About

I am an Associate Professor at York University, Canada, and Director of the Intelligent Visualization Lab. Before joining York, I was a Postdoctoral Fellow at Stanford University with Maneesh Agrawala and earned my Ph.D. in Computer Science from the University of British Columbia under the supervision of Giuseppe Carenini.

My research aims to democratize data science and analytics by integrating information visualization, natural language processing (NLP), and human–computer interaction (HCI) to make data exploration more accessible, inclusive, and responsible. Our recent work advances multimodal large language models (LLMs) and agentic frameworks that connect language, vision, and interaction—producing influential and widely adopted benchmarks and models for data visualization and analytics.

My research has appeared in nearly 100 papers across leading venues in NLP (ACL, EMNLP, COLM), visualization (IEEE VIS, EuroVis), and HCI (CHI, UIST), earning multiple Best Paper and Honorable Mention awards, as well as the Dean’s Award for Research Excellence. I serve as an Area Chair for the ACL Rolling Review and on the IEEE VIS program committee, and have co-organized several tutorials and panels at major international conferences, including IEEE VIS (2022–2025) and EMNLP 2023.

My research is supported by the Natural Sciences and Engineering Research Council of Canada (NSERC), the Canada Foundation for Innovation (CFI), and the National Research Council Canada (NRC), among others.

Intelligent Visualization Lab icon
Please consult my research Lab's website for our active projects and latest publications.

Research Interests

Multimodal AI for Visualization Understanding and Generation

  • Chart comprehension, visual reasoning, and data narratives
  • Multimodal and vision–language models for visualization (VLMs / MLLMs)
  • Text–to–visualization and visualization–to–text generation

Human-Centered & Responsible AI for Data Visualization

  • Accessible and inclusive visualization for diverse users
  • Bias, fairness, and deception in visual communication
  • Trust, interpretability, and robustness of AI systems

Agentic & Interactive AI for Data Science Workflows

  • Multimodal agents for data exploration and decision support
  • Natural-language interaction with data and visualizations
  • Human–AI alignment and co-creative analytic interfaces

Visual & Interactive Document Analytics

  • Visual text analytics for large document collections
  • Interactive systems for reading and interpreting text-rich documents