LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching

• URL: http://arxiv.org/abs/2606.00228v1
• Date: Fri, 29 May 2026 18:01:59 GMT
• Title: LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
• Abstract summary: Inverse Lithography Technology (ILT) generates optimized masks that enhance the fidelity of pattern transfer onto wafers.<n>We introduce LithoGRPO, an ILT framework that integrates the flow-matching paradigm with GRPO-based reinforcement learning (RL) fine-tuning.<n>To improve RL sampling efficiency, we propose a fast shot-counting algorithm for manufacturability evaluation, achieving over 130x speedup.
• Score: 51.14153938143746
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• MorphOPC: Advancing Mask Optimization with Multi-scale Hierarchical Morphological Learning [11.329737398904875]
  Optical proximity correction (OPC) is widely used to ensure pattern fidelity and manufacturability.<n>Recent generative mask optimization models can synthesize near-optimal masks, serving as fast machine learning (ML) surrogates for traditional OPC.<n>We propose textitMorphOPC, a multi-scale hierarchical model with neural morphological modules to learn these transformations.
  arXiv  Detail & Related papers  (2026-04-13T14:40:34Z)
• Timestep-Aware Block Masking for Efficient Diffusion Model Inference [48.764748095994996]
  Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency.<n>We propose a novel framework to optimize the computational graph of pre-trained DPMs on a per-timestep basis.
  arXiv  Detail & Related papers  (2026-03-20T13:35:03Z)
• MaskOpt: A Large-Scale Mask Optimization Dataset to Advance AI in Integrated Circuit Manufacturing [9.945697214043385]
  We present MaskOpt, a large-scale benchmark dataset constructed from real IC designs at the 45$mathrmnm$ node.<n>We evaluate state-of-the-art deep learning models for IC mask optimization to build up benchmarks.
  arXiv  Detail & Related papers  (2025-12-18T05:53:45Z)
• Inpainting-Guided Policy Optimization for Diffusion Large Language Models [67.97530437998117]
  Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs.<n>We explore how inpainting can inform RL algorithm design for dLLMs.
  arXiv  Detail & Related papers  (2025-09-12T16:44:31Z)
• FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities [76.46448367752944]
  multimodal large language models (MLLMs) unify visual understanding and image generation within a single framework.<n>Most existing MLLMs rely on autore (AR) architectures, which impose inherent limitations on future development.<n>We introduce FUDOKI, a unified multimodal model purely based on discrete flow matching.
  arXiv  Detail & Related papers  (2025-05-26T15:46:53Z)
• Fast inverse lithography based on a model-driven block stacking convolutional neural network [10.170465557304897]
  This paper presents a novel inverse lithographic approach to Optical Proximity Correction (OPC)<n>It employs a model-driven, block stacking deep learning framework that expedites the generation of masks conducive to manufacturing.<n> Numerical experiments have substantiated the efficacy of the proposed end-to-end approach.
  arXiv  Detail & Related papers  (2024-12-19T07:42:07Z)
• Cross-Scan Mamba with Masked Training for Robust Spectral Imaging [51.557804095896174]
  We propose the Cross-Scanning Mamba, named CS-Mamba, that employs a Spatial-Spectral SSM for global-local balanced context encoding.<n>Experiment results show that our CS-Mamba achieves state-of-the-art performance and the masked training method can better reconstruct smooth features to improve the visual quality.
  arXiv  Detail & Related papers  (2024-08-01T15:14:10Z)
• ILILT: Implicit Learning of Inverse Lithography Technologies [5.373749225521622]
  We propose an implicit learning ILT: ILILT, which leverages the implicit learning inputs to ground-conditioned ILT solutions, significantly improving efficiency and quality.
  arXiv  Detail & Related papers  (2024-05-06T15:49:46Z)
• Inverse Lithography Physics-informed Deep Neural Level Set for Mask Optimization [0.8547032097715571]
  Level set-based inverse lithography technology (ILT) has drawn considerable attention as a promising OPC solution. Deep learning (DL) methods have shown great potential in accelerating ILT. We propose an inverse lithography physics-informed deep neural level set (ILDLS) approach for mask optimization.
  arXiv  Detail & Related papers  (2023-08-15T01:56:22Z)
• Large Scale Mask Optimization Via Convolutional Fourier Neural Operator and Litho-Guided Self Training [54.16367467777526]
  We present a Convolutional Neural Operator (CFCF) that can efficiently learn mask tasks. For the first time, our machine learning-based framework outperforms state-of-the-art numerical mask dataset.
  arXiv  Detail & Related papers  (2022-07-08T16:39:31Z)

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.