

• Beijing Outstanding Gradates, 2021.6
• Tsinghua Excellent Gradates, Tsinghua University, 2021.6
• China National Scholarship, Tsinghua University, 2018.10
• The first prize of “Gao Jiao She Bei”national mathematical modeling competition for College Students, 2018.10
• Silver Award of Chinese Mathematical Olympiad (CMO), 2016.11

Teaching

• 2024 Fall, TA in Advanced Machine Learning, instructed by Prof. Jie Tang and Prof. Jun Zhu
• 2022 Spring, TA in Deep Learning, instructed by A/Prof. Xiaolin Hu and Prof. Jun Zhu
• 2022 Spring, TA in Statistical Machine Learning, instructed by Prof. Jun Zhu
• 2021 Spring & 2021 Fall & 2023 Spring & 2024 Spring & 2025 Spring, TA in Discrete mathematics for Computer Science, instructed by A/Prof. Hang Su

Miscellaneous

Reading group slides:

• Foundation Models for Reinforcement Learning
• PaLM-E
• Generalization in Reinforcement Learning
• A Generalist Agent
• Meta Reinforcement Learning
• Max-Entropy Reinforcement Learning

Last update: Febrary 2025 by Chengyang Ying