Shaobo Wang

Mail: gszfwsb@gmail.com

Tel: (+86) 15000937315

City: Shanghai, 200240

I am now a second-year master’s student at CSE Department from Shanghai Jiao Tong University (rank 2/81, GPA 3.98/4.0), supervised by Prof. Junchi Yan. Previously, I got my B.Eng. degree from HIT in 2022 (rank 1/181, GPA 3.96/4.0), and enjoyed wonderful time during my internship at Shanghai Jiao Tong University and Tsinghua University.

My research focuses on theoretical machine learning, computer vision, and natural language processing. I am dedicated to uncovering the fundamental aspects of deep neural networks (DNNs) and applying these insights to real-world applications through a theoretical perspective.

👋 I am open to collaborate and engage in discussions related to my field. Should you have any inquiries or are interested in collaborating, please do not hesitate to contact me via email, Wechat, or Twitter (X).

Beyond academia, I’ve been playing the piano for over 10 years and had the honor of performing alongside the renowned pianist Lang Lang. My favorite composers are Chopin and Liszt. While my musical roots are in classical music, I have a strong affinity for R&B and Neo-Soul genres. In my teenage years, I won several chess championships in Anhui Province, China, under the mentorship of Grandmaster Chongsheng Zeng and Master Yongjin Zhou. I also like reading detective and historical novels, and solving magic cubes.

Currently, I'm actively seeking research internships, open to both on-site and remote opportunities. Additionally, I am exploring Ph.D. positions for Fall 2025 to further my academic pursuits.

Selected Publications

* denotes the equal contribution.

NeurIPS

Visualizing the emergence of intermediate visual patterns in dnns

Mingjie Li , Shaobo Wang, and Quanshi Zhang

Advances in Neural Information Processing Systems, 2021

Bib PDF

@article{li2021visualizing,
  title = {Visualizing the emergence of intermediate visual patterns in dnns},
  author = {Li, Mingjie and Wang, Shaobo and Zhang, Quanshi},
  journal = {Advances in Neural Information Processing Systems},
  volume = {34},
  pages = {6594--6607},
  year = {2021},
}

arXiv

Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework

Shaobo Wang, Xiangdong Zhang , and Junchi Yan

arXiv preprint arXiv:2311.15993 (arXiv), 2023

Bib PDF

@article{wang2023unified,
  title = {Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework},
  author = {Wang, Shaobo and Zhang, Xiangdong and Yan, Junchi},
  year = {2023},
  eprint = {2311.15993},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  journal = {arXiv preprint arXiv:2311.15993 (arXiv)},
}

arXiv

Trap of Feature Diversity in the Learning of MLPs

Dongrui Liu* , Shaobo Wang*, Jie Ren , and 4 more authors

arXiv preprint arXiv:2112.00980 (arXiv), 2022

Bib PDF

@article{liu2022trap,
  title = {Trap of Feature Diversity in the Learning of MLPs},
  author = {Liu*, Dongrui and Wang*, Shaobo and Ren, Jie and Wang, Kangrui and Yin, Sheng and Deng, Huiqi and Zhang, Quanshi},
  year = {2022},
  eprint = {2112.00980},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  journal = {arXiv preprint arXiv:2112.00980 (arXiv)}
}

arXiv

Think2Drive: Brick by Brick to Build a Model-based RL Agent for Quasi-Realistic Autonomous Driving (in CARLA-v2)

Qifeng Li , Xiaosong Jia , Shaobo Wang, and 1 more author

arXiv preprint arXiv:2402.16720 (arXiv), 2024

Bib PDF

@article{dreamer,
  title = {Think2Drive: Brick by Brick to Build a Model-based RL Agent for Quasi-Realistic Autonomous Driving (in CARLA-v2)},
  author = {Li, Qifeng and Jia, Xiaosong and Wang, Shaobo and Yan, Junchi},
  year = {2024},
  journal = {arXiv preprint arXiv:2402.16720 (arXiv)},
}