Computer Science Ph.D. Candidate at University of Maryland Baltimore County
Research: Multimodal Grounded Language Learning
📍 Baltimore, MD, USA
About Me
I am a Computer Science Ph.D. candidate at University of Maryland, Baltimore County where I am very fortunate to be advised by Cynthia Matuszek and work closely with Frank Ferraro and Edward Raff. Before that, I obtained my B.Sc. in Computer Science from Shahid Beheshti University. My research interests are artificial intelligence, multimodal machine learning and the intersection of computer vision and natural language processing. I'm currently working on grounded language learning.
Education
2018-PresentPh.D., Computer Science at University of Maryland, Baltimore County
2013-2018
B.Sc., Computer Science at Shahid Beheshti University
Research
My current research is on multimodal machine learning which is the idea of learning a shared representation of a concept from different types of data such as RGB image, depth image, or any other sensory inputs.
More specifically, in my research, I connect natural language to perceptual data (anything in the world that can be sensed or measured). The ultimate goal of my research is to develop AI agents (and robots) that humans can interact with in an intuitive way. My hypothesis is that natural language is the most natural form of communication.
To learn the connection between natural language and perceptual data, I utilize different learning methods such as deep learning, probabilistic graphical models, contrastive learning, cross-entropy, and self-supervised learning.
Publications
For the most up-to-date list of my publications, please refer to my Google Scholar page.Multimodal Language Learning for Object Retrieval in the Face of Missing Modalities. Kasra Darvish, Edward Raff, Francis Ferraro, and Cynthia Matuszek. Under review at The Transactions on Machine Learning Research (TMLR), 2023.
A Spoken Language Dataset of Descriptions for Speech-Based Grounded Language Learning. Gaoussou Youssouf Kebe, Padraig Higgins, Patrick Jenkins, Kasra Darvish, Rishabh Sachdeva, Ryan Barron, John Winder, Donald Engel, Edward Raff, Francis Ferraro, Cynthia Matuszek. In press at the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2021.
Discriminative and Generative Transformer-based Models For Situation Entity Classification. Mehdi Rezaee, Kasra Darvish, Gaoussou Youssouf Kebe, Francis Ferraro. arXiv preprint arXiv:2109.07434, 2021.
Towards Making Virtual Human-Robot Interaction a Reality. Padraig Higgins, Gaoussou Youssouf Kebe, Kasra Darvish, Don Engel, Francis Ferraro, Cynthia Matuszek. In press at the 3rd International Workshop on Virtual, Augmented, and Mixed-Reality for Human-Robot Interactions (VAM-HRI), Boulder, CO, USA, 2021.
Practical Cross-Modal Manifold Alignment for Robotic Grounded Language Learning. Andre T Nguyen, Luke E Richards, Gaoussou Youssouf Kebe, Edward Raff, Kasra Darvish, Frank Ferraro, Cynthia Matuszek. In press at Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021.
Learning Object Attributes with Category-Free Grounded Language from Deep Featurization. Luke E. Richards, Kasra Darvish, Cynthia Matuszek. In press at The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, Nevada, USA, October 2020.
A Manifold Alignment Approach to Grounded Language Learning. Luke E. Richards, Andre T. Nguyen, Kasra Darvish, Edward Raff, Cynthia Matuszek. The Northeast Robotics Colloquium (NERC 2019), Philadelphia, Pennsylvania, USA, October 2019.
Skills
👨💻 Programming
- Proefficient in Python, PyTorch, Pandas, NumPy, Scikit-learn
- Familiar with C++, Java, Matlab
📚 Topics
- AI, ML, NLP, Computer Vision
- Algorithms
🛠 Tools
- Bash, Oh My Zsh, Vim, Emacs
- LATEX, HTML, Markdown, Org Mode
💻 Operating Systems
- GNU/Linux
- Mac OS X
Memberships and Services
2021-PresentNeural Information Processing Systems (NeurIPS): Reviewer
2020
Intelligent Robots and Systems (IROS): Reviewer
2022-2023
Vice President of Iranian Graduate Student Association (IGSA) at University of Maryland, Baltimore County
2018-PresentBoard member of Iranian Graduate Student Association (IGSA) at University of Maryland, Baltimore County
2014-2016
Executive Director of "Pardazeh" which is the Scientific Journal of Computer Science Association, Shahid Beheshti University
2017
IOI Office member at the 29th International Olympiad in Informatics, Tehran, Iran
Teaching
September 2018 - May 2019Teaching Assistant for Algorithms
University of Maryland, Baltimore County
September 2017 - January 2018
Teaching Assistant for Computational Geometry
Shahid Beheshti University
September 2017 - January 2018
Teaching Assistant for Compiler Theory
Shahid Beheshti University
February 2016 - July 2016
Teaching Assistant for Automata Theory
Shahid Beheshti University
Soft Skills
In terms of soft skills, I am a friendly human being, and I believe that collaboration is the only way to have impactful contributions. I am happy to take the lead in a project, but I am also perfectly fine being a contributing member
My experience as a PhD student taught me that the most important factor in problem-solving is not intelligence, but rather persistence. Moreover, I learned the value of understanding when to stop and when to continue. I don't believe in the stereotype that if you work hard enough you can achieve whatever you want; In my opinion, one has to be wise to know when to stop and look differently.
News
July 2023I successfully defended my Ph.D. proposal and became a Ph.D. candidate.
July 2022
I'm attending ICML in Baltimore, MD. Let's meet up if you are attending.
August 2018
I received Morgan Stanley scholarship as a Data Science researcher ($5,000)
Misc
♪ Playing The Piano
I play classical piano. The problem is that you cannot move your piano with yourself. Therefore, I have my music sheets with me almost always, so that I can practice if I find a piano somewhere.My favorite composers are Wolfgang Amadeus Mozart and Frédéric Chopin.
My favorite classical pieces are Rondo Alla Turca (Turkish March) by Mozart and Wedding of Love by Paul de Senneville.
⚽ Soccer
I was a professional player when I was in high school and middle school. I was in the youth team of Saipa football club. The positiion I play the most is central midfielder.My favorite soccer players are Kevin De Bruyne, Ronaldo Nazário, Cristiano Ronaldo, and Zidane.
📚 Reading Books
Check my goodreads page for the books that I'm curerntly reading and my reviews on the books I've read so far.I see each book as an opportunity to dive into the author's mind and learn a great deal about their ideas.
My favorite genres are Sci-Fi, classic, and non-fiction.
The books I enjoyed reading the most include The Three-Body Problem by Cixin Liu, The Stranger by Albert Camus, The Little Prince by Antoine de Saint-Exupéry, Man's Search for Meaning by Viktor Frankl, and Thinking Fast and Slow by Daniel Kahneman.
🎮 Games
My all-time favorite game is Braid. My other favorite video games are The Sims, Fifa, The Last of Us, and Age of Mythology.I learned a great deal about ancient Greece and Greek mythology just by playing Age of Mythology when I was in middle school. I learned the flags of countries by playing Fifa. You see the pattern, right? I believe that games are powerful tools for learning.
Teaching