cs.LG · 2606.25753 Copy arXiv ID · Jun 24, 2026 Save Gradient-based inverse lithography for EUV masks via the waveguide method and a physics-informed neural operator Authors: Vasiliy A. Es'kin , Egor V. Ivanov
Organizations: Department of Radiophysics, University of Nizhny Novgorod 23 Gagarin Ave., Nizhny Novgorod 603022, Russia
Abstract Gradient-based inverse lithography technology~(ILT) for extreme ultraviolet~(EUV) masks is presented. A novel framework treats the differentiable waveguide method and the recently proposed waveguide neural operator~(WGNO) as end-to-end physics engines, recovering the permittivity of the absorber of the mask through automatic differentiation of the full forward diffraction model. Numerical experiments on realistic 2D and 3D absorbers of the mask (TaBN, La, U) at λ = 11.2 λ{=}11.2 λ = 11.2
Explore similar work May 29, 2026 · Yao Lai, Xuyuan Xiong, Zeyue Xue +7 Lithography Industrial Automation
Jul 28, 2026 · Doyun Kim, Werner Gillijns Lithography Cold-Start
Sep 10, 2026 · Vasiliy A. Es'kin, Egor V. Ivanov, Olga V. Martynova Lithography Fringe Projection Profilometry
May 29, 2026 · cs.LG J/K move · Enter open · S save
Yao Lai, Xuyuan Xiong, Zeyue Xue, Guojin Chen +6
In semiconductor manufacturing, lithography projects circuit layouts onto silicon wafers through an optical mask. As circuit features shrink below the wavelength of light, optical diffraction causes the printed patterns to deviate from their intended layouts. Inverse Lithography Technology (ILT) addresses this challenge by generating optimized masks that enhance the fidelity of pattern transfer onto wafers. While ILT resembles an image synthesis task, its reliance on explicit physical metrics for mask evaluation limits the applicability of existing generative models. We introduce LithoGRPO, an ILT framework that integrates the flow-matching paradigm with GRPO-based reinforcement learning (RL) fine-tuning, enabling efficient exploration of diverse masks for a given target layout. Unlike purely generative or optimization-based approaches, RL in LithoGRPO exploits the explicitly defined, physics-based reward function of ILT, enabling optimization under complex, process-aware constraints. To the best of our knowledge, this is the first framework that unifies flow matching and RL for mask optimization. To improve RL sampling efficiency, we propose a fast shot-counting algorithm for manufacturability evaluation, achieving over 130x speedup while preserving the mask ranking of the traditional shot-count metric. Extensive experiments demonstrate that LithoGRPO achieves state-of-the-art performance over both optimization-based and learning-based methods, while maintaining efficient mask generation.