Keynote Speakers
Svetozar Margenov
Professor
Bulgarian Academy of Sciences
Speech Title:Performance Analysis of Modern Supercomputers, Problem-Oriented Metrics, and Applications
Abstract:Modern computer technologies provide more and more computing power. At the same time, high-performance computing (HPC) systems are becoming more widespread. Let us note the following example, with an increasing impact on the daily life of each of us. The availability of Big Data together with artificial intelligence (AI) tools and the rapid growth of affordable supercomputing resources have posed new challenges to language and content technologies aimed at building ever more innovative products and services. The second example is a little different. Quantum computing is considered one of the most promising technological directions of strategic importance. Although they are still at an early stage of development, quantum computing systems are already available. The synergy between advanced e-infrastructure and AI in a Big Data environment creates qualitatively new opportunities for science and engineering.
The first part of the talk discusses the current development of the computing power of HPC systems. The LINPACK benchmark has been used for more than 30 years to build the TOP500 list ranking the world's most powerful supercomputers. Although the computational linear algebra forms a backbone of the whole computing, the real life HPC performance is rather different than the one achieved on any single benchmark. This necessitates additional application-oriented approaches and metrics to HPC performance evaluation. Here we analyze data from the last two editions of the TOP500. Trends in the development of HPC architectures from the point of view of AI applications are identified. In addition, the increasingly important topic of energy efficiency is discussed. In this context, the capabilities of the petascale supercomputer HEMUS are also discussed. HEMUS is a part of the Infrastructure Complex for Digital Transformation and Large-scale Computing build in the Institute of Information and Communication Technologies of the Bulgarian Academy of Sciences.
In the second part of the presentation, we look at three case studies illustrating the concept of synergy between HPC performance and the scalability of modern methods and algorithms in a Big Data environment. Our developed BURA (Best Uniform Rational Approximation) method has a fundamental role in a wide range of computational models where the process does not satisfy the Brownian motion hypothesis, thus exhibiting anomalous (fractional) diffusion. BURA has several levels of parallelism that enable efficient use of the hierarchical architecture of modern supercomputers. The second case study discusses a biomedical application showing the necessity of supercomputing performance. The process of radiofrequency hepatic tumor ablation is modelled to optimize the parameters of the electrosurgical equipment. The problem is inherently 3D in space, nonlinear, multiscale and multiphysics, with the computer model reaching O(1012) degrees of freedom. The third but equally important example concerns the improvement of scalability and accuracy of quantum annealing computations. The advantages of the developed algorithms are confirmed by results of numerical experiments on a D-Wave 2000 Q system with more than 5000 qubits. The improvement of quantum algorithms often requires the application of fundamentally new approaches. One may be surprised by the interpretation of the substantially changed concepts of parallelism in the proposed parallel quantum annealing.
At the end, concluding remarks are given, including some open problems.
Biography: Svetozar Margenov is a corresponding member of the Bulgarian Academy of Sciences (BAS) and a professor in Computational Mathematics. He graduated from the Faculty of Mathematics and Informatics of the Sofia University “St. Kliment Ohridski”, a PhD and a Doctor of Science form the BAS. The main scientific achievements of prof. Margenov are in the field of information technologies including computational complexity, numerical methods for partial differential equations, numerical solution of fractional diffusion problems, multilevel iterative methods for ill-conditioned large-scale linear systems, parallel methods and algorithms, and supercomputer applications. He has published over 200 scientific papers and two monographs. Svetozar Margenov is the director of the Institute of Information and Communication Technologies (IICT-BAS) and head of the Department of Scientific Computing with Laboratory of 3D Digitization and Microstructure Analysis. He is a co-founder of the Bulgarian section of SIAM and its chairman for the first two mandates. Prof. Margenov has made a great contribution to the development of the modern Bulgarian HPC infrastructure and a high level of expertise in HPC applications. He currently leads the Center of Excellence in Informatics and ICT, within which the last Bulgarian petascale supercomputer HEMUS was opened in 2023. Prof. Svetozar Margenov is awarded the highest distinction of the Bulgarian Academy of Sciences - The Badge of Honor “Marin Drinov” on a Ribbon. He is recipient of the 2024 Walter Scott Award in Information Technology and has also been elected as a Fellow of the International Academy of Information Technology and Quantity Management.
