About

I study how people can understand, revise, and guide AI systems through interactive explanations. My research combines human-computer interaction, explainable AI, and human behavior modeling to help people shape AI decisions around their knowledge and preferences, with applications in healthcare and transportation.

I am a PhD student at Ubicomp Lab at the National University of Singapore, advised by Prof. Brian Lim. Before joining NUS, I spent two years as a research assistant at COOLA Lab in Southeast University, where I worked with Prof. Yan LYU and Prof. Wanyuan Wang.

Publications

CHI'26
Editable XAI: Toward Bidirectional Human-AI Alignment with Co-Editable Explanations of Interpretable Attributes
H Chen, J Bai, T Fang, B Lim
Project page PDF Code
AAAI'24
i-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance
H Chen, P Sun, Q Song, W Wang, W Wu, W Zhang, G Gao, Y Lyu
PDF Code
AIAHPC'22
Multi-agent Reinforcement Learning for Fleet Management: A Survey
H Chen, Z Li, X Yao
PDF

Research Projects

Editable XRL

CoChoice makes an RL agent’s actions, predictions, and values editable through Markov trees. Corrections guide continued learning, helping people and agents coordinate their roles.

Project page

Trellis

An interactive graph workspace for LLM-assisted sensemaking. People can branch into alternatives, merge insights, and reorganize conversations while controlling the context available to the model.

Project page

TreePINN

Turns fitted decision trees into trainable neural networks. Tree structure and rules initialize the model; a learned Route-State carries earlier decision context into later routing.

Editable XAI

CHI 2026

CoExplain lets people revise explanations through rules on interpretable attributes. A study with 43 participants found improvements in understanding and alignment compared with read-only explanations.

Project page Paper Code

i-Rebalance

AAAI 2024

Personalizes ride-hailing vehicle repositioning using driver preferences, response modeling, and reinforcement learning. A field study with 106 professional drivers informed the design.

Paper Code

Interpretable Medical Decision Support

A visual programming toolkit for customizable diagnostic models. Doctors can express their preferred examination sequences and thresholds in an interpretable model.

RapidMiner extension RuleBuilder

Ear Motion for VR

An ear-motion input system for accessible interaction with VR devices. A study with 15 volunteers found the approach effective and easy to use.

Code

Teaching

National University of Singapore

Service

  • ACM Conference on Human Factors in Computing Systems (CHI) Reviewer · 2027
  • AAAI Conference on Artificial Intelligence (AAAI) Reviewer · 2027
  • ACM Conference on Human Factors in Computing Systems (CHI) Reviewer · 2026
  • IEEE Transactions on Intelligent Transportation Systems Reviewer · 2025