DynaMix
(accepted NeurIPS 2025 paper)
DynaMix is a foundation model for zero-shot inference of dynamical systems that preserves long-term statistics. Unlike traditional approaches that require retraining for each new system, DynaMix provides context driven generalization to unseen dynamical systems.
- Accurate Zero-Shot Dynamical Systems Reconstruction: DynaMix generalizes across diverse dynamical systems without fine-tuning, accurately capturing attractor geometry and long-term statistics.
- Context Felxible Dynamics Modeling: The multivariate architecture captures dependencies across system dimensions and adapts to different dimensionalities and context lengths.
- Efficient and Lightweight: Designed to be efficient with a few thousand parameters, DynaMix can also run on CPU for inference, and is enabling orders-of-magnitude faster inference than traditional foundation models.
- General Time Series Forecasting: Extends beyond DSR to general time series forecasting using adaptable embedding techniques.
For complete documentation and code, visit the DynaMix repository.
Model Description
DynaMix is based on a mixture of experts (MoE) architecture operating in latent space:
Expert Networks: Each expert is a specialized dynamical model, given trhough RNN based architectures
Gating Network: Selects experts based on the provided context and current latent representation of the dynamics
By aggregating the expert weighting with the expert prediction the next state is predicted.
Usage
To load the model in python using the corresponding codebase DynaMix repository, use:
from src.utilities.utilities import load_hf_model
# Initialize model with architecture
model = load_hf_model(model_name="dynamix-3d-alrnn-v1.0")
Given context data from the target system with shape (T_C, S, N) (where T_C is the context length, S the number of sequences that should get processed and N the data dimensionality), generate forecasts by passing the data through the DynaMixForecaster along with the loaded model. Further details can be found in the GitHub repository DynaMix repository.
Citation
If you use DynaMix in your research, please cite our paper:
@misc{hemmer2025truezeroshotinferencedynamical,
title={True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics},
author={Christoph Jürgen Hemmer and Daniel Durstewitz},
year={2025},
eprint={2505.13192},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2505.13192},
}