A NeurIPS 2021 method paper introducing Noise Contrastive Priors to address the VAE ‘prior hole’ problem, where standard Gaussian priors assign high density to regions of latent space that don’t correspond to realistic data, using energy-based models trained with contrastive learning to match the aggregate posterior.

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 billion systematically generated small organic molecules with up to 17 atoms, representing 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.

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 data augmentation and improving data efficiency for scientific applications with rotational symmetry like molecular and protein structures.

A comprehensive phylogenomic study dating LUCA to ~4.2 Ga and reconstructing it as a complex, anaerobic acetogen. The authors employ a novel cross-bracing molecular clock method and gene-tree-species-tree reconciliation to infer that LUCA possessed an early immune system and lived within a hydrogen-recycling ecosystem.

A provocative 2024 Nature Machine Intelligence paper challenging the assumption that invalid SMILES are failures, showing empirically that the ability to generate invalid outputs actually improves chemical language model performance by enabling quality filtering and providing richer training signals.

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.