Converting SMILES and SELFIES to 2D Molecular Images
Build a Python CLI tool that converts SMILES and SELFIES notation into 2D molecular images with chemical formulas and legends, including an SVG path for figures.
Hunter Heidenreich | Senior AI Research Scientist — Page 2
Exponential Random Numbers: Two Classic Algorithms
Explore two fundamental approaches to generating exponentially distributed random numbers: the modern inverse transform method using logarithms and von Neumann’s ingenious 1951 comparison-based algorithm that avoids transcendental functions entirely.
Implementing the Müller-Brown Potential in PyTorch
Step-by-step implementation of the classic Müller-Brown potential in PyTorch, with performance comparisons between analytical and automatic differentiation approaches for molecular dynamics and machine learning applications.
Müller-Brown Potential: A PyTorch ML Testbed
A PyTorch testbed for the Muller-Brown potential: analytical and autograd force kernels, and a BAOAB Langevin sampler validated against the canonical distribution.
Modernizing Rahman's 1964 Argon Simulation
I replicated Rahman’s landmark 1964 liquid argon molecular dynamics simulation using modern tools, building a Python analysis pipeline with caching, vectorization, and type hints to bridge vintage science with modern software engineering.
Modernizing Rahman's 1964 Argon Simulation
A modern replication of Rahman’s 1964 argon molecular dynamics paper in LAMMPS, with a cached, vectorized Python analysis pipeline and an agreement table.
Vectorized Word2Vec in Pure PyTorch
A ground-up PyTorch Word2Vec. Tensorizing the Huffman tree turns pointer-chasing Hierarchical Softmax into dense GPU ops compatible with torch.compile.
GEOM Dataset: 3D Molecular Conformer Generation
Get a practical overview of the GEOM dataset and learn how it’s advancing 3D molecular machine learning by bridging static graphs and dynamic reality.
LLMs for Insurance Document Automation
We explore LLM applications for page stream segmentation in insurance document processing, demonstrating that parameter-efficient fine-tuning achieves strong accuracy but revealing significant calibration challenges that limit deployment confidence.
LLMs for Page Stream Segmentation
We create TabMe++, an enhanced page stream segmentation benchmark with commercial-grade OCR, and show that parameter-efficiently fine-tuned decoder-based LLMs like Mistral-7B achieve 80% straight-through processing rates, outperforming encoder-based models.
Synthetic Isomer Data Generation Pipeline
An end-to-end data factory for molecular machine learning that transforms raw chemical formulas (e.g., C6H14) into labeled 3D conformer datasets, using MAYGEN for structural isomer enumeration, RDKit for 3D embedding, and physics-based featurization to address data scarcity in computational drug discovery.
Modern PyTorch VAEs: A Detailed Implementation Guide
A complete guide to implementing modern Variational Autoencoders in PyTorch. Includes a copy-pasteable implementation, explanation of KL annealing to fix posterior collapse, and a deep dive into stable standard deviation parameterizations.