About me
I'm a final year PhD student in UW CSE, advised by Prof. Jon Froehlich at the Makeability Lab.
My research focuses on Human-AI Interaction, especially how AI systems can understand, reason about, and support human interaction with real-world spaces. I pursue two connected directions:
Spatial reasoning and world understanding — building indoor mapping, navigation, and assessment tools using drones, computer vision, 3D graphics, and MLLMs. I aim to advance how AI perceives and reasons about spatial environments for navigation, accessibility, and safety.
Creativity support tools — developing MLLM-based systems for audio, visual, and UI design. I invent creative interfaces, define domain-specific languages, and fine-tune models with domain data to ground AI in real creative workflows.
I'm graduating in summer 2026 and actively seeking full-time industry opportunities as a research scientist or engineer. Please feel free to reach out if you have any opportunities!
Recent Experiences
-
Apple AIML, Seattle
Machine Learning Intern. Apr 2025-Sep 2025
-
Adobe Research, San Francisco
Research Scientist Intern. Jun 2024-Sep 2024
-
Adobe Research, San Jose
Research Scientist Intern. Jun 2023-Sep 2023
-
Microsoft Research Asia, Beijing
Research Intern. Jun 2020-Mar 2021
Education
-
University of Washington
PhD of Computer Science & Engineering, 2021-2026 (est)
-
University of Washington
Master of Computer Science & Engineering, 2021-2024
-
Tsinghua University
Master of Engineering, 2018-2021
-
Tsinghua University
Bachelor of Architecture, 2014-2018
Selected Publications
-
Flymethrough: Human-ai collaborative 3d indoor mapping with commodity drones
UIST'25
-
Accessibility Scout: Personalized Accessibility Scans of Built Environments
UIST'25
-
RAIS: Towards A Robotic Mapping and Assessment Tool for Indoor Accessibility Using Commodity Hardware
ASSETS'24 Poster
-
SonifyAR: Context-Aware Sound Generation in Augmented Reality
UIST'24
-
RASSAR: Room Accessibility and Safety Scanning in Augmented Reality
CHI'24
-
Kinergy: Creating 3D Printable Motion using Embedded Kinetic Energy
UIST'22
-
Interior Layout Generation Based on Scene Graph and Graph Generation Model
Design Computing and Cognition’20
-
Category, process, and recommendation of design in an interactive evolutionary computation interior design experiment: a data-driven study
AI EDAM 34, 2