Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that Generalize
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use a vector potential to represent velocity rather than predict velocity directly (ablation) | a-Net versus v-Net · 100x100 benchmark, μ=0.1, ρ=4, dt=4 | L_d: 8.66e-7 -> 5.44e-7 | Helped |
| Use a vector potential to represent velocity rather than predict velocity directly (ablation) | a-Net versus v-Net · 100x100 benchmark, μ=0.1, ρ=4, dt=4 | L_p: 4.87e-5 -> 1.56e-5 | Helped |
| Use a vector potential to represent velocity rather than predict velocity directly (ablation) | a-Net versus v-Net · 100x100 benchmark, μ=0.1, ρ=4, dt=4 | CPU [TPS]: 82 -> 82 | No clear effect |
| Use a vector potential to represent velocity rather than predict velocity directly (ablation) | a-Net versus v-Net · 100x100 benchmark, μ=0.1, ρ=4, dt=4 | GPU [TPS]: 311 -> 311 | No clear effect |
| Stop resetting old training environments, removing periodic cold starts (ablation) | a-Net training · validation during training | validation loss stability | Hurt |
| Stop resetting old training environments, removing periodic cold starts (ablation) | a-Net training · cold-start simulation | cold-start convergence | Hurt |
Closest papers by meaning
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS simulations of Turbulent Flows (NeurIPS 2026 · similarity 0.87)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024 · similarity 0.87)
- Space and time continuous physics simulation from partial observations (ICLR 2024 · similarity 0.87)
- MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation (ICML 2025 · similarity 0.87)
- Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics (ICLR 2024 · similarity 0.87)
- HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction (ICML 2024 · similarity 0.86)
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.