PhD Candidate in Human–AI Collaboration
I design intelligent systems that strengthen human decision-making — combining multimodal behavioral analysis with cognitive state modeling to make AI collaboration trustworthy and useful in practice.
Advised by Professor Kazuo Hiekata
Recent
Built and presented the first LLM-powered paper network at a conference — CAS 2026.
An interactive 3D semantic map (51 papers · 125 links; SPECTER embeddings + PCA) that lets every author see where their work sits. A team effort.
Paper accepted at TE2026 — Behavioral Adaptation in Human-AI Decision Making.
Paper accepted at IJHCI — Calibrated Intervention in Human-AI Collaborative Forecasting.
Currently working on
Modelling human behaviour in high-risk decision workflows using eye-tracking data — the empirical arm of the PhD, spanning six papers across IJHCI, TOCHI, TE, and INCOSE CAS.
Read more →Building
End-to-end workflow with OCR, LLM validation, and a React + Python stack.
A decentralised reading community in Tokyo — 40+ sessions, 600+ participants across disciplines.
LLM-powered real estate analysis platform: data, retrieval, and product design.
Writing
Zhang, Y., Hiekata, K., & Nakashima, T.
Published · International Journal of Human-Computer Interaction
Process-Informed Crowd Selection: Recovering Collective Prediction Gains Under AI Anchoring Through Eye-Tracking-Based Evidence Engagement Estimation
Y. Zhang, K. Hiekata, T. Nakashima, Q. Shao
Preprint · Under Review · ACM Transactions on Computer-Human Interaction (TOCHI)
Behavioral Adaptation in Human-AI Decision Making: A Longitudinal Study Using Synchronized Eye and Mouse Tracking
Y. Zhang, K. Hiekata, T. Nakashima, Q. Shao
Accepted · 33rd Int. Conf. Transdisciplinary Engineering (TE2026)
Y. Zhang, K. Hiekata, T. Nakashima, Q. Shao
Accepted · 32nd Int. Conf. Transdisciplinary Engineering (TE2025)
Get in touch
