Research map / Time series / Causal and generative time series
Multi-Step Time Series Generator for Molecular Dynamics
Katsuhiro Endo, Katsufumi Tomobe, Kenji Yasuoka
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 |
|---|---|---|---|
| evolve a dense low-dimensional latent variable z instead of the raw feature sequence (latent variable model) (ablation) | MD-GAN · Harmonic oscillator with noise, 128 to 1024 steps | MSE of normalized spectra: 79 times better than naive model | Improved |
| use MD-GAN instead of C-RNN-GAN | time series generator · Harmonic oscillator with noise | MSE of normalized spectra: 104 times better | Improved |
| use MD-GAN instead of GROMACS MD to get averaged MSD for 40 ns | polymer melts MSD · Polymer melts | computation time: 55.2 days -> 2.83 days | Improved |
| increase training data size (ablation) | MD-GAN · Water vibrational spectra | libration peak noise | Improved |
| use U-net based generator instead of deconvolution-only network (ablation) | MD-GAN generator G_Y · MD time series generation | accuracy | Improved |
Closest papers by meaning
- Generative Modeling of Molecular Dynamics Trajectories (NeurIPS 2024 · similarity 0.87)
- Deep Generative Markov State Models (NeurIPS 2018 · similarity 0.86)
- Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation (AAAI 2024 · similarity 0.83)
- FlashMD: long-stride, universal prediction of molecular dynamics (NeurIPS 2025 · similarity 0.83)
- Equivariant Neural Diffusion for Molecule Generation (NeurIPS 2024 · similarity 0.83)
- Wasserstein Convergence of Critically Damped Langevin Diffusions (NeurIPS 2025 · 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.
