arXiv：cs.LG· Xiang Zhang, Varchas Gopalaswamy, Rahman Ejaz, Riccardo Betti, Dongfang Liu·· 4 小时前AI 评分36
ICF-DLM：分解引导的扩散语言模型用于惯性约束聚变预测
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
AI 导读
研究者提出 ICF-DLM，据称是首个基于语言模型的惯性约束聚变（ICF）预测器，可从激光脉冲与靶设计参数直接推断 512 步中子产率波形。在 ICFBench（5 万次模拟 + 232 次实验打靶）上，其峰值时间误差从匹配的自回归 LLaMA-3-8B 的 11.6 步降至 9.2 步，并优于经典序列模型和基于 LLM 的时间序列预测器。
正文
Abstract:Inertial confinement fusion (ICF) is a leading pathway toward clean energy, but each shot at the National Ignition Facility costs on the order of one million dollars, making accurate AI surrogates a high-value target. We study exogenous-driven ICF waveform prediction, where a 512-step neutron-rate diagnostic must be inferred directly from a laser pulse and target design parameters, with no historical response observed. The regime stresses standard time-series predictors with temporal sparsity (picosecond peak in a nanosecond window), input-output scale mismatch (under 300 real shots), and peak sensitivity (picosecond timing). We propose ICF-DLM, to our knowledge the first LM-based ICF predictor, combining (i) a physics-typed decomposition into yield $Y_{DT}$, peak timing $t_{\mathrm{peak}}$, and local waveform $w_{\mathrm{local}}$; (ii) bidirectional denoising that defers commitment to peak location; and (iii) a physics-driven PPO reward re-injecting metric structure across numeric tokens. On ICFBench (50K simulations + 232 experimental shots), ICF-DLM cuts peak-timing error from 11.6 to 9.2 steps over a matched autoregressive LLaMA-3-8B and outperforms classical sequence models and LLM-based time-series predictors. Beyond ICF, the recipe shows potential to address science domains with low data and sparse events.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2609.07756 [cs.LG] |
| (or arXiv:2609.07756v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.07756 arXiv-issued DOI via DataCite |
Submission history
From: Xiang Zhang [view email]
[v1]
Mon, 7 Sep 2026 17:00:02 UTC (817 KB)
[v2]
Wed, 7 Oct 2026 01:45:22 UTC (828 KB)
来源：arXiv：cs.LG · arxiv.org