Projects
Browsable PDF artifacts from graduate coursework, organized by topic, plus longer-form project write-ups.
Reinforcement Learning Video Notes
Short explainer videos and notes on policy gradients, Q-learning and evaluation, with worked examples and recorded demos.
Kaggle Competition Playbook
Reusable Kaggle notebooks covering baselines, feature engineering, cross-validation and ensembling, applied to RSNA knee imaging and Gemm...
Master's Theorem Visual Guide
A visual guide to the Master Theorem for divide-and-conquer recurrences, with worked examples and a quick-reference table for the a, b an...
Q-Learning Pac-Man Agent
A comprehensive reinforcement learning project implementing Q-Learning algorithm to teach an agent to play Pac-Man, demonstrating fundame...
vLLM HPCC Simulation & NeuroGolf ONNX Optimization
A comprehensive hardware-software co-design project that simulates vLLM microarchitectural bottlenecks (KV cache, TLB) and applies those ...
Spatial Gaussian Process Hidden Semi-Markov Model (GP-HSMM) for Stratigraphic Prediction
A robust mathematical architecture unifying spatial statistics, duration-explicit sequence modeling, and Bayesian non-parametrics for sub...
Kaggriculture MuZero: agent demo, explainer and post-mortem
A MuZero macrocontroller that plans each farm day over ten strategic plans, with a hemisphere crew layer and a Hungarian-assignment micro...
RSNA Knee Abnormality Detection: what a 0.941 blend is made of
RSNA's 2026 knee-MRI challenge scores twelve findings by mean AUC. I took the 0.956/0.941 public tri-model blend apart down to tensor lev...
Future research: a USD-literate LLM and a knee-scene prediction challenge
A research plan for a fine-tuned LLM that reads, repairs and writes OpenUSD (.usda) scenes. It is anchored on my Archetypal Knee USD mode...
![Screen Capture 001 VagueSpecAgent LangSmith [smith.langchain.com] (preview)](/assets/images/work-pdf-thumbs/w_88b879c9c310537c.png)
Featured Project: Subsurface Stratigraphic Prediction
- Spatial Gaussian Process Hidden Semi-Markov Model (GP-HSMM) - A mathematical architecture unifying spatial statistics, duration-explicit sequence modeling, and Bayesian non-parametrics for geosteering.
- Kaggle Notebook Implementation