# Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks

arXiv: https://arxiv.org/abs/2203.08616 · HTML: https://mlsanity.com/paper/2203.08616/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 12 Mar 2022.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [DAMO: Deep Agile Mask Optimization for Full Chip Scale](https://mlsanity.com/paper/2008.00806/) (2020)
- [Data Efficient Lithography Modeling with Transfer Learning and Active Data Selection](https://mlsanity.com/paper/1807.03257/) (2018)

## Built on by (most cited first, 14 of 14)

- [Neural Operators for Accelerating Scientific Simulations and Design](https://mlsanity.com/paper/2309.15325/) (2023)
- [Large Scale Mask Optimization Via Convolutional Fourier Neural Operator and Litho-Guided Self Training](https://mlsanity.com/paper/2207.04056/) (2022)
- [TANTE: Time-Adaptive Operator Learning via Neural Taylor Expansion](https://mlsanity.com/paper/2502.08574/) (2025)
- [ILILT: Implicit Learning of Inverse Lithography Technologies](https://mlsanity.com/paper/2405.03574/) (2024)
- [Physics-Informed Optical Kernel Regression Using Complex-valued Neural Fields](https://mlsanity.com/paper/2303.08435/) (2023)
- [Inverse Lithography Physics-informed Deep Neural Level Set for Mask Optimization](https://mlsanity.com/paper/2308.12299/) (2023)
- [Reinforcement Learning for Photonic Component Design](https://mlsanity.com/paper/2307.11075/) (2023)
- [An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design](https://mlsanity.com/paper/2210.15765/) (2022)
- [Optimizing Predictive AI in Physical Design Flows with Mini Pixel Batch Gradient Descent](https://mlsanity.com/paper/2402.06034/) (2024)
- [Pushing the Limits of Inverse Lithography with Generative Reinforcement Learning](https://mlsanity.com/paper/2602.19027/) (2026)
- [Physics-Informed Neural Systems for the Simulation of EUV Electromagnetic Wave Diffraction from a Lithography Mask](https://mlsanity.com/paper/2603.15584/) (2026)
- [DevelSet: Deep Neural Level Set for Instant Mask Optimization](https://mlsanity.com/paper/2303.12529/) (2023)
- [Neural Lithography: Close the Design-to-Manufacturing Gap in Computational Optics with a 'Real2Sim' Learned Photolithography Simulator](https://mlsanity.com/paper/2309.17343/) (2023)
- [LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching](https://mlsanity.com/paper/2606.00228/) (2026)

## Abstract (arXiv)

Lithography simulation is a critical step in VLSI design and optimization for manufacturability. Existing solutions for highly accurate lithography simulation with rigorous models are computationally expensive and slow, even when equipped with various approximation techniques. Recently, machine learning has provided alternative solutions for lithography simulation tasks such as coarse-grained edge placement error regression and complete contour prediction. However, the impact of these learning-based methods has been limited due to restrictive usage scenarios or low simulation accuracy. To tackle these concerns, we introduce an dual-band optics-inspired neural network design that considers the optical physics underlying lithography. To the best of our knowledge, our approach yields the first published via/metal layer contour simulation at 1nm^2/pixel resolution with any tile size. Compared to previous machine learning based solutions, we demonstrate that our framework can be trained much faster and offers a significant improvement on efficiency and image quality with 20X smaller model size. We also achieve 85X simulation speedup over traditional lithography simulator with 1% accuracy loss.