Research map / Probabilistic and scientific modeling / Differential equations and PDEs
FCMO: A Flow-Curv Mamba Operator for Large-Scale 3D Vehicle Aerodynamics
Yuchen Xie, Yufeng Xie, Hanyu He, Yue Huang, Lijuan Sun, Hengyi Ren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add flow-aware Mamba processor (ablation) | FCMO · Ahmed-Body | surface pressure L2 error: 0.1045 -> 0.0718 | Improved |
| add feature-aware sequentialization (ablation) | FCMO · Ahmed-Body | surface pressure L2 error: 0.0912 -> 0.0718 | Improved |
| add dual-scale position encoding (ablation) | FCMO · Ahmed-Body | surface pressure L2 error: 0.0856 -> 0.0718 | Improved |
| add FlowCurv sampling (ablation) | FCMO · Ahmed-Body | surface pressure L2 error: 0.0834 -> 0.0718 | Improved |
| add adaptive k-NN (ablation) | FCMO · Ahmed-Body | surface pressure L2 error: 0.0789 -> 0.0718 | Improved |
| add physics constraints (ablation) | FCMO · Ahmed-Body | surface pressure L2 error: 0.0751 -> 0.0718 | Improved |
| add flow-aware Mamba processor (ablation) | FCMO · DrivAerNet (500/50 subset) | surface pressure L2 error: 0.1834 -> 0.1445 | Improved |
| use FCMO instead of AeroGTO | FCMO · Ahmed-Body | surface pressure L2 error: 0.0757 -> 0.0718 | Improved |
| use FCMO instead of AeroGTO | FCMO · FLOPs | GFLOPs: 175.3 -> 158.7 | Improved |
| use FCMO instead of AeroGTO | FCMO · DrivAerNet++ OOD Reynolds | drag coefficient MRE: 0.1267 -> 0.0634 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Transolver — Transolver: A Fast Transformer Solver for PDEs on General Geometries (ICML 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AeroGTO: An Efficient Graph-Transformer Operator for Learning Large-Scale Aerodynamics of 3D Vehicle Geometries (AAAI 2025 · similarity 0.91)
- DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization (NeurIPS 2025 · similarity 0.87)
- DragSolver: A Multi-Scale Transformer for Real-World Automotive Drag Coefficient Estimation (ICML 2025 · similarity 0.86)
- AutoHood3D: A Multi‑Modal Benchmark for Automotive Hood Design and Fluid–Structure Interaction (NeurIPS 2025 · similarity 0.86)
- Aerodynamic Coefficients Prediction via Cross-Attention Fusion and Physical-Informed Training (AAAI 2025 · similarity 0.86)
- WindsorML: High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
