CGIIT 2025

Prof. Irwin King

(Keynote Speaker)

IEEE Fellow, Distinguished Member of ACM

The Chinese University of Hong Kong, Hong Kong S. A. R., China

Title of Speech: Multimodal Continual Learning: Current Challenges, Advances, and Future Directions
Abstract: Continuous Learning (CL) empowers machine learning models to continuously learn from novel data while retaining previously acquired knowledge. Given the evolution of machine learning models from small to large pre-trained architectures and from supporting unimodal to multimodal data, it has become increasingly crucial to develop AI systems capable of learning continuously from new datasets while maintaining computational and resource efficiency. This has led to the emergence of multimodal continual learning (MMCL), which aims to address these challenges. We present an overview of recent developments on multimodal continual learning and highlight some of our contributions to provide a comprehensive perspective on this emerging topic with promising future research directions.

Biography: Professor Irwin King, a distinguished professor at the Department of Computer Science & Engineering, The Chinese University of Hong Kong. His research interests span machine learning, social computing, artificial intelligence, and data mining. Professor King’s extensive research has been recognized through numerous publications and awards in internationally renowned venues. He holds prestigious fellowships in the ACM, IEEE, INNS, AAIA, and HKIE. In addition to his research work, he has also been an evangelist, promoting E-Learning with AI technology. He serves as the Director of the ELearning Innovation and Technology (ELITE) Centre, the Machine Intelligence and Social Computing (MISC) Lab, and the Trustworthy Machine Intelligent Joint Lab. Professor King obtained his Bachelor of Science degree from California Institute of Technology (Caltech) and his Master’s and Doctorate degrees in Computer Science from the University of Southern California (USC).

Prof. Shahram Latifi

(Keynote Speaker)

University of Nevada, Las Vegas, USA

Title of Speech: Generative Models for Imaging Applications
Abstract: As artificial intelligence (AI) and machine learning (ML) continue to advance at an unprecedented pace, generative AI models have emerged as groundbreaking tools, revolutionizing the way we generate and interact with data. These models are pushing the boundaries of realism, enabling the creation of data that is more lifelike and accurate than ever before. Their impact is far-reaching, benefiting industries across diverse sectors such as healthcare, education, and entertainment by enhancing data quality, fostering creativity, and accelerating production processes.

This talk will delve into two of the most prominent generative models—Generative Adversarial Networks (GANs) and Diffusion Models—with a specific focus on their applications in imaging. We will explore the fundamental principles behind each model, highlighting their unique strengths, challenges, and real-world use cases. By comparing these models, we aim to provide a comprehensive understanding of their capabilities and limitations, offering insights into how they can be leveraged for various imaging tasks. Whether you're interested in cutting-edge AI research or practical applications, this discussion will illuminate the transformative potential of generative AI in reshaping industries and creating new opportunities for innovation.

Biography: Shahram Latifi, received the Master of Science and the PhD degrees both in Electrical and Computer Engineering from Louisiana State University, Baton Rouge, in 1986 and 1989, respectively. He is currently a Professor of Electrical Engineering at the University of Nevada, Las Vegas. Dr. Latifi is the co-director of the Center for Information Technology and Algorithms (CITA) at UNLV. He has designed and taught undergraduate and graduate courses in the broad spectrum of Computer Science and Engineering in the past four decades. He has given keynotes and seminars on machine learning/AI and IT-related topics all over the world. He has authored over 300 technical articles in the areas of networking, AI/ML, cybersecurity, image processing, biometrics, fault tolerant computing, parallel processing, and data compression. His research has been funded by NSF, NASA, DOE, DoD, Boeing, and Lockheed. Dr. Latifi was an Associate Editor of the IEEE Transactions on Computers (1999-2006), an IEEE Distinguished Speaker (1997-2000), Co-founder and Chair of the IEEE Int'l Conf. on Information Technology (2000-2004) and founder and Chair of the International Conf. on Information Technology-New Generations (2005-Present) . Dr. Latifi is the recipient of several research awards, the most recent being the Barrick Distinguished Research Award (2021). Dr. Latifi was recognized to be among the top 2% researchers around the world in December 2020, according to Stanford top 2% list (publication data in Scopus, Mendeley). He is an IEEE Fellow (2002) and a Registered Professional Engineer in the State of Nevada.

Prof. Marjan Mernik

(Invited Speaker)

The University of Maribor, Slovenija

Title of Speech: How Evolutionary Algorithms Can Efficiently Explore and Exploit the Search Space
Abstract: Evolutionary Algorithms mimic nature with mechanisms such as selection, crossover and mutation to solve various optimization problems in different fields, including Machine Vision and Information Technology. To properly apply Evolutionary Algorithms, a deep understanding of various selection, crossover and mutation operators is required. However, crucial steps and even more important concepts for any search algorithm are exploration and exploitation. On the other hand, these fundamental concepts are not very well understood among practitioners using evolutionary algorithms. Furthermore, how to measure exploration and exploitation directly is an open problem in the field of Evolutionary Computation. In this talk, I will first introduce the basic ingredients of every evolutionary algorithm and point to many problems and mistakes inexperienced users are facing, as well as different applications of evolutionary algorithms in Machine Vision and Information Technology.
In the second part of my talk, our novel direct measure of exploration and exploitation will be explained as based on attraction basins — parts of a search space where each part has its own point called an attractor, to which neighbouring points tend to evolve. Each search point can be associated with a particular attraction basin. If a newly generated search point belongs to the same attraction basin as its parent, the search process is identified as exploitation, otherwise as exploration. In the last part, I will mention some open problems regarding computing attraction basins for continuous problems.

Biography: Marjan Mernik received the MSc and PhD degrees in Computer Science from the University of Maribor in 1994 and 1998, respectively. He is currently a professor at the University of Maribor, Faculty of Electrical Engineering and Computer Science. He was a visiting professor at the University of Alabama at Birmingham, Department of Computer and Information Sciences. His research interests include programming languages, domain-specific (modelling) languages, grammar and semantic inference, and evolutionary computations. He is the Editor-in-Chief of the Journal of Computer Languages, as well as Associate Editors of the Applied Soft Computing Journal, Information Sciences Journal, and Swarm and Evolutionary Computation Journal. He has been named a Highly Cited Researcher for years 2017 and 2018. More information about his work is available at https://lpm.feri.um.si/en/members/mernik/.