Ding Xia

Ph.D. Student
The University of Tokyo
xia-ding1995 (at) g.ecc.u-tokyo.ac.jp

About Me

I am a Ph.D. student at the Information Science and Technology department of The University of Tokyo, under the supervision of Takeo Igarashi. I study Computer Vision, Human–Computer Interaction, Large Language Models, and Explainable AI.

Research Interests

Computer Vision: Object detection, medical imaging, image alignment, and explainable AI
Human-Computer Interaction: User interface design, user studies and evaluation, creative tools, and brain-computer interfaces
Natural Language Processing: Large language models (LLMs), pre-training and fine-tuning, prompt engineering, document understanding and design, multimodal NLP, and benchmark development

News

[Aug 2025] 🎉 Our paper on automating EHMI action design with LLMs has been accepted to EMNLP 2025 Findings.
[Aug 2025] 🎉 Our paper HealthGenie has been accepted to CIKM 2025 Demo Paper Track.
[June 2025] 🎉 Our paper on document design, in collaboration with CyberAgent AI Lab, has been accepted to ICDAR 2025.
[Feb 2025] 🎉 Our paper on hand-drawing systems for CAD has been accepted to CHI 2025.

Publications

EMNLP

Automating eHMI Action Design with LLMs for Automated Vehicle Communication

Ding Xia, Xinyue Gui, Fan Gao, Dongyuan Li, Mark Colley, Takeo Igarashi

Findings of the Association for Computational Linguistics (EMNLP), 2025.

PDF Code

CIKM

HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Models

Fan Gao, Xinjie Zhao, Ding Xia, Zhongyi Zhou, Rui Yang, Jinghui Lu, Hang Jiang, Chanjun Park, Irene Li

ACM International Conference on Information and Knowledge Management (CIKM), 2025.

PDF Demo

ICDAR

ColorGPT: Leveraging Large Language Models for Multimodal Color Recommendation

Ding Xia, Naoto Inoue, Qianru Qiu, and Kotaro Kikuchi

International Conference on Document Analysis and Recognition (ICDAR), 2025.

PDF Poster

CHI

Draw2Cut: Direct On-Material Annotations for CNC Milling

Xinyue Gui*, Ding Xia*, Wang Gao, Mustafa Doga Dogan, Maria Larsson, Takeo Igarashi (*Co-first authors)

Proceedings of The ACM conference on Human Factors in Computing Systems (CHI), 2025.

PDF Code Project Page Oral

IUI

SpaceEditing: A Latent Space Editing Interface for Integrating Human Knowledge into Deep Neural Networks

Jiafu Wei, Ding Xia, Haoran Xie, Chia-Ming Chang, Chuntao Li, Xi Yang

Proceedings of the 29th International Conference on Intelligent User Interfaces (IUI), 2024.

PDF

ECCV

PairingNet: A Learning-based Pair-searching and-matching Network for Image Fragments

Rixin Zhou, Ding Xia, Yi Zhang, Honglin Pang, Xi Yang, Chuntao Li

European Conference on Computer Vision (ECCV), 2024.

PDF Code Poster

MICCAI

Data-Driven Multi-modal Partial Medical Image Preregistration by Template Space Patch Mapping

Ding Xia, Xi Yang, Oliver van Kaick, Taichi Kin, Takeo Igarashi

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022.

PDF Code Poster

CVPR

Intra: 3D Intracranial Aneurysm Dataset for Deep Learning

Xi Yang, Ding Xia, Taichi Kin, Takeo Igarashi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

PDF Code Oral