Embedded Files
Agenda (GMT +9)
Agenda (GMT +9)
10:00 AM - 11:00 AM Full paper presentations (15 min presentation + 3 min Q&A, Session Chair: John Stamper)
Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification by Haocheng Zhang, Zhuqian Zhou, Kirk Vanacore, Bakhtawar Ahtisham and René Kizilcec (Cornell) [Slides]
The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation by Zhengyuan Liu, Stella Xin Yin, Bryan Chen, Zhengyu Tan, Roy Ka-Wei Lee, Guimei Liu, Dion Hoe-Lian Goh, Wenya Wang and Nancy F. Chen (A*STAR, SUTD, and NTU) [Slides]
PEELing Argumentation: Scaffolding Elementary Argumentative Writing with Decomposed LLM Feedback by Stella Yin, Geyu Lin, Zhengyuan Liu, Brian Y Lim and Nancy F. Chen (NTU, NUS, and A*STAR) [Slides]
11:00 AM - 12:00 AM Keynote Speakers (25 min presentation + 5 min discussion): Xiangen Hu, John Stamper
12:00 AM - 1:30 PM Lunch
1:30 PM - 2:30 PM Full paper presentations (15 min presentation + 3 min Q&A, Session Chair: Yang Shi)
CFL-KG: A Knowledge Graph for Instructional Support in Chinese as a Foreign Language by Han Wang, Qianyu Wang, Yunshi Lan, Ye Wang, Yuanyuan Liang and Anqi Ding (ECNU) [Slides]
When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring by Nischal Ashok Kumar, Payu Wittawatolarn, Sana Kang, Marisa Peczuh, Blair Lehman, Ryan Baker, Caitlin Mills, Sherry Lachman, Ruochen Sun and Andrew Lan (UMass, UMN, Brighter Research, Adelaide, AERDF) [Slides]
2:10 PM - 2:30 PM Short Networking Break (due to an author no-show)
2:30 PM - 3:30 PM Research Track Presentations (15 min presentation + 3 min Q&A, Session Chair: Xiangliang Zhang)
Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective by Ziwen Wang, Shangshang Yang, Xiaoshan Yu, Haiping Ma and Xingyi Zhang (AHU)
HiLLM-CD: LLM-Enhanced Hierarchical Cognitive Diagnosis by Yuquan Xie, Wanqi Yang, Bo Zhang, Zekun Li, Lei Wang, Ming Yang and Yang Gao (NJNU, Wollongong, NJU)
HRKT: Hierarchical Recurrent Knowledge Tracing for Efficient Transformer-Based Long-Sequence Modeling by Ju-Yeong Park, Tae-Gwon Lee and Ji-Hoon Bae (KNUE)
3:30 PM - 4:00 PM Coffee Break
4:00 PM - 5:00 PM Community discussion and round table: The future of AI in education and data mining
5:00 PM - 6:00 PM Posters (Full + Short papers)
Poster-only full paper list:
Causality-Inspired Representation Learning for Student Performance Prediction by Boya Liu, Zijun Li and Jie Yang (Xi'an Eurasia, Tongji)
Short paper list:
FairTutor: Equity-Aware Pedagogical LLM Routing for Budget-Constrained AI Tutoring by Qingyang Xu
From Live Concert to Pedagogical Insight: Designing an Intelligent Concert Knowledge Navigation Panel by In Son Zeng (UMich)
AILitHub: Building AI Literacy Infrastructure to Situate Frameworks into Practice by Jiayi Wang, Ruiwei Xiao, Manqing Yu, Hsuan Nieu, Ying-Jui Tseng, John Stamper and Xinying Hou (UMD, CMU, NTHU, UMich)
Genie in a Bottle: Constrained LLM Feedback for Code Tracing Exercises by Aysa Fan (UIUC) (Canceled as no presenter will be available)
Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction by Yongkyung Oh, Lynn Talton and Alex Bui (UCLA)
Keynote Speakers
Keynote Speakers
Dr. Xiangen Hu is a DoERC & Chair Professor of Learning Sciences and Technologies at The Hong Kong Polytechnic University (Poly U). Dr. Hu received his MS in applied mathematics from Huazhong University of Science and Technology, MA in social sciences and Ph.D. in Cognitive Sciences from the University of California, Irvine. Prof. HU's research focuses on four key areas: developing mathematical models to decode human cognitive behavior, specializing in research design and statistical analysis particularly for categorical data using general processing tree models, delving into artificial intelligence for knowledge representation, creating computerized tutoring systems, and enhancing distributed learning technologies. His work has attracted significant funding from prestigious bodies like the US National Science Foundation, the US Institute of Education Sciences, the Advanced Distributed Learning initiative of the US Department of Defense, the US Army Medical Research Acquisition Activity, the US Army Research Laboratories, and the US Office of Naval Research. As the lead principal investigator, Prof. HU has managed projects with over $10 million in funding, and as a co-principal investigator, he has been involved in projects amassing more than $30 million in grants.
Dr. John Stamper is an Associate Professor & the METALS Program Director at the Human-Computer Interaction Institute of Carnegie Mellon University. He earned his Ph.D. in computer science at the University of North Carolina at Charlotte. His main area of research is focused on using big data from educational systems to improve learning. He generally publishes in the areas of intelligent tutoring systems and educational data mining. He is also the lead researcher behind DataShop, which is the largest open repository of log data from learning systems. Prior to starting his Ph.D., Stamper spent over ten years in the business world. Although he is still consulting, his most recent major position was Vice President of Development for VSI Technolgies, Inc. During this role, he earned his MCSE (Microsoft Certified Systems Engineer) and MCDBA (Microsoft Certified Database Administrator) certifications. Recently, he has been involved in creating a new startup called TutorGen, which is looking to help build intelligent tutoring capabilities for existing educational technologies with the use of big data.
Google Sites
Report abuse