~~ I like to Observe. Look for Patterns. Ponder over these Generalizations. Try to Refute them. Or otherwise prove their Validity. And re-image their Applications in alternate spheres ~~

Pratyush Maini

I am a Final Year Undergraduate Student of Computer Science and Engineering at IIT Delhi. My broad area of interest lies in analyzing and developing robust, secure and explainable methods for machine learning and natural language processing. I am advised by Prof. Mausam for my B.Tech. thesis.

During my undergraduate years, I have been fortunate to have had the opportunity to adapt and learn from the research styles of my amazing collaborators: Prof. Zico Kolter, Eric Wong, Danish at CMU, Prof. Bo Li, Prof. Dawn Song, Xinyun Chen at UIUC/UCB, Prof. Nicolas Papernot at UofT/Vector and Prof. James Larus at EPFL during research internships.

Recent News (Scroll for more)

July 2020: Completed my Bachelors of Technology in Computer Science and Engineering at IIT Delhi. Drop in at my thesis: Analyzing the Learnability and Representability of Recurrent Architectures.
June 2020: New work on Classifying Adversarial Perturbations to be presented at ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning.
May 2020: Our paper Adversarial Robustness Against the Union of Multiple Perturbation Models was accepted at ICML 2020. Final version and video presentation to be released soon!
May 2020: Preprint released for Why and when should you pool? Analyzing Pooling in Recurrent Architectures.
See blog post here.
April 2020: Our entry, The Delusional (with artistic pieces, prose and poems in both English & Hindi) won the best Magazine in Gazettale 2020.
Jan 2020: Started TAing the course "Data Structures & Algorithms" [Link] .
Dec 2019: Started (slowly) setting up my personal website.
Sep 2019: Preprint released for Adversarial Robustness Against the Union of Multiple Perturbation Models
Aug 2019: Started TAing the course "Introduction to Artificial Intelligence" [Link] (Graduate and Undergraduate bridge course).