Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction

• URL: http://arxiv.org/abs/2609.07756v1
• Date: Mon, 07 Sep 2026 17:00:02 GMT
• Title: Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
• Abstract summary: Each shot at the National Ignition Facility costs on the order of one million dollars, making accurate AI surrogates a high-value target.<n>We propose ICF-DLM, to our knowledge the first LM-based ICF predictor.<n>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.
• Score: 20.091343436161385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Do Time-Series Foundation Models Pay Off for Industrial Monitoring? A Cost-Aware Empirical Study [1.8419890068150178]
  Time-series foundation models (TSFMs) promise reusable representations and zero-shot forecasts.<n>This work presents a protocol-aware empirical assessment across three settings.
  arXiv  Detail & Related papers  (2026-08-24T08:30:06Z)
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Multimodal Transformer Based Generic Mixture Density Network for Scattering Timescale Estimation of Fast Radio Bursts [0.7632410926487435]
  We present a deep learning approach named Multimodal Transformer Based Generic Mixture Density Network (MT-GMDN) to estimate the astrophysical parameter value.<n>We trained MT-GMDN on $sim3500$ FRBs from CHIME/FRB cattwo while holding out some fraction of FRBs for validation during training and for testing after the training completes.<n>The model achieves a coefficient of determination ($R2$) value of $94%$ on the expected value of $$ for the events with measurable scattering with an excellent recall value of $90%$ on the test
  arXiv  Detail & Related papers  (2026-06-02T13:01:08Z)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• ABM-UDE: Developing Surrogates for Epidemic Agent-Based Models via Scientific Machine Learning [1.949837893170278]
  We develop county-ready surrogates that learn directly from exascale ABM trajectories using Universal Differential Equations (UDEs)<n>We adapt multiple shooting and an observer-based prediction-error method (PEM) to stabilize identification of neural-augmented epidemiological dynamics across intervention-driven regime shifts.<n>Inference runs in seconds on commodity CPUs (20-35 s per $sim$90-day forecast), enabling nightly ''what-if'' sweeps on a laptop.
  arXiv  Detail & Related papers  (2026-02-25T05:19:43Z)
• Optimal Learning-Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay [9.371921537573346]
  We study optimal learning-rate schedules (LRSs) under the functional scaling law.<n>LRSs accurately models the loss dynamics of both linear regression and large language model (LLM) pre-training.<n>We analyze optimal shape-fixed schedules, where only the peak learning rate is tuned.
  arXiv  Detail & Related papers  (2026-02-06T15:52:30Z)
• MeanFlow Transformers with Representation Autoencoders [71.45823902973349]
  MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data.<n>We develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE)<n>We achieve a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256.
  arXiv  Detail & Related papers  (2025-11-17T06:17:08Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• PINGS: Physics-Informed Neural Network for Fast Generative Sampling [0.0]
  We introduce PINGS, a framework that amortizes diffusion sampling by training a physics-informed network to approximate reverse-time probability-flow dynamics.<n>As a proof of concept, we learn a direct map from a 3D standard normal to a non-Gaussian Gaussian Mixture Model (GMM)<n>PINGS frames generative sampling as a PINN-style residual problem with endpoint anchoring, yielding a white-box, differentiable map with NFE = 1.
  arXiv  Detail & Related papers  (2025-09-14T14:22:33Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Inertial Confinement Fusion Forecasting via Large Language Models [48.76222320245404]
  In this study, we introduce $textbfLPI-LLM$, a novel integration of Large Language Models (LLMs) with classical reservoir computing paradigms. We propose the $textitLLM-anchored Reservoir$, augmented with a $textitFusion-specific Prompt$, enabling accurate forecasting of $textttLPI$-generated-hot electron dynamics during implosion. We also present $textbfLPI4AI$, the first $textttLPI$ benchmark based
  arXiv  Detail & Related papers  (2024-07-15T05:46:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.