NEXT CHAPTER
Monash University
Incoming PhD
Zhilin (Julian)
Fan.
Making AI a little
more human.
I explore how AI can help people learn,
make sense of things, and make better decisions.
A curious mind, in its natural habitat.
01 / A BIT ABOUT ME
2023 — 2026
Beijing Normal University
M.Sc. · Educational Technology
2019 — 2023Nanjing University of
Nanjing University of
Information Science & Technology
B.E. · Computer Science & Technology
Hi, I’m Julian — an AI in Education researcher interested in the space where people, learning, and intelligent systems meet.
I’m an incoming PhD student at the Centre for Learning Analytics at Monash (CoLAM), supervised by Dr. Mladen Rakovic, with co-supervision from Dr. Guanliang Chen and Dr. Yi-Shan Tsai.
Previously, I completed my M.Sc. in Educational Technology at Beijing Normal University, advised by Prof. Yu Lu and co-advised by Prof. Penghe Chen. My work brings together explainable dialogue systems, LLMs, and user studies to support teachers’ decision-making.
News
- NEW
🎓 Awarded the Monash University–China Scholarship Council (CSC) Joint Scholarship for my PhD at Monash University.
🎉 Our two papers: “Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis” and “Multidisciplinary Theory Empowered LLM Multi-agent System for Student Problem Behavior Diagnosis” accepted at AIED 2026.
📄 “KnowSTU: Diagnosing Students’ Problem Behaviors Using Fine-Tuned LLM and RAG” published in IEEE Transactions on Learning Technologies.
✨ “Why Did the AI Suggest That? Designing an Explainable Educational Counseling System” accepted as a full paper at AIED 2025.
💬 “PBChat: Enhance Student’s Problem Behavior Diagnosis with Large Language Model” accepted as a full paper at AIED 2024.
02 / RESEARCH INTERESTS
01
AIED
Supporting teachers and learners with educational dialogue systems and thoughtful pedagogical agents.
02
HCI
Understanding how people interact with AI through human-centered design, experiments, and user studies.
03
Trustworthy AI
Investigating how explanations and evidence shape teachers’ trust in AI-assisted decision-making.
04
Interpretability
Understanding the internal mechanisms of large language models — how representations and computations give rise to their behavior.
03 / PUBLICATIONS
04 / LET’S CONNECT
Interested in AIED, human–AI interaction, or explainable AI?
I’d love to exchange ideas.