Saved in:
Bibliographic Details
Main Authors: Jin, Qian, Liu, Yumeng, Jiang, Yuqi, Sun, Qi, Zhuo, Cheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10255
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909901747388416
author Jin, Qian
Liu, Yumeng
Jiang, Yuqi
Sun, Qi
Zhuo, Cheng
author_facet Jin, Qian
Liu, Yumeng
Jiang, Yuqi
Sun, Qi
Zhuo, Cheng
contents Reliable, generalizable data foundations are critical for enabling large-scale models in computational lithography. However, essential tasks-mask generation, rule violation detection, and layout optimization-are often handled in isolation, hindered by scarce datasets and limited modeling approaches. To address these challenges, we introduce Unitho, a unified multi-task large vision model built upon the Transformer architecture. Trained on a large-scale industrial lithography simulation dataset with hundreds of thousands of cases, Unitho supports end-to-end mask generation, lithography simulation, and rule violation detection. By enabling agile and high-fidelity lithography simulation, Unitho further facilitates the construction of robust data foundations for intelligent EDA. Experimental results validate its effectiveness and generalizability, with performance substantially surpassing academic baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10255
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unitho: A Unified Multi-Task Framework for Computational Lithography
Jin, Qian
Liu, Yumeng
Jiang, Yuqi
Sun, Qi
Zhuo, Cheng
Machine Learning
Reliable, generalizable data foundations are critical for enabling large-scale models in computational lithography. However, essential tasks-mask generation, rule violation detection, and layout optimization-are often handled in isolation, hindered by scarce datasets and limited modeling approaches. To address these challenges, we introduce Unitho, a unified multi-task large vision model built upon the Transformer architecture. Trained on a large-scale industrial lithography simulation dataset with hundreds of thousands of cases, Unitho supports end-to-end mask generation, lithography simulation, and rule violation detection. By enabling agile and high-fidelity lithography simulation, Unitho further facilitates the construction of robust data foundations for intelligent EDA. Experimental results validate its effectiveness and generalizability, with performance substantially surpassing academic baselines.
title Unitho: A Unified Multi-Task Framework for Computational Lithography
topic Machine Learning
url https://arxiv.org/abs/2511.10255