I am a first-year PhD student at Berkeley AI Research, advised by Alexei Efros. I work on teaching machines a high-level creative understanding of the dynamic real world, which I believe requires learning from video without manual supervision. I am also interested in language, machine learning, image synthesis, and interaction as they relate to this.

Previously, I worked with Chen Sun, Jiajun Wu, and Cordelia Schmid at Google Research. Before that, I graduated from Columbia University with a BS in computer science, where I was lucky to be introduced to computer vision and advised by Carl Vondrick.


  • Learning Temporal Dynamics from Cycles in Narrated Video NEW!Dave Epstein, Jiajun Wu, Cordelia Schmid, Chen Sun
  • Globetrotter: Unsupervised Multilingual Translation from Visual Alignment NEW!Dídac Surís, Dave Epstein, Carl Vondrick
    PaperProject Page
  • Learning Goals from FailureDave Epstein, Carl Vondrick
    PaperProject Page
  • Oops! Predicting Unintentional Action in VideoDave Epstein, Boyuan Chen, Carl Vondrick
    PaperProject PageTalk
    CVPR 2020
  • Learning to Learn Words from Visual ScenesDídac Surís*, Dave Epstein*, Heng Ji, Shih-Fu Chang, Carl Vondrick
    PaperProject PageTalk
    ECCV 2020


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