Sangnie Bhardwaj

I am an AI Resident at Google Research in Mountain View, where I work on unsupervised representation learning. Before this, I was an undergraduate at the Computer Science Department, Indian Institute of Technology (IIT) Delhi.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Research

I am interested in building systems that generalize as well as humans do, with little supervision, using knowledge of human psychology and cognition.

project image

An Unsupervised Information-Theoretic Perceptual Quality Metric


Sangnie Bhardwaj, Ian Fischer, Johannes Ballé, Troy Chinen
NeurIPS 2020, 2019
paper / poster

We develop PIM, a perceptual quality metric, by combining recent advances in information-theoretic objective functions with a computational architecture informed by the physiology of the human visual system.
project image

CaRB: A Crowdsourced Benchmark for Open IE


Sangnie Bhardwaj,Samarth Aggarwal, Mausam
EMNLP-IJCNLP 2019, 2019
paper / code

We release CaRB, an improved crowdsourced dataset and framework for testing Open Information Extraction systems.

Design and source code from Leonid Keselman's Jekyll fork of Jon Barron's website.