The KAIST Interaction Lab (KIXLAB, https://www.kixlab.org/) is a human-computer interaction research group in the School of Computing at KAIST. Our mission is to improve the ways in which people learn, collaborate, discuss, make decisions, and take action online by designing new AI-infused interactive systems.
With the recent advances in AI, more AI-powered interactive systems have been designed to support people in various everyday tasks. Tension arises, however, when we apply state-of-the-art AI technology to a real-world task without careful consideration of users and their context. In KIXLAB, we believe that human-AI interaction should be considered as a first-class object when designing AI-powered systems.
We build novel interactive systems that use AI techniques to support everyday tasks. RecipeScape (top image, https://recipescape.kixlab.org/) is a visual analytics system that allows large-scale analyses of cooking recipes. The system uses AI to compute the procedural and semantic similarity between recipes to generate a Recipe Map, where hundreds of recipes for a single food are visualized with information about clusters of similar approaches and pairwise similarity. SolutionChat (bottom image, https://solutionchat.kixlab.org/) is a system that supports chat-based online discussions by recommending useful moderation messages and questions in real-time. The system uses AI that analyzes discussion text in real-time to recommend messages and questions that are contextually appropriate. Our evaluation shows that the burden undertaken by moderators is reduced with the system.
We strive to make a real-world impact with our research. We’re always looking for ways to transfer our findings from research projects to practical applications. Many of our research projects have been deployed to the public. We also attempt to open our source code and data to the public whenever we can. We actively collaborate with companies. Many members of the lab are drawn to the vision of creating interactive systems that provide practical value to real users.
Professor Juho Kim is an Associate Professor in the School of Computing and affiliated faculty in the Kim Jaechul Graduate school of AI at KAIST. He is the director of KIXLAB (KAIST Interaction Lab). He earned his Ph.D. from MIT in 2015, M.S. from Stanford University in 2010, and B.S. from Seoul National University in 2008. In 2015-2016, he was a Visiting Assistant Professor and a Brown Fellow at Stanford University. He is a recipient of KAIST’s Songam Distinguished Research Award, Grand Prize in Creative Teaching, and Excellence in Teaching Award, as well as 12 paper awards from ACM CHI, ACM CSCW, ACM Learning at Scale, ACM IUI, ACM DIS, and AAAI HCOMP.
