Hi! I am an incoming Assistant Professor at Columbia University, Dept of Biomedical Informatics. I focus on applying human-computer interaction (HCI), artificial intelligence (AI) methods for health applications.
I lead the SEA (Sense, Empower, and Augment) Lab. We aim to leverage everyday data and build better human-centered methods, devices, and systems to sense, empower, and augment human health and well-being.
Interests
- Human-Computer Interaction
- Artificial Intelligence
- Healthcare
- Behavior Change Intervention
Education
Postdoc, 2024
Massachusetts Institute of Technology
PhD, 2023
University of Washington
BS, 2018
Tsinghua University
Latest
- Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
- Evaluating the Privacy Valuation of Personal Data on Smartphones
- Harnessing LLMs for Automated Video Content Analysis: An Exploratory Workflow of Short Videos on Depression
- Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults
- Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention
- AdaptiveVoice: Cognitively Adaptive Voice Interface for Driving Assistance
- Can AI Relate: Testing Large Language Model Response for Mental Health Support
- Contextual AI Journaling: Integrating LLM and Time Series Behavioral Sensing Technology to Promote Self-Reflection and Well-being using the MindScape App
- Fast-Forward Reality: Authoring Error-Free Context-Aware Policies with Real-Time Unit Tests in Extended Reality
- From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models
- From Text to Self: Users’ Perception of AIMC Tools on Interpersonal Communication and Self
- G-VOILA: Gaze-Facilitated Information Querying in Daily Scenarios
- MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
- Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis
- Adaptive Collaboration Strategy for LLMs in Medical Decision Making
- Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data
- InteractOut: Leveraging Interaction Proxies as Input Manipulation Strategies for Reducing Smartphone Overuse
- A Framework for Designing Fair Ubiquitous Computing Systems
- An Autoethnographic Case Study of Generative Artificial Intelligence's Utility for Accessibility
- SmartASL: \"Point-of-Care\" Comprehensive ASL Interpreter Using Wearables
- ConeSpeech: Exploring Directional Speech Interaction for Multi-Person Remote Communication in Virtual Reality
- Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images
- Reviewing and Reflecting on Smart Home Research from the Human-Centered Perspective
- UnlockedMaps: A Web-Based Map for Visualizing the Real-Time Accessibility of Urban Rail Transit Stations
- XAIR: A Framework of Explainable AI in Augmented Reality
- Nightly sleep duration predicts grade point average in the first year of college
- GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling
- Towards Future Health and Well-being: Bridging Behavior Modeling and Intervention
- UnlockedMaps: Visualizing Real-Time Accessibility of Urban Rail Transit Using a Web-Based Map
- HearCough: Enabling continuous cough event detection on edge computing hearables
- Detecting Physiological Responses Using Multimodal Earbud Sensors
- DiverSense: Maximizing Wi-Fi Sensing Range Leveraging Signal Diversity
- EarCommand: \"Hearing\" Your Silent Speech Commands In Ear
- Impact of Online Learning in the Context of COVID-19 on Undergraduates with Disabilities and Mental Health Concerns
- Ubilung: Multi-Modal Passive-Based Lung Health Assessment
- BoldMove: Enabling IoT Device Control on Ubiquitous Touch Interfaces by Semantic Mapping and Sequential Selection
- Enabling Hand Gesture Customization on Wrist-Worn Devices
- TypeOut: Leveraging Just-in-Time Self-Affirmation for Smartphone Overuse Reduction
- GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization
- ReflecTrack: Enabling 3D Acoustic Position Tracking Using Commodity Dual-Microphone Smartphones
- Understanding practices and needs of researchers in human state modeling by passive mobile sensing
- College from home during COVID-19: A mixed-methods study of heterogeneous experiences
- Understanding the Design Space of Mouth Microgestures
- Auth+Track: Enabling Authentication Free Interaction on Smartphone by Continuous User Tracking
- HulaMove: Using Commodity IMU for Waist Interaction
- LightWrite: Teach Handwriting to The Visually Impaired with A Smartphone
- Voicemoji: Emoji Entry Using Voice for Visually Impaired People
- MetaPhys: few-shot adaptation for non-contact physiological measurement
- Leveraging Collaborative-Filtering for Personalized Behavior Modeling: A Case Study of Depression Detection among College Students
- Listen2Cough: Leveraging End-to-End Deep Learning Cough Detection Model to Enhance Lung Health Assessment Using Passively Sensed Audio
- FrownOnError: Interrupting Responses from Smart Speakers by Facial Expressions
- Understanding User Behavior For Document Recommendation
- Recognizing Unintentional Touch on Interactive Tabletop
- EarBuddy: Enabling On-Face Interaction via Wireless Earbuds
- Leveraging Routine Behavior and Contextually-Filtered Features for Depression Detection among College Students
- Clench Interface: Novel Biting Input Techniques