Ziqi Liu 刘子琦

Hi! I’m Ziqi Liu 刘子琦

I’m a first-year M.phil student at the UbiquitousX Lab at Hong Kong University of Science and Technology, supervised by Qijia Shao. Prior to HKUST, I got my B.Eng degree at Tsinghua University, supervised by Yuntao Wang and Haipeng Mi.

My research focuses on the synergy between AI-driven sensing and adaptive intervention. By integrating hardware and software innovations across ubiquitous devices and wearables, I design and develop closed-loop systems that tightly couple the implicit, continuous sensing of behavioral and physiological states with just-in-time, context-aware interventions.

I have gained valuable research experience in multiple esteemed labs, inlucding the Future Lab and Pervasive HCI Group at Tsinghua University.

Research Interests

Pervasive Sensing

Acquiring behavioral and physiological signals through two complementary approaches:

Everyday devices — repurposing built-in sensors to capture rich signals during natural interaction.
Custom wearables — designing devices that unobtrusively collect modalities beyond commodity hardware.

Personalized State Inference

Transforming sensor data into user- and context-aware user-state estimates::

Interaction intent — recognizing implicit goals and attention patterns for interaction applications.
Health & cognitive states — inferring physiological and psychological indicators for continuous health monitoring.

Just-in-Time Intervention

Moving beyond always-on feedback by identifying, for each user and context, the precise moments when intervention is most beneficial. The system continuously evaluates situational cues and inferred user states to identify critical windows of need, then delivers personalized, context-sensitive support in both interaction and health domains.

News

Dec 08, 2025	Our project “Hand Motion Prediction for Adaptive Smartphone UI with Zero-permission Sensors” has won the Best Award for UROP at HKUST! Congrulations to Ziyi and the team! 🎉
Nov 08, 2025	Spent a wonderful week at Mobicom 2025 in Hong Kong as a student volunteer! 📸
Aug 15, 2025	Arrived in Hong Kong and started my M.Phil at HKUST! 🌊
Jun 22, 2025	I have successfully graduated from Tsinghua University with a Bachelor’s degree in Engineering！🎓
Jun 05, 2025	I passed my undergraduate thesis defense！🗣️
Feb 23, 2025	Our paper “AroMR: Decentralizing Olfactory Displays into the Environment for Olfactory-Augmented Experiences in Mixed Reality” has been accepted to CHI 2025 Late Breaking Work! 🎉
Jan 17, 2025	Our paper “Enhancing Smartphone Eye Tracking with Cursor-Based Interactive Implicit Calibration” has been accepted to CHI 2025! 🎉
Oct 11, 2024	Established a new wedsite for myself! 🥳

Publications

Enhancing Smartphone Eye Tracking with Cursor-Based Interactive Implicit Calibration

Chang Liu, Xiangyang Wang, Chun Yu, and 5 more authors

In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, , 2025

Abs DOI

The limited accuracy of eye-tracking on smartphones restricts its use. Existing RGB-camera-based eye-tracking relies on extensive datasets, which could be enhanced by continuous fine-tuning using calibration data implicitly collected from the interaction. In this context, we propose COMETIC (Cursor Operation Mediated Eye-Tracking Implicit Calibration), which introduces a cursor-based interaction and utilizes the inherent correlation between cursor and eye movement. By filtering valid cursor coordinates as proxies for the ground truth of gaze and fine-tuning the eye-tracking model with corresponding images, COMETIC enhances accuracy during the interaction. Both filtering and fine-tuning use pre-trained models and could be facilitated using personalized, dynamically updated data. Results show COMETIC achieves an average eye-tracking error of 278.3 px (1.60 cm, 2.29°), representing a 27.2% improvement compared to that without fine-tuning. We found that filtering cursor points whose actual distance to gaze is 150.0 px (0.86 cm) yields the best eye-tracking results.
AroMR: Decentralizing Olfactory Displays into the Environment for Olfactory-Augmented Experiences in Mixed Reality

Yibo Wang, Ziqi Liu, Jiao Xue, and 1 more author

In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, , 2025

Abs DOI

Smell, as a vital sensory modality, has the potential to significantly enhance user experience in immersive environments; however, its application in mixed reality (MR) remains underexplored. Current olfactory displays (ODs) are typically fixed to head-mounted displays (HMDs) as active olfactory inputs, limiting interaction and failing to capture the dynamic nature of human olfactory perception. To better integrate olfactory experiences into MR, we propose a "field-centric" strategy that decentralizes ODs into the physical environment as passive outputs. We further introduce AroMR, a proof-of-concept system that employs this strategy to incorporate olfactory feedback into MR experiences. A user study involving eight participants interacting with AroMR across three pre-designed scenarios revealed the potential of our approach to enhance engagement and create more immersive MR experiences. Based on these findings, we propose a conceptual design space to guide future research on integrating olfactory elements into MR.