| CARVIEW |
 |
Qi WANG (王琦)
|
Biography
Qi Wang is a Ph.D. candidate at Shanghai Jiao Tong University. Qi's research focuses on reinforcement learning, computer vision, and world models. He has published several papers at top-tier conferences, including NeurIPS, ICLR, and ICCV, with one selected for oral presentation. He is also an avid open-source contributor, with projects amassing over 25,000 GitHub stars. He has authored two bestselling books based on his tutorials. He is the chief organizer of NeurIPS 2025 Workshop on Embodied World Models for Decision Making.Research Interest
I work in the field of Reinforcement learning, Computer vision, Deep learning, and Machine learning. Currently, I focus on the following research topics:- Reinforcement learning
- World models
- Embodied intelligence
Education
- 2022.09-2026.06 Ph.D. Candidate in the School of Computer Science at the Shanghai Jiao Tong University (Also as a joint student in the Eastern Institute for Advanced Study), supervised by Xiaokang Yang (IEEE Fellow, Winner of National Science Fund for Distinguished Young Scholars/国家杰青), Wenjun Zeng (Fellow of CAE/加拿大工程院外籍院士, IEEE Fellow), and I also work closely with Yunbo Wang, and Xin Jin.
- 2019.09-2022.07 M.E. in the Shenyang Institute of Computing Technology at the University of Chinese Academy of Sciences. GPA 3.81/4.0.
Publications
Conferences
[5] Qi Wang*, Zhipeng Zhang*, Baao Xie*, Xin Jin, Yunbo Wang, Shiyu Wang, Liaomo Zheng, Xiaokang Yang, Wenjun Zeng, 'Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning', ICCV 2025. [PDF] [Website] [PyTorch Code 
[4] Jiajian Li*, Qi Wang*, Yunbo Wang, Xin Jin, Yang Li, Wenjun Zeng, Xiaokang Yang, 'Open-World Reinforcement Learning over Long Short-Term Imagination', ICLR 2025 Oral (Top 1.8%). [PDF][Website] [PyTorch Code 
[3] Qi Wang*, Junming Yang*, Yunbo Wang, Xin Jin, Wenjun Zeng, Xiaokang Yang, 'Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning', NeurIPS 2024 [PDF] [Website] [PyTorch Code 
[2] Qi Wang , Liaomo Zheng, Shiyu Wang, Xinjun Liu, 'Lightweight Stacked Hourglass Network for Efficient Robotic Arm Pose Estimation,' IEEE International Conference on Computer and Communications (ICCC), 2021. (EI, Best Presentation Award)
[1] Liaomo Zheng, Xiaojie Wang, Qi Wang , Shiyu Wang, Xinjun Liu, 'A Fabric Defect Detection Method Based on Improved YOLOv5,' IEEE International Conference on Computer and Communications (ICCC), 2021. (EI)
Preprint
[4] Qi Wang*, Mian Wu*, Yuyang Zhang*, Mingqi Yuan, Wenyao Zhang, Haoxiang You, Yunbo Wang, Xin Jin, Xiaokang Yang, Wenjun Zeng, 'Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning'. [arXiv]
[3] Tan Wang, Yun Wei Dong, Tao Zhang, Qi Wang,'HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting'. [arXiv]
[2] Mingqi Yuan*, Qi Wang*, Guozheng Ma*, Bo Li, Xin Jin, Yunbo Wang, Xiaokang Yang, Wenjun Zeng, Dacheng Tao, 'Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning'. [arXiv][Code 
[1] Yuyang Zhang, Baao Xie, Hu Zhu, Qi Wang, Huanting Guo, Xin Jin, Wenjun Zeng, 'Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning'. [arXiv]
Books
[3] Qi Wang, Yiyuan Yang, Ji Jiang, 'LeeDL-Tutorial' (深度学习详解), Posts & Telecom Press, 2024. (Influential New Book of the 2024 in PTP Epubit, 2024 Jingdong Top 100 Books, Reported by China Central Television/CCTV). [GitHub Repo] [E-book] [Douban] [Dangdang] [Jingdong] [CCTV Video Report] [Trophy]
[2] Yang Li, Qi Wang, Junjun Liu, Chen Li, 'A Practical Guide to Getting Started with Deep Reinforcement Learning', 2024. (Preprint, Officially Recommended by Hugging Face). [WeChat] [ZhiHu] [Bilibili] [XiaoHongShu]
[1] Qi Wang, Yiyuan Yang, Ji Jiang, 'Easy RL: Reinforcement Learning Tutorial' (Easy RL：强化学习教程), Posts & Telecom Press, 2022. (Excellent book for 2022 Q1th in PTP, Bestselling New Book of the 2022 in PTP Epubit, Reported by Zhejiang Satellite TV/浙江卫视). This book is recommended by many famous reinforcement learning experts, such as Hung-yi Lee (Professor at Taiwan University), Shengbo Li (Professor at Tsinghua University), Jun Wang (Professor at UCL), Bolei Zhou (Assistant Professor at UCLA), etc. [GitHub Repo] [Online version] [E-book] [Douban] [Taobao] [Dangdang] [Jingdong]
Patents
[2] Yunbo Wang, Xiaokang Yang, Qi Wang, 'A Reinforcement Learning System for Offline Visual Control of Intelligent Robots', Chinese invention patent, Publication Number: CN118014052A.
