Shreyan Mitra.

Shreyan Mitra

Student researcher · Software developer

Making machine learning more robust, accessible, and sustainable. Studying computer science at the University of Washington, Seattle — and building tools that bring research into the real world.

Machine learning · Responsible computing

View research Publications CV / Résumé
University of WashingtonPaul G. Allen SchoolSeattle, WA
Portrait of Shreyan Mitra
Shreyan Mitra

Shreyan Mitra

Student researcher · Computer science

University of Washington, Seattle

I am a student researcher and software developer focused on making machine learning more robust, accessible, and sustainable. Based in Santa Clara, CA.

Areas of Focus

Research

With great power comes great responsibility. My research explores how we can make machine learning more reliable, useful, and accountable to the people it serves.

Explore my research approach ↓

ML Robustness

Making ML models less susceptible to error and more applicable to the tasks at hand.

ML Accessibility

Ensuring people of different backgrounds, ages, and coding experiences can use ML tools to make their lives easier.

Social & Environmental Impact

Using AI in ethical and sustainable ways to further social and conservation goals.

Explainability

Comparing explanations for ML models and bringing explanatory systems together in a unified interface.

LLM Hallucinations & Reasoning

Studying why language models hallucinate and developing faster, more memory-efficient detection methods.

Applied Research & Tools

Accompanying research with libraries and software that apply findings to real-world problems.

Research approach & current inquiries

In recent years, machine learning (ML) has become a hot topic because of its tremendous capabilities and numerous applications. However, with great power comes great responsibility. Because of this, I have focused my college research career on the following three areas:

  1. Machine Learning Robustness - Making ML models less susceptible to error and more applicable to the tasks at hand.
  2. Machine Learning Accessibility - Ensuring people of different backgrounds, ages, and coding experiences can use ML tools to make their lives easier.
  3. Social and Environmental Impact - Ensuring ML, and artificial intelligence in general, are used in ethical and sustainable ways to further social and conservation goals.

I like to be hands-on in my research, and most of my research work is accompanied by libraries or software tools that apply my findings to the real world.

Specific lines of inquiry I have pursued / am currently pursuing include:

Explainability
In short, explainability refers to understanding why ML models behave the way they do. Several explainability tools ("explanatory systems") have been developed in the last few years. My work on this topic includes devising a metric to compare different explanations for a given model and deciding which of them better approximates the ground truth. My research also brought me to create a library and framework in Python and Matlab that brings all the different explanatory systems onto an unified interface. The library further democratizes AI by not requiring users to have any coding experience and to seamlessly deploy the models they need for their use case.
Hallucinations and Reasoning in Large Language Models
Large language models (LLMs) like ChatGPT or Llama have gained widespread popularity due to their ability to answer questions and converse like humans. However, unlike humans, LLMs often fail to reason about scenarios in a logical and accurate manner. When LLMs generate incorrect, irrelevant, or nonsensical output, we say that it "hallucinates". I study the factors leading to LLM hallucinations and attempt to generate faster, more memory-efficient ways to detect hallucinations when they occur. I also look at ways to reduce the risk of such erroneous output, such as by incorporating symbolic reasoning, integrating a common sense database, or adding self-evaluation stages.


Of course, I am open to any new research area other than the ones above if it allows me to grow and aligns with my interest in responsible computing.

Selected Papers

Publications

All publications
Google Scholar ↗

Selected Work

Projects & Skills

All projects & skills
Featured
01Libraries

Tabalchi

A library to parse, generate, and transcribe Indian classical music.

MIDIAudio playbackJSONLLM prompting
Explore project
Featured
02AI & Tools

WebAssistant

An AI assistant for any website, combining a React and Express app, a Python deployment interface, and retrieval augmented generation.

ReactExpressPythonRAG
Explore project
03Applications

GoThere

An iOS travel app using image classification and location tracking to identify geographic features and build itineraries.

SwiftXcodeMapKitImage classification
Explore project
04Applications

Choitee

A web and Android app providing mental health guidance to teenagers and connecting them with trusted people and medical professionals.

JavaScriptAndroidPHP
Explore project

Courses & Mentorship

Teaching

From K–12 math and computer science to teaching across five college disciplines.

Full teaching history →

Service & Community

Leadership

Full record & awards

Presentations & Talks

Talks

All talks

Background & Experience

About

Education & training

Completed or in progress

BS, Computer Science (minor Entrepreneurship)

AS, Computer Information Systems

AA, Natural Science and Math

Machine Learning Specialization

High School Diploma

Visharad, Indian Classical Music

Languages · Professional fluency

Bengali · French · English

Research affiliations

AIEA Lab · UC Santa Cruz ↗

SocialRL Lab · University of Washington

Hello! :wave: I’m Shreyan Mitra, a student in the Paul G. Allen School of Computer Science at the University of Washington, Seattle.

In addition to my research, I am also the President and Co-founder of Computing for Environmental and Social Advocacy (CESA), a 30+ member team affiliated with the University of Washington Allen School that focuses on applied topics such as an AI-driven solution to the climate crisis and a software tool to check for potential ethical violations/accessibility concerns in code. Currently, we’re working on modeling pollution in disadvantaged communities of the Puget Sound area.

In my free time, I enjoy playing cricket. I am the President of the Husky Cricket Club at the University of Washington, and always open for a late afternoon game.

About this site

This is my professional portfolio. Here, you’ll find examples of my research, publications, and teaching experience. However, wherever possible, I have included links to external sites if you want to learn more about me as a person.

Awards & Recognition

  • National Merit Scholar
  • President's Volunteer Service Gold Medal
  • National Champion NSF Senior Geography Bee
All awards & recognition
View my résumé

Let’s Connect

Contact

I am open to new research areas that allow me to grow and align with my interest in responsible computing.

shreyan.m.mitra@gmail.com ↗

Artificial Intelligence Explainability & Accountability

Research group

University of California, Santa Cruz

At the AIEA Lab, I lead a team of 5–6 fellow researchers in large language model robustness.

Lab website →

Computing for Environmental & Social Advocacy

Computing for a better world

A 30+ member team affiliated with the University of Washington Allen School.

Meet CESA →