Research map / Probabilistic and scientific modeling / Differential equations and PDEs
ODE-RSSM: Learning Stochastic Recurrent State Space Model from Irregularly Sampled Data
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 |
|---|---|---|---|
| Add latent overshooting to ODE-RSSM (ablation) | ODE-RSSM · Winding | RRSE: 0.5389 -> 0.4768; 0.4444 -> 0.4045 | Helped |
| Add latent overshooting to ODE-RSSM (ablation) | ODE-RSSM · Thickening | RRSE: 1.5349 -> 1.3678; 1.4174 -> 1.3064 | Mixed |
| Use ODE-RSSM-O instead of ODE-RSSM (ablation) | CSTR 25% uneven · CSTR | RRSE: 0.2979 -> 0.2807 | Hurt |
| Use ODE-RSSM-O instead of ODE-RSSM (ablation) | CSTR 50% uneven · CSTR | RRSE: 0.1486 -> 0.1336 | Helped |
| Use ODE-RSSM-O instead of ODE-RSSM (ablation) | Thickening 25% uneven · Thickening | RMSE: 0.0558 -> 0.0504 | Helped |
| Model latent-state evolution with a continuous-time ODE-Net rather than discrete-time RSSM transitions | ODE-RSSM-O · Winding 25% uneven | RRSE: 0.5667 -> 0.4768 | Helped |
| Model latent-state evolution with a continuous-time ODE-Net rather than discrete-time RSSM transitions | ODE-RSSM-O · Thickening 25% uneven | RRSE: 1.619 -> 1.3678 | Helped |
| Train with different sampling ratios and evaluate on a 25% uneven test set | ODE-RSSM · Winding | RRSE: 0.4934 (0); 0.5754 (0.1545) | Mixed |
| Use the parallel reparameterized solver rather than solving over the union of time points | Batched ODE solving · Batched ODEs | time consumption | Helped |
Closest papers by meaning
- Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction (NeurIPS 2026 · similarity 0.86)
- ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow (NeurIPS 2026 · similarity 0.86)
- Learning long range dependencies through time reversal symmetry breaking (NeurIPS 2025 · similarity 0.86)
- LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models (NeurIPS 2026 · similarity 0.86)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.86)
- Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs (ICLR 2025 · 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.