Generative AI and Advanced Computational Methods for Intelligent Systems

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Engineering Mathematics".

Deadline for manuscript submissions: closed (30 November 2024) | Viewed by 1229

Special Issue Editors


E-Mail Website
Guest Editor
School of Engineering Technology, Purdue University, West Lafayette, IN 47907, USA
Interests: manufacturing system; generative AI; operation research; deep learning; artificial intelligence; optimization

E-Mail Website
Guest Editor
School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
Interests: production control and manufacturing system reconfiguration
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Mechanical Engineering, Zhejiang University, Hangzhou 310058, China
Interests: intelligent manufacturing systems; digital twin (DT) and human digital twin (HDT); human-centric smart manufacturing and robotics; human–cyber–physical systems (HCPSs)
Special Issues, Collections and Topics in MDPI journals
School of Engineering, Rutgers University, Piscataway, NJ 08854, USA
Interests: reconfigurable manufacturing systems; modeling and operations of complex engineering systems; decision making under uncertainty; engineering education
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In this era of rapid technological advancements, artificial intelligence (AI) stands as a transformative force shaping the landscape of intelligent systems across various domains. This Special Issue serves as a platform to explore the synergies between conventional AI techniques and the innovative realm of generative AI.

Artificial intelligence has evolved beyond traditional classification and regression approaches, now embracing generative AI, which focuses on making decisions, designs, and insights rather than simply interpreting them. Generative models, such as Generative Adversarial Networks (GANs), diffusion models, and variational autoencoders, open new frontiers for intelligent systems by enabling them to generate novel and diverse outputs, fostering creativity and adaptability.

This Special Issue invites contributions that delve into the intersection of intelligent systems and generative AI and other advanced computational methods, aiming to advance the capabilities of intelligent systems, spanning from smart manufacturing, supply chain management, autonomous vehicles, and energy management. Topics of interest include but are not limited to machine learning, deep learning, computational intelligence, robotics, and autonomous systems. We encourage researchers to explore how these technologies can collectively propel the development of intelligent systems, enhancing their decision making, problem solving, and adaptability.

Join us on this intellectual journey to unravel the potential of artificial intelligence and generative AI in shaping the future of intelligent systems. We anticipate insightful contributions that push the boundaries of innovation and redefine the landscape of intelligent technologies.

Dr. Xingyu Li
Dr. Sihan Huang
Prof. Dr. Baicun Wang
Dr. Xi Gu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • generative AI
  • decision support systems
  • autonomous systems
  • intelligent automation
  • computational intelligence
  • natural language processing
  • smart manufacturing
  • autonomous vehicles
  • quality control systems
  • supply chain management
  • human–robot collaboration
  • energy management systems

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

13 pages, 602 KiB  
Article
LoRA Fusion: Enhancing Image Generation
by Dooho Choi, Jeonghyeon Im and Yunsick Sung
Mathematics 2024, 12(22), 3474; https://doi.org/10.3390/math12223474 - 7 Nov 2024
Viewed by 714
Abstract
Recent advancements in low-rank adaptation (LoRA) have shown its effectiveness in fine-tuning diffusion models for generating images tailored to new downstream tasks. Research on integrating multiple LoRA modules to accommodate new tasks has also gained traction. One emerging approach constructs several LoRA modules, [...] Read more.
Recent advancements in low-rank adaptation (LoRA) have shown its effectiveness in fine-tuning diffusion models for generating images tailored to new downstream tasks. Research on integrating multiple LoRA modules to accommodate new tasks has also gained traction. One emerging approach constructs several LoRA modules, but more than three typically decrease the generation performance of pre-trained models. The mixture-of-experts model solves the performance issue, but LoRA modules are not combined using text prompts; hence, generating images by combining LoRA modules does not dynamically reflect the user’s desired requirements. This paper proposes a LoRA fusion method that applies an attention mechanism to effectively capture the user’s text-prompting intent. This method computes the cosine similarity between predefined keys and queries and uses the weighted sum of the corresponding values to generate task-specific LoRA modules without the need for retraining. This method ensures stability when merging multiple LoRA modules and performs comparably to fully retrained LoRA models. The technique offers a more efficient and scalable solution for domain adaptation in large language models, effectively maintaining stability and performance as it adapts to new tasks. In the experiments, the proposed method outperformed existing methods in text–image alignment and image similarity. Specifically, the proposed method achieved a text–image alignment score of 0.744, surpassing an SVDiff score of 0.724, and a normalized linear arithmetic composition score of 0.698. Moreover, the proposed method generates superior semantically accurate and visually coherent images. Full article
Show Figures

Figure 1

Back to TopTop