Research · Computer vision
Satellite imagery: detection and segmentation
Ongoing faculty-supervised research comparing object-detection and semantic-segmentation approaches on remote-sensing imagery.
Technical work
Projects
Implementations, experiments, and systems I have built to understand how models work. I distinguish verified results from exploratory work and proposed extensions.
Information retrieval · RAG
Document retrieval and question answering
A modular document-search implementation built to understand how document representation and retrieval influence evidence-grounded question answering.
Reinforcement learning
Learning through interaction: Q-Learning and PPO
Experiments with tabular value learning and neural policy optimization across several Gymnasium and Unity environments.
Generative models · Paper reproduction
Understanding diffusion models by implementing DDPM
A PyTorch implementation of the core denoising diffusion probabilistic model, motivated by understanding image generation from first principles.
Representation learning · NLP
Learning word representations from context
Implementations of CBOW and Skip-gram with negative sampling, first in NumPy and then in PyTorch.
Generative models · Representation learning
Probabilistic latent representations with VAEs
A PyTorch implementation exploring variational inference, reconstruction, KL regularization, and latent-variable generation.
Supervised learning · Evaluation
A reproducible XGBoost classification workflow
A structured classification pipeline exploring how validation, hyperparameter selection, and data preparation affect generalization.
Stochastic processes · Quantitative engineering
LambdaLab: modeling trade arrivals with Hawkes processes
An exploratory quantitative-modeling application connecting point-process theory, parameter fitting, simulation, and interactive visualization.