Keynote Speech 1
Evolution of Networking Stacks into the Cloud
Abstract
For most of the 20th century networking platforms have remained mostly dedicated hardware with proprietary software stacks. As the number of networking applications such as QoS controllers, VPN gateways, WAN optimizers, and firewalls, has increased, demand for flexible network configuration has never been stronger. Furthermore, the exponential growth of the datacenter networking market has pushed technological breakthroughs in high performance networking.In this talk we cover past history of networking stacks based on commodity hardware with a focus on projects in our Advanced Networking Lab, namely PacketShader, NBA, S6, Dilos and Adios. From Packet Shader to NBA, we have put batching as the first principle in high-performance networking platform design and exploited not just for IO but also for computing. ? In S6 we have expanded our research on high-speed networking platforms to elastic scaling of NFVs in datacenters. Also we are looking at RDMA as an alternative high-speed interconnect for disaggregated datacenters. We conclude with remaining technical challenges and emerging relevant trends.
Bio: Sue Moon received her B.S. and M.S. from Seoul National University, Seoul, Korea, in 1988 and 1990, respectively, all in computer engineering. She received Ph.D.in computer science from the University of Massachusetts at Amherst in 2000. From 1999 to 2003, she worked in the IPMON project at Sprint ATL in Burlingame, California. In August of 2003, she joined KAIST and now teaches in Daejeon, Korea. Her research interests lie in datacenter networking. She has served in numerous technical committees of prestigious conferences and served as chairs for WWW 2013 and ACM CoNEXT 2017, just to name a few. She was named a N2Women Star in Computer Networking and Communications by IEEE ComSoc in 2021. Her Best Paper of ACM IMC 2007 won the Test of Time Award in 2022. In 2021 she served as a deliberative member in the Presidential Advisory Council on Science and Technology in 2021. In 2026 she serves as president of KIISE (Korea Institute of Information Science and Engineering).
Keynote Speech 2
Geospatial entity representation and city foundation models.
Abstract
The talk will cover the following research problems on geospatial AI: 1) Geospatial entity representation for point objects, trajectory, and regions and their applications, e.g., spatial keyword search, POI recommendation, speed inference, region population estimations, etc. ?2) foundation models for geospatial applications and efforts toward city foundation models. The first part primarily concentrates on learning representations to facilitate geospatial entity querying and analysis. The second part focuses on self-supervised learning approaches applied to geospatial entities, and several research attempts towards city foundation models.
Bio: Gao Cong is currently a Professor in the College of Computing and Data Science (CCDS) at Nanyang Technological University (NTU). He previously worked at Aalborg University, Denmark, Microsoft Research Asia, and the University of Edinburgh. His current research interests include Data+AI, spatial data management, spatial-temporal data mining, and recommendation systems. His citation in Google Scholar was over 23,000 with H-index 78. He received SIGIR'25 test of time award honorable mention award, and ?the best paper runner-up awards at the WSDM'20 and WSDM'22 conferences for two of his research papers. He served as a PC co-chair for ICDE'2022, the associate general chair of KDD'21, a PC co-chair for E&A track of VLDB 2014, and a PC vice-Chair for ICDE'18. He serves as an associate editor for ACM TODS and IEEE TKDE.
Keynote Speech 3
Innovation and Practice of AI Infrastructure for Multi-modal Data Processing Needs.
Abstract
Abstract: In the Data+AI era, the real-time processing capability of multi-modal data is the core driving force for building Agentic AI. The new-generation intelligent cloud-native database, with its extreme elasticity, outstanding performance, and inherent intelligent capabilities, provides a solid and efficient data infrastructure for the development of upper-layer intelligent applications and Agentic AI. It provides foundational support for unlocking the value of multi-modal data in complex business scenarios.
Bio: Wenchao ZHOU is the Director of OLAP and Data Products at the Database Business Unit of Alibaba Cloud Intelligence. Prior to joining Alibaba Cloud Intelligence, he was a tenured Professor at the Computer Science Department of Georgetown University. Wenchao is an expert and a veteran in Databases and Distributed Systems with over 10 years academic and industrial experience. He has published over 70 papers at leading conferences. He has been recognized by multiple prestigious awards, including NSF CAREER award, SIGMOD Jim Gray Dissertation award, and several best paper awards. Wenchao receives his PhD and Masters from University of Pennsylvania, and his Bachelor from Tsinghua University, all in Computer Science.