A research framework for language-model agents playing a social deduction game. I developed game logic, agent reasoning modules, and an evaluation pipeline to compare how agents use incomplete information.
Compared agent behavior across 499 games and five configurations.
Python · Mistral-7B · LoRA / PEFT · LangChain
A natural-language interface to an NBA database. I built the data preparation pipeline, SQL generation, and a Streamlit interface that shows the query alongside its explanation.
Separate paths for reading, exploring, and modifying data.
Python · MySQL · OpenAI · Streamlit
An NBA data pipeline packaged for use in R. I connected scheduled box-score collection, data cleaning, and package distribution so the analysis starts with reusable data.
An installable package with scheduled collection and testthat tests.
R · Python · GitHub Actions · testthat
A computer-vision study of whether video content can predict engagement. The project combines a custom dataset, two definitions of virality, and fine-tuning of a pretrained video model.
The evaluation exposed prediction collapse rather than a reliable predictor.
PyTorch · R(2+1)D-18 · Computer vision · Pandas