[1] Xiaokang Yang, Yunbo Wang, Qi Wang, Wendong Zhang, 'A Reinforcement Learning System for Multi-Task Long-Horizon Decision Making in Robotic Arms', Chinese invention patent, Publication Number: CN117584127A.
Projects
Open-Source Projects
- LeeDL-Tutorial: A Chinese deep learning tutorial and it has already received 15,000 more stars and 2,800 more forks on GitHub, which includes an
an e-book and
codes (Recommended by Hung-yi Lee). [Twitter] Here are some links to our book.
[Douban]
[Jingdong]
[Dangdang]
- Easy-RL: A reinforcement learning tutorial and it has already received 11,000 more stars and 1,900 forks on GitHub, which includes
an e-book and
an online tutorial. Also, there is an online tutorial collaboration with Baidu PaddlePaddle AI Studio (1k more participants).
Here are some links of our book.
[Douban]
[Jingdong]
[Taobao]
[Dangdang]
Our book topped the list of computer new books on Dangdang and the list of AI-field New books on Jingdong within ten days. The number of related tweets reads exceeded 100,000, and it was recommended to the libraries of the North China Electric Power University, Shanghai Ocean University, SIGS at Tsinghua University. Also, it is included in the National Library of China, Library of Chinese Academy of Sciences, Library of Tsinghua University, Library of Shanghai Jiao Tong University, Library of Zhejiang University, and Library of University of Science and Technology of China, and so on. The electronic version has been downloaded over 10,000 times, and the paper version won the PTP key book selection and Excellent book for 2022 Q1th in PTP. - Awesome Visual RL: A curated list of reinforcement learning with vision resources.
- Awesome-World-Model: Collect some world models (for autonomous driving) papers.
- Translated articles in the field of data science are as follows. [This Is How Reinforcement Learning Works ] [Build PyTorch Models Easily Using torchlayers] [Automated Machine Learning: How do teams work together on an AutoML project? ] [What are Python Iterators and Generators? Programming Concepts Every Data Science Professional Should Know] [A Gentle Introduction to Ensemble Learning] [A Gentle Introduction to Computational Learning Theory] [Decision Tree Algorithm With Hands On Example] [Fundamentals of Deep Learning – Activation Functions and When to Use Them?] [5 Techniques to Prevent Overfitting in Neural Networks] [4 Ways to Address Gender Bias in AI] [SVP：An efficient data selection method for deep learning]
- More open-source contents can be found on my GitHub.
Honors and Awards
- 2025, Zhefu Tao Scholarship, Shanghai Jiao Tong University.
- 2025, Best Popularity Award of 2024, AI Time. [Link]
- 2024, Influential New Book, Epubit, PTPress. [Link]
- 2024, Merit Student, Shanghai Jiao Tong University.
- 2023, Outstanding Authors and Translators for the 70th Anniversary, Posts & Telecom Press.[Certification]
- 2023, National Second Prize,"Optics Valley Of China·Huawei Cup" The 19th China Post-Graduate Mathematical Contest in Modeling, with faculty advisor Xiaofeng Gao (Professor at SJTU).
- 2023, Author of 2022 Bestselling New Book and Influential Author, Epubit, PTPress.[Link][Picture1][Picture2] [Trophy1] [Certification1] [Trophy2] [Certification2]
- 2022, 'ZhiZhuo Honor' of Datawhale. [ZhiZhuo]
- 2022, Excellent Book's Author for 2022 Q1th in PTP, China. [Picture]
- 2020, Excellent Undergraduate Thesis of Jiangsu Province.
- 2019, First Prize, Undergraduate Excellent Graduation Thesis (Top 0.5%).
- 2018, International Second Prize, Asia and Pacific Mathematical Contest in Modeling (APMCM).
- 2017, National Second Prize, Chinese College Students Computer Design Contest.
- 2017, Provincial Second Prize, "Challenge Cup" Jiangsu Province Selection Competition.
Services and Activities
Program Chair
- Organizer of NeurIPS 2025 Embodied World Models for Decision Making Workshop.
Reviewer
- IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
- International Journal of Computer Vision (IJCV), 2025
- International Conference on Learning Representations (ICLR), 2026.
- Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2025.
- Neural Information Processing Systems (NeurIPS), 2025.
Teaching
- 2023, Teaching assistant of JCCX0021: Fundamentals of Artificial intelligence, Shanghai Jiao Tong University.
- 2021, Teaching assistant of Pietro Liò, the professor of the University of Cambridge, UK. He is also the member of the Academia Europaea (欧洲科学院院士). The class name is Reinforcement Learning.
