Home | Google Scholar ｜Xiaohongshu | Twitter / X

About me and featured research

Blogs

• **Misalignments and RL failure modes in the early stage of superintelligence |**

  2025/07｜lesswrong link

• **Two New Concepts for Frontier AI Systems: Context Engineering'' and Chain of Command''** | 2025/10

Random blog checkpoint here. ⬇️:

Shu’s blog

News

• Misc
• Publications
• Some progress

Services

• Reviewer for Conference: NeurIPS 2024,2025; ICML 2025,2026; ICLR 2025,2026; AISTATS 2025, 2026; ARR (ACL, EMNLP, EACL); AAAI 2026, CVPR 2026, CoLM2026
• Reviewer for Journal: Applied Artificial Intelligence; TALLIP
• Teaching Assistant: KAUST CS 325 Private Data Analysis 2025 fall
• Workshop organize: First Workshop on LLM Persona Modeling, NeurIPS 2025

Talk

• 12.10/2025 EdinburghNLP Who Is Controlling the Game? Opportunities and Challenges in Bidirectional Human–AI Alignment

Visiting and Collaboration

• 2026.02 will join the Stanford Institute for Human-Centered Artificial Intelligence (HAI) as a Visiting Student Researcher.