Kaiyang Wan

About me: My name is Kaiyang Wan, and I am a PhD student at INSAIT — starting in Jan. 2026, where I am fortunate to be supervised by Dr. Yuxia Wang, an exceptionally supportive and empathetic mentor. I study Natural Language Processing, Large Language Model, and Agents. Before joining INSAIT, I obtained my Bachelor’s degree in Beijing University of Posts and Telecommunications.

Education & Experience:
Beijing University of Posts and Telecommunications – Bachelor of Computer Science – 2020.09-2024.07

MBZUAI – Research Associate under Dr. Xiuying Chen – 2024.09-2025.09

A Stealth Startup in Silicon Valley, America – Research Intern in Hallucination Detection – 2025-2026

Report&Interview:
Report by MIT Tech Review: https://www.mittrchina.com/news/detail/15356

Representative Publications:

A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA – ICLR 2026

2026

Kaiyang Wan, Lang Gao, Honglin Mu, Preslav Nakov, Yuxia Wang, Xiuying Chen
A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA
The Fourteenth International Conference on Learning Representations (ICLR 2026)