Research map / Probabilistic and scientific modeling / Dynamical systems
Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics
Mathias Schreiner, Ole Winther, Simon Olsson
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 |
|---|---|---|---|
| train with stochastic lag (DisExp(1000)) instead of fixed lag 10 (ablation) | MB-ITO · Muller-Brown, lag 10 | VAMP2 score gap: -0.0351 ($5$) -> {\bf -0.0312} | Improved |
| train with stochastic lag (DisExp(1000)) instead of fixed lag 100 (ablation) | MB-ITO · Muller-Brown, lag 100 | VAMP2 score gap: -0.1189 ($2$) -> {\bf -0.0970} | Improved |
| train with stochastic lag instead of fixed lag (ablation) | SE3-ITO · Alanine dipeptide | VAMP2 gap over epochs | No clear effect |
| compare CG-SE3-ITO against all-atom MD on Chignolin folding free energy | CG-SE3-ITO · Chignolin | dG_fold/kT: -1.28(1) -> -0.64(33) | Mixed |
| compare CG-SE3-ITO against all-atom MD on Trp-Cage folding free energy | CG-SE3-ITO · Trp-Cage | dG_fold/kT: 1.47(6) -> 2.84(6) | Mixed |
| compare CG-SE3-ITO against all-atom MD on Trp-Cage folding MFPT | CG-SE3-ITO · Trp-Cage | MFPT folding (us): 13.6(4) -> 37(2) | Mixed |
| compare CG-SE3-ITO against all-atom MD on BBA unfolding MFPT | CG-SE3-ITO · BBA | MFPT unfolding (us): 5.1(1) -> 1.75(4) | Mixed |
| compare CG-SE3-ITO against all-atom MD on Villin folding free energy | CG-SE3-ITO · Villin | dG_fold/kT: 1.21(2) -> 2.22(3) | Mixed |
| compare CG-SE3-ITO against all-atom MD on Chignolin unfolding MFPT | CG-SE3-ITO · Chignolin | MFPT unfolding (us): 2.01(2) -> 2.12(34) | No clear effect |
Closest papers by meaning
- Langevin-Informed Transfer Learning: Replacing the Target Samples by Black-Box Feedback (NeurIPS 2026 · similarity 0.88)
- From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach (NeurIPS 2024 · similarity 0.87)
- Generative Modeling of Molecular Dynamics Trajectories (NeurIPS 2024 · similarity 0.87)
- FlashMD: long-stride, universal prediction of molecular dynamics (NeurIPS 2025 · similarity 0.87)
- Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models (NeurIPS 2025 · similarity 0.87)
- Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials (NeurIPS 2026 · 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.