Chang-Yun Lin
Professor
National Chung Hsing University
Speech Title:Multiresponse surface methodology for hyperparameter tuning to optimize multiple performance measures of statistical and machine learning algorithms
Abstract: Hyperparameter tuning is an important task in machine learning for controlling model complexity and improving prediction performance. Most methods in the literature can only be used to tune hyperparameters to optimize a single performance measure. In practice, participants may want to optimize multiple measures of the model; however, optimizing one measure may worsen another. Therefore, a hyperparameter tuning method is proposed using the multiresponse surface methodology to solve the tradeoff problem between multiple measures. A search algorithm that requires fewer tuning runs is developed to find the optimal hyperparameter settings systematically based on the preferences of participants for multiple measures of the model. An example using the random forest algorithm is provided to demonstrate the application of the proposed method to improve the prediction performance of the model on unbalanced data.
Biography: Dr. Chang-Yun Lin is a distinguished scholar and professor at the Department of Applied Mathematics, National Chung Hsing University (NCHU). With a strong foundation in applied mathematics, Dr. Chang-Yun Lin's research focuses on experimental design, statistical modeling, and data-driven optimization. Over the years, Dr. Chang-Yun Lin has contributed significantly to advancing methodologies in areas such as order-of-addition experiments, block designs, and split-plot structures, with practical applications spanning engineering, biology, and industrial processes.
An accomplished educator, Dr. Chang-Yun Lin is also dedicated to fostering student success, blending innovative teaching techniques with real-world applications to inspire the next generation of problem solvers.
When not engaged in academic pursuits, Dr. Chang-Yun Lin explores cutting-edge collaborations that merge mathematics, artificial intelligence, and statistical analysis to address complex challenges in science and industry.
Huawei Huang
Associate Professor
Sun Yat-Sen University, China
ORCID: https://orcid.org/0000-0002-7035-6446
Speech Title:BrokerFi, Broker2Earn, and BlockEmulator: Building the Ecosystem of BrokerChain
Abstract: This talk presents the ecosystem built on top of BrokerChain, which is a sharding blockchain developed by Prof. Huawei Huang’s research group (i.e., HuangLab: http://xintelligence.pro/ ).
BrokerChain was originally designed as a cross-shard transaction protocol, and was published in INFOCOM 2022. Starting from BrokerChain protocol, HuangLab members have kept building a sharding blockchain, also named BrokerChain. To keep improving the performance of BrokerChain, we also proposed Broker2Earn protocol (published in INFOCOM 2024), which serves as an incentive mechanism for BrokerChain because it can help recruit enough broker accounts and offer token-liquidity service for other BrokerChain clients. We then developed a DeFi product, named BrokerFi, by integrating the blockchain BrokerChain and the Broker2Earn protocol. Via participating in BrokerFi, brokers can earn native revenues when they stake their idle tokens in the Broker2Earn protocol. On the other hand, Broker2Earn can also benefit the sharded blockchain BrokerChain because it can efficiently spend each staked token on improving BrokerChain’s performance, such as TPS (transaction per second), TCL (transaction confirmation latency), and the queueing length in transaction pools. In the near future, we shall try our best to promote BrokerFi as a real DeFi product in the Hong Kong Web3 market.
BlockEmulator is a blockchain experimental tool open-sourced by HuangLab. Its homepage is https://www.blockemulator.com/. We are currently building a DAO for BlockEmulator on top of BrokerChain, aiming to incentivize blockchain researchers to contribute to and participate into the ecosystem of BlockEmulator.
Biography: Huawei Huang earned his Ph.D. in Computer Science and Engineering from the University of Aizu, Japan. He is currently an Associate Professor at Sun Yat-Sen University, China. His research interests include Blockchains, Web3, and DeFi protocol. He has served as a JSPS research fellow, a visiting scholar at Hong Kong Polytechnic University, and an Assistant Professor at Kyoto University, Japan (日本京都大学). He is a senior member of IEEE. He has been recognized as the world-ranking Top 2% Scientist since 2023. Lab page: xintelligence.pro
Google scholar: https://scholar.google.com/citations?user=DlKPajcAAAAJ&hl=en
Minxian XU
Associate Professor
Chinese Academy of Sciences
ORCID: https://orcid.org/0000-0002-0046-5153
Speech Title:Cloud-native System Support for Efficient Large Language Models Inference Serving
Abstract:Large Language Models (LLMs) are revolutionizing artificial intelligence by enabling advanced natural language processing applications. However, the computational demands of LLM inference require scalable, efficient, and robust system support. This talk investigates cloud-native techniques to optimize LLM inference serving. Specifically, it explores (1) batching inference requests to optimize key-value (KV) cache utilization for enhanced GPU performance and throughput, (2) leveraging containerization for fine-grained resource control to achieve lightweight scheduling and replication, and (3) dynamically balancing workloads through adaptive resource allocation and scaling. Collaborating with industry leaders, this research will integrate first-hand workload data into system design and validation. The outcomes aim to advance system-level support for LLMs, contributing to improved performance and reduced costs for cloud-native AI services.
Biography:Dr. Minxian Xu is an Associate Professor at Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences. He received his Ph.D. in Computing and Information Systems from the University of Melbourne in 2019. Dr. Xu has authored over 70 research papers in leading journals and conferences, including CSUR, TSC, TMC, TAAS, and TOIT. His work has garnered more than 3,800 citations (Google Scholar), which focuses on the efficient management of distributed and cloud computing systems, with expertise in areas such as load balancing and energy efficiency for cloud platforms, microservice management in cloud-native environments. Dr. Xu's research achievements include winning the 2019 IEEE TCSC Outstanding PhD Dissertation Award and the 2023 IEEE TCSC Award for Excellence (Early Career Award). He has also been recognized as one of the World’s Top 2% Scientists in 2023 and 2024 by Stanford University. He is a Senior Member of both IEEE and CCF.
Google scholar:https://scholar.google.com/citations?user=KeJL7gEAAAAJ&hl=zh-CN&oi=ao
Ahmad Ali
Dr.
Shanghai Jiao Tong University
Speech Title:Exploiting Dynamic Spatio-Temporal Graph Convolutional Neural Networks for Citywide Traffic Flow Prediction
Abstract:In this talk, I will present recent advancements in using spatio-temporal graph convolutional neural networks for predicting citywide traffic flows. These models capture both spatial dependencies across road networks and temporal patterns of traffic dynamics, enabling accurate forecasting of traffic congestion. I will discuss key challenges, model design, and real-world applications that can significantly improve traffic management in smart cities.
Biography:Dr. Ahmad Ali completed his PhD at Shanghai Jiao Tong University. He is currently a postdoctoral researcher at Shenzhen University. Dr. Ali has reviewed over 1150 articles for well-reputed journals, including Applied Soft Computing, Information Fusion, Information Sciences, Neural Networks, Applied Intelligence, and IEEE Transactions on Industrial Informatics.
Ahmad Lutfi Amri Ramli
Assoc. Prof. Dr.
Universiti Sains Malaysia
Speech Title:Travel Time Prediction Based on Road Geometry
Abstract:Traditional travel time predictions rely on traffic or historical data to estimate driving time accurately. However, in rural and mountainous areas, vehicle movement is primarily influenced by road geometry rather than traffic congestion. Curvy roads can significantly impact travel time compared to straight roads, where speed remains more consistent. In this study, we fit various parametric curves or arcs to road coordinates to compute curvature information, which is then used to determine the design speed of a given road segment. The design speed is used to approximate a driver's driving speed at a particular location. By incorporating average driving speed for personalization, we refine our estimations. Experimental validation at a selected location shows that our approach yields highly accurate travel time predictions when compared to available traffic data.
Biography:Assoc. Prof. Dr. Ahmad Lutfi Amri Ramli is an esteemed academic at the School of Mathematical Sciences, Universiti Sains Malaysia (USM). He holds a PhD from Durham University, an MSc in Computational Mathematics with Modelling from Brunel University, and a BSc in Mathematics from USM.
Dr. Lutfi specializes in applied mathematics, focusing on motion planning for robots, curve and surface modeling, and computational techniques. His research also explores gamification in education, integrating innovative methods to enhance student engagement in mathematical learning.
As a researcher and academic leader, he actively contributes to advancing mathematical sciences through research, student mentorship, and the development of effective teaching methodologies, enriching both theoretical and applied aspects of the field.
Ehsan Raeisidehkordi
Dr.
Researcher in AI and Future Communication Networks
Speech Title:The Role of Artificial Intelligence (AI) in the Future of Internet of Things (IoT) Networks
Abstract:Future communication networks, including sixth-generation (6G) and the Internet of Things (IoT), are expected to support higher capacity, improved quality of service, and increasing user demands. However, serving a massive number of users in future networks poses a significant bandwidth limitation challenge. Non-orthogonal multiple access (NOMA) has been proposed for future IoT and 6G networks to address this issue by serving multiple users within a single resource block.
However, real-world limitations such as intra- and inter-network interference and unknown Channel State Information (CSI) parameters make the optimization problem significantly more complex. As a result, the outcomes are generally in non-closed or highly complex forms. In this regard, machine learning (ML) approaches play a crucial role in optimizing future networks.
This presentation will discuss the importance and latest advancements of ML in the future of IoT networks. The results highlight the significance of these models in optimizing networks for practical scenarios.
Biography:Dr. Ehsan Raeisidehkordi received his Ph.D. in 2022 and is currently a researcher in the field of AI and IoT networks. His research interests include artificial intelligence (AI), machine learning, the Internet of Things (IoT), and next-generation cellular networks (5G and 6G). His recent work focuses on optimizing Non-Orthogonal Multiple Access (NOMA) for future IoT and 6G networks under imperfect Channel State Information (CSI) and inter-network interference, leveraging ML techniques to address real-world complexities. He has authored multiple papers in high-impact journals, including the IEEE Internet of Things Journal and the International Journal of Communication Systems. His book chapter, “Non-Orthogonal Multiple Access Technique for 6G Enabled IoT Networks,” reflects his contributions to the advancement of AI-driven communication technologies.
Zijian Győző Yang
Dr.
HUN-REN Hungarian Research Centre for Linguistics
Speech Title:HuGME, PULI: The Hungarian Large Language Model Family – Development and Evaluation
Abstract:Large Language Models (LLMs) have seen rapid advancements, with enterprises focusing on optimizing these models for diverse natural language processing tasks. For the Hungarian language, the PULI foundation model family (PULI 3SX, PULI Trio) marks a significant milestone in Hungarian LLM development. Our new research introduces PULI LlumiX, a novel LLM that undergoes continual pretraining on LLaMA models, followed by fine-tuning with custom-developed instruction and chat prompts. Our work demonstrates that transfer learning enables cross-linguistic insights, facilitating the effective adaptation of a LLaMA model to Hungarian. This results in state-of-the-art performance across multiple Hungarian NLP benchmarks among small-sized (7–8B) LLMs.
To systematically evaluate Hungarian LLMs, we introduce the Hungarian Generative Model Evaluation (HuGME) benchmark—a comprehensive framework assessing linguistic and reasoning skills, including bias, toxicity, faithfulness, summarization, readability, and domain-specific knowledge through tasks like Needle in the Haystack, TruthfulQA, and MMLU. Applying HuGME to various models, we provide a comparative analysis of their linguistic proficiency.
Biography:Dr. Zijian Győző Yang is a research fellow at the HUN-REN Hungarian Research Centre for Linguistics, where he specializes in large language models and machine translation. He obtained his PhD in Human Language Technology from Pázmány Péter Catholic University.
He has played a leading role in developing Hungarian-centric large language models, including PULI 3SX, PULI Trio (Hungarian-Chinese-English), and PULI LlumiX (Llama-based continual pretrained model). The PULI model family is the first and only set of foundational models developed exclusively for Hungarian.
In addition to his research, he has been actively involved in teaching at Pázmány Péter Catholic University and Eszterházy Károly Catholic University, covering topics such as artificial intelligence, data structures, and language technology.
His academic contributions include award-winning papers, program committee memberships, and organizing international computational linguistics conferences. He actively promotes Hungarian and multilingual AI development while fostering international research collaborations.
Fazel Ziraksaz
Lecturer
Shahid Beheshti University
Speech Title:Power amplifier design methodologies for 5G and 6G, their areas of application, and strategies for low-power operation to reduce component costs
Abstract:The evolution of wireless communication into 5G and 6G networks imposes stringent requirements on power amplifier (PA) design, demanding a balance between efficiency, linearity, bandwidth, and power consumption. This keynote will provide a comprehensive review of state-of-the-art PA design methodologies tailored for 5G and 6G applications, with a special focus on harmonic injection techniques. Unlike conventional approaches such as Doherty, envelope tracking (ET), and linear amplification with nonlinear components (LINC), harmonic injection offers a promising pathway to enhanced efficiency and linearity without the need for complex circuit elements.
The talk will delve into the key challenges associated with PA design for these advanced networks, including power consumption reduction, cost-effectiveness, and integration with next-generation semiconductor technologies such as CMOS, GaN, and SOI. Additionally, the discussion will highlight how harmonic injection can be leveraged to achieve superior performance in modern telecommunication infrastructures.
Furthermore, I will present insights from my recent research papers and an upcoming book that explores novel PA architectures utilizing internal harmonic generation. These findings offer a roadmap for overcoming critical design bottlenecks while ensuring scalability and adaptability for future wireless standards.
By addressing both theoretical advancements and practical implementation strategies, this keynote aims to provide researchers and industry professionals with a clear vision for designing low-power, high-efficiency power amplifiers that align with the evolving demands of 5G and 6G networks.
Biography:FAZEL Ziraksaz received the B.S.E.E degree from Azad University west Tehran branch, Iran, in 2016, and M.S.E.E degree from Tarbiat Modares University, Tehran, Iran, in 2019. He ranked the 1st among Electrical undergraduate students of Electronics Engineering of Azad University west Tehran branch with a GPA: 19.25/20. From 2015 to 2017, he was a member of Young researchers and Elite Club. He has been a member of Iranian Microelectronics Association since 2019. Now, he is currently Ph.D. candidate at Shahid Beheshti University, Tehran, Iran with GPA: 19.13/20. He is the author of the book “Fundamentals of Low Voltage, Low Power Integrated Circuit Design”. Now, he is writing a book about power amplifier design. He is the section editor of Insight-Energy Science journal and Computer and Telecommunication Engineering, and the reviewer of Journal of Electronics and Electrical Engineering (JEEE), Telecommunication Computing Electronics and Control (TELKOMNIKA), Asian Journal of Science and Technology (AJST) and American Journal of Electrical and Computer Engineering (AJECE). He is the committee member, chair and keynote speaker in the 3rd International Meet on Electronics and Electrical Engineering which is to be held in Barcelona, Spain during August 22-24, 2024. His research interests include RF circuits, and CMOS Integrated Circuits (ICs), and he recently studies power amplifiers (PAs) and modulators.