Embedded Files
Presentation at the Conference
- Oral Presentations
Each oral presentation is allocated 12 minutes for the talk, followed by 3 minutes for questions and discussion. Presenters are expected to adhere strictly to the allocated time to ensure a smooth session flow.
Slides should be prepared in 16:9 format and in PDF format.
Poster Presentations
Posters must be A0 size, vertical orientation, and printed.
Authors are responsible for printing and bringing their posters to the conference.
Poster boards and mounting materials will be provided on-site.
Posters and Presentations must be uploaded by February 20th using the following form.
Detailed Program
Thursday, February 26
17:15 - 18:00 Registration
18:00 - 19:00 Guided tour of Buonconsiglio Castle and Torre Aquila
19:00 Welcome aperitif – Scuderie del Castello
Friday, February 27
8:30 - 9:15 Registration
9:15 - 9:45 [Session 1] Welcome
9:45 - 10:45 [Session 1] Keynote: Asli Celikyilmaz
10:45 - 11:15 Coffee Break
11:15 - 12:45 [Session 2] Dialogue and Interactive Systems (Chair: Joakim Gustafsson)
MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations. Emre Can Acikgoz, Jinoh Oh, Joo Hyuk Jeon, Jie Hao, Heng Ji, Dilek Hakkani-Tur, Gokhan Tur, Xiang Li, Chengyuan Ma, Xing Fan
FlowSwitch: A State-Aware Framework for Workflow Transitions in Adaptive Dialogue Agents. Wen Yu Chang, Luning Qiu, Yi-Hung Liu, Yun-Nung Chen
Personality Expression in Spoken Dialogue Systems: From Text to Speech. Kenta Yamamoto, Kazunori Komatani
Reproducing Proficiency-Conditioned Dialogue Features with Full-duplex Spoken Dialogue Models. Takao Obi, Sadahiro Yoshikawa, Mao Saeki, Masaki Eguchi, Yoichi Matsuyama
Automatic Evaluation of Open-Domain Real Conversations. Cristina Conforto López, Marcos Estecha-Goritagoitia, Mario Rodriguez-Cantelar, Ricardo Córdoba, Luis Fernando D’Haro
12:45 - 14:00 Lunch Break
14:00 - 15:15 [Session 3] Special Session: Human-Machine Dialogue in the Era of Multimodal Foundation Models (Chair: Luis Fernando D'Haro)
Do Audio and Visual Tokenizers Capture Backchannels? Benoit Favre, Auriane Boudin
The Context Trap: Why End-to-End Audio Language Models Fail Multi-turn Dialogues. Zhi Rui Tam, Wen Yu Chang, Yun-Nung Chen
Analysing Next Speaker Prediction in Multi-Party Conversation Using Multimodal LLMs. Taiga Mori, Koji Inoue, Divesh Lala, Keiko Ochi, Tatsuya Kawahara
Exploring Emotional Nuances in Spoken Dialogue: Dataset Construction and Prediction of Emotional Dialogue Breakdown. Hyuga Nakaguro, Koichiro Yoshino
15:15 - 16:15 [Session 3] Panel: Human-Machine Dialogue in the Era of Multimodal Foundation Models
Panelists:
Yun-Nung (Vivian) Chen (co-Chair), National Taiwan University, Taiwan
Geraldine Damnati, Orange S.A., France
Asli Celikyilmaz, Meta Fundamentals AI Research (FAIR)
Michael Johnston (co-Chair), Amazon
16:15 - 16:45 Coffee Break
16:45 - 17:30 [Session 4] Poster Session
Effects of Dialogue Corpora Properties on Fine-Tuning a Moshi-Based Spoken Dialogue Model. Yuto Abe, Mao Saeki, Atsumoto Ohashi, Shinnosuke Takamichi, Shiyna Fujie, Tetsunori Kobayashi, Tetsuji Ogawa, Ryuichiro Higashinaka
Mixed-Initiative Dialogue Management for Human–Virtual Agents Interaction in Forum Theatre-Inspired Training. Samuel Otofa, Yacine Zerenini, Frederic Bechet, Benoit Favre, Jean-Marie Pergandi, Magalie Ochs
Development of an Evaluation System for a Fan-Engagement Chat Application Us ing LLM-as-a-Judge. Yuki Fujita, Yasunobu Sasaki, Ryota Arashi, Hokuto Ototake, Shinya Takahashi
Analyzing Utterance Selection for Unnoticeable Topic Induction in Target-Guided Conversation Systems. Kai Yoshida, Koichiro Yoshino
A Dialogue Agent to Let Users Experience and Gently Enhance the "Gyaru-Mind". Momoka Ikegami, Takuya Kato, Saizo Aoyagi, Tatsunori Hirai
