TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910024434974720 |
|---|---|
| author | Boschi, Tobia Loreti, Andrea Amorisco, Nicola C. Ordonez-Hurtado, Rodrigo H. Rousseau, Cécile Holt, George K. Székely, Eszter Whittle, Alexander Jackson, Samuel Agnello, Adriano Pamela, Stanislas Pascale, Alessandra Akers, Robert Moreno, Juan Bernabe Alexandrov, Vassil Zayats, Mykhaylo |
| author_facet | Boschi, Tobia Loreti, Andrea Amorisco, Nicola C. Ordonez-Hurtado, Rodrigo H. Rousseau, Cécile Holt, George K. Székely, Eszter Whittle, Alexander Jackson, Samuel Agnello, Adriano Pamela, Stanislas Pascale, Alessandra Akers, Robert Moreno, Juan Bernabe Alexandrov, Vassil Zayats, Mykhaylo |
| contents | We present TokaMind, an open-source foundation model framework for fusion plasma modeling, based on a Multi-Modal Transformer (MMT) and trained on heterogeneous tokamak diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model components. To represent multi-modal signals, we use a training-free Discrete Cosine Transform embedding (DCT3D) and provide a clean interface for alternative embeddings (e.g., Variational Autoencoders - VAEs). We evaluate TokaMind on the recently introduced MAST benchmark TokaMark, comparing training and embedding strategies. Our results show that fine-tuned TokaMind outperforms the benchmark baseline on all but one task, and that, for several tasks, lightweight fine-tuning yields better performance than training the same architecture from scratch under a matched epoch budget. These findings highlight the benefits of multi-modal pretraining for tokamak plasma dynamics and provide a practical, extensible foundation for future fusion modeling tasks. Training code and model weights will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15084 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics Boschi, Tobia Loreti, Andrea Amorisco, Nicola C. Ordonez-Hurtado, Rodrigo H. Rousseau, Cécile Holt, George K. Székely, Eszter Whittle, Alexander Jackson, Samuel Agnello, Adriano Pamela, Stanislas Pascale, Alessandra Akers, Robert Moreno, Juan Bernabe Alexandrov, Vassil Zayats, Mykhaylo Plasma Physics Artificial Intelligence Machine Learning We present TokaMind, an open-source foundation model framework for fusion plasma modeling, based on a Multi-Modal Transformer (MMT) and trained on heterogeneous tokamak diagnostics from the publicly available MAST dataset. TokaMind supports multiple data modalities (time-series, 2D profiles, and videos) with different sampling rates, robust missing-signal handling, and efficient task adaptation via selectively loading and freezing four model components. To represent multi-modal signals, we use a training-free Discrete Cosine Transform embedding (DCT3D) and provide a clean interface for alternative embeddings (e.g., Variational Autoencoders - VAEs). We evaluate TokaMind on the recently introduced MAST benchmark TokaMark, comparing training and embedding strategies. Our results show that fine-tuned TokaMind outperforms the benchmark baseline on all but one task, and that, for several tasks, lightweight fine-tuning yields better performance than training the same architecture from scratch under a matched epoch budget. These findings highlight the benefits of multi-modal pretraining for tokamak plasma dynamics and provide a practical, extensible foundation for future fusion modeling tasks. Training code and model weights will be made publicly available. |
| title | TokaMind: A Multi-Modal Transformer Foundation Model for Tokamak Plasma Dynamics |
| topic | Plasma Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.15084 |