Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.04173 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908354387902464 |
|---|---|
| author | Wang, Zixiao Zhao, Wenqian Shen, Yunheng Bai, Yang Chen, Guojin Farnia, Farzan Yu, Bei |
| author_facet | Wang, Zixiao Zhao, Wenqian Shen, Yunheng Bai, Yang Chen, Guojin Farnia, Farzan Yu, Bei |
| contents | 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 \tool{DiffPattern}-Flex, a novel approach designed to generate reliable layout patterns efficiently. \tool{DiffPattern}-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 \tool{DiffPattern}-Flex significantly outperforms existing methods and excels at producing reliable layout patterns. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04173 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion Wang, Zixiao Zhao, Wenqian Shen, Yunheng Bai, Yang Chen, Guojin Farnia, Farzan Yu, Bei Machine Learning Computer Vision and Pattern Recognition 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 \tool{DiffPattern}-Flex, a novel approach designed to generate reliable layout patterns efficiently. \tool{DiffPattern}-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 \tool{DiffPattern}-Flex significantly outperforms existing methods and excels at producing reliable layout patterns. |
| title | DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04173 |