Jiarui Wang

I’m a Ph.D. student in Computer Science at the School of Computer Science, Shanghai Jiao Tong University (SJTU), advised by Prof. Zhouhan Lin in Language Understanding and Machine Intelligence Algorithms (LUMIA) Group. I received my B.S. in Computer Science from SJTU.

My research focuses on machine learning and large language models (LLMs), with particular interests in:

• Next-Generation LLM Architectures — exploring new architectural paradigms that decouple knowledge storage from reasoning to improve knowledge acquisition, reasoning, and generalization.

• Parametric Memory — developing parametric memory modules for LLMs that efficiently acquire, retain, and update knowledge.

I’m always open to discussing research, collaboration, and new ideas. Please feel free to reach out!

🔥 News

• 2026.07 🚀 Intern-S2-Preview-397B released — led the research and development of its memory architecture.
• 2026.07 🚀 MemSFT released — paper, model weights, and code are now open-sourced.
• 2026.07 🚀 Memory Decoder at Scale released.
• 2026.01 🎉 MLP Memory accepted to ICLR 2026
• 2025.10 🚀 MLP Memory released.
• 2025.09 🚀 Memory Decoder released.
• 2025.09 🎉 Memory Decoder accepted to NeurIPS 2025
• 2024.05 🏆 Our Robocup team SRC won Second Place in RoboCup China Open

📚 Publications

• MemSFT: Mitigating Alignment Tax with an External Parametric Memory
  Jiarui Wang*, Xiang Shi*, Jiaqi Cao, Rubin Wei, Xiquan Wang, Hao Sun, Jingzhi Wang, Zhiqi Yang, Qipeng Guo, Bowen Zhou, Zhouhan Lin
  arXiv preprint (2026)
  🔗 arXiv · GitHub · Hugging Face · * Equal Contribution

• Intern-S2-Preview: Scientific Agentic Foundation Model
  Intern-S2-Preview Team, Shanghai AI Laboratory
  Co-author; arXiv preprint (2026)
  🔗 arXiv · GitHub · Hugging Face

• Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
  Rubin Wei, Jiaqi Cao, Jiarui Wang, Junming Zhang, Qipeng Guo, Bowen Zhou, Zhouhan Lin
  arXiv preprint (2026)
  🔗 arXiv · GitHub · Hugging Face

• MLP Memory: A Retriever-Pretrained Memory for Large Language Models
  Rubin Wei*, Jiaqi Cao*, Jiarui Wang, Jushi Kai, Qipeng Guo, Bowen Zhou, Zhouhan Lin
  ICLR 2026
  🔗 arXiv · GitHub · Hugging Face · * Equal Contribution

• Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
  Jiaqi Cao*, Jiarui Wang*, Rubin Wei, Qipeng Guo, Kai Chen, Bowen Zhou, Zhouhan Lin
  NeurIPS 2025
  🔗 arXiv · GitHub · Hugging Face · * Equal Contribution

🎓 Education

• 2025.09–Present, Ph.D. Student, School of Computer Science, Shanghai Jiao Tong University
• 2021.09–2025.06, B.E. in Computer Science, Shanghai Jiao Tong University

💼 Internships

• 2025.08–Present, Shanghai AI Lab, Shanghai, China

🏅 Honors and Awards

• Second Place, RoboCup China Open - Small Size League, 2024
• Third Prize, Prototype System Competition, CCF Chinasoft, 2023
• Provincial First Prize, Senior Group, National Olympiad in Informatics in Provinces (NOIP), 2018