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
Scientific machine learning (neural PDE solvers, operator learning, equation discovery)
Scientific ML builds learned surrogates and solvers for physical systems: neural operators and PDE foundation models trained on simulation data, physics-informed networks trained on the governing-equation residual, differentiable simulators used inside training loops, and symbolic regression that recovers closed-form laws. Results are evaluated against trusted numerical solvers (relative L2 / nRMSE, rollout stability, conservation errors) and judged on the accuracy-versus-cost trade-off relative to a classical solver at matched resolution.