Projects
×
Low Resource RAG: From Slide Data Processing to RAG Systems
For my Honors Thesis, I develop a retrieval-augmented generation system with Hyundai for automotive safety collision test questions using multimodal slides, finding that fine-tuned embedding models achieve the highest accuracy.
Nutrify: Your Musical Nutrition!
Nutrify transforms your Spotify listening habits into a fun cereal box nutrition label! Discover your musical taste profile, create playlists, and visualize your music consumption like never before.
Cyberbullying Classification
A collection of models ranging from classical machine learning to fine-tuned LLMs to detect cyberbullying in text messages. Achieved 99% accuracy utilizing BERT and RoBERTa models for the classification task. Won Best Project Award in CS334: Machine Learning.
Resume Revamper
An LLM-powered resume editing tool that enhances word choice, phrasing, tone, and focus on big picture content goals. Automatically parses PDF resume and outputs a PDF resume when finished. Able to follow user instructions at an accuracy of 92.5%, evaluated through custom evaluation framework.
Student Dropout Prediction
Trained 4 different tabular deep learning networks to predict whether a student is likely to drop out or graduate based on 12 features generated and picked from over 36. Utilized feature engineering, hyper parameter tuning, and deep learning models to achieve 91% accuracy.
Muse Bot - Musical Channels!
Muse_Bot is a Discord Bot that can play all the music that you could ever want, straight in your discord channel rooms. You can see whats playing now, vote to skip music, remove and add to a queue, and much more!
Madness in the Abyss
Madness in the Abyss is a Rogue-like video game, containing 3 different levels and a variety of monsters, from spooky ghosts to one-eyes flesh monsters, the player fights through different levels to escape the abyss! Semester Project for CS Practicum.