Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Machine learning for chemistry and materials science
Chemistry and materials ML predicts molecular and crystal properties, replaces quantum-mechanical calculations with learned interatomic potentials, screens and generates new materials and molecules, and plans chemical synthesis. Evaluation uses reference quantum-chemistry or experimental labels with fixed community splits (QM9, MD17, Matbench, Matbench Discovery, OC20, USPTO-50K, GuacaMol / PMO); beyond held-out error, the field increasingly demands task-level checks such as stable molecular dynamics, discovery hit rate, and oracle-budgeted optimisation.