Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.07173 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914311938506752 |
|---|---|
| author | Jian, Tong Dai, Tianyu Yu, Tao |
| author_facet | Jian, Tong Dai, Tianyu Yu, Tao |
| contents | LLMs have shown strong in-context learning (ICL) abilities, but have not yet been extended to signal processing systems. Inspired by their design, we have proposed for the first time ICL using transformer models applicable to motor feedforward control, a critical task where classical PI and physics-based methods struggle with nonlinearities and complex load conditions. We propose a transformer based model architecture that separates signal representation from system behavior, enabling both few-shot finetuning and one-shot ICL. Pretrained on a large corpus of synthetic linear and nonlinear systems, the model learns to generalize to unseen system dynamics of real-world motors only with a handful of examples. In experiments, our approach generalizes across multiple motor load configurations, transforms untuned examples into accurate feedforward predictions, and outperforms PI controllers and physics-based feedforward baselines. These results demonstrate that ICL can bridge synthetic pretraining and real-world adaptability, opening new directions for data efficient control of physical systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07173 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Nonlinear Systems In-Context: From Synthetic Data to Real-World Motor Control Jian, Tong Dai, Tianyu Yu, Tao Machine Learning Systems and Control LLMs have shown strong in-context learning (ICL) abilities, but have not yet been extended to signal processing systems. Inspired by their design, we have proposed for the first time ICL using transformer models applicable to motor feedforward control, a critical task where classical PI and physics-based methods struggle with nonlinearities and complex load conditions. We propose a transformer based model architecture that separates signal representation from system behavior, enabling both few-shot finetuning and one-shot ICL. Pretrained on a large corpus of synthetic linear and nonlinear systems, the model learns to generalize to unseen system dynamics of real-world motors only with a handful of examples. In experiments, our approach generalizes across multiple motor load configurations, transforms untuned examples into accurate feedforward predictions, and outperforms PI controllers and physics-based feedforward baselines. These results demonstrate that ICL can bridge synthetic pretraining and real-world adaptability, opening new directions for data efficient control of physical systems. |
| title | Learning Nonlinear Systems In-Context: From Synthetic Data to Real-World Motor Control |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2602.07173 |