I am currently a Researcher at Nex-AGI, working on LLM Agent research, with broader interests in MLLMs, LLM Agent, Agent Memory, Agent RL, and Multi-Agent Systems. Previously, I was a Senior Research Scientist of Multimodal Intelligence Team in Microsoft CoreAI , where I worked on OCR, Document Intelligence, RAG and MLLMs research, and led the development of the industry-leading Azure Layout API.

I obtained my Ph.D. degree from the joint Ph.D. program between University of Science and Technology of China (USTC) and Microsoft Research Asia (MSRA) in 2024, under the supervision of Prof. Qiang Huo and Prof. Jun Du. During my Ph.D., I interned at DeepSeek, contributing to DeepSeek OCR, DeepSeek VL2, DeepSeek V3, and DeepSeek R1, and at MSRA, working on Microsoft OneOCR and Document Intelligence. I have published 10+ papers at top international AI journals and conferences, and one of my papers received the Best Paper Award at ICDAR 2021.

If you are seeking any form of academic cooperation, please feel free to email me at kaihu.kh@gmail.com. We are hiring interns! If you’d like to have a coffee chat, please feel free to reach out. I really enjoy connecting with different people! ☕😊✨