[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

GA algorithm to solve bin packing and production scheduling problems

currently work in progress expect massive performance upgrade and overhaul coming in a few days

Synthetic sounds datasets and real sounds datasets of waterflow sounds for the repo 'Neural-Texture-Sound-Synthesis-with-physically-driven-continuous-controls'.

R scripts and data sets to reproduce the results in the paper "Accounting for shared covariates in semi-parametric Bayesian additive regression trees". The Annals of Applied Statistics (to appear).

Implementation of SQL commands using various strategies, including B* Tree, to manipulate a real database provided by Secretariat of Public Security of São Paulo, containing information about cellphone thefts.

ML pipeline for predicting medical claim costs from non-linear, sequential visit data. Accuracy is built to improve with new visit inputted. Uses LSTM autoencoder embeddings + XGBoost complexity router (87% accuracy) to classify claims as LOW/MED/HIGH complexity, then routes to specialized regression models.

Predict crop yields using machine learning. Flask web app with high accuracy for assisting farmers and policymakers.

Academic project with a group of 6. Studying and analyzing real data from Toronto Traffic Collisions.

SEIHRF-OD epidemic model coupled with opinion dynamics for the 2026 Ebola outbreak in eastern DRC.

Exploratory Data Analysis on real-world Zomato dataset with actionable insights and visualizations