Jialong Wu

About Me

I am currently a second-year Ph.D. student at Machine Learning Group (THUML), School of Software, Tsinghua University, advised by Prof. Mingsheng Long. Before that, I received my Bachelor’s degrees in Software Engineering, and Pure and Applied Mathematics (second degree), from Tsinghua University. In high school, I was quite into competitive programming and used to compete in Olympiad in Informatics (OI).

My research goal is to develop fundamental techniques in pursuit of general decision intelligence and advance their applications in the real world (both physically and computationally). Currently, my research interests include:

Data-driven reinforcement learning & decision making: offline reinforcement learning, imitation learning, model-based reinforcement learning
Deep learning: world models, foundation models, transfer learning

My Quote

“The people who are crazy enough to think they can change the world, are the ones who do.” —Think Different

News

[Sept. 2023] One paper about world model pre-training is accepted by NeurIPS 2023!

Publications & Preprints [Google Scholar] [Semantic Scholar] [DBLP]

arXiv

HarmonyDream: Task Harmonization Inside World Models

Haoyu Ma*, Jialong Wu*, Ningya Feng, Chenjun Xiao, Dong Li, Jianye Hao, Jianmin Wang, Mingsheng Long#

arXiv preprint, 2023.

arXiv BibTeX

NeurIPS

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

Jialong Wu*, Haoyu Ma*, Chaoyi Deng, Mingsheng Long#

Conference on Neural Information Processing Systems (NeurIPS), 2023.

arXiv Code Poster Slides Blog BibTeX

ICML

CLIPood: Generalizing CLIP to Out-of-Distributions

Yang Shu*, Xingzhuo Guo*, Jialong Wu, Ximei Wang, Jianmin Wang, Mingsheng Long#

International Conference on Machine Learning (ICML), 2023.

arXiv Code BibTeX

NeurIPS

Supported Policy Optimization for Offline Reinforcement Learning

Jialong Wu, Haixu Wu, Zihan Qiu, Jianmin Wang, Mingsheng Long#

Conference on Neural Information Processing Systems (NeurIPS), 2022.

arXiv Code Poster Slides BibTeX

CoRL

Out-of-Dynamics Imitation Learning from Multimodal Demonstrations

Yiwen Qiu, Jialong Wu, Zhangjie Cao, Mingsheng Long#

Conference on Robot Learning (CoRL), 2022.

arXiv Code BibTeX

ICML

Flowformer: Linearizing Transformers with Conservation Flows

Haixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long#

International Conference on Machine Learning (ICML), 2022.

arXiv Code BibTeX

* Equal Contribution, # Corresponding Author

Selected Projects [GitHub]

Awesome Multi-task Learning
A curated list of datasets, codebases, and papers on Multi-Task Learning (MTL), from a Machine Learning perspective.

Education

Ph.D. in Software Engineering, 2022-2027 (expected)
School of Software, Tsinghua University
Bachelor in Software Engineering, 2018-2022
School of Software, Tsinghua University
GPA: 3.98/4.0, Rank: 1/89
Bachelor in Pure and Applied Mathematics (Second Degree), 2019-2022
Department of Mathematical Sciences, Tsinghua University
GPA: 3.75/4.0

Honors & Awards

NeurIPS 2023 Top Reviewer [Link]
Future Researcher Scholarship of Tsinghua (清华大学未来学者奖学金), 2022
Outstanding Graduates of Tsinghua (清华大学优秀毕业生, Top 2%), 2022
Outstanding Graduates of Beijing (北京市优秀毕业生, Top 5%), 2022
National Scholarship (国家奖学金, Top 1%), 2020
Comprehensive Excellence Award of Tsinghua (清华大学综合优秀奖), 2019, 2021
34th National Olympiad in Informatics (NOI), Silver Medal (81st Place), 2017

Academic Services

Conference Reviewer | PC Member

International Conference on Learning Representations (ICLR) 2024
Conference on Neural Information Processing Systems (NeurIPS) 2023
International Conference on Machine Learning (ICML) 2022-2023

Teaching Assistant

Deep Learning, Fall 2023. Instructor: Prof. Mingsheng Long
Introduction to Algorithms, Spring 2023. Instructor: Prof. Bin Wang
Machine Learning, Fall 2022. Instructor: Prof. Mingsheng Long
Introduction to Artificial Intelligence, Spring 2021-2022. Instructor: Prof. Mingsheng Long