Ravsehaj Singh Puri

I am a computer science graduate student in the School of Computing and Augmented Intelligence at Arizona State University. Previously I was part of the Talent Insights team at Eightfold AI as a Software Engineering Intern and was a Visiting Research Intern at the University of Toronto and Vector Institute where i worked under the supervision of Animesh Garg. Prior to that, I was part of the research group directed by Parteek Bhatia wherein i worked in the field of Deepfake Detection. I envision a world with intelligent systems interacting with us in a human-like fashion.

E-mail / Github / Google Scholar / CV / Twitter / LinkedIn

If you would like to collaborate on projects and discuss ideas, please feel free to contact me. I would love to learn from talking with people sharing a common interest.


27th, Mar'22   First research paper accepted at ACL Workshop Spa-NLP
17th, Mar'22   Submitted my first research paper in NLP on arxiv
19th, Aug'21   Starting MS in Computer Science at Arizona State University, Tempe, United States
2nd, Jul'21   Graduated with BE in Computer Engineering from TIET, India
1st, Feb'21   Joining Eightfold AI as a Software Engineering Intern in Talent Insights team
1st, Jan'21   Joining PAIR Lab at University of Toronto as an Undergraduate Research Assistant
24th, Dec'20   Completed my undergraduate academic studies in CS from TIET, India
20th, Nov'20   Compiled my research in Deepfake detection and submitted a presentation to Supervisor
8th, Oct'20   Started working in Multi-Object Tracking project on procedural tasks


I'm broadly interested in Artificial Intelligence(AI) specifically in the fields of Machine Learning, Deep Learning, Natural Language Processing & Understanding, Computer Vision and Data Analytics. My first research project was in deepfake detection folllowed by some work in the field of Multi-Object Tracking. My current research area is Learning from Instructions. Alongside, I am also interested in combined vision and language research, Distributed Deep Learning, Robust NLP, Automatic Data Generation using Language Models and Robotics. I am a strong team player and feel empowered by collaborating with amazing engineers and researchers for cutting-edge projects in fields unexplored.

ACL Workshop 2022
How Many Data Samples is an Additional Instruction Worth?
Ravsehaj Singh Puri Swaroop Mishra, Mihir Parmar, Chitta Baral
Learning from Instructions
Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks.
Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Ravsehaj Singh Puri, Yeganeh Kordi et. al
Learning from Instructions