In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 10

Multi modal large model training strategy for functional image data

Ming Yibo
Chen Yanmin
Zhao Jialu
College of Computer Science & Technology, Xinjiang Normal University, Ürümqi 830054, China
DOI: 10.19734/j.issn.1001-3695.2025.02.0063

Abstract

In recent years, multimodal large language models have undergone rapid development and demonstrated excellent performance in various multimodal downstream tasks. However, the current mainstream multimodal large language models still perform unsatisfactorily in function image reasoning tasks, which requires the model to not only possess strong visual perception capabilities but also perform chained thinking reasoning to accurately understand and answer questions involving mathematical functions. To address these issues, a specially designed instruction fine-tuning dataset, FunctionQA, tailored for function image reasoning tasks was first constructed. Each data point, in addition to standard question-answer pairs, also includes a detailed chained reasoning process, ensuring that the model can learn complex reasoning steps during training. Secondly, a four-stage fine-tuning strategy was designed for function image reasoning tasks, gradually optimizing the visual encoder, multimodal adapter, and large language model, and incorporating LoRA technology to reduce training costs. Experimental results show that the mFunction-4B model, built on the LLaVA framework, achieved an accuracy of 43.55% on the MathVista testmini FunctionQA subset with 4B parameters after optimization using the FunctionQA dataset and the four-stage fine-tuning strategy, representing a 14.52% improvement over the baseline model LLaVA-1.5-7B, validating the feasibility and effectiveness of the proposed method.

Foundation Support

新疆维吾尔自治区自然科学基金资助项目(2022D01A227)
新疆维吾尔自治区重点研发专项(2022B01007-1)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.02.0063
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 10

Publish History

[2025-06-18] Accepted Paper

Cite This Article

明一博, 陈彦敏, 赵嘉璐. 面向函数图像数据的多模态大模型训练策略 [J]. 计算机应用研究, 2025, 42 (10). (2025-06-19). https://doi.org/10.19734/j.issn.1001-3695.2025.02.0063. (Ming Yibo, Chen Yanmin, Zhao Jialu. Multi modal large model training strategy for functional image data [J]. Application Research of Computers, 2025, 42 (10). (2025-06-19). https://doi.org/10.19734/j.issn.1001-3695.2025.02.0063. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)