internal representations of LDMs

As AI image generators gained popularity, we researched how LDMs encode 3D information like saliency, depth, and shading (we probe the internal activations of the LDMs U-Net using linear probing classifiers). We can further explore how to modify the 3D layout of the generated image without changing the prompt or seed by editing the foreground mask or depth map.

panama papers

We utilize a dataset from ICIJ, which includes millions of leaked documents exposing personal financial information through offshore entities. Using XGBoost, we predict which entities are likely to be engaged in illegal activities. Our model intends to assist governments and NGOs in pinpointing entities most likely be involved in suspicious activities.

sussy stock trades

Are representatives from the state of Michigan better traders? Here, we conduct hypothesis testing on 14,000+ stock trade transactions to assess the trading skills of representatives. We also perform permutation testing to address data gaps and apply effective imputation techniques to handle incomplete data.

Clothing Fit Recommender System

This project aims to develop and compare various machine learning approaches for predicting clothing ratings and fit. Leveraging interaction data and user/product features, this project delves into models such as linear regression, logistic regression, Jaccardian similarity, and TF-IDF.

TreeHacks '24: AutoScore

We are currently working to make this into a full-fledged product, hence the github repo is private. Stay tuned for more! AutoScore aims to simplify the free response grading pipeline by utilzing ChromaDB, Reflex, and classical ML. (we're not just a GPT-wrapper, trust me!)