Grounding Language in Vision and Interaction

We are sorry, this position has been filled.

The goal of this project is to train a machine learning agent to acquire language by interacting with its visual environment.

Lab: Columbia Computer Vision lab

Direct Supervisor: Carl Vondrick

Position Dates: 6/1/2020 - 9/1/2020

Hours per Week: 20

Paid Position: Yes

Credit: Yes

Number of positions: 3

Qualifications: Computer vision and deep learning

Eligibility: Freshman, Sophomore, Junior, Senior, Master's (SEAS only)

Carl Vondrick, vondrick@cs.columbia.edu