I am currently a Ph.D. student at the Department of Computer Science and Engineering of Shanghai Jiao Tong University (SJTU), advised by Prof. Dacheng Tao and Prof. Ya Zhang. I received my bachelor’s degree from Shanghai Jiao Tong University in June 2022, during which I worked as a research assistant at ThinkLab under the guidance of Prof. Junchi Yan.

I am currently seeking online internship opportunities and am also open to potential collaborations. If you are interested, please feel free to contact me via email or WeChat (id: Chitande).

🔎 Research

My current research interests focus on two key areas:

  • Computer Vision: autonomous driving, embodied AI
  • Machine Learning: reinforcement learning, continuous learning

🔥 News

  • [Apr. 2025] One paper is accepted to J-STSP (IEEE Journal of Selected Topics in Signal Processing).
  • [Feb. 2025] One paper is accepted to SCIS (CCF-A Journal).
  • [Feb. 2025] One paper is accepted to ICLR 2025 (Oral).
  • [Jan. 2025] I was selected as Young Talent Support Project Doctoral Special Program (青年人才托举工程博士生专项计划).
  • [Dec. 2024] One paper is accepted to AAMAS 2025.
  • [Dec. 2024] I went to NTU for one year of research.
  • [Nov. 2024] I received the national scholarships of 2024.
  • [Sep. 2024] One paper is accepted to NeurIPS 2024.
  • [May. 2024] One paper is accepted to TPAMI.
  • [May. 2024] Three papers are accepted to ICML 2024.
  • [Jan. 2024] Our paper about multi-agent communication is accepted to ICLR 2024.
  • [Jun. 2022] Our paper about autonomouse driving is accepted to ECCV 2022.

📝 Publications (Full List)

2025
  • Reconstruct the Pruned Model without Any Retraining
    Pingjie Wang, Ziqing Fan, Shengchao Hu, Zhe Chen, Yanfeng Wang, Yu Wang,
    IEEE Journal of Selected Topics in Signal Processing (J-STSP), SCI 2, 2025
    [Paper][Code]
  • Graph decision transformer for offline reinforcement learning
    Shengchao Hu, Li Shen, Ya Zhang, Dacheng Tao,
    Science China Information Sciences (SCIS), CCF-A, 2025
    [Paper][Code]
  • Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection
    Ziqing Fan, Siyuan Du, Shengchao Hu, Pingjie Wang, Li Shen, Ya Zhang, Dacheng Tao, Yanfeng Wang,
    International Conference on Learning Representations (ICLR), non-CCF, Oral, 2025
    [Paper][Code]
  • Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization
    Shengchao Hu, Wanru Zhao, Weixiong Lin, Li Shen, Ya Zhang, Dacheng Tao,
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS), CCF-B, 2025
    [Paper][Code]
2024
  • On Transforming Reinforcement Learning by Transformer: The Development Trajectory
    Shengchao Hu, Li Shen, Ya Zhang, Yixin Chen, Dacheng Tao,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), CCF-A, 2024
    [Paper][Code]
  • Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
    Yang Dai, Oubo Ma, Longfei Zhang, Xingxing Liang, Shengchao Hu, Mengzhu Wang, Shouling Ji, Jincai Huang, Li Shen,
    Neural Information Processing Systems (NeurIPS), CCF-A, 2024
    [Paper][Code]
  • Locally Estimated Global Perturbations is Better than Local Perturbations for Federated Sharpness-aware Minimization
    Ziqing Fan, Shengchao Hu, Jiangchao Yao, Gang Niu, Ya Zhang, Masashi Sugiyama, Yanfeng Wang,
    International Conference on Machine Learning (ICML), CCF-A, Spotlight, 2024
    [Paper][Code]
  • HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
    Shengchao Hu, Ziqing Fan, Li Shen, Ya Zhang, Yanfeng Wang, Dacheng Tao,
    International Conference on Machine Learning (ICML), CCF-A, 2024
    [Paper][Code]
  • Q-value Regularized Transformer for Offline Reinforcement Learning
    Shengchao Hu, Ziqing Fan, Chaoqin Huang, Li Shen, Ya Zhang, Yanfeng Wang, Dacheng Tao,
    International Conference on Machine Learning (ICML), CCF-A, 2024
    [Paper][Code]
  • Learning Multi-Agent Communication from Graph Modeling Perspective
    Shengchao Hu, Li Shen, Ya Zhang, Dacheng Tao,
    International Conference on Learning Representations (ICLR), non-CCF, 2024
    [Paper][Code]
2022
  • St-p3: End-to-end vision-based autonomous driving via spatial-temporal feature learning
    Shengchao Hu, Li Chen, Penghao Wu, Hongyang Li, Junchi Yan, Dacheng Tao,
    European Conference on Computer Vision (ECCV), CCF-B, 2022
    [Paper][Code]

🎖 Honors and Awards

  • 2025.01 Young Talent Support Project Doctoral Special Program (青年人才托举工程博士生专项计划)
  • 2024.09 National Scholarships
  • 2020-2021 Shanghai Jiao Tong University Category C Scholarship
  • 2018-2022 Zhiyuan Honor Scholarship of Shanghai Jiao Tong University
  • 2020.12 Interdisciplinary Contest In Modeling, Honorable Mention
  • 2020.12 National Undergraduate Mathematical Modeling Contest in Shanghai Division, Second Prize
  • 2019.11 Non-Mathematics Category of Shanghai College Student Mathematics Competition (Higher Education Society Cup), First Prize

📖 Educations

2022.09 - Now
PhD, Computer Science, Shanghai Jiao Tong University
2024.11 - 2025.11
PhD Visiting Student, Computer Science, Nanyang Technological University (NTU)
2018.09 - 2022.06
Bachelor, Computer Science, Shanghai Jiao Tong University

🎡 Service

💻 Internships

GenAI Lab, Nanyang Technological University
Research Assistant, 2024-2025
Mentor: Dacheng Tao
Smart Medical Research, Shanghai AI Lab
Research Assistant, 2023-2024
Mentor: Ya Zhang
OpenDriveLab, SenseTime
Research Intern, 2021-2022
Topics: Autonomous Driving
Mentor: Hongyang Li
ThinkLab, Shanghai Jiao Tong University
Research Assistant, 2019-2022
Mentor: Junchi Yan