Xingyu Bruce Liu

刘星宇

prof_pic_2.jpg

📧 xingyuliu@ucla.edu

🐦 @liu_xingyu

Semantic Scholar

Google Scholar

Curriculum vitae

Greetings! I’m Bruce, a Ph.D. student at the UCLA HCI lab advised by Professor Xiang ‘Anthony’ Chen.

I focus on HCI+AI research, exploring the future forms of LLMs and AI agents beyond a turn-based chatbot.

Examples include: agents that can proactively engage in group conversations by modeling human-like motivations (Inner Thoughts), multimodal agents that stay in sync with real-world context (Human I/O), real-time AI that dynamically generates visuals to complement speech (Visual Captions), and a document interface that lets anyone author generative videos by simply writing (Doki).

My work has been recognized and supported by an Amazon Ph.D. Fellowship, an ACM UIST Best Paper Award 🏆, two ACM CHI Best Paper Honorable Mentions 🏅. I also did research internships at Adobe Research, Google, Meta Reality Labs and Snap Research.

news

Sep 29, 2025 I’ll be at UIST 2025 in Busan, Korea! 🇰🇷
Apr 15, 2025 Attending CHI 2025 in Yokohama, Japan! 🍣 I’ll be presenting Inner Thoughts and Interacting with Thoughtful AI. If you’re attending CHI 2025, please say hi!
Jan 23, 2025 Inner Thoughts has been accepted to CHI 2025! 💭
Aug 15, 2024 Serving on the Program Committee and as the Video Presentation Chair for CHI 2025. 🎏
Jun 25, 2024 Starting an internship at Meta Reality Labs Research!

selected publications

  1. A Text-Native Interface for Generative Video Authoring
    Xingyu Bruce Liu, Mira Dontcheva, and Dingzeyu Li
    In Submission (Under Review)
  2. Thought as a Substrate in Human-AI Interaction
    Xingyu Bruce Liu
    In UIST 2025 Doctoral Symposium (UIST ’25)
    PDF DOI
  3. Proactive Conversational Agents with Inner Thoughts
    Xingyu Bruce Liu, Shitao Fang, Weiyan Shi, Chien-Sheng Wu, Takeo Igarashi, and Xiang Anthony Chen
    In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25)
    PDF arXiv Code Website DOI
  4. Human I/O: Towards a Unified Approach to Detecting Situational Impairments
    Xingyu Bruce Liu, Jiaohao Nick Li, David Kim, Xiang Anthony Chen, and Ruofei Du
    In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI ’24)
    🏅 Best Paper Honorable Mention
    PDF Blog Website DOI
  5. Visual Captions: Augmenting Verbal Communication with On-the-fly Visuals
    Xingyu Bruce Liu, Vladimir Kirilyuk, Xiuxiu Yuan, Alex Olwal, Peggy Chi, Xiang Anthony Chen, and Ruofei Du
    In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23)
    PDF Blog CodeVideo Website DOI
  6. CrossA11y: Identifying Video Accessibility Issues via Cross-Modal Grounding
    Xingyu Bruce Liu, Ruolin Wang, Dingzeyu Li, Xiang Anthony Chen, and Amy Pavel
    In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST ’22)
    🏆 Best Paper Award
    PDFVideo Website DOI
  7. What Makes Videos Accessible to Blind and Visually Impaired People?
    Xingyu Liu, Patrick Carrington, Xiang Anthony Chen, and Amy Pavel
    In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI ’21)
    PDFVideo DOI