Hi, I'm Saumik!
I'm currently a 4th-year PhD student at Washington University in St. Louis, working in the field of Artificial Intelligence with Chien-Ju Ho. I also heavily collaborate with Sid Sen at Microsoft Research NYC.
In 2019, I graduated from the University of Minnesota with a BS in Computer Science, and I spent a year between undergrad and grad school as an Associate Researcher at SIFT.
My current research focuses on the area of AI-Assisted Human Decision Making, and I have two different lines of work in this area. Most of my recent projects have focused on the domain of chess, due to the huge amount of human data available for free. My work aims to answer two questions. (1) How can we design intervention strategies to improve outcomes in real-time? (2) How can we create personalized teaching tools which lead to long-term human growth?
My second line of work focuses on the ethical side of human-AI teams. In this project, our goal is to better understand how various forms of AI assistance affect human ethical decision making. So far, I have looked at the impact of AI predictions and AI recommendations in the domain of Kidney Transplant Allocation. Next, I plan to analyze this impact across other domains such as judicial and medical. I'm especially excited about the idea of ethically-aware AI algorithms for transit route setting.
In the past, I've worked in many other areas of CS as well - check out the projects page for more details.
Feel free to contact me!
Introduction Light rail (or LRT) is a type of transit which uses street-running, at-grade trains to transport passengers. It’s been seeing a growing surge of interest in American cities over the last few decades, and Read more…
I have a lot of experience watching bad presentations, starting right from elementary school, and going all the way through undergrad, in industry, and in my PhD. This is almost certainly true of everybody reading Read more…
Recently, I started a mini-project to write a Python script for transliterating the Tamil Script, since I couldn't find a good one which already existed. Transliteration (also known as Romanization) simply means taking the native Read more…
A few years ago, I wrote in a blog post that I would start working more on Tamil again, and while I was able to read through the Colloquial Tamil book and pick up some Read more…
In 2022, I published my first ever, first-author publication as a PhD student — How Does Predictive Information Affect Human Ethical Preferences?, which was published at AIES 2022. Since then, I've been meaning to write Read more…
One of my current research projects deals with applying elements of Curriculum Learning (CL) for designing real-world human learning curricula. In the last few weeks, I've read a number of CL papers, and in this Read more…
