Kevin Pu

40 St George St.

Toronto, ON, M5S 2E4

jpu at dgp dot toronto dot edu

Welcome! I’m a third year PhD student in Computer Science at the University of Toronto. I am advised by Prof. Tovi Grossman at the Dynamic Graphics Group (DGP) lab and Prof. Yan Chen.

My research interests lie in human-computer interaction, artificial intelligence, and their intersection. My past works have focused on aligning AI support with human capabilities to build harmonious mixed-initiative and AI-proactive workflows for automation, programming, and ideation.

Before PhD, I received my MSc. degree from the University of Toronto where I was advised by Prof. Tovi Grossman and Prof. Yan Chen, and B.S. degree with high distinction in Computer Science and Psychology from the University of Michigan, where I had the pleasure to work at the Computational HCI lab with Prof. Nikola Banovic.

news

Apr 25, 2025	Attending CHI 2025 in Yokohama, Japan! I will be presenting two papers on proactive programming tools and interactive research idea development!
Mar 28, 2025	Wrapped up my internship at Meta Reality Labs and submitted to UIST 2025. Fingers crossed!
Jan 16, 2025	Two papers conditionally accepted to CHI 2025 !! See you in Yokohama, Japan!
Oct 28, 2024	Started my internship as a Research Scientist intern at Meta Reality Labs in Toronto!
Oct 13, 2024	Excited to serve as an SV again at UIST 2024 in Pittsburgh! Xiaohang is going to present our collaborative work VizGroup.

selected publications

CHI

Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support

Kevin Pu, Daniel Lazaro, Ian Arawjo, Haijun Xia, Ziang Xiao, Tovi Grossman, and Yan Chen

To appear at CHI, 2025

Bib PDF

@article{Pu2025AssistanceOD,
  title = {Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support},
  author = {Pu, Kevin and Lazaro, Daniel and Arawjo, Ian and Xia, Haijun and Xiao, Ziang and Grossman, Tovi and Chen, Yan},
  journal = {To appear at CHI},
  year = {2025},
  volume = {abs/2502.18658},
  url = {https://api.semanticscholar.org/CorpusID:276617613},
}

CHI

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

Kevin Pu, K. J. Kevin Feng, Tovi Grossman, Tom Hope, Bhavana Dalvi Mishra, Matt Latzke, Jonathan Bragg, Joseph Chee Chang, and Pao Siangliulue

To appear at CHI, 2025

Bib PDF

@article{pu2024ideasynthiterativeresearchidea,
  title = {IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback},
  author = {Pu, Kevin and Feng, K. J. Kevin and Grossman, Tovi and Hope, Tom and Mishra, Bhavana Dalvi and Latzke, Matt and Bragg, Jonathan and Chang, Joseph Chee and Siangliulue, Pao},
  year = {2025},
  eprint = {2410.04025},
  journal = {To appear at CHI},
  archiveprefix = {arXiv},
  primaryclass = {cs.HC},
  url = {https://arxiv.org/abs/2410.04025},
}

UIST
SemanticOn: Specifying Content-Based Semantic Conditions for Web Automation Programs

Kevin Pu, Rainey Fu, Rui Dong, Xinyu Wang, Yan Chen, and Tovi Grossman

In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, Bend, OR, USA, 2022

Abs Bib PDF Video

Data scientists, researchers, and clerks often create web automation programs to perform repetitive yet essential tasks, such as data scraping and data entry. However, existing web automation systems lack mechanisms for defining conditional behaviors where the system can intelligently filter candidate content based on semantic filters (e.g., extract texts based on key ideas or images based on entity relationships). We introduce SemanticOn, a system that enables users to specify, refine, and incorporate visual and textual semantic conditions in web automation programs via two methods: natural language description via prompts or information highlighting. Users can coordinate with SemanticOn to refine the conditions as the program continuously executes or reclaim manual control to repair errors. In a user study, participants completed a series of conditional web automation tasks. They reported that SemanticOn helped them effectively express and refine their semantic intent by utilizing visual and textual conditions.
@inproceedings{10.1145/3526113.3545691, author = {Pu, Kevin and Fu, Rainey and Dong, Rui and Wang, Xinyu and Chen, Yan and Grossman, Tovi}, title = {SemanticOn: Specifying Content-Based Semantic Conditions for Web Automation Programs}, year = {2022}, isbn = {9781450393201}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3526113.3545691}, doi = {10.1145/3526113.3545691}, booktitle = {Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology}, articleno = {63}, numpages = {16}, keywords = {user intent, semantics, Web automation, PBD}, location = {Bend, OR, USA}, series = {UIST '22}, }