Hi, I’m Hunter!
I work on machine learning problems in NLP and scientific computing, particularly computational chemistry. Here I share what I’m learning, projects I’m building, and research I find interesting. More about me →
Recent Research
LLMs for Insurance Document Automation
LLM applications for insurance document automation using parameter-efficient fine-tuning and analysis of calibration …...
Deconstructing Neural Networks for Time Series Forecasting
Ablation study of neural network components for forecasting, finding gating and attention improve RNNs while recurrence …...
LLMs for Page Stream Segmentation
Enhanced TABME benchmark for page stream segmentation, creating TABME++, showing fine-tuned decoder-based LLMs …...
Recent Posts
Exponential Random Number Generation: Two Classic Algorithms Compared
Compare inverse transform sampling and von Neumann's rejection method for exponential random numbers with Python …
Implementing the Müller-Brown Potential in PyTorch
Guide to implementing the Müller-Brown potential in PyTorch, comparing analytical vs automatic differentiation with …
Replicating Rahman's 1964 Liquid Argon Simulation
Recreating the foundational 1964 molecular dynamics simulation with modern Python and LAMMPS, testing whether Rahman's …...
GEOM Dataset: 3D Molecular Conformer Generation
Learn how GEOM transforms 2D molecular graphs into dynamic 3D conformer ensembles for molecular machine learning …
Recent Projects
Müller-Brown Potential in PyTorch
PyTorch implementation of the Müller-Brown potential with performance optimizations, MD simulations, and analytical vs …...
Rahman's 1964 Liquid Argon Simulation Replication
Replication of Rahman's 1964 molecular dynamics simulation using modern LAMMPS and Python, achieving quantitative …...
Mini-Protein Trajectory Generation
GROMACS workflows for amino acid dipeptide trajectories across nine residue types, creating diverse MD datasets for ML …
Recent Notes
Communication in the Presence of Noise
Shannon's 1949 foundational paper establishing information theory, channel capacity, and the sampling theorem for …...
Levinthal's Paradox and the Kinetic Pathway of Protein Folding
Levinthal's famous paradox: protein folding's astronomical search space proves folding must follow guided kinetic …...
MARCEL: Molecular Representation and Conformer Ensemble Learning
MARCEL dataset provides 722K+ conformers across 76K+ molecules for drug discovery, catalysis, and molecular …