Florian Pecune
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Florian Pecune has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Catherine Pelachaud
ISIR, CNRS, Sorbonne Université
4 shared publications - Laurence Chaby
Université Paris Cité, Vision Action Cognition, Boulogne- Billancourt, France
4 shared publications - Lucie Galland
ISIR, Sorbonne University
4 shared publications - Pierre Philip
Univ. Bordeaux, CNRS, SANPSY, UMR6033 CHU Bordeaux, Sleep Medicine Unit Bordeaux, France, Bordeaux, France
4 shared publications - Agnès Helme-Guizon
University of Grenoble Alpes, Grenoble INP, CERAG
3 shared publications - Carla Baudonne
University of Bordeaux, cours de la Libération
3 shared publications
Latest Publications
- Open Access
- 6 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
French translation of the Artificial-Social-Agent questionnaire (ASAq) instrument for evaluating human-agent interactions
- 6 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessFrench translation of the Artificial-Social-Agent questionnaire (ASAq) instrument for evaluating human-agent interactions
- 2 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Modélisation de la prise de décision d'un agent conversationnel animé en fonction de son attitude sociale
Afin d’être considérés comme des partenaires crédibles lors d’une interaction, les agents virtuels doivent transmettre une attitude sociale adéquate. Cette attitude sociale exprimée par l’agent doit refléter la situation dans laquelle il se trouve. L’agent doit donc prendre en compte son rôle et sa relation sociale vis à vis de son interlocuteur lorsqu’il choisit comment réagir au cours de l’interaction. Afin de construire un tel agent capable de raisonner en fonction de son rôle et de sa relation, et capable d’adapter son attitude sociale, nous avons construit un modèle de prise de décision sociale. Dans un premier temps, nous formalisons la dynamique de la relation sociale à travers une combinaison de buts et de croyances. Puis, nous définissons un modèle de prise de décision basé sur les buts sociaux et situationnels de l’agent. Pour finir, nous avons réalisé une étude perceptive dans un contexte d’interaction tuteur/enfant virtuels au cours de laquelle les participants évaluaient l’attitude sociale du tuteur envers l’enfant. La relation sociale et le rôle social du tuteur étaient manipulés par notre modèle. Les résultats montrent qu’à la fois le rôle et la relation du tuteur ont une influence sur son attitude sociale perçue.
- 2 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Modélisation de la prise de décision d'un agent conversationnel animé en fonction de son attitude sociale
Afin d’être considérés comme des partenaires crédibles lors d’une interaction, les agents virtuels doivent transmettre une attitude sociale adéquate. Cette attitude sociale exprimée par l’agent doit refléter la situation dans laquelle il se trouve. L’agent doit donc prendre en compte son rôle et sa relation sociale vis à vis de son interlocuteur lorsqu’il choisit comment réagir au cours de l’interaction. Afin de construire un tel agent capable de raisonner en fonction de son rôle et de sa relation, et capable d’adapter son attitude sociale, nous avons construit un modèle de prise de décision sociale. Dans un premier temps, nous formalisons la dynamique de la relation sociale à travers une combinaison de buts et de croyances. Puis, nous définissons un modèle de prise de décision basé sur les buts sociaux et situationnels de l’agent. Pour finir, nous avons réalisé une étude perceptive dans un contexte d’interaction tuteur/enfant virtuels au cours de laquelle les participants évaluaient l’attitude sociale du tuteur envers l’enfant. La relation sociale et le rôle social du tuteur étaient manipulés par notre modèle. Les résultats montrent qu’à la fois le rôle et la relation du tuteur ont une influence sur son attitude sociale perçue.
