MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
arXiv preprint arXiv:2502.09692 , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 10representative citing papers
TNOs lift neural operators to topological cell complexes via Discrete Exterior Calculus for cross-dimensional coupling, subsuming prior NOs and showing accuracy gains on PDE benchmarks with irregular geometries.
GeoABC is a geometry-conditioned anisotropic boundary correction method that reduces near-boundary L2 error by ~38% in neural operator-based simulations of 2D airfoils and 3D cars.
Releases first open high-fidelity CFD dataset of 1800 samples from 180 variants of NASA high-lift CRM at 10 angles of attack using GPU-accelerated wall-modeled LES.
A graph-based neural operator trained on expert-validated race-car CFD data reaches accuracy levels usable for early-stage interactive aerodynamic design exploration.
Scale-autoregressive modeling (SAR) samples fluid flow distributions hierarchically from coarse to fine resolutions on meshes, achieving lower distributional error and 2-7x faster runtime than diffusion or flow-matching baselines.
Self-attention mechanisms are used to build mesh-preserving neural surrogates that approximate PFEM dynamics for free-surface flows, delivering accurate transient predictions and improved scalability on 2D and 3D benchmarks.
ShardTensor is a domain-parallelism system for SciML that enables flexible scaling of extreme-resolution spatial datasets by removing the constraint of batch size one per device.
Neural surrogates systematically under-resolve high-frequency content in multiscale PDEs due to spectral bias and irreversible coarse-graining losses, with success confined to low-dimensional manifolds and weather prediction as a non-generalizable case.
RETO achieves relative L2 errors of 0.063 on ShapeNet and 0.089/0.097 on DrivAerML surface pressure/velocity, outperforming Transolver and other baselines.
citing papers explorer
-
HiLiftAeroML: High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics
Releases first open high-fidelity CFD dataset of 1800 samples from 180 variants of NASA high-lift CRM at 10 angles of attack using GPU-accelerated wall-modeled LES.