Michael J. Ryan

Michael J. Ryan

Masters student in NLP

Stanford University

Hi, I’m Michael Ryan and I’m a Master’s student studying Artificial Intelligence at Stanford University. I’m fortunate to be doing NLP research as a member of Dr. Diyi Yang’s SALT Lab! This Spring I am the Head Course Assistant for CS221: Artificial Intelligence: Principles and Techniques with Dr. Nima Anari, Dr. Moses Charikar, and Dr. Sanmi Koyejo.

My research interests include LLM personalization for various cultures, languages, and individuals. Right now I am looking at some of the effects of preference tuning on LLMs. I am also exploring prompt optimization strategies via DSPy. Previously I was an undergraduate researcher in Dr. Wei Xu’s NLP X Lab at Georgia Tech.

Have a look at my CV, or if you’re in a hurry, check out my resume!

Interests
  • LLM Personalization
  • Prompt Optimization
  • Simplification and Readability
  • Fairness in NLP
Education

  • MS in Computer Science, 2025

    Stanford University

  • BSc in Computer Science (Intelligence & Systems/Architecture), 2023

    Georgia Institute of Technology

Research

Unintended Impacts of LLM Alignment on Global Representation
Michael J. Ryan, William Held, Diyi Yang
(To Appear) 62nd Annual Meeting of the Association for Computational Linguistics (Main Conference)
PDF Cite
Revisiting non-English Text Simplification: A Unified Multilingual Benchmark
Michael J. Ryan, Tarek Naous, Wei Xu
61st Annual Meeting of the Association for Computational Linguistics
Best Paper Award Honorable Mention
PDF Cite Code Dataset Poster Slides Video DOI
Having Beer after Prayer? Measuring Cultural Bias in Large Language Models
Tarek Naous, Michael J. Ryan, Wei Xu
(To Appear) 62nd Annual Meeting of the Association for Computational Linguistics (Main Conference)
PDF Cite
Towards Massively Multi-domain Multilingual Readability Assessment
Tarek Naous, Michael J. Ryan, Mohit Chandra, Wei Xu
ArXiv Preprint
PDF Cite
Facial Composite Generation from Natural Language Text Descriptions using Stacked Generative Adversarial Networks
Michael J. Ryan
AP Research Project (Score 5/5)
PDF Cite
See all publications

Teaching

CS221 - Artificial Intelligence Principles and Techniques (Head CA)
As Head CA for CS221 I led a teaching team of 17 CAs for a class of 285 students. I would run our weekly staff meetings, delegate responsibilities, organize office hours, facilitate course activities, and adapt the course based on student, CA, and instructor feedback.
Last updated on May 17, 2024
CS124 - From Languages to Information
As a CA for CS124 my primary responsibility was updating and administering the final course project. This iteration of the course the final course project involved making a movie recommendation chatbot using sentiment analysis, collaborative filtering, regular expressions, and similar fundamental NLP and IR concepts. The project also involved hands-on experience with modern LLMs to enhance the virtual assistants conversational capabilities.
Last updated on May 17, 2024
Code
CS221 - Artificial Intelligence Principles and Techniques
For CS221 I ran the weekly problem session review. I would review the course material and go over practice problems. Course content included machine learning, search, mdps, games, csps, bayes nets, and logic.
Last updated on Jan 4, 2024
CS3600 - Introduction to AI (Head TA)
As Head TA for CS3600 I was responsible for organizing the grading and office hours of 26 TAs to make sure that the class ran smoothly for 1,633 students (across 4 semesters). I had the opportunity to teach about search, reinforcement learning, bayesian inference, and machine learning.
Last updated on May 17, 2024
Video

Work Experience

 
 
 
 
 
Microsoft Corporation
Software Engineer Intern
Microsoft Corporation
May 2022 – August 2022 Seattle, WA
  • Designed and programmed static analysis tool in C++ for identifying security vulnerabilities throughout Windows OS.
 
 
 
 
 
Microsoft Corporation
Software Engineer Intern
Microsoft Corporation
May 2021 – August 2021 Virtual
  • Refactored existing codebase from .NET Framework to .NET Core.
  • Ported server-specific architecture to serverless functional units using Azure Durable Functions.
 
 
 
 
 
Uber Inc.
Software Engineer Intern
Uber Inc.
May 2020 – August 2020 Virtual
  • Implemented end-to-end testing in GoLang for bike, scooter, and moped rentals by building a simulated 3rd party CRUD API.

Projects

*
All Natural Language Processing Computer Vision
Knock Knock: Neural Joke Generation and Classification
A joke generator built on GPT-2 and joke classifier built on BERT for CS4650 Natural Language Understanding.
PDF Code
Knock Knock: Neural Joke Generation and Classification
Sign Assist
Sign Assist is a digital American Sign Language (ASL) interpreter. Using a Kinect camera and computer vision Sign Assist tracks user movements and patterns to detect different signs. Sign Assist can output these signs as both text and speech.
Code Video
Sign Assist

Awards

Honors Program Distinction in Research
Georgia Tech Honors Program Dec 2022
Awarded for completing Honors Level Coursework and Approved Research as an undergraduate at Georgia Tech
See certificate
Outstanding Undergraduate TA for Interactive Computing
Georgia Tech Center for Teaching and Learning Mar 2022
Awarded for contributions to teaching excellence at Georgia Tech School of Interactive Computing

Contact