Hello! I am Liwenhan Xie (Shelly). I am a Ph.D. candidate at The Hong Kong University of Science and Technology, advised by Prof. Huamin Qu.

With a background in information visualization and human-computer interaction, I study the design of interactive systems that prioritize human agency in creative tasks, focusing on its nuanced, exploratory, and unquantifiable aspect. My recent work explores co-creating expressive visualizations with foundation models.

🦄 
Job Hunting: Postdoc/Researcher (2026 Spring)
Let's chat about human-AI co-creation & animated visual storytelling!
Latest News  
⊙ I defended my Ph.D. dissertation!
⊙ I received 5 (out of 6) special recognition for outstanding reviews at CHI’26.
⊙ Awarded the HKUST Redbird Scholarship.
⊙ DataWink was accepted to IEEE VIS. See you in Vienna!
⊙ Excited to intern at Adobe exploring controllable animation generation!
⊙ I passed my Ph.D. thesis proposal!
Liwenhan Xie

Projects   Overview

DataSway
Ongoing

DataSway brings metaphorical visualizations to life, translating a creator’s high-level animation intent into vivid motion that can be tweaked with low-level clips.

Website Video Demo
DataWink
VIS'25

DataWink supports creative reuse, using a VLM-powered pipeline to extract a template from a vis example and allows dynamic adaptation in low-level features.

Website Video Code
WaitGPT
UIST'24

WaitGPT translates complex LLM-generated code into a live, interactive diagram, giving data analysts the power to proactively steer the agent’s analysis.

Website Video
Wakey-Wakey
UIST'23

Wakey-Wakey applies the motion pattern of a sticker into kinetic typography, giving creators a powerful new path while allowing tweaking with intermediate features.

Website Talk Code
Emordle
TVCG'23

Emordle generates word clouds that express nuanced emotion, moving beyond simple categories to allow for subtle and personal refinement with dedicated parameters.

Website Talk Demo

My Research    Publications   Projects

Designing Interactive Scaffolds for Steering VLM-Powered Visualization Generation

Liwenhan Xie
Ph.D. Dissertation
About Thesis Slides (.pdf) Slides (.pptx) Ack

DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination

Liwenhan Xie, Jiayi Zhou, Anyi Rao, Huamin Qu, Xinhuan Shu
ArXiv 2025 ArXiv Preprint
arXiv Website Video Corpus Demo

DataWink: Reusing and Adapting SVG-based Visualization Examples with Large Multimodal Models

Liwenhan Xie, Yanna Lin, Can Liu, Huamin Qu, Xinhuan Shu
VIS 2025 IEEE Transactions on Visualization and Computer Graphics -Early Access
DOI arXiv Website Video Slides (.pptx)

WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization

Liwenhan Xie, Chengbo Zheng, Haijun Xia, Huamin Qu, Chen Zhu-Tian
UIST 2024 ACM Symposium on User Interface Software and Technology in Pittsburgh, USA
DOI arXiv Website Preview Video Slides (.pptx)

Wakey-Wakey: Animate Text by Mimicking Characters in a GIF

Liwenhan Xie*, Zhaoyu Zhou*, Kerun Yu, Yun Wang, Huamin Qu, Siming Chen
UIST 2023 ACM Symposium on User Interface Software and Technology in San Francisco, USA
DOI arXiv Website Preview Talk Code Slides (.pptx)

Creating Emordle: Animating Word Cloud for Emotion Expression

Liwenhan Xie, Xinhuan Shu, Jeon Cheol Su, Yun Wang, Siming Chen, Huamin Qu
TVCG 2023 IEEE Transactions on Visualization and Computer Graphics
DOI arXiv Website Preview Talk Corpus Demo Slides (.pptx)