Towards a proactive cooking companion for the elderly. Katarina Esteve, Morgan Fredriksson, Joakim Gustafson, Dimosthenis Kontogiorgos, Timo Mashiyi-Veikkola
Saturday, February 28
8:30 - 9:00 Registration
9:00 - 10:00 [Session 5] Keynote: Gabriel Skantze
10:00 - 10:45 [Session 5] Industry Track (Chair: Géraldine Damnati)
Conversational AI for Virtual Standardized Patients using a Speech-to-Speech LLM. Andrew Emerson, Keelan Evanini, Su Somay, Kevin Frome, Le An Ha, Polina Harik
Can Small-Scale LLMs Balance Content Accuracy and Speaker Faithfulness in Noisy French Dialogue Summarization?. Rim Abrougui, Guillaume Lechien, Elisabeth Savatier, Benoît Laurent
ORCHESTRA: AI-Driven Microservices Architecture to Create Personalized Experiences. Jaime Bellver Soler, Samuel Ramos-Varela, Anmol Guragain, Ricardo Córdoba, Luis Fernando D’Haro
10:45 - 11:15 Coffee Break
11:15 - 12:45 [Session 6] Resources and Evaluation (Chair: Frédéric Béchet)
Benchmarking Multilingual Temporal Reasoning in LLMs: The Temporal Reasoning Dataset. Vittorio Mazzia, Sandro Pollastrini, Davide Bernardi, Chiara Rubagotti, Daniele Amberti
Retrospective Speech Recognition for Spoken Dialogue System: Exploiting Subsequent Utterances to Enhance ASR Performance. Ryu Takeda, Kazunori Komatani
From Fact to Judgment: Impact of Task Framing on LLM Conviction in Dialogue Systems. Parisa Rabbani, Nimet Beyza Bozdag, Dilek Hakkani-Tür
Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction. Galann Pennec, Zhengyuan Liu, Nicholas Asher, Philippe Muller, Nancy F. Chen
Multilingual and Continuous Backchannel Prediction: A Cross-lingual Study. Koji Inoue, Mikey Elmers, Yahui Fu, Zi Haur Pang, Taiga Mori, Divesh Lala, Keiko Ochi, Tatsuya Kawahara
12:45 - 14:00 Lunch Break
14:00 - 15:15 [Session 7] Special Session: ConvAI Application in Robotics & Virtual Reality (Chair: Benoit Favre)
Vanishing Point of Attention: A Platform for Adaptive Driver Dialogue Experiments. Morgan Fredriksson, Yanis Yaici, Kevin Lam, Jurgen Konigsmann, Jens Edlund
When social robots see our sketches: evaluating human perception of a robot and a VLM model performance in a drawing task. Viktoria Paraskevi Daniilidou, Nikolai Ilinykh, Vladislav Maraev
Adding Determinism to a Dialogue Agent for a Robotic Environment. Oihana Garcia, Riccardo Cocola, Cristina Aceta
Context-Aware Language Understanding in Human-Robot Dialogue with LLMs. Svetlana Stoyanchev, Youmna Farag, Simon Keizer, Mohan Li, Rama Doddipatla
15:15 - 16:15 [Session 7] Panel: ConvAI Application in Robotics & Virtual Reality
Panelists:
Koichiro Yoshino, Tokyo Institute of Technology / RIKEN, Japan
Gabriel Skantze, KTH Royal Institute of Technology, Sweden
Giulio Jacucci (Chair), University of Helsinki, Finland
David Traum, University of Southern California (USC), USA
16:15 - 16:45 Coffee Break
16:45 - 17:30 [Session 8] Poster Session
Learning Vision–Language Alignment in Unified LLMs with 24 Text Tokens per Image. Nicola Irmiger, Yixuan Xu, Raphael Kreft, Aram Davtyan, Manuel Kaufmann, Imanol Schlag
Incorporating Respect into LLM-Based Academic Feedback: A BI-R Framework for Instructing Students after Q&A Sessions. Mayuko Aiba, Daisuke Saito, Nobuaki Minematsu
The Complementary Role of Para-linguistic cues for Robust Pronunciation Assessment. Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali
Evaluating LLM Style Transfer Through Readability-Based Age Assessments. Maria Di Maro, Antonio Origlia, Leonilda Bilo, Roberta Meo, Pietro Maturi, Francesca Nappo
SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning. Emre Can Acikgoz, Jinoh Oh, Jie Hao, Joo Hyuk Jeon, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur, Xiang Li, Chengyuan Ma, Xