arXiv：cs.LG· Peter Steiner, Azarakhsh Jalalvand, Nathaniel Chen, Kouroche Bouchiat, Ricardo Shousha, SangKyeun Kim, Egemen Kolemen·· 3 小时前AI 评分43
IGNITE：面向核聚变等离子体的生成式世界模型架构
IGNITE Tokamak World Model Architecture
AI 导读
IGNITE 是一个面向聚变等离子体行为的生成式世界基础模型，基于 DIII-D 国家聚变设施十余年无标注实验数据以自监督方式训练。其核心动力学模型可由执行器轨迹模拟 DIII-D 放电，轨迹可手动给定，也可由文本提示词或目标实验结果即时生成。模型由多个时空 tokenizer 嵌入时间序列、图像序列与高分辨率频谱图，主干为自回归动力学模型，理论上可在无限时间跨度上预测完整放电过程。
正文
Abstract:We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade of unlabeled experimental data at the DIII-D National Fusion Facility. The core of IGNITE is a dynamics model that can simulate DIII-D discharges from a given set of actuator trajectories. These trajectories can be supplied or generated on-the-fly from a textual prompt or from desired experimental outcomes. The model architecture consists of several spatio-temporal tokenizers that embed the different input modalities, including time-series like spatio-temporal measurement data, image sequences, and high-resolution spectrograms, each of which collected at vastly different time scales. The backbone is composed of an auto-regressive dynamics model that has the capacity to predict entire DIII-D discharges given initial latent plasma states and actuator trajectories over a theoretical infinite horizon. IGNITE paves the way towards efficient AI-driven experimental planning and world modeling for nuclear fusion.
| Subjects: | Plasma Physics (physics.plasm-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02515 [physics.plasm-ph] |
| (or arXiv:2610.02515v1 [physics.plasm-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02515 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Peter Steiner [view email]
[v1]
Thu, 1 Oct 2026 21:37:44 UTC (7,809 KB)
来源：arXiv：cs.LG · arxiv.org