Department of Artificial Intelligence

Event Information Topic: ZotDance - an AI-powered open platform for Dancer Training and Beyond Speaker: Associate Professor of Teaching Quoc-Viet Dang, Department of Electrical Engineering and Computer Science, University of California, Irvine Time: 2026.05.15 (Fri) 12:10-13:30 Venue: CGU Future Classroom (Management Building 9F) About the Speaker Quoc-Viet "QV" Dang received his Ph.D. in Computer Systems and Software from the University of California, Irvine, United States in 2017. His dissertation research focused on using latent semantic analysis to create an intelligent recommendation system for students throughout their courses. Dr. Dang joined UC Irvine as an Assistant Professor of Teaching in 2017 where his primary focus is improving the educational experience of students throughout their college career. He continues his work in automated recommendation tools with research collaborators in the machine learning field and is facilitating multiple proof-of-concept student projects collaborating with industry partners including Texas Instruments, Thales, and Cadence. Organizers Artificial Intelligence Research Center College of Intelligent Computing Registration Registration Link: https://reurl.cc/K2dLGR Contact person：Sue LIu Contact number：409-3001

Topic： Hiding a Swarm's Leader from RL Agent and Human AI Safety in the Information and Physical Spaces Speaker:  Prof. Michael Lewis School of Computing and Information, Department of Informatics and Networked Systems, University of Pittsburgh Prof. Katia Sycara Edward Fredkin Research Professor of Robotics, School of Computer Science, Carnegie Mellon University Time: 2026/05/12 (二)  15:00-17:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/xW6OmZ or scan QR code on poster About the Speaker: Michael Lewis is a Professor at the School of Computing and Information at the University of Pittsburgh. Trained in engineering psychology, his research focuses on human-computer interaction, human-agent teaming, and swarm robotics. He investigates how humans interact with complex autonomous systems, with particular emphasis on trust, decision-making, and coordination in multi-agent environments. His work integrates artificial intelligence, visualization, and human factors to improve the effectiveness of human–AI collaboration. Professor Lewis has led and contributed to numerous research projects supported by agencies such as DARPA, NSF, and other U.S. government organizations. He has published extensively in leading journals and conferences in human-machine systems, robotics, and AI. Katia Sycara is the Edward Fredkin Research Professor in the School of Computer Science at Carnegie Mellon University and a Research Professor at the Robotics Institute. She is a leading expert in artificial intelligence, multi-agent systems, and human-agent collaboration. Her research spans AI autonomy, distributed intelligent systems, and trust in human-AI interaction, with applications in robotics, defense, and large-scale information systems. She has been a pioneer in agent-based systems and has made significant contributions to semantic web technologies and collaborative AI. Professor Sycara has received numerous honors, including recognition as a Fellow of the Association for the Advancement of Artificial Intelligence and the Institute of Electrical and Electronics Engineers. She has also served in key advisory roles for government and international research initiatives, and her work has had a lasting impact on the development of intelligent, cooperative systems. Abstract: Hiding a Swarm's Leader from RL Agent and Human This talk explores methods for protecting leadership within robotic swarms, where leader-based control improves coordination but introduces vulnerability. Using graph neural networks (GNNs), swarms can be trained to follow a leader, while adversarial models attempt to identify it. Results show that although AI models outperform humans in identifying leaders under normal conditions, humans become more effective when swarms adopt deception strategies to hide leaders. Even with adaptive adversaries and increased visual complexity, human observers demonstrate robust performance. These findings highlight key differences between human perception and AI in complex multi-agent environments. AI Safety in the Information and Physical Spaces In this talk, we will present our work on vulnerabilities of Foundational Multi-Modal Models. In particular, we will present jailbreaking of Frontier Models via intention deception and conditions that make multi modal models more vulnerable to adversarial attacks in disclosing dangerous information. We will also propose safety mitigations. Additionally, we will introduce contextual safety and its challenges in the physical world. ※ No registration needed.

Topic：The Digital Shift: Transforming Clinical Trials with Big Data and AI Speaker: PhD degree in Biomedical Informatics from Stanford University Time: 2026/05/05 (二)  14:00-16:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/WbvX79 or scan QR code on poster About the Speaker: Dr. Ray Lin got his BS and MS degrees in Computer Science and Information Engineering from National Taiwan University, specializing in AI in his Master’s Thesis. He later obtained a MS degree in Statistics and a PhD degree in Biomedical Informatics from Stanford University. His PhD research focused on synthetic clinical trials using computer-simulated virtual patients to evaluate cancer screening for lung cancer and breast cancer. Dr. Lin has accumulated 15 years of experience in drug development with Genentech (Roche) supporting clinical trials for developing new cancer treatments, including therapies approved in multiple cancer types globally. He has also been actively engaging in cross-industry collaborations and professional organizations, including multiple leadership positions in an American Statistical Association (ASA) scientific working stream, a US FDA initiated cross-pharma initiative in oncology, and the ASA San Francisco Bay Area local chapter. Abstract: Randomized controlled trials (RCTs) remain the gold standard for clinical research; however, they face significant hurdles, including high costs, lengthy timelines, and ethical or feasibility constraints. The era of Big Data and AI presents transformative opportunities to address these challenges. Real-world data (RWD)—such as electronic medical records, insurance databases, and disease registries—can supplement RCTs to reduce costs, enhance enrollment, and accelerate timelines, particularly for rare diseases with high unmet medical needs. Simultaneously, AI-driven models can predict patient outcomes, enabling the simulation of "virtual patients" in synthetic clinical trials when traditional randomization is impractical or unethical. This presentation features two case studies: (1) A novel dynamic borrowing method that integrates RCTs with external data to increase study efficiency while minimizing selection bias and maintaining trial integrity; (2) The use of virtual patients and synthetic trials to evaluate cancer screening programs. These findings were incorporated into the National Cancer Institute’s Cancer Intervention and Surveillance Modeling Network consortium (CISNET) consortium and have directly influenced breast cancer screening recommendations in the U.S. and Taiwan. ※ No registration needed.

