Most recommendation systems are designed to maximize immediate engagement—the “next click.” However, true user value is built over entire sessions. In this project, RL-RECSYS, I explored how Reinfo...

Neural networks are often treated as “black boxes,” full of abstract matrices and hidden weights. To bridge the gap between theory and intuition, I developed MANIM-AI, an extension for the Manim an...

In an era of trillion-parameter models and massive compute clusters, it’s easy to forget that capacity matters, constraints are the point, and craft beats brute force. This is the philosophy behin...

The original GPT-2 architecture, released in 2019, remains the bedrock of modern NLP. However, the “standard” recipe for training Transformers has shifted dramatically. In this project, I rebuilt t...

This paper presents CTRCBO (Cohort-Based Trust Region Contextual Bayesian Optimization), a hybrid framework designed for personalizing ad load in large-scale social networks like Meta. Key Contrib...