Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
ICF-DLM, the first language-model-based inertial confinement fusion predictor, cuts peak-timing error from 11.6 to 9.2 steps versus LLaMA-3-8B.
Each National Ignition Facility shot costs roughly one million dollars, motivating accurate AI surrogates for predicting 512-step neutron-rate waveforms from laser pulses and target parameters. ICF-DLM combines physics-typed decomposition into yield, peak timing, and local waveform; bidirectional denoising that defers commitment to peak location; and a physics-driven PPO reward. On ICFBench (50,000 simulations plus 232 experimental shots) it outperforms a matched autoregressive LLaMA-3-8B, classical sequence models, and LLM-based time-series predictors.
- First language-model-based predictor for inertial confinement fusion waveforms
- Combines physics-typed decomposition, bidirectional denoising, and physics-driven PPO reward
- Evaluated on ICFBench with 50,000 simulations and 232 experimental shots
- Peak-timing error reduced from 11.6 to 9.2 steps over LLaMA-3-8B
- Tags
- diffusion-modelsicfbenchinertial-confinement-fusionlanguage-modelsreinforcement-learningsurrogate-modeling
- Products
- LLaMA-3-8B
- Organizations
- National Ignition Facility
- AI models
- LLaMA-3-8BICF-DLM
From the original article
1 min read at arxiv.orgInertial 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.
By Xiang Zhang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.