HCI Sorbonne

Oleksandra Vereschak invites you all to a research seminar on Human-AI Collaboration on Tue, Dec 13, 2022. It will consist of 4 talks around the topics of how people trust and make decisions with Artificial Intelligence and how this knowledge can inform meaningful interactions with AI. The invited speakers are: Thomas Baudel (IBM France), Niels van Berkel (Aalborg University), Nicole Krämer (Universität Duisburg-Essen), Baptiste Caramiaux (Sorbonne Université). The event is organized with the support of ISIR, CAPSULE, Gilles Bailly, and Baptiste Caramiaux.

Full program: [here]

Benoît Geslain, supervised by Gilles Bailly and Sinan Haliyo, will defend his thesis entitled “Visuo-haptic Illusions in Virtual Reality Design and Learning” on December 07, 2022.

Jianyong Xue joined the team of Interactions Multi-Échelles as a new post-doc in the ISIR lab of Sorbonne Université, on the topic of research of computational models for studying HCI in learning and decision-making with neuroscience approaches, under the supervision of Dr. Gilles Bailly.

Before he joined the ISIR, he did the post-doc in the team of Mnemosyne of Inria Bordeaux Sud-Ouest and Institut des maladies neurodégénératives de Bordeaux (IMN), under the supervision of Professor Frédéric Alexandre. Basically, his work aims at models of computational neuroscience to explore mechanisms in decision-making and contextual control learning as the cortical level, such as the capacity of the hippocampus to categorize diverse contexts, and the rule of prefrontal cortex to modulate appropriate behavioral activities.

You could find his contributions in scientific domain: [google scholar]

Demos  and simulations of robots that he has designed in [youtube channel]

Implementations for related projects in [github repositories].

Théo Jourdan is now part of the ANR-funded project ARCOL “Interactive Reinforcement Co-Learning” led by Baptiste Caramiaux. He is now working on the use of Machine Learning (ML) algorithms to support learning and exploration in music making. Théo previously worked on the privacy aspects of using ML in healthcare applications, where the data collected are particularly sensitive and in need of privacy protection mechanism.

More about his previous research: [Google Scholar]

Who: Sebastien Lallé (Sorbonne Université – LIP6)
Where: Room 304, ISIR
When: June 30, 11:00AM

Title: Eye-tracking for User-Adaptive Visualizations
Abstract: Information visualization (InfoVis) is a thriving area of research that takes advantage of the strength of human perception to facilitate the analysis of data. Visualizations are typically designed based on the data to be displayed and the tasks to be supported, but they typically follow a one-size-fits-all approach when it comes to their users. There is, however, mounting evidence that the users’ individual characteristics, preferences and behaviors can significantly influence the effectiveness of the visualization. These findings have prompted research on user-adaptive visualizations, i.e., visualizations that can track and adapt to relevant user needs at runtime. In this talk, I will present results on how the needs of the users can be captured using predictive models based on eye-tracking data during visualization processing. I will also report on how to leverage these eye-tracking-based models to provide personalized support meant to improve the user’s experience with the visualization.

Bio: His main area of research is in Human-Centered AI (HCAI), a highly interdisciplinary field at the intersection of AI, HCI, and Data Science. Specifically, the main objective of his research is to create intelligent systems that can better support effective human-computer interaction by integrating traditional HCI approaches with innovative AI techniques that enable advanced forms of interaction. To this end, He has focused on designing intelligent user-adaptive systems that can: (i) Recognise the specific needs, affect and abilities of their users (a task called user modeling); (ii) Provide users with a personalized interaction experience by adapting in real-time to the detected user’s needs and abilities.
He has conducted several user studies to investigate the user perception, impacts and benefits of such user adaptation for a variety of systems, including intelligent educational environments, pedagogical virtual agents, visualizations, decision support systems, and citizen engagement platforms.

Host: Gilles Bailly

Fatemeh Alizadeh, Dominik Pins and Oleksandra Vereschak co-organized ECSCW2022 Workshop on appropriate trust in AI with the support of their suporvisors Gunnar Stevens, Gilles Bailly, and Baptiste Caramiaux.

Check out the panel discussion.

Photo memory: here.

Who: Antti Oulasvirta
Where: Room 304, ISIR
When: June 21, 10:00 AM
Title: Computational Rationality as a theory of interaction
Abstract: How do people interact with computers? This fundamental question was asked by Card, Moran and Newell in 1983 with a proposition to frame it as a question about human cognition, in other words as a question of how information is processed in the mind. Recently, the question has been reframed as a question of adaptation: how do people adapt interaction to the limits imposed by cognition, device design and its environment? We synthesize advances in answering this question under the theoretical framework of _computational rationality_. The core assumption is that users act according to what is best for them given the limits imposed by their cognitive architecture and their experience of the task environment. The theory can be expressed in computational models which use reinforcement learning to explain and predict interaction. I review the theoretical commitments and emerging applications in HCI. I close by outlining challenges for future work.

Bio: Antti Oulasvirta leads the User Interfaces research group at Aalto University and the Interactive AI research program at FCAI (Finnish Center for AI). Prior to joining Aalto, he was a Senior Researcher at the Max Planck Institute for Informatics and the Cluster of Excellence on Multimodal Computing and Interaction at Saarland University. He received his doctorate in Cognitive Science from the University of Helsinki in 2006, after which he was a Fulbright Scholar at the School of Information in the University of California-Berkeley in 2007-2008 and a Senior Researcher at Helsinki Institute for Information Technology HIIT in 2008-2011. During his postgraduate studies in 2002-2003, he was an exchange student at UC Berkeley’s Neuropsychology Lab. He was awarded the ERC Starting Grant (2015-2020) for research on the computational design of user interfaces. Dr. Oulasvirta serves as an associate editor for ACM TOCHI and has previously served the International Journal of Human-Computer Studies, as well as served as a column editor for IEEE Computer. He frequently participates in the paper committees of HCI conferences, including the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI). His work has been awarded the Best Paper Award and Best Paper Honorable Mention at CHI fiften times between 2008 and 2022. He has held keynote talks on computational user interface design at NordiCHI’14, CoDIT’14, EICS’16, IHCI’17, ICWE’19, and Chinese CHI ’19. He is a member of ELLIS (European Laboratory for Learning and Intelligent Systems). In 2019, he was invited to the Finnish Academy of Science and Letters.

Téo Sanchez, supervised by Baptiste Caramiaux and Wendy E. Mackay, will defend his thesis entitled “Interactive Machine Teaching with and for novices” on June 20, 2022.
Link to the live stream: [here]
Link to his PhD thesis: https://hal.science/tel-03807887v2/file/106366_SANCHEZ_2022_archivage.pdf

Oleksandra Vereschak, PhD student, presented a working paper “What AI Practitioners Say about Human-AI Trust: Its Role, Importance, and Factors That Affect It” with permanent researchers Gilles Bailly and Baptiste Caramiaux at HHAI2022, first International Conference on Hybrid Human-Artificial Intelligence.