Kaylee Yaxuan Li
Ph.D. Candidate in Computer Science and Engineering
University of Michigan
I am a Ph.D. candidate in Computer Science and Engineering at the University of Michigan, advised by Alanson P. Sample and Kang G. Shin.
My research develops wearable and ubiquitous AI systems that interpret human activity and context from multimodal data. I focus on sensing and efficient semantic representations of daily life, long-horizon memory architectures for scalable reasoning, and proactive assistance on resource-constrained wearable and mobile platforms. My work seeks to transform everyday human experience into persistent, actionable intelligence that augments human perception, memory, reasoning, and decision-making, with broader implications for physical AI and human–agent interaction.
Selected Publications
2026
-
GOHi: Goal-Oriented Highlight Extraction for Long-Form Egocentric Video
ACM IMWUT, 2026
-
-
AutoCLC: Towards Automated Assessment and Feedback on Closed-Loop Communication in Team-based Healthcare Simulation Training
ACM Transactions on Computing for Healthcare, vol. 7, no. 1, 2026
2025
-
Leveraging AI for Automated Evaluation of Closed-Loop Communication in VR-based Acute Care Team Training
International Conference on Computer-Supported Collaborative Learning (CSCL), 2025
-
2024
-
ECG Signal Construction From Heart Sounds via Single Node, Surface Acoustic Sensing
IEEE EMBC, 2024
2022
2021
-
-
Towards Context-aware Automatic Haptic Effect Generation for Home Theatre Environments
ACM VRST, 2021
-
-
Context-aware Automatic Haptic Effect Generation Algorithm for Improved Content Viewing Experiences
IEEE World Haptics Conference (WHC), Work-in-Progress, 2021
2019
-
Safe Navigation of Quadrotors with Jerk Limited Trajectory
Frontiers of Information Technology & Electronic Engineering, vol. 20, no. 1, 2019