# DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion

arXiv: https://arxiv.org/abs/2505.04173 · HTML: https://mlsanity.com/paper/2505.04173/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 12 of its 40 references that are in the map.
- First posted on arXiv 7 May 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [A note on the evaluation of generative models](https://mlsanity.com/paper/1511.01844/) (2015)
- [DiffPattern: Layout Pattern Generation via Discrete Diffusion](https://mlsanity.com/paper/2303.13060/) (2023)
- [Layout decomposition for triple patterning lithography](https://mlsanity.com/paper/1402.2459/) (2014)
- [Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos](https://mlsanity.com/paper/2212.13495/) (2022)
- [ChatPattern: Layout Pattern Customization via Natural Language](https://mlsanity.com/paper/2403.15434/) (2024)

## Abstract (arXiv)

Recent advancements in layout pattern generation have been dominated by deep generative models. However, relying solely on neural networks for legality guarantees raises concerns in many practical applications. In this paper, we present toolDiffPattern-Flex, a novel approach designed to generate reliable layout patterns efficiently. toolDiffPattern-Flex incorporates a new method for generating diverse topologies using a discrete diffusion model while maintaining a lossless and compute-efficient layout representation. To ensure legal pattern generation, we employ an optimization-based, white-box pattern assessment process based on specific design rules. Furthermore, fast sampling and efficient legalization technologies are employed to accelerate the generation process. Experimental results across various benchmarks demonstrate that toolDiffPattern-Flex significantly outperforms existing methods and excels at producing reliable layout patterns.