Sidebar[Skip]

Special Session 5:
Generative AI, Transformers and Applications

---

Generative AI, and particularly models built on transformer architectures, have fundamentally transformed the landscape of natural language processing and other fields, such as computer vision. These models are designed to understand and generate human language by capturing complex contextual relationships across large volumes of text, enabling highly accurate and coherent language generation. Their capabilities extend far beyond simple text production, they power applications such as conversational agents, automated content creation, machine translation, summarization, and semantic information extraction. One of their most impactful uses lies in structuring unstructured text data into meaningful representations, such as semantic graphs, which visualize relationships between entities and concepts. This fusion of Generative AI and semantic technologies enables intelligent systems to perform advanced reasoning, support decision-making, and provide rich, interactive user experiences. As transformer-based models continue to advance, their application is expanding across diverse domains including healthcare, finance, law, education, and the creative industries, highlighting their growing role in shaping the future of human-machine interaction.

Scope and topics:

This special session focuses on recent advancements in Generative AI, transformer-based models, and their applications. It aims to showcase how large language models are transforming the processing of unstructured data into organized semantic formats, such as graphs, while addressing the challenges of scale, diversity, and complexity. The session welcomes innovative research and real-world applications that demonstrate the power and versatility of transformers in language understanding and generation.

We invite submissions on the following, but not limited to, topics:

• Generative AI for Text Generation and Summarization
• Semantic Topic Modeling
• Large Language Models (LLMs) for Semantic Understanding
• Semantic Information Extraction from Unstructured Data
• Knowledge Graph Construction and Maintenance
• Entity Recognition and Relationship Extraction
• Semantic Search and Question Answering Systems
• Deep Learning for Semantic Graph Construction
• Graph Neural Networks for NLP Applications
• Few-shot Learning for Information Extraction
• Transfer Learning for Semantic Extraction Tasks
• Real-World Applications of Semantic Graphs in Industry
• AI-powered Virtual Assistants
• Automated Knowledge Base Creation
• Decision Support Systems
• Intelligent Content Recommendation Systems
• Graph-based Models for Multi-modal Data (Text + Images/Videos)
• Reinforcement Learning for Optimizing Information Extraction Models
• Challenges in Handling Noisy, Ambiguous, and Sparse Data for Graph-based NLP
• Semantic Graphs in Healthcare, Finance, and Legal Tech

Chairs:

• Chair Emails

Hamed Jelodar: h.jelodar@unb.ca
Roozbeh Razavi-Far: roozbeh.razavi-far@unb.ca
Dr.Vasile Palade:ab5839@coventry.ac.uk


• Chair Biographies

Hamed Jelodar is a research scientist at CIC, University of New Brunswick, Canada, specializing in AI, Generative AI (Gen-AI), Large Language Models (LLMs), and NLP techniques. His research focuses on information retrieval, machine learning, and natural language processing. His work has been published in leading journals, and he serves as an editorial board member for prominent AI journals, having also organized special issues for several publications.


Roozbeh Razavi-Far is an Associate Professor with the Faculty of Computer Science, University of New Brunswick. His research focuses on machine learning, big data analytics, computational intelligence, and cybersecurity of cyber-physical systems. He has authored or co-authored more than 170 papers in scholarly journals and international conferences. In 2024, Stanford listed him among the top two percent of most-cited researchers for the third consecutive year. He is the recipient of several awards and grants including NSERC-DG, NSERC-ECR, NBIF, USRG and NSERC-PDF. He is an associate editor at several journals, including the Neurocomputing, Machine Learning and Knowledge Extraction, Machine Learning with Applications, Discover Artificial Intelligence, IEEE Transactions on Industrial Cyber-Physical Systems, and IEEE Access. He served as a guest editor and chair for several journals and peer-reviewed conferences, and the chapter chair of IEEE Computational Intelligence, and Systems, Man and Cybernetics Societies at Windsor Section.


Dr. Vasile Palade: Details are available here.

Technical Committee

• Roozbeh Razavi-Far, University of New Brunswick, Canada
• Vasile Palade, Coventry University, UK
• Hamed Jelodar, University of New Brunswick, Canada
• Sajjad Bagheri Baba Ahmadi, University of the West of Scotland, UK
• Milad Taleby Ahvanooey, Warsaw University of Technology, Poland
• Ruxin Zhao, Yangzhou University, China

Paper Submission Instructions

All papers will be double-blind reviewed and must present original work.

• CMT Submission Site
• Select the track: Special Session 5: Generative AI, Transformers and Applications

Papers submitted for reviewing should conform to IEEE specifications. Manuscript templates can be downloaded from:

• IEEE website

Keydates

• Submission due date: August 20, 2025
• Notification of Acceptance: September 10, 2025
• Camera Ready Papers: September 20, 2025
• Pre-registration: September 20, 2025
• Conference: December 3-5, 2025

Registration

In order for your paper to be presented and published in the proceedings, you must register to the conference.

Paper Presentation Instructions

The papers submitted to this track will be presented in person as part of the conference. There is no virtual presentation for this session.