WeChat Mini Program
Old Version Features

    • Fast Source Mask Optimization Adopting Mask Prediction and Feedback Method with Similarity Penalty

    Weichen Huang,Yanqiu Li,Miao Yuan, Zhaoxuan Li,He Yang, Zhen Li

    APPLIED OPTICS（2025）

    Cited 0|Views2
    Abstract
    Source mask optimization (SMO) based on gradient descent is a widely utilized technique in computational lithography. However, it is crucial to enhance the optimization efficiency of SMO, especially at advanced nodes. A mask predictive feedback with similarity penalty term SMO method is developed in this paper. This method incorporates a similarity penalty term into the loss function. It also employs a mask prediction feedback (MPF) method to more effectively utilize the mask and its gradient information during the iterative process. The simulation results indicate that the proposed method can reduce running time by at least 30% compared to using the Adam optimizer while ensuring target optimization conditions. Additionally, ablation experiments reveal that the proposed method improves algorithm efficiency more effectively than using the MPF method or similarity penalty term individually. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.
    More
    Translated text
    求助PDF
    上传PDF
    View via Publisher
    Bibtex
    AI Read Science
    AI Summary
    AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
    Example
    Background
    Key content
    Introduction
    Methods
    Results
    Related work
    Fund
    Key content
    • Pretraining has recently greatly promoted the development of natural language processing (NLP)
    • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
    • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
    • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
    • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
    Upload PDF to Generate Summary
    Must-Reading Tree
    Example
    Generate MRT to find the research sequence of this paper
    Data Disclaimer
    The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
    Chat Paper
    Summary is being generated by the instructions you defined