- Open Access
- 31 March 2026
- Published by Elsevier in Computers in Human Behavior: Artificial Humans
- Vol. 8
Simulated emotional reactions affect (dis)honesty in speech-free human–agent interactions
- 31 March 2026
- Published by Elsevier in Computers in Human Behavior: Artificial Humans
- Vol. 8
Open AccessSimulated emotional reactions affect (dis)honesty in speech-free human–agent interactions
- 24 December 2025
- Published by MyJove Corporation
- No. 226,p. e69254
JoVE Video Dataset
The growing demand for therapeutic support increasingly exceeds the capacity of available professionals. A virtual agent capable of performing motivational interviewing (MI) offers a promising solution to assist patients in reaching their goal of behavior change between sessions with human therapists. MI is inherently a cooperative and adaptive form of communication. Therefore, developing an agent capable of adapting its conversational strategies to the context could significantly enhance the effectiveness of therapy. During MI sessions, human therapists adjust both their verbal and nonverbal behaviors based on the human patients' responses, as well as their profiles. Depending on the patient's level of motivation, the therapist will modify their approach accordingly. Thus, personalization and adaptability are essential for developing effective MI virtual agents. In this paper, we present a virtual agent capable of conducting MI sessions by dynamically adapting verbally and nonverbally to users in real time. Leveraging state-of-the-art models, this system enables MI interactions. The virtual agent is embodied using the Greta 2.0 platform. Its nonverbal behavior is generated through a diffusion model called MODIFF, which adapts to the user's facial expressions and their readiness to change. These facial expressions were learned on an MI corpus and validated through a dedicated user study. The dialogue is generated using a state-of-the-art large language model (LLM), enhanced by a dialogue manager specifically designed for MI, with a reinforcement learning approach, and validated through user testing. Furthermore, the dialogue manager is able to adapt to different user profiles. The resulting platform is open-source and facilitates the generation of real-time, multimodal MI dialogues, providing new tools for digitally mediated therapeutic interactions.
- 24 December 2025
- Published by MyJove Corporation
- No. 226,p. e69254
JoVE Video Dataset
The growing demand for therapeutic support increasingly exceeds the capacity of available professionals. A virtual agent capable of performing motivational interviewing (MI) offers a promising solution to assist patients in reaching their goal of behavior change between sessions with human therapists. MI is inherently a cooperative and adaptive form of communication. Therefore, developing an agent capable of adapting its conversational strategies to the context could significantly enhance the effectiveness of therapy. During MI sessions, human therapists adjust both their verbal and nonverbal behaviors based on the human patients' responses, as well as their profiles. Depending on the patient's level of motivation, the therapist will modify their approach accordingly. Thus, personalization and adaptability are essential for developing effective MI virtual agents. In this paper, we present a virtual agent capable of conducting MI sessions by dynamically adapting verbally and nonverbally to users in real time. Leveraging state-of-the-art models, this system enables MI interactions. The virtual agent is embodied using the Greta 2.0 platform. Its nonverbal behavior is generated through a diffusion model called MODIFF, which adapts to the user's facial expressions and their readiness to change. These facial expressions were learned on an MI corpus and validated through a dedicated user study. The dialogue is generated using a state-of-the-art large language model (LLM), enhanced by a dialogue manager specifically designed for MI, with a reinforcement learning approach, and validated through user testing. Furthermore, the dialogue manager is able to adapt to different user profiles. The resulting platform is open-source and facilitates the generation of real-time, multimodal MI dialogues, providing new tools for digitally mediated therapeutic interactions.
- 23 December 2025
- Published by MyJove Corporation in Journal of Visualized Experiments
- No. 226,p. e69254
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
The growing demand for therapeutic support increasingly exceeds the capacity of available professionals. A virtual agent capable of performing motivational interviewing (MI) offers a promising solution to assist patients in reaching their goal of behavior change between sessions with human therapists. MI is inherently a cooperative and adaptive form of communication. Therefore, developing an agent capable of adapting its conversational strategies to the context could significantly enhance the effectiveness of therapy. During MI sessions, human therapists adjust both their verbal and nonverbal behaviors based on the human patients' responses, as well as their profiles. Depending on the patient's level of motivation, the therapist will modify their approach accordingly. Thus, personalization and adaptability are essential for developing effective MI virtual agents. In this paper, we present a virtual agent capable of conducting MI sessions by dynamically adapting verbally and nonverbally to users in real time. Leveraging state-of-the-art models, this system enables MI interactions. The virtual agent is embodied using the Greta 2.0 platform. Its nonverbal behavior is generated through a diffusion model called MODIFF, which adapts to the user's facial expressions and their readiness to change. These facial expressions were learned on an MI corpus and validated through a dedicated user study. The dialogue is generated using a state-of-the-art large language model (LLM), enhanced by a dialogue manager specifically designed for MI, with a reinforcement learning approach, and validated through user testing. Furthermore, the dialogue manager is able to adapt to different user profiles. The resulting platform is open-source and facilitates the generation of real-time, multimodal MI dialogues, providing new tools for digitally mediated therapeutic interactions.
