Vol. 2 No. 2 (2025)

					View Vol. 2 No. 2 (2025)

All articles published in this issue have undergone a thorough peer review process, and stringent checks for repetition rates have been implemented to ensure the integrity of the content.

Total number of articles in this issue: 4
Total number of pages in this issue: 34

For inquiries regarding the content of specific articles, please feel free to contact the respective authors via their provided email addresses. For questions related to the journal itself, please reach out directly to SUAS Press.

Published: 2025-04-14

Articles

  • Authors: Tao Bo, Weiyi Li, Yue Liu
    Resource Type: Article
    Disciplines: Computer Science | Subjects: Artificial Intelligence
    Publication ID: v2n2a01
    Abstract: Seq2Seq models and their variants have become a mainstay of modern natural language processing and sequence modelling tasks. Just Information about Seq2Seq models. In this paper, we provide a comprehensive overview of the evolution of Seq2Seq...
    1-9
    DOI Icon Abstract views: 29 | DOI Icon PDF downloads: 10 | DOI Icon references: 25
    DOI Icon DOI: 10.70393/616a6e73.323834
    DOI Icon ARK: ark:/40704/AJNS.v2n2a01
  • Authors: Qiming Xing, Yankuan Wang
    Resource Type: Article
    Disciplines: Computer Science | Subjects: Data Science
    Publication ID: v2n2a02
    Abstract: This paper investigates the application of a decision tree model for the binary classification task of the 'Position' category on the CLUENER2020 dataset, aiming to provide a lightweight and efficient method for named entity recognition....
    10-15
    DOI Icon Abstract views: 32 | DOI Icon PDF downloads: 10 | DOI Icon references: 14
    DOI Icon DOI: 10.70393/616a6e73.323835
    DOI Icon ARK: ark:/40704/AJNS.v2n2a02
  • Authors: Yui Ishikawa
    Resource Type: Article
    Disciplines: Computer Science | Subjects: Artificial Intelligence
    Publication ID: v2n2a03
    Abstract: Large language models (LLMs) achieve high benchmark performance, but whether this stems from genuine generalization or data contamination remains unclear. This paper proposes a three-tier framework to disentangle these effects, combining n-gram...
    16-22
    DOI Icon Abstract views: 40 | DOI Icon PDF downloads: 15 | DOI Icon references: 38
    DOI Icon DOI: 10.70393/616a6e73.323836
    DOI Icon ARK: ark:/40704/AJNS.v2n2a03
  • Authors: Xuzhong Jia, Chenyu Hu, Guancong Jia
    Resource Type: Article
    Disciplines: Information Science | Subjects: Information Retrieval
    Publication ID: v2n2a04
    Abstract: This paper proposes a novel cross-modal contrastive learning framework for robust visual representation under dynamic environmental conditions. We address the challenge of maintaining consistent performance across varying environments by...
    23-34
    DOI Icon Abstract views: 30 | DOI Icon PDF downloads: 18 | DOI Icon references: 33
    DOI Icon DOI: 10.70393/616a6e73.323833
    DOI Icon ARK: ark:/40704/AJNS.v2n2a04