Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908489944662016 |
|---|---|
| author | Ulmen, Jonas Sundaram, Ganesh Görges, Daniel |
| author_facet | Ulmen, Jonas Sundaram, Ganesh Görges, Daniel |
| contents | With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for creating world models using continuous-time dynamic systems from arbitrary observation data. The proposed method integrates sequence embeddings with neural ordinary differential equations (neural ODEs). It employs loss functions that enforce contractive embeddings and Lipschitz constants in state transitions to construct a well-organized latent state space. The approach's effectiveness is demonstrated through the generation of structured latent state-space models for a simple pendulum system using only image data. This opens up a new technique for developing more general control algorithms and estimation techniques with broad applications in robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10489 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures Ulmen, Jonas Sundaram, Ganesh Görges, Daniel Machine Learning With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for creating world models using continuous-time dynamic systems from arbitrary observation data. The proposed method integrates sequence embeddings with neural ordinary differential equations (neural ODEs). It employs loss functions that enforce contractive embeddings and Lipschitz constants in state transitions to construct a well-organized latent state space. The approach's effectiveness is demonstrated through the generation of structured latent state-space models for a simple pendulum system using only image data. This opens up a new technique for developing more general control algorithms and estimation techniques with broad applications in robotics. |
| title | Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.10489 |