I am a second-year PhD student at Columbia University advised by Carl Vondrick. I am interested in building machines that leverage multimodal signals (e.g. vision, vibration, audio) and natural transformations in the physical world to creatively perceive and interact with their environment. My research is supported by the Columbia Center of Artifical Intelligence & Technology (CAIT) & Amazon Science Ph.D. Fellowship.

I previously graduated from the University of Pennsylvania advised by Jianbo Shi, with a BA in Computer Science, and minors in Math, Computational Neuroscience, and Systems Eng. In my free time I play with art projects, make useless but beautiful datasets (see Reflections),read (my GoodReads), play piano, and sometimes, scuba dive.

Research

  • Real-Time Neural Voice Camouflage Mia Chiquier, Chengzhi Mao, Carl Vondrick
    PaperProject Page
    ICLR 2022 (Oral,Top 1.6%)
  • The Boombox: Visual Reconstruction from Acoustic Vibrations Boyuan Chen, Mia Chiquier, Hod Lipson, Carl Vondrick
    PaperProject Page
    CoRL 2021
  • Adversarial Attacks are Reversible with Natural Supervision Chengzhi Mao, Mia Chiquier, Hao Wang, Junfeng Yang, Carl Vondrick
    Paper
    ICCV 2021

Teaching/Service

Courses
Advanced Computer Vision (COMS 4731, Summer 2021)
Head Teaching Assistant
Columbia University
Dynamical Systems (ESE 210, Fall 2019)
Head Teaching Assistant
University of Pennsylvania
Service
Reviewer
ICCV 2021, CVPR 2022
Columbia University
BEARS Mentorship (Spring 2021, Spring 2022)
Undergraduate Mentor
Barnard College
Organizer: Learning from Unlabeled Video Workshop (CVPR 2021)
Workshop Organizer
Columbia University