Research map / Probabilistic and scientific modeling / Dynamical systems
Modulated Neural ODEs
Ilze Amanda Auzina, Cagatay Yildiz, Sara Magliacane, Matthias Bethge, Efstratios Gavves
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 dynamics and static modulator framework | NODE · Sinusoidal T=150 | test MSE: 1.84 -> 0.29 | Improved |
| Add modulator framework | SONODE · Predator-prey T=300 | test MSE: 40.92 -> 6.70 | Improved |
| Add modulator framework | HBNODE · Predator-prey T=300 | test MSE: 3346.62 -> 10.21 | Improved |
| Add modulator framework | HBNODE · Predator-prey T=100 | test MSE: 0.88 -> 0.94 | Hurt |
| Add modulator framework | NODE · Bouncing Ball | test MSE: 0.0199 -> 0.0164 | Improved |
| Add modulator framework | LSONODE · Bouncing Ball | test MSE: 0.0181 -> 0.014 | Improved |
| Add modulator framework | NODE · Mocap | test MSE: 72.2 -> 57.7 | Improved |
| Add modulator framework | NODE · Mocap-shift | test MSE: 61.6 -> 58.0 | Improved |
| Use dynamics modulator as regression input for factors of variation | NODE · Predator-prey | R2: -1.35 -> 0.39 | Improved |
| Replace autoregressive encoder with RNN encoder and sweep N_incr 1,3,5,10 (ablation) | HBNODE · Sine validation | validation MSE: 0.164 -> 0.066 | Improved |
| Change ODE solver from euler to rk4 or dopri5 (ablation) | MoNODE · Sinusoidal T=50 | test MSE: 0.07 -> 0.04 | Mixed |
| Latent dimensionality for NODE vs MoNODE on Rot.MNIST at T=45 (ablation) | MoNODE · Rot.MNIST | test MSE: 0.098 -> 0.034 | Improved |
Closest papers by meaning
- KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis (ICML 2025 · similarity 0.88)
- ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence (NeurIPS 2024 · similarity 0.88)
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective (ICML 2024 · similarity 0.87)
- From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems (ICML 2024 · similarity 0.87)
- Simulation-Free Training of Neural ODEs on Paired Data (NeurIPS 2024 · similarity 0.87)
- Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach (AAAI 2024 · similarity 0.87)
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.