Topic: Transforming Assistive Oral Communication Technologies through Artificial Intelligence Speaker: Prof. Yu Tsao, Research Fellow (Professor) and the Deputy Director at the Research Center for Information Technology Innovation, Academia Sinica Time : April 21, 2026 (Tuesday), 2:00 – 4:00 p.m. Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/grQlk4 or scan QR code on poster  About the Speaker:    Yu Tsao (Senior Member, IEEE) received the B.S. and M.S. degrees in Electrical Engineering from National Taiwan University, Taipei, Taiwan, in 1999 and 2001, respectively, and the Ph.D. degree in Electrical and Computer Engineering from the Georgia Institute of Technology, At-lanta, GA, USA, in 2008. From 2009 to 2011, he was a Researcher at the National Institute of Information and Communications Technology (NICT), Tokyo, Japan, where he conducted re-search and product development in multilingual speech-to-speech translation systems, focusing on automatic speech recognition. He is currently a Research Fellow (Professor) and the Deputy Director at the Research Center for Information Technology Innovation, Academia Sinica, Tai-pei, Taiwan. He also holds a joint appointment as a Professor in the Department of Electrical Engineering at Chung Yuan Christian University, Taoyuan, Taiwan. His research interests in-clude assistive oral communication technologies, audio coding, and bio-signal processing. He serves as an Associate Editor for IEEE Transactions on Consumer Electronics and IEEE Signal Processing Letters. He received the Outstanding Research Award from Taiwan’s National Sci-ence and Technology Council (NSTC), the 2025 IEEE Chester W. Sall Memorial Award, and served as the corresponding author of a paper that won the 2021 IEEE Signal Processing Society Young Author Best Paper Award. Abstract: This presentation provides an overview of AI-driven assistive oral communication technologies, encompassing both assistive speaking and assistive hearing domains. The first part focuses on assistive speaking technologies, highlighting intelligent diagnostic and enhancement frame-works for speech disorders. It introduces machine learning approaches for pathological speech classification, severity assessment, and targeted enhancement for conditions such as dysarthria, post-surgical speech impairment, and electrolaryngeal speech. The second part addresses assis-tive hearing, presenting recent advances in AI-based diagnostic and signal processing tech-niques for hearing disorders. Representative applications include automated detection of otitis media with effusion, as well as AI-driven speech generation and objective quality assessment methods for hearing aids and cochlear implants. By integrating speech enhancement, assess-ment, and generation within a unified AI framework, this presentation demonstrates the poten-tial of neural-based technologies to enhance communication effectiveness and accessibility, while underscoring the importance of interdisciplinary research in advancing next-generation, human-centered assistive systems. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center ※ No registration needed.

Topic: Genomics, Big Data, and AI: New Approaches for Understanding Complex Diseases Speaker: Prof. AiRu Hsieh — Associate Professor, Department of Statistics, National Taipei University Time: March 25, 2026 (Tuesday), 12:10 – 14:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/lpdb2q or scan QR code on poster Registration: https://forms.office.com/r/iUTLaer75x or scan QR code on poster  About the Speaker:   Professor Ai-Ru Hsieh is a researcher in statistical genetics and biomedical data science. Her work focuses on integrating genome-wide association studies (GWAS), polygenic risk scores (PRS), Mendelian randomization (MR), and machine learning approaches to investigate the genetic architecture and causal mechanisms of complex diseases. By leveraging large-scale biobank resources and high-dimensional biomedical data, her research aims to develop interpretable models for disease risk prediction and biological discovery. Her work contributes to advancing precision medicine and improving our understanding of disease mechanisms at both clinical and population health levels. Abstract: Recent discoveries in human genetics are driving precision medicine forward. Large-scale genome-wide association studies (GWAS) have mapped thousands of variants related to complex diseases, offering insight into their biology. Polygenic risk scores (PRS) pull together these small genetic signals to flag people who might warrant earlier screening or closer monitoring. Mendelian Randomization (MR) provides a statistical framework for evaluating potential causal relationships between exposures and disease outcomes, offering support for targeted interventions. In addition, machine learning approaches provide powerful tools for feature selection and predictive modeling in high-dimensional biomedical datasets. Techniques such as LASSO, random forests, and gradient boosting models can identify informative genetic variants, biomarkers, and clinical variables from large-scale datasets. These approaches improve disease risk prediction, refine polygenic risk models, and help uncover hidden patterns in MR analysis. By integrating statistical genetics methods, machine learning algorithms, and large-scale biomedical data resources, we can build interpretable models for disease prediction and biological discovery. The findings from these approaches make us more understanding of disease mechanisms and guide more effective prevention and treatment efforts in both clinical and population health contexts. Organizers: Institute of Health Data Science ※ Registration needed.