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.
Subfield
Physics-informed neural networks and physics-based losses
Benchmarks: PINNacle, PINN failure-mode problems, PDEBench (PINN track), Expert's guide PINN suite. Datasets: Raissi PINN reference data, PINNacle reference solutions. Baselines: PINN, Learning-rate annealing, NTK loss weighting, Self-adaptive PINN and others.