- 2020, Teaching assistant of Yiyu Shi, the professor of the Department of Computer Science and Engineering at the University of Notre Dame, USA. The class name is Deep Learning for Embedded Systems.
- 2019, Teaching assistant of Francis Steen, the professor of the UCLA, USA. The class name is Multimodal Communication and Artificial Intelligence.
- 2020, Teaching assistant of Rakesh Kumar, the professor of the Department of Electrical and Computer Engineering at the UIUC, USA. The class name is Artificial Intelligence and Machine Learning for Beginners.
Volunteering & Leadership
- Assistance in organizing ICCV 2025 DRL4Real Workshop.
- 2024.05-Now, DeepTimber Youth Executive Committee Member.
- 2024.01, Host of AI Institute of Shanghai Jiao Tong University's year-end party. 2023.05-Now, Intel Edge Innovator (英特尔边缘计算创新大使), promotion of Intel-related technologies. [Trophy1] [Trophy2]
- 2023.04-Now, Hugging Face volunteer, translating high-quality articles in the Hugging Face.
- 2022.10-Now, AI Time volunteer, AI Time Shanghai Jiao Tong University Club President, sharing the AI future and recent researches.
- 2022.10-2023.03, excellent volunteer, Academic Division of the Graduate Student UNION of Shanghai Jiao Tong University, organizing related academic activities and sharing.
- 2022.10-2023.03, excellent volunteer, Academic Division of the Graduate Student UNION of the School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, organizing related academic activities and sharing. [Certification]
- 2022.09-Now, Ph.D. Class Monitor, School of Computer Science, Shanghai Jiao Tong University.
- 2020.05-Now, Datawhale member (an open-source AI organization), helped data science fans get involved in the AI community.
- 2019.11-Now, Datapi THU volunteer, translating cutting edge articles related to AI.
Invited Talks and Lives
- 2024.09, Research Experience Sharing in the AI Time. [Bilibili][WeChat1][WeChat2]
- 2024.08, Tutorial on reinforcement learning at 1st Computational Decision Neuroscience (CDN) Summer School and Decision Neuroscience Symposium. [WeChat]
- 2024.04, PhD Debate on Mamba and its variants in the AI Time. [Bilibili][WeChat1][WeChat2][XiaoYuZhou] [Zhipu AI Assistant]
- 2023.07, ChatGPT and reinforcement learning sharing, and a book signing of Easy-RL book in the Global AI Developer Conference (WAIC, 世界人工智能大会). [Link1] [Picture1] [Picture2] [Picture3]
- 2023.04, Research in the era of large models sharing, CVPR 2023 Pre-Seminar (Shanghai Jiao Tong University Speical Session) in the AI Time. [Link1] [Link2]
- 2023.03, ChatGPT and reinforcement learning sharing, Doctoral Forum for Electrical Discipline of Shanghai Jiao Tong University and Fudan University. [Second Prize for Sharing] [Link]
- 2023.02, ChatGPT and reinforcement learning sharing, and a book signing of Easy-RL book in the Global AI Developer Conference (GAIDC, 全球人工智能开发者先锋大会). [Shanghai Release WeChat Official Account, 上海发布微信公众号] [Link2] [Link3] [Picture1] [Picture2] [Picture3]
- 2022.12, Experience Sharing for 2022 in the Datawhale. [Link]
- 2022.11, An online tutorial collaboration with Baidu PaddlePaddle AI Studio. [Link1] [Link2] [Picture1] [Picture2]
- 2022.09, A live stream about Open Source in the AI Time. [Video] [Link1] [Link2] [Picture1] [Picture2]
- 2022.06, Bilibili Programmers read classic IT books. [Link] [Video1] [Video2] [Video3] [Picture]
- 2022.06, How to grow from beginner to AI engineer, Datawhale. [Bilibili]
- 2022.05, Experience of learning reinforcement learning sharing, OSCHINA. [Link]
- 2022.05, Easy-RL book sharing, SICT, University of Chinese Academy of Sciences. [Link]
- 2022.05, Graduate interview/story, SICT, University of Chinese Academy of Sciences. [Link]
- 2022.05, WeChat Media Platform "Gu-Yue-Ju" Easy-RL book live sharing. [Link1] [Link2] [Picture]
- 2022.05, "Bright Top" Forum Easy-RL book live sharing.
- 2022.04, Easy-RL book live sharing with Posts and Telecommunications Press. [Link1] [Link2] [Link3] [Link4] [Link5] [Link6] [Link7] [Link8] [Link9] [Link10] [Link11] [Link12] [Link13] [Link14] [Link15] [Link16] [Link17] [Link18] [Link19] [Link20] [Picture1] [Picture2] [Picture3] [Picture4] [Picture5] [Picture6] [Picture7] [Picture8] [Picture9] [Picture10] [Picture11] [Picture12]