Bryan Wang

prof_pic.jpg

📧 bryanw@dgp.toronto.edu

🎓 Google Scholar

🐩 Twitter

Research Interests:

  • Human-AI Interaction
  • Creativity Support
  • Generative AI

I am a Computer Science Ph.D. student at the University of Toronto, working with Prof. Tovi Grossman at the Dynamic Graphics Project Lab.

My research area focuses on Human-AI Interaction.I apply my expertise in human-computer interaction and machine learning to develop interactive AI systems and study their implications for users. These systems leverage state-of-the-art AI to enhance human capabilities in creating and consuming digital content, including video, audio, images, and GUIs. Recently, my exploration has centered on leveraging multimodal generative AI models to enable novel interaction paradigms.

I graduated with a Bachelor’s degree in computer science from National Taiwan University. I have also spent wonderful time as a research intern at Google, Adobe, and Meta.

I run pro bono office hours for HCI. If you’re a junior student seeking advice or guidance in HCI research, I’m here to help.

🌟 I’m on the job market for full-time industry research positions starting in 2024. Please reach out if you are aware of any suitable openings!

News

Dec 14, 2023 Two papers accepted to IUI ‘24! One paper from my Meta internship on LLM-Augmented Video Editing. The other, led by MSc student Stephen Brade from U of T, on AI-assisted synthesizer sound retrieval and exploration. More details to come.
Oct 26, 2023 One paper on AI-assisted synthesizer sound retrieval and exploration was accepted to the Machine Learning for Creativity and Design Workshop at NeurIPS ‘23. Great Work led by MSc student Stephen Brade!
Oct 6, 2023 One paper on LLM agent accepted to EMNLP ‘23 Findings Track. Congrats to the co-authors at Google! Details to come.
Aug 15, 2023 Thesis proposal “Democratizing Content Creation and Consumption through Human-AI Co-Pilot Systems” is accepted to UIST 2023 Doctoral Symposium. Looking forward to the event!
Aug 3, 2023 Promptify is accepted to UIST 2023. Great work led by mentee Stephen Brade!
Aug 1, 2023 Co-chairing the Student Innovation Competition at UIST 2023 on LLM systems. Submit your idea!
Jul 28, 2023 The ICML AI and HCI workshop was a great success. A big shout out to all co-organizers, speakers, reviewers, and authors!
Jun 2, 2023 Invited talk at UW HCI Seminar and Huawei Canada.
May 15, 2023 Started internship at Meta Reality Labs — Research with Raj Sodhi in Hrvoje Benko’s group.
Apr 12, 2023 Invited talk at Meta Reality Lab’s HCI seminar.
Mar 31, 2023 Excited to serve on the program committee of UIST 2023.
Jan 13, 2023 Three papers accepted to CHI 2023. Congrats to all co-authors!
Jan 12, 2023 Gave a talk at Takeo Igarashi’s Lab at Univeristy of Tokyo.
Oct 30, 2022 Presented paper Record Once, Post Everywhere: Automatic Shortening of Audio Stories for Social Media at UIST 2022 in Bend, Oregon.
Oct 27, 2022 Project page for Record Once, Post Everywhere (ROPE) is up!
May 31, 2022 Started an in-person summer internship with Yang Li at Google Research in Mountain View, CA.
May 9, 2022 Wrapped up a remote internship with Gautham J. Mysore and Zeyu Jin at Adobe Research.

Representative Publications

  1. LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing
    Bryan Wang, Yuliang Li, Zhaoyang Lv, Haijun Xia, Yan Xu, and Raj Sodhi
    In Proceedings of ACM Conference on Intelligent User Interfaces (IUI) 2024
  2. Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models
    Stephen Brade, Bryan Wang, Mauricio Sousa, Sageev Oore, and Tovi Grossman
    In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST) 2023
  3. Enabling Conversational Interaction with Mobile UI using Large Language Models
    Bryan Wang, Gang Li, and Yang Li
    In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI) 2023
  4. Record Once, Post Everywhere: Automatic Shortening of Audio Stories for Social Media
    Bryan Wang, Zeyu Jin, and Gautham Mysore
    In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST), 2022
  5. Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning
    Bryan Wang, Gang Li, Xin Zhou, Zhourong Chen, Tovi Grossman, and Yang Li
    In Proceedings of the 34th Annual ACM Symposium on User Interface Software and Technology (UIST), 2021
  6. Soloist: Generating Mixed-Initiative Tutorials from Existing Guitar Instructional Videos Through Audio Processing
    Bryan Wang, Meng Yu Yang, and Tovi Grossman
    In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI), 2021