A PyTorch testbed for the Müller-Brown potential energy surface, built as ground truth for ML-in-molecular-dynamics work. It pairs analytical and autograd force kernels (the analytical path compiled with torch.compile) with a BAOAB Langevin sampler validated against the canonical distribution and a two-tier test suite.
A digital restoration of Rahman’s seminal 1964 molecular dynamics paper using LAMMPS and a Python analysis pipeline featuring decorator-based caching, fully vectorized NumPy computations for O(N^2) operations, and modern tooling (uv, type hints, Makefile automation) transforming academic scripts into a reproducible research toolkit.
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.
A ground-up PyTorch implementation of Word2Vec treating it as a systems engineering challenge, with “tensorized tree” architecture converting pointer-chasing Hierarchical Softmax into dense GPU operations, infinite streaming datasets with Zipfian subsampling, and torch.compile compatibility.
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.
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.
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.
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.
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.
What happens when you achieve 99.8% accuracy on sarcasm detection? You might have accidentally built a domain classifier. A cautionary ML tale about dataset bias.
Can mathematical signatures capture molecular shape? We test whether Coulomb matrix eigenvalues can distinguish alkane constitutional isomers, from unsupervised clustering failures to supervised learning successes.
We test three ML models on 48K congressional bills to see how well they can predict policy areas from bill text. Results show logistic regression performs best, with a certified weighted-F1 of ~0.88 within-Congress (0.877) and ~0.87 out-of-Congress (0.871).