In modern science and technology, modeling uncertainty and indeterminacy plays a crucial role in various fields such as artificial intelligence, decision-making, data analysis, and automated reasoning. Intuitionistic Fuzzy Sets (IFS), proposed by Krassimir Atanassov, extend classical fuzzy sets by introducing an additional degree of uncertainty. This enriched mathematical structure allows for more precise modeling of uncertain information and finds applications in numerous domains, including machine learning, expert systems, optimization, and pattern recognition.
With the increasing demand for processing complex and ambiguous data, IFS provide a more flexible alternative to classical fuzzy sets, as they simultaneously account for degrees of membership, non-membership, and uncertainty. This makes the method highly effective in decision-making under uncertainty. Recent studies show that intuitionistic fuzzy sets have wide-ranging applications in data classification, image processing, bioinformatics, and medical diagnostics.
This session will focus on the latest developments and applications of intuitionistic fuzzy sets, as well as their impact on the future of artificial intelligence and automated reasoning systems.
We invite researchers and practitioners to present innovative approaches, theoretical developments, and practical applications related to intuitionistic fuzzy sets. Contributions that demonstrate novel techniques for handling uncertainty, real-world applications, and effective methods for improving reasoning and complex data analysis are particularly welcome.
This session will bring together scientists, engineers, and industry experts to discuss the current state and future prospects of intuitionistic fuzzy sets, exchange knowledge, and collaborate to advance mathematical modeling of uncertainty and artificial intelligence.
In the digital age, vast amounts of data are generated daily through web interactions, social media platforms, and other online sources. Extracting meaningful insights from this ever-growing and dynamic data requires advanced techniques in data mining, web mining, and social media analysis. Flexible Query-Answering Systems (FQAS) are at the forefront of addressing these challenges by providing adaptive, context-aware solutions that efficiently respond to complex and diverse information needs. This special session explores the latest advancements and emerging trends in data, web, and social media mining within the context of these intelligent, flexible systems.
As information retrieval and data processing become more complex, FQAS must evolve to handle both structured and unstructured content, including text, images, and videos. Additionally, the integration of machine learning, deep learning, and natural language processing (NLP) is transforming how query-answering systems interact with data sources in real-time, offering new opportunities for personalized, context-sensitive, and dynamic responses.
This session will focus on how these emerging trends shape the future of flexible query-answering systems, enabling better user interactions, faster decision-making, and more accurate insights from data, the web, and social media. It will also cover innovative approaches for handling large-scale, noisy, and heterogeneous data while ensuring relevance, accuracy, and efficiency.
We invite contributions discussing both theoretical innovations and practical applications of flexible query-answering systems in data mining and social media analysis. Papers highlighting novel approaches to real-world challenges—such as information overload, noisy data, and dynamic query environments—will be especially valuable.
This session brings together researchers, practitioners, and industry leaders to discuss the current state and future directions of flexible query-answering systems in the evolving landscape of data, web, and social media mining. Participants will explore emerging trends, share insights, and collaborate to advance the field of intelligent, adaptive query-answering systems.
In an increasingly complex and data-driven world, effective decision-making is critical, particularly in high-stakes and risk-sensitive domains such as security, finance, healthcare, and disaster management. The goal of this special session is to explore how information retrieval (IR) and knowledge management (KM) techniques can be leveraged to support risk-based decision-making processes. By focusing on the intersection of IR, KM, and risk management, this session aims to address the challenges and opportunities in providing relevant, timely, and accurate information to decision-makers under uncertainty.
This session invites contributions that address both theoretical advancements and practical applications, with an emphasis on novel methods that enhance the efficiency and effectiveness of decision-making processes in risk-intensive environments. Contributions from interdisciplinary fields that combine IR, KM, data science, and risk management are particularly encouraged.
This special session will bring together experts in information retrieval, knowledge management, decision theory, and risk management to share insights, discuss emerging trends, and explore collaborative approaches to developing advanced systems that assist with risk-based decision-making.
Over the past five years, large language, visual, and multimodal models have revolutionized AI research. They have demonstrated human-level performance in many complex tasks, significantly impacting natural language processing, computer vision, healthcare, and scientific discovery. These powerful models enable groundbreaking innovations, transforming how we approach problem-solving, automation, and human-AI collaboration.
This special session aims to bring together researchers working on advanced applications of large AI models beyond traditional question-answering (QA) systems. The session will focus on innovative methods for leveraging large-scale AI models across various domains, their integration into real-world applications, and the challenges associated with their deployment, such as interpretability, fairness, and efficiency.
We invite high-quality research contributions on topics including, but not limited to:
Authors are invited to submit original research papers following the FQAS 2025 submission guidelines. All submissions will undergo peer review, and accepted papers will be included in the conference proceedings. The conference website contains details on the submission deadline, formatting requirements, and instructions.
This special session aims to:
We look forward to receiving your submissions and engaging in meaningful discussions on the future of large AI models and their transformative impact across various fields.
The rapid development of intelligent systems and artificial intelligence (AI) has opened new opportunities for optimizing and automating academic processes. Universities and research institutions increasingly rely on AI-driven decision-making tools to enhance efficiency, improve educational outcomes, and support flexible decision-making in dynamic academic environments.
This special session aims to bring together researchers, educators, and practitioners to explore the latest developments in AI and intelligent systems for academic processes, including adaptive learning, automated assessment, research management, and institutional decision-making. The session will focus on how intelligent systems can facilitate flexibility and personalization while maintaining transparency and fairness in academic environments.
We invite high-quality research contributions on topics including, but not limited to:
Authors are invited to submit original research papers following the FQAS 2025 submission guidelines. All submissions will undergo peer review, and accepted papers will be included in the conference proceedings. The submission deadline, formatting details, and further instructions can be found on the conference website.
This special session aims to:
We look forward to receiving your submissions and engaging in meaningful discussions on the future of intelligent systems in academia.
Language models have emerged as transformative tools in the field of Information Retrieval (IR), redefining how information is accessed, ranked, and understood. Their ability to capture deep semantic representations and contextual information has significantly advanced traditional IR methodologies, enabling more accurate, efficient, and intelligent retrieval systems.
This special session focuses on the role of language models in addressing core challenges and in exploring new opportunities in Information Retrieval. We welcome academic and industrial contributions that demonstrate how language models can enhance search, recommendation, ranking, question answering, and other IR-related tasks.
We invite high-quality research contributions on topics including, but not limited to:
Authors are invited to submit original research papers following the FQAS 2025 submission guidelines. All submissions will undergo peer review, and accepted papers will be included in the conference proceedings. The submission deadline, formatting details, and further instructions can be found on the conference website.
This special session aims to:
We look forward to receiving your submissions and engaging in meaningful discussions on the future of intelligent systems in academia.