Lennard-Jones’s 1932 theoretical paper applying quantum mechanical potential energy surfaces to gas-solid interactions, providing the first unified framework explaining both physisorption and chemisorption as different regions of the same energy landscape.
GDB-13 contains nearly 1 billion systematically generated small organic molecules with up to 13 atoms, achieving billion-scale chemical space exploration while maintaining drug-like properties.
GDB-17 contains 166.4 billion systematically generated small organic molecules with up to 17 atoms. It represents the most comprehensive exploration of drug-relevant chemical space achieved through computational enumeration.
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 for production-grade efficiency.
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.
SubGrapher introduces a visual fingerprinting approach to Optical Chemical Structure Recognition that detects functional groups directly from images, enabling chemical database searches without full structure reconstruction and handling complex patent images including Markush structures.
Weiler et al.’s NeurIPS 2018 paper introducing 3D Steerable CNNs that achieve SE(3) equivariance through group representation theory and spherical harmonic convolution kernels, eliminating the need for rotational data augmentation and improving data efficiency for scientific applications with rotational symmetry like molecular and protein structures.
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.
Proposes Ring-Free Language (RFL) to hierarchically decouple molecular graphs into skeletons, rings, and branches, solving issues with 1D serialization of complex 2D structures. Introduces the Molecular Skeleton Decoder (MSD) to progressively predict these components, achieving strong results on handwritten and printed chemical structure recognition benchmarks.
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, dramatically 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.