About
me
Research Software Engineer, Ph.D. student
Google Brain Robotics, University of Toronto (CV)
Hello World!
My name is Maria and a Robotics Research Engineer in Google Brain and a Ph.D. student at the University of Toronto. My current focus is on One-Shot Visual Imitation Learning in Robotics and methods that attempt to apply continual and adaptive learning in Robotics manipulation.
I'm a happy human that loves Math a little too much if there is such a thing, and has a deep appreciation for shiny, colorful, glittery things and patterns which I like to express through photography. I like to laugh and I have a very detailed memory (which usually works to my favor) about anything and everything except acronyms and keyboard shortcuts.
P.S. Hope you enjoyed the Mandelbrot set animation, it's being calculated and colored on the fly using a custom palette because, why not, it's beautiful. :) For the curious, code can be found here.
Research
Interests
Robotics, Cognitive Science,
Machine Learning
My research interests lie in the intersection of Robotics and Cognitive Science. I'm particulary fascinated by the idea of a robot that can understand the reasoning behind human behavior and motivation (or even infer our emotions) or just imitate a human that shows it how to do a task, and use this to perform informed decision-making. I'm excited to see how advancements in this area can be applied into Affective Computing and Assistive Robotics with the goal of making human lives easier and happier.
There is a big portion of the world that does not have an easy life. I am hopeful and a strong believer that technology, especially robotics, can help.
Recent
Projects
Some cool research
with some cool people!
"See, Plan, Predict: Language-guided Cognitive Planning with Video Prediction"
Maria Attarian*, Advaya Gupta*, Ziyi Zhou, Wei Yu, Igor Gilitschenski, Animesh Garg
ArXiv
"Transforming Neural Network Visual Representations to Predict Human Judgments of Similarity"
Maria Attarian, Brett D. Roads, Michael C. Mozer
NeurIPS 2020 Second Workshop on Shared Visual Representations in Human and Machine Intelligence (SVRHM). ArXiv
“Rearranging the Visual World: Transporter Networks”
Andy Zeng, Pete Florence, Jonathan Tompson, Stefan Welker, Jonathan Chien, Maria Attarian, Travis Armstrong, Ivan Krasin, Dan Duong, Vikas Sindhwani, Johnny Lee
4th Conference on Robot Learning (CoRL) 2020. (Paper was one of only 20 selected for a plenary talk, 4.1% of all submitted papers, and one of 3 finalists for the Best Paper Presentation award). ArXiv
“Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation”
Pablo Samuel Castro, Maria Attarian
NeurIPS 2018 Second Workshop on Machine Learning for Creativity and Design (poster session). ArXiv
Contact Information
University of Toronto CS
jmattarian@cs.toronto.edu