About Us

Following the recent development of artificial intelligence (AI) technology, there have been growing research interests and opportunities in applying AI to enhance data visualizations and enrich the way people engage with data.

We, the AI4VIS research team in HKUST VisLab, are exploring AI-powered techniques for modelling, authoring, analysing, and interacting with data visualizations. In vision of formalizing visualizations as an emerging data format, we apply advanced AI techniques to visualizations. We have diverse research interests such as visualization recommendation, information extraction from visualizations and automated layouting.


  • Check our latest survey on AI4VIS (to appear in TVCG) to learn more about the emerging field!
  • Two papers on visualization recommendation were accepted on IEEE VIS!
  • Two papers of on AI for color design in vis were published in TVCG. Stay tuned for the VIS’21 presentation of InfoColorizer.
  • One paper on assessing chart aesthetics was accepted in CHI.
  • Two papers were accepted in VIS.
  • Three papers were accepted in VIS.
  • Publications


    MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation

    KG4Vis: A Knowledge Graph-Based Approach for Visualization Recommendation

    InfoColorizer: Interactive Recommendation of Color Palettes for Infographics

    Linping Yuan, Ziqi Zhou, Jian Zhao, Yiqiu Guo, Fan Du, Huamin Qu


    MobileVisFixer: Tailoring Web Visualizations for Mobile Phones Leveraging an Explainable Reinforcement Learning Framework


    LassoNet: Deep Lasso-Selection of 3D Point Clouds

    Zhutian Chen, Wei Zeng, Zhiguang Yang, Lingyun Yu, Chi-Wing Fu, Huamin Qu

    Towards Automated Infographic Design: Deep Learning-based Auto-Generation of Extensible Timeline


    Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach

    Hammad Haleem, Yong Wang, Abishek Puri, Sahil Wadhwa, Huamin Qu

    Current Members