Research map / Probabilistic and scientific modeling / Dynamical systems
Euler–Poincaré Neural Dynamics: A Geometric-Mechanics Framework for Scientific Simulation
Sungwoo Park, Jongwon Lee, Jiwoong Kim
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 |
|---|---|---|---|
| use Lie-group Euler-Poincare flow instead of Koopman operator Koopa | surrogate model · Villin | Best MSE: 2.32×10−2 -> 5.56×10−3 | Improved |
| use EPND instead of GeoTDM | surrogate model · Villin | Cα-RMSD: 1.32×100 -> 5.09×10−1 | Improved |
| use EPND instead of Koopa | surrogate model · TRP-CAGE | Best MSE: 4.75×10−2 -> 7.60×10−3 | Improved |
| use EPND instead of KooNPro | surrogate model · TRP-CAGE | Cα-RMSD: 2.81×100 -> 2.91×100 | No clear effect |
| use EPND instead of KoVAE | surrogate model · Mg2+ hydration | Best MSE: 3.61×10−2 -> 3.03×10−2 | Improved |
| use EPND instead of KoVAE | surrogate model · Mg2+ hydration | Delta(Mg-O): 1.09×10−1 -> 9.28×10−2 | Improved |
| use Euler-Poincare prefix scan instead of Koopman baselines for inference | EPND · Villin | inference time (s): 3.74×10−2 -> 2.61×10−2 | Improved |
| use EPND instead of KoNODE | surrogate model · Mg2+ hydration | inference time (s): 5.77×10−1 -> 1.59×10−2 | Improved |
| use prefix scan for training instead of Koopman baselines | EPND · Villin | training time (s): 7.76×10−1 -> 5.33×10−2 | Improved |
| extend rollout to 10^5 steps | EPND · Villin | Best MSE: 5.56×10−3 -> 4.63×10−2 | Mixed |
Closest papers by meaning
- A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics (ICLR 2025 · similarity 0.87)
- Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators (NeurIPS 2024 · similarity 0.86)
- DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction (ICML 2025 · similarity 0.86)
- Equivariant Graph Neural Operator for Modeling 3D Dynamics (ICML 2024 · similarity 0.85)
- Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure (AAAI 2025 · similarity 0.85)
- Stable Long-Horizon PDE Forecasting via Latent Structured Spectral Propagators (NeurIPS 2026 · 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.
