Keynote Speakers

Chloé Clavel

Chloé Clavel is a Senior Researcher in the ALMAnaCH team at INRIA Paris (the French national research institute for digital science and technology). Until October 2023, she was a Professor of Affective Computing at LTCI, Telecom-Paris, Institut Polytechnique de Paris, where she coordinated the Social Computing team. Her research interests are in the areas of Affective Computing and Artificial Intelligence that lie at the crossroads of multiple disciplines including, speech and natural language processing, machine learning, and social robotics. She studies computational models of socio-emotional behaviors (e.g., sentiments, social stances, engagement, trust) in interactions be it human-human interactions (social networks, job interviews) or human-agent interactions (conversational agents, social robots).

Title: Socio-conversational AI: Modelling the socio-emotional component of interactions using neural models 

Abstract: A single lack of social tact on the part of a conversational system (chatbot, voice assistant, social robot) can lead to a decrease in the user’s trust and engagement in the interaction. This lack of social intelligence affects the willingness of a large audience to view conversational systems as acceptable. To understand the state of the user, the current research community in affective/social computing has drawn on research in artificial intelligence and social science. In recent years, however, the trend has shifted towards a monopoly of deep learning methods, which are quite powerful but opaque, greedy for annotated data and less suited for integrating social science knowledge. I will present here the research we are doing to develop machine learning approaches (from classical approaches to large language models) for modelling the social component of interactions. In particular, I will focus on research that aims to improve the explainability of the models as well as their transferability to new data and new socio-emotional phenomena.

Katja Zibrek is a researcher at Inria center at Rennes University, France. She holds a bachelor's and master's degree in Psychology from the University of Ljubljana, Slovenia, and a doctorate in Computer Science from Trinity College Dublin, Ireland. She received a Marie Sklodowska-Curie postdoctoral fellowship at the Inria center at Rennes University, France. Her primary research focus is on the perception of virtual humans. She is particularly interested in using indirect measures to evaluate the perception, employing virtual reality as the main method for collecting behavioral data.

Title: The importance of animation in virtual human design

Abstract: Animation is the crucial part in designing autonomous virtual humans (agents) for immersive applications. It is the source of valuable information about the agent and important in communication with the user. Creating a truly adaptive and responsive agent in virtual reality is a considerably challenging endeavour, especially when striving to achieve a high level of appearance and behavioural realism. With the recent advances in LLM, agents can now be endowed with a convincing verbal responses but how about their non-verbal responses in the form of body and facial movements? In this talk, we will explore some of the advances and limitations on agent non-verbal behaviour in the present literature and present our own research done in the area of agent animation.