The foundational 1984 paper introducing EAM, a semi-empirical many-body interatomic potential that incorporates density functional theory concepts to accurately simulate metallic systems while maintaining computational efficiency comparable to pair potentials.
Torrie and Valleau’s 1977 paper introducing importance sampling with non-physical distributions to overcome the sampling gap problem in Monte Carlo free-energy calculations, particularly for phase transitions.
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.
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.
A 2025 Vision-Language Model for OCSR that uses graph traversal chain-of-thought reasoning and a two-stage SFT plus GRPO training scheme to handle both printed molecules (including chemical abbreviations like Ph and Et) and hand-drawn structures, achieving strong performance on the new MolRec-Bench benchmark.
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.
Proposes the ‘Optical Chemical Structure Understanding’ (OCSU) task to translate molecular images into multi-level descriptions (motifs, IUPAC, SMILES). Introduces the Vis-CheBI20 dataset and two paradigms: DoubleCheck (OCSR-based) and Mol-VL (OCSR-free).
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.