OpenFusion

Workshops

• [2026-01-09] 智聚未来：AI 与核聚变交叉创新研讨会 [公众号信息]

🎯 Video Tutorials:

• JT-60SA, a step closer to fusion energy [Youtube]

• MIT’s Tiny Fusion Reactor Could Beat ITER [Youtube]

• Nuclear Fusion Breaks Multiple Records 2026.02 [Youtube] Nuclear fusion is the energy source of the future. But after decades of waiting for progress, people are understandably growing more and more skeptical that our fusion-powered future is actually on its way. Recently, though, the headlines have been filled with stories of fusion companies across the globe breaking different milestones. Is this real progress or just more hype? Let’s take a look.

🎯 q-distribution Prediction

• Wang, Shiao, et al. "Multi-modal fusion based q-distribution prediction for controlled nuclear fusion." International Conference on Brain Inspired Cognitive Systems. Singapore: Springer Nature Singapore, 2024. [Paper]

• Ma, Qingchuan, et al. "Exploiting memory-aware q-distribution prediction for nuclear fusion via modern hopfield network." International Conference on Brain Inspired Cognitive Systems. Singapore: Springer Nature Singapore, 2024. [Paper]

🎯 Foundation Models (1D, LLM, VLM) for Fusion

• XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion, Xiao Wang, Qingquan Yang, Fuling Wang, Qiang Chen, Wentao Wu, Yu Jin, Jingtao Jiang, Liye Jin, Bo Jiang, Dengdi Sun, Wanli Lv, Meiwen Chen, Zehua Chen, Guosheng Xu, Jin Tang arXiv Pre-print arXiv:2502.05615 [Paper]

xihefusion_720P_github.mp4

🎯 AI4Fusion Survey

🎯 Fusion_2D_Inversion

🎯 Time_Series_Analysis

• HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis, Xiao Wang, Hao Si, Fan Zhang, Xiaoya Zhou, Dengdi Sun, Wanli Lyu, Qingquan Yang, Jin Tang, arXiv:2508.02411 [Paper] [github.com/Event-AHU/Time_Series_Analysis]

🎯 PINNs and PDE

• Revisiting Heat Flux Analysis of Tungsten Monoblock Divertor on EAST using Physics-Informed Neural Network, Xiao Wang, Zikang Yan, Hao Si, Zhendong Yang*, Qingquan Yang*, Dengdi Sun, Wanli Lyu, Jin Tang [Paper]

• [CVPR-2026] NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training, Dengdi Sun, Xiaoya Zhou, Xiao Wang, Hao Si, Wanli Lyu, Jin Tang, Bin Luo [Paper]

• [arXiv:2603.10466] UniPINNs: Unified Physical-informed Neural Network, Dengdi Sun, Jie Chen, Xiao Wang*, Jin Tang [Paper]

🎯 Citations

If you find this GitHub repository helpful for your research, please cite the following papers and give us a star. Thanks! If you have any questions about our work, please leave an issue.

@article{sun2026NESTOR,
  title={NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training},
  author={Sun, Dengdi and Zhou, Xiaoya and Wang, Xiao and Si, Hao and Lyu, Wanli and Tang, Jin and Luo, Bin},
  journal={arXiv preprint arXiv:2602.22059},
  year={2026}
}

@article{wang2025revisiting,
  title={Revisiting Heat Flux Analysis of Tungsten Monoblock Divertor on EAST using Physics-Informed Neural Network},
  author={Wang, Xiao and Yan, Zikang and Si, Hao and Yang, Zhendong and Yang, Qingquan and Sun, Dengdi and Lyu, Wanli and Tang, Jin},
  journal={arXiv preprint arXiv:2508.03776},
  year={2025}
}

@article{wang2025HGTSFormer,
  title={HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis},
  author={Wang, Xiao and Si, Hao and Zhang, Fan and Zhou, Xiaoya and Sun, Dengdi and Lyu, Wanli and Yang, Qingquan and Tang, Jin},
  journal={arXiv preprint arXiv:2508.02411},
  year={2025}
}

@article{wang2025xihefusion,
  title={Xihefusion: Harnessing large language models for science communication in nuclear fusion},
  author={Wang, Xiao and Yang, Qingquan and Wang, Fuling and Chen, Qiang and Wu, Wentao and Jin, Yu and Jiang, Jingtao and Jin, Liye and Jiang, Bo and Sun, Dengdi and others},
  journal={arXiv preprint arXiv:2502.05615},
  year={2025}
}

@inproceedings{ma2024exploiting,
  title={Exploiting memory-aware q-distribution prediction for nuclear fusion via modern hopfield network},
  author={Ma, Qingchuan and Wang, Shiao and Zheng, Tong and Dai, Xiaodong and Wang, Yifeng and Yang, Qingquan and Wang, Xiao},
  booktitle={International Conference on Brain Inspired Cognitive Systems},
  pages={104--114},
  year={2024},
  organization={Springer}
}

@inproceedings{wang2024multi,
  title={Multi-modal fusion based q-distribution prediction for controlled nuclear fusion},
  author={Wang, Shiao and Wang, Yifeng and Ma, Qingchuan and Wang, Xiao and Yan, Ning and Yang, Qingquan and Xu, Guosheng and Tang, Jin},
  booktitle={International Conference on Brain Inspired Cognitive Systems},
  pages={115--125},
  year={2024},
  organization={Springer}
}