Kaiqiao Han (Kai)

My name is Kaiqiao Han(Kai). I'm pursuing my Ph.D. at UCLA, advised by Prof. Yizhou Sun. My research interests include large language models, agent systems, and AI for Science (Biology and Healthcare). I also receive guidance from Prof. Carl Yang at Emory University. Previously, I received my CS bachelor's degree at Zhejiang University, working on a large language model and graph, advised by Prof. Yang Yang.

Email /  Google Scholar  

Research Interest

My research interests span three primary areas:

• Large Language Models (LLMs).
  I study the reasoning and adaptation capabilities of LLMs, including graph-enhanced reasoning models such as GraphLLM and the use of GNNs as effective structural adapters for LLMs (Graph-Adapter). I also examine model robustness and abstraction abilities through tasks like the Concept-Reversed Winograd Schema Challenge (CR-WSC).


• Agent Systems.
  My work explores the RAG systems in conversational agents, controllable decision-making, and mechanisms that enable multi-step planning and tool-use.


• AI for Science (Biology & Healthcare).
  I develop machine learning methods for dynamic scientific and biomedical systems, including neural ODE–based approaches for brain signal analysis (BrainODE), models for longitudinal disease progression forecasting, generative modeling for physiological time-series such as ECG and EGG, and data-driven frameworks for simulating complex physical or biological processes.

Education

Work Experience

Miscellanea

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.