Research map / Time series / Causal and generative time series
Neural Pharmacodynamic State Space Modeling
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 pharmacodynamic mechanism functions with attention over mechanisms | SSM PK-PD · Synthetic, training size 100 | NELBO: 55.34 +/- .03 vs 58.57 +/- .06 | Helped |
| Use pharmacodynamic mechanism functions with attention over mechanisms | SSM PK-PD · Synthetic, training size 1000 | NELBO: 39.84 +/- .02 vs 44.75 +/- .02 | Helped |
| Use pharmacodynamic mechanism functions with attention over mechanisms | SSM PK-PD · ML-MMRF | NELBO: 61.54 vs 73.44 | Helped |
| Replace Neural Treatment Exponential with another g1 instance (ablation) | SSM PK-PD · Synthetic, training size 100 | NELBO: 55.34 +/- .03 -> 58.39 +/- .05 | No clear effect |
| Replace Neural Treatment Exponential with another g1 instance (ablation) | SSM PK-PD · Synthetic, training size 1000 | NELBO: 39.84 +/- .02 -> 38.93 +/- .01 | Helped |
| Remove the local clock (ablation) | SSM PK-PD · Synthetic | treatment-response dynamics | Hurt |
| Replace mechanism functions with learned MLP experts | SSM MOE · ML-MMRF | NELBO: 61.54 vs 73.44 | Hurt |
| Increase SSM Linear model size to match SSM PK-PD | SSM Linear · ML-MMRF | held-out likelihood | No clear effect |
Closest papers by meaning
- Attentive State-Space Modeling of Disease Progression (NeurIPS 2019 · similarity 0.89)
- Learning Patient-Specific Disease Dynamics With Latent Flow Matching For Longitudinal Imaging Generation (ICLR 2026 · similarity 0.86)
- Temporal Phenotyping using Deep Predictive Clustering of Disease Progression (ICML 2020 · similarity 0.85)
- Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models (NeurIPS 2024 · similarity 0.84)
- Improving the Generation and Evaluation of Synthetic Data for Downstream Medical Causal Inference (NeurIPS 2025 · similarity 0.83)
- A scalable generative model for dynamical system reconstruction from neuroimaging data (NeurIPS 2024 · similarity 0.82)
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.