About
Building reliable, human-centered AI for the messiness of the real world.
I am a second year PhD student in Electrical Engineering at Columbia University, advised by Prof. Xiaofan Jiang and Prof. Xuhai Xu. Before starting my PhD, I earned an MS in Computer Science from Columbia University and a BA in Computer Science from New York University, where I graduated summa cum laude.
My research focuses on LLMs and foundation models for health, especially how to make them more reliable, adaptive, and useful when deployed with noisy multimodal data. I am interested in reinforcement learning, multimodal reasoning, and sensing systems that connect language models with behavioral, physiological, and visual signals in real-world care settings.
More broadly, I aim to build AI systems that can support health and well-being beyond idealized benchmarks: models that personalize to people over time, reason across heterogeneous data sources, and remain trustworthy in the messy environments where they are actually used.
Publications
Selected publications
MindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System
Poster: Split-and-Combine Rectification of Ultra-Wide Fisheye Images into Cubemaps
SoundTrack: A Contactless Mobile Solution for Real-time Running Metric Estimation for Treadmill Running in the Wild
TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models
Multi-Modal Dataset Across Exertion Levels: Capturing Post-Exercise Speech, Breathing, and Phonocardiogram
LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart Devices
Exploring Foundation Models in Detecting Concerning Daily Functioning in Psychotherapeutic Context Based on Images from Smart Home Devices
A Data-Driven and Human-Centric EV Charging Recommendation System at City-Scale
AI Therapist for Daily Functioning Assessment and Intervention Using Smart Home Devices
CV
Education
PhD Student, Electrical Engineering
Columbia University. Advisors: Xiaofan Jiang and Xuhai Xu.
MS in Computer Science
Columbia University. GPA: 3.95.
BA in Computer Science
New York University. GPA: 3.97, summa cum laude.
Teaching
TA
- 2026 Embedded AI, Columbia University
- 2025 Artificial Intelligence of Things, Columbia University
Service
Reviews
- 2025 Reviewer for ACM IMWUT
- 2025 Reviewer for ACM Transactions on Computing for Healthcare
Organizing
- 2025 Social Media Chair, HumanSys 2025
Contact