I am a senior at Columbia University studying computer science, advised by Carl Vondrick. My main research interests are in computer vision and machine learning (in particular, self-supervised), as well as in language, sound, and interaction. This summer, I will be working with Chen Sun at Google Research.

Previously, I was a member of Suman Jana's Security laboratory, where we investigated adversarial robustness in neural nets and machine learning applications for automated vulnerability detection. I spent a summer working on machine learning optimization at Intel.

Research

I believe that the future of artificial intelligence lies in algorithms that can learn from massive amounts of unlabeled data. I enjoy working on research that uses self-supervision to train machines to solve complex tasks and develop a rich conceptual understanding of the open world.

Publications
  • Oops! Predicting Unintentional Action in Video
    Dave Epstein, Boyuan Chen, Carl Vondrick
    PaperProject Page
  • Learning to Learn Words from Narrated Video
    Dídac Surís*, Dave Epstein*, Heng Ji, Shih-Fu Chang, Carl Vondrick
    PaperProject Page
  • What's Missing from Self-Supervised Representation Learning?
    Dave Epstein*, Yiliang Shi*, Eugene Wu, Carl Vondrick
  • NEUZZ: Efficient Fuzzing with Neural Program Learning
    Dongdong She, Kexin Pei, Dave Epstein, Junfeng Yang, Baishakhi Ray, Suman Jana
    IEEE S&P 2019
    Paper

Teaching

Past
Advanced Computer Vision
Teaching Assistant
COMS 6998-3 (Spring 2019)
Data Structures and Algorithms
Head Teaching Assistant
COMS 3134 (Fall 2017 - Summer 2019)