← Back to all news
arXiv AI By Ricardo Luna Gutierrez, Vineet Gundecha, Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Sahand Ghorbanpour, Aarne Lees, Soumyendu Sarkar

Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion

Read the original on arXiv AI →

The paper introduces the ICF Laser Pulse Shape Design System (LPDS), a generative inverse modeling framework that directly maps desired fusion outcomes and pellet configurations to optimized laser pulse shapes. It incorporates a multi-objective loss function to enforce physical constraints and experimental requirements, and offers tools such as constraint-conditioning, inpainting, and gradient-based editing for fine-grained pulse control. The authors also demonstrate the framework’s applicability to a limited set of real experimental shots, positioning LPDS as a data-driven approach to advance practical inertial confinement fusion.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 14

Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion

arXiv:2607. 10366v1 Announce Type: new Abstract: Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable.

By Jiatong Zhao, Tengyue Zhang, Yuhan Wang, Fuyuan Wu, Junchi Yan
reinforcement-learningfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Oct 12

Reinforcement learning for inverse silhouette design and rapid laser cutting of compact parallelogram quad kirigami prototypes

The paper introduces RL‑Kirigami, an inverse design framework that uses optimal‑transport conditional flow matching (OT‑CFM) and reinforcement learning to generate compatible ratio fields for compact reconfigurable parallelogram quad kirigami. A marching decoder enforces global geometric compatibility, while Group Relative Policy Optimization (GRPO) aligns the generator with nondifferentiable rewards for silhouette matching, feasibility, and ratio‑field regularity. The method achieves high silhouette IoU scores (up to 94.91%) and reduces forward simulator evaluations from hundreds to one, enabling rapid laser‑cut prototypes in polymeric sheets within about eight minutes.

By Milad Yazdani, Shahriar Shalileh, Dena Shahriari
diffusionreinforcement-learning
More like this →