- 23 December 2025
- Published by MyJove Corporation in Journal of Visualized Experiments
- No. 226,p. e69254
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
The growing demand for therapeutic support increasingly exceeds the capacity of available professionals. A virtual agent capable of performing motivational interviewing (MI) offers a promising solution to assist patients in reaching their goal of behavior change between sessions with human therapists. MI is inherently a cooperative and adaptive form of communication. Therefore, developing an agent capable of adapting its conversational strategies to the context could significantly enhance the effectiveness of therapy. During MI sessions, human therapists adjust both their verbal and nonverbal behaviors based on the human patients' responses, as well as their profiles. Depending on the patient's level of motivation, the therapist will modify their approach accordingly. Thus, personalization and adaptability are essential for developing effective MI virtual agents. In this paper, we present a virtual agent capable of conducting MI sessions by dynamically adapting verbally and nonverbally to users in real time. Leveraging state-of-the-art models, this system enables MI interactions. The virtual agent is embodied using the Greta 2.0 platform. Its nonverbal behavior is generated through a diffusion model called MODIFF, which adapts to the user's facial expressions and their readiness to change. These facial expressions were learned on an MI corpus and validated through a dedicated user study. The dialogue is generated using a state-of-the-art large language model (LLM), enhanced by a dialogue manager specifically designed for MI, with a reinforcement learning approach, and validated through user testing. Furthermore, the dialogue manager is able to adapt to different user profiles. The resulting platform is open-source and facilitates the generation of real-time, multimodal MI dialogues, providing new tools for digitally mediated therapeutic interactions.
- Open Access
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
We present an open-source virtual agent platform for conducting real-time motivational interviews, combining state-of-the-art language and diffusion models to adapt to users' behavior and profile. Utilizing the Greta 2.0 platform, it supports various topics, including nutrition and sport-focused interventions, and offers a flexible, validated tool for enhancing digital therapeutic interactions. The growing demand for therapeutic support increasingly exceeds the capacity of available professionals. A virtual agent capable of performing motivational interviewing (MI) offers a promising solution to assist patients in reaching their goal of behavior change between sessions with human therapists. MI is inherently a cooperative and adaptive form of communication. Therefore, developing an agent capable of adapting its conversational strategies to the context could significantly enhance the effectiveness of therapy. During MI sessions, human therapists adjust both their verbal and nonverbal behaviors based on the human patients' responses, as well as their profiles. Depending on the patient's level of motivation, the therapist will modify their approach accordingly. Thus, personalization and adaptability are essential for developing effective MI virtual agents. In this paper, we present a virtual agent capable of conducting MI
Open AccessVirtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
We present an open-source virtual agent platform for conducting real-time motivational interviews, combining state-of-the-art language and diffusion models to adapt to users' behavior and profile. Utilizing the Greta 2.0 platform, it supports various topics, including nutrition and sport-focused interventions, and offers a flexible, validated tool for enhancing digital therapeutic interactions. The growing demand for therapeutic support increasingly exceeds the capacity of available professionals. A virtual agent capable of performing motivational interviewing (MI) offers a promising solution to assist patients in reaching their goal of behavior change between sessions with human therapists. MI is inherently a cooperative and adaptive form of communication. Therefore, developing an agent capable of adapting its conversational strategies to the context could significantly enhance the effectiveness of therapy. During MI sessions, human therapists adjust both their verbal and nonverbal behaviors based on the human patients' responses, as well as their profiles. Depending on the patient's level of motivation, the therapist will modify their approach accordingly. Thus, personalization and adaptability are essential for developing effective MI virtual agents. In this paper, we present a virtual agent capable of conducting MI
- Open Access
- 16 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
SMART-DREAM: To Condition or Not to Condition; A Study on the Impact of LLM Conditioning on Motivational Interview Dialog Virtual Agent
- 16 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessSMART-DREAM: To Condition or Not to Condition; A Study on the Impact of LLM Conditioning on Motivational Interview Dialog Virtual Agent
- Open Access
- 16 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-3
The Future is Near: Design Fiction Explorations of Virtual Companions
- 16 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessThe Future is Near: Design Fiction Explorations of Virtual Companions
- 18 July 2025
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (4) , 3741-3764
EMMI–Empathic Multimodal Motivational Interviews: automatic multimodal features extraction and patient type definition
- 18 July 2025
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (4) , 3741-3764
EMMI–Empathic Multimodal Motivational Interviews: automatic multimodal features extraction and patient type definition