:::

News bulletin board

AI Seminar

20250415_YufengJaneTseng.png
01

【AI Seminar】2025.04.15 AI in Drug Discovery and Development - Prof. Yufeng Jane Tseng

2025.03.25
Topic: AI in Drug Discovery and Development Speaker: Yufeng Jane Tseng.  Department of Computer Science and Information Engineering, National Taiwan University Time: 2025/04/15 (Tue) 14:00-16:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/XAeDDa or scan QR code on poster  About the Speaker:   Professor Yufeng Jane Tseng received her B.S. degree in Pharmacy from National Taiwan University in 1997. Prof. Tseng then received her Ph.D. in Medicinal Chemistry and Pharmacognosy from the University of Illinois at Chicago (UIC) in 2002 and received the Charles Bell Award for Computational Chemistry in 2001. From 1998 to 2006, Prof. Tseng worked as a Principal Molecular Modeling Software Developer at The Chem21 Group, Inc., in Lake Forest, USA. From 2004 to 2006, Prof. Tseng also worked as a postdoctoral research fellow at the National Center for Biotechnology Information, National Institutes of Health in Bethesda, MD, USA. Prof. Tseng joined the Department of Computer Science and Information Engineering at National Taiwan University (NTU) in 2006 as an Assistant Professor and holds a joint appointment at the School of Pharmacy also at NTU. Prof. Tseng has devoted 19 years of active service in education and is a leader in computational chemistry and computer-aided drug design. Since 2009, she has founded and served as the Principal Investigator of the Metabolomics Core Laboratory at NTU. Since 2010, Prof. Tseng has been organizing and chairing the Drug Discovery Symposium at the American Chemical Society (ACS) National Meetings and continues her services at ACS to the present. In 2014, she became a Professor at the Graduate Institute of Biomedical Electronics and Bioinformatics, with the Department of Computer Science and Information, and at the School of Pharmacy. Prof. Tseng was appointed the Director of the Drug Research Center at NTU, and in 2016, she was appointed the associate Director of the Neurobiology and Cognitive Science Center at NTU. In 2019, she was appointed as the associate chair of the Computer Science and Engineering department at NTU and the center scientists at the National Center for Theoretical Sciences, Physics Division (NCTS Physics). In 2020, she was appointed as the Principal Investigator at Stanford-Taiwan Biomedical Fellowship Program, STPI. Abstract: AI or deep learning is a buzzword in recent years. How it was applied and truly helped remained vague in drug discovery and drug development. This talk is going to cover the use of computer-aided techniques as well as the true AI aided process in the CNS disease. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center ※ No registration needed.
4ee24ffc-5250-41c2-9322-d80c4da09edd.png
02

【AI Seminar】2025.03.25 Video Understanding and Generation on Multimodal Foundation Models - Prof. Ming-Hsuan Yang

2025.03.06
Topic: Video Understanding and Generation with Multimodal Foundation Models Speaker: Ming-Hsuan Yang.  Department of Electrical Engineering and Computer Science, University of California, Merced Time: 2025/03/25 (Tue) 14:10-16:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/b3M6rd or scan QR code on poster  About the Speaker:   Ming-Hsuan Yang is a Professor at the University of California, Merced, and a Research Scientist at Google DeepMind. He has received numerous prestigious awards, including the Google Faculty Award 2009, the NSF CAREER Award 2012, and the Nvidia Pioneer Research Award 2017 and 2018. He received Best Paper Honorable Mention at UIST 2017, Best Paper Honorable Mention at CVPR 2018, Best Student Paper Honorable Mention at ACCV 2018, Longuet-Higgins Prize (Test-of-Time Award) at CVPR 2023, Best Paper at ICML 2024, and Test-of-Time Award from at WACV 2025. Yang is an Associate Editor-in-Chief of IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) and an Associate Editor for the International Journal of Computer Vision (IJCV). Previously, he was the Editor-in-Chief of Computer Vision and Image Understanding (CVIU) and Program Co-Chair for ICCV 2019. He is a Fellow of IEEE, ACM, and AAAI. Abstract: Recent advances in vision and language models have significantly improved visual understanding and generation tasks. In this talk, I will present our latest research on designing effective tokenizers for transformers and our efforts to adapt frozen large language models for diverse vision tasks. These tasks include visual classification, video-text retrieval, visual captioning, visual question answering, visual grounding, video generation, stylization, outpainting, and video-to-audio conversion. If time permits, I will also discuss our recent findings on learning diffusion models and dynamic 3D vision. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center ※ No registration needed.
20250318_Stanley Chang.png
03

【AI Seminar】2025.03.18 Mobile Attention Management: Evolving from Protection to Enhanced Notification Interaction and Digital Engagement - Prof. Yung-Ju (Stanley) Chang

2025.03.05
Topic: Program-Guided Robot Learning Speaker: Yung-Ju (Stanley) Chang.  Associate Professor, Department of Computer Science, Institute of Communication Studies, National Yang Ming Chiao Tung University Time: 2025/03/04 (Tue) 14:10-16:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/kMDxab or scan QR code on poster  About the Speaker:   Yung-Ju (Stanley) Chang received his M.S. and Ph.D. degrees in Information Science from the University of Michigan. He is currently a professor in the Department of Computer Science at National Yang Ming Chiao Tung University (NYCU). His research interests lie in the area of Human-Computer Interaction (HCI), with a specific focus on attention management, notification systems, mobile crowdsourcing, human-AI interaction, and social media influencers. Abstract: Over the past decade, research on attention management within Human-Computer Interaction (HCI) has evolved significantly. Early studies primarily focused on protecting users' attention by identifying appropriate moments for interruptions and analyzing how people respond to them. However, as the field has progressed, the focus has gradually shifted toward enhancing users’ interactions with incoming information and ensuring that digital engagement and time allocation become more efficient, effective, and meaningful. Throughout this evolving trend, new research challenges have emerged. My past projects have explored and addressed these challenges, while my current work continues to tackle the latest issues arising from these ongoing developments. In this talk, I will present these projects and discuss how they contribute to navigating the continuously shifting landscape of attention management. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center   ※ No registration needed.
20250304_ShaoHuaSun.png
04

【AI Seminar】2025.03.04 Program-Guided Robot Learning - Prof. Shao-Hua Sun

2025.03.05
Topic: Program-Guided Robot Learning Speaker: Shao-Hua Sun.  Assistant Professor, Department of Electrical Engineering and the Graduate Institute of Communication Engineering, National Taiwan University (NTU) Time: 2025/03/04 (Tue) 14:10-16:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: Click here or scan QR code on poster  About the Speaker:   Shao-Hua Sun is an Assistant Professor in the Department of Electrical Engineering at National Taiwan University (NTU). He completed his Ph.D. in Computer Science at the University of Southern California (USC) and holds a B.S. in Electrical Engineering from NTU. He has been awarded Yushan Young Fellow by the Ministry of Education, Taiwan. Prof. Sun's research interests include machine learning, robot learning, reinforcement learning, and program synthesis. His work has been presented at premier conferences across diverse fields, including machine learning (NeurIPS, ICML, ICLR), robot learning (CoRL), computer vision (CVPR, ECCV), and natural language processing (EMNLP, COLM). He has organized tutorials at ACML 2023 and NeurIPS 2024. Abstract: Recent developments in artificial intelligence and machine learning have remarkably advanced machines’ ability to understand images and videos, comprehend natural languages and speech, and outperform human experts in complex games. However, building intelligent robots that can operate in unstructured environments, manipulate unknown objects, and acquire novel skills – to free humans from tedious or dangerous manual work – remains challenging. My research focuses on developing a robot learning framework that enables robots to acquire long-horizon and complex skills with hierarchical structures, such as furniture assembly and cooking. Specifically, I present an interpretable and generalizable program-guided robot learning framework, which represents desired behaviors as a program and acquires primitive skills for executing desired skills. This talk will discuss a series of projects toward building this framework. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center   ※ No registration needed.
1105英文演講海報-張明清_S.png
05

【AI Seminar】2024.11.05 Trustworthy AI in a Smarter World: Addressing Awareness, Authenticity, and Security Challenges- Ming-Ching Chang, Associate Professor

2024.09.25
Topic: Trustworthy AI in a Smarter World: Addressing Awareness, Authenticity, and Security Challenges Speaker: Ming-Ching Chang, Associate Professor, Dept. of Computer Science, College of Engineering and Applied Sciences University at Albany, State University of New York Time: 2024/11/05 (Tue) 14:10-16:00 Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://gqr.sh/LrGY   About the Speaker: Ming-Ching Chang is an Associate Professor with tenure (since Fall 2022) in the Department of Computer Science at the University at Albany, SUNY. He previously held positions in the Department of Electrical and Computer Engineering (2016-2018) and as an Adjunct Professor in Computer Science (2012-2016). From 2008 to 2016, he worked as a Computer Scientist at GE Global Research Center and was an Assistant Researcher at the Mechanical Industry Research Labs, ITRI in Taiwan from 1996 to 1998. Dr. Chang earned his Ph.D. in Engineering Man/Machine Systems from Brown University in 2008, along with an M.S. in Computer Science and Information Engineering (1998) and a B.S. in Civil Engineering (1996) from National Taiwan University. His research focuses on video analytics, computer vision, image processing, and artificial intelligence, with over 70 published papers. His projects have received funding from DARPA, IARPA, NIJ, VA, GE Global Research, Kitware Inc., and the University at Albany. Dr. Chang is a senior member of IEEE. Abstract: Trustworthy AI research aims to create AI models that are efficient, robust, secure, fair, privacy-preserving, and accountable. As the adoption of Foundation Models and Generative AI grows, enabling the composition of articles and the generation of hyper-realistic images, the boundary between authenticity and deception is increasingly blurred in our rapidly evolving digital landscape. The demand for sophisticated tools and techniques to authenticate media content and discern the real from the fake has never been more urgent. In this talk, I will explore recent breakthroughs in Trustworthy AI, Digital Media Forensics, and secure computation. First, I will introduce a novel approach to learning multi-manifold embeddings for Out-of-Distribution (OOD) detection, along with a method for uncovering hidden hallucination factors in large vision-language models through causal analysis. Additionally, I will cover a noisy-label learning technique designed to tackle long-tailed data distributions. In the field of Digital Media Forensics, I will showcase novel advancements in Image Manipulation Detection (IMD) using implicit neural representations under limited supervision. This includes the development of IMD datasets featuring object-awareness and semantically significant annotations, leveraging stable diffusion to emulate real-world scenarios more effectively. Finally, I will discuss key innovations in secure encrypted computation, particularly in accelerating Fully Homomorphic Encryption (FHE) for deep neural network inference using GPUs, as well as enhancing functional bootstrapping through quantization and network fine-tuning strategies.   Organizers: College of Intelligent Computing & Artificial Intelligence Research Center ※ No registration needed.