Abstract
In recent years, AI research has showcased tremendous potential to impact positively humanity and society. Although AI frequently outperforms humans in tasks related to classification and pattern recognition, it continues to face challenges when dealing with complex tasks such as intuitive decision-making, sense disambiguation, sarcasm detection, and narrative understanding, as these require advanced kinds of reasoning, e.g., commonsense reasoning and causal reasoning, which have not been emulated satisfactorily yet. The Seven Pillars for the future of AI (https://sentic.net/7-pillars-for-the-future-of-ai.pdf) address these shortcomings and pave the way for more efficient, scalable, safe and trustworthy AI systems.

Bio
Erik Cambria is a Professor at Nanyang Technological University, where he also holds the appointment of Provost Chair in Computer Science and Engineering, and Founder of several AI companies, such as SenticNet (https://business.sentic.net), offering B2B sentiment analysis services, and finaXai (https://finax.ai), providing fully explainable financial insights. Prior to moving to Singapore, he worked at Microsoft Research Asia (Beijing) and HP Labs India (Bangalore), after earning his PhD through a joint program between the University of Stirling (UK) and MIT Media Lab (USA). Today, his research focuses on neurosymbolic AI for interpretable, trustworthy, and explainable affective computing in domains like social media monitoring, financial forecasting, and AI for social good. He is ranked in Clarivate's Highly Cited Researchers List of World's Top 1% Scientists, is recipient of many awards, e.g., IEEE Outstanding Early Career, was listed among the AI's 10 to Watch, and was featured in Forbes as one of the 5 People Building Our AI Future. He is an IEEE Fellow, Associate Editor of various top-tier AI journals, e.g., Information Fusion and IEEE Transactions on Affective Computing, and is involved in several international conferences as keynote speaker, program chair and committee member.

Abstract
The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. This report will first summarize the key challenges of continual learning for LLMs under the task-id agnostic settings, namely catastrophic forgetting and knowledge transfer. Then, it will review classic continual learning algorithms and their applications in LLMs, thereby summarizing the existing paradigms of continual learning for LLMs. Specifically, they devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input. However, these methods tend to address only one of the challenges, ignoring the potential of aligning the two modules to effectively address catastrophic forgetting and knowledge transfer simultaneously. To this end, we propose a novel Shared Attention Framework (SAPT), to align the PET learning and selection via the Shared Attentive Learning & Selection module. Extensive experiments on two CL benchmarks demonstrate the superiority of SAPT. Moreover, SAPT consistently demonstrates its superiority when we scale it to different model sizes (from 770M to 13B), different model architectures (T5 and LLaMA-2) and unseen tasks.

Bio
Wanxiang Che is a professor/doctoral supervisor of Computing Faculty at Harbin Institute of Technology, deputy director of the Artificial Intelligence Research Institute, a national-level young talent, a Longjiang Scholar "Young Scholar", and a visiting scholar at Stanford University. He is currently a director of the Chinese Information Society of China, deputy director and secretary-general of the Computational Linguistics Professional Committee; executive committee member and secretary-general of the Asia-Pacific Branch of the International Association for Computational Linguistics (AACL); co-chair of the program committee of the top international conference ACL 2025. Undertakes a number of scientific research projects such as key projects of the National Natural Science Foundation of China and the 2030 "New Generation Artificial Intelligence" major projects. Author of the book "Natural Language Processing: Methods Based on Pre-trained Models". Won the AAAI 2013 Best Paper Nomination Award. The Language Technology Platform (LTP) responsible for research and development has been authorized to Baidu, Tencent, Huawei and other companies for paid use. In 2016, he won the first prize of the Heilongjiang Province Science and Technology Progress Award (ranked 2nd), and in 2020, he won the Heilongjiang Province Youth Science and Technology Award.

Abstract
Computational psychophysiology is a new direction that broadens the field of psychophysiology by allowing for the identification and integration of multimodal signals to test specific models of mental states and psychological processes. Additionally, such approaches allows for the extraction of multiple signals from large-scale multidimensional data, with a greater ability to differentiate signals embedded in background noise. Further, these approaches allows for a better understanding of the complex psychophysiological processes underlying brain disorders such as autism spectrum disorder, depression, and anxiety. Given the widely acknowledged limitations of psychiatric nosology and the limited treatment options available, new computational models may provide the basis for a multidimensional diagnostic system and potentially new treatment approaches.

Bio
Prof. Bin Hu received his Ph. D. degree in computer science from the Institute of Computing Technology, Chinese Academy of Science in 1998. He is a National Distinguished Expert, the Chief Scientist of 973 as well as the National Advanced Worker in 2020, who was elected as a IEEE/IET/AAIA Fellow. He is a Member of the Steering Council of the ACM China Council and the Vice-Chair of the China Committee of the International Society for Social Neuroscience. He serves as the Editor-in-Chief for the IEEE Transactions on Computational Social Systems. He is also the TC Co-Chair of computational psychophysiology in the IEEE Systems, Man, and Cybernetics Society (SMC). He is a Member of the Steering Committee of Computer Science at the Chinese Ministry of Education, Science and Technology Commission at the Chinese Ministry of Education. His awards include the 2014 China Overseas Innovation Talent Award, the 2016 Chinese Ministry of Education Technology Invention Award, the 2018 Chinese National Technology Invention Award, and the 2019 WIPO-CNIPA Award for Chinese Outstanding Patented Invention. He is a Principal Investigator for large grants such as the National Transformative Technology “Early Recognition and Intervention Technology of Mental Disorders Based on Psychophysiological Multimodal Information”, which have greatly promoted the development of objective, quantitative diagnosis and non-drug interventions for mental disorders.

Abstract
This presentation delves into the innovative convergence of human activity recognition (HAR) and behavioral support systems aimed at empowering vulnerable populations. Our research focuses on developing cutting-edge technologies to provide essential support for elderly individuals, those affected by bullying, and people with hearing impairments. By harnessing HAR, we gain profound insights into human behavior, facilitating the development of intelligent systems tailored to meet the unique needs of these groups. I will showcase three key projects: an Anomaly and Fall Detection System for the elderly, a Bullying Detection and Prediction System for individuals experiencing bullying, and a Gesture Recognition and Text Output System for people with hearing impairments. These projects exemplify how integrating HAR with behavioral insights can significantly enhance quality of life and safety, underscoring the pivotal role of advanced technology in fostering inclusive and supportive environments.

Bio
Runhe Huang received her B.Sc. in Electronics Technology from the National University of Defense Technology, China, in 1982, and her Ph.D. in Computer Science and Mathematics from the University of the West of England, UK, in 1993. She is a full professor in the Faculty of Computer and Information Sciences at Hosei University, Japan, where she has held the position since 2003. She served as the head of the Department of Computer Science from 2008 to 2010 and currently holds the position of Deputy Director at Hosei University Library. She is a senior member of IEEE and ACM, and served as the IEEE CIS SWTC chair and vice chair from 2019 to 2022. Her research fields include Artificial Intelligence, Ubiquitous Intelligence Computing, Machine Intelligence, Cognitive Computing, and Knowledge Modeling. She has authored more than 200 academic papers.