Keynote Speakers
Nava Tintarev
Title: One-size Explanations still do not fit all
Abstract: Many people recognize the importance of explainable AI, yet we often lose sight of the purpose of these explanations. This talk explores why we should develop decision support systems that can explain themselves. It highlights state-of-the-art explanation approaches across domains such as music, tourism, and search results, illustrating how they help align the mental models of systems and users. At the same time, generating rich and complex explanations is not enough to support effective decision-making. Designers must carefully decide which information to present and how to present it, taking into account the target users and contextual factors. With the rise of generative AI, these continue to be valid research questions, even if generating the explanations can at least at first sight seem quicker or easier. We must also reconsider what has changed: new challenges—beyond hallucinations—have become more prominent, including subtle stereotyping and data leakage Bio: Prof. Nava Tintarev is a Full Professor in Explainable AI at Maastricht University in the Department of Advanced Computing Sciences (DACS). Her interdisciplinary work bridges computer science and human-centered evaluation, focusing on making AI systems more transparent and increasing user control. Prof. Tintarev specializes in developing interactive explanation interfaces for recommender systems and search technologies, emphasizing user empowerment and decision support. She is a lab director of the ICAI TAIM lab, working on trustworthy AI in media. She was a founding co-investigator of ROBUST, a €87 million Dutch national initiative advancing trustworthy AI. Her research has also been supported by major organizations including IBM, Twitter, and the European Commission. Recognized as a Senior Member of the ACM in 2020, Prof. Tintarev’s team has received multiple best paper awards for research contributions at UMAP, CHI, CHIIR, Hypertext, and HCOMP. She is also active in Dutch developing research policy for computer science in the Netherlands, as the Chair of the round table member for informatics, and as a board member of the ICT-Research Platform Netherlands (IPN).
Sahar Asadi
Title: Understanding Players Through Context: A Foundation Model Perspective
Bio: Sahar Asadi is Director of AI Labs at King, part of Microsoft Gaming, where she leads industrial research on reinforcement learning, foundation models, representation learning, and player behavior understanding. Her research centers on translating advances in AI into practical applications, with a particular emphasis on systems that improve player experience and support game development. She received her Ph.D. in Computer Science from Örebro University and has held research and applied machine learning roles at Spotify, Meltwater, and Clusterone. She has co-authored work published at NeurIPS, AAAI, EMNLP, IDA, AIIDE, IEEE Transactions on Games, and delivered keynotes at IEEE Conference on Games, GDC, and FDG. She serves as Associate Editor at IEEE Transactions on Games and an Area Chair of ECML PKDD.
Ranjitha Kumar
Bio: Ranjitha Kumar is an Associate Professor in the Siebel School of Computing and Data Science and (by courtesy) the Department of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. She leads the Data Driven Design Group, where her research focuses on the intersection of machine learning and effective user experiences. She also serves as the Director of the Innovation Leadership and Engineering Entrepreneurship (ILEE) Program in the Grainger College of Engineering.
In addition to her academic leadership, she is the Chief Scientist at UserTesting. Since 2019, she has guided the company’s AI-product strategy, working to bridge quantitative and qualitative experience testing. She received her B.S. and Ph.D. from the Department of Computer Science at Stanford University. Based on her dissertation work, she co-founded Apropose, a data-driven design startup backed by top Silicon Valley venture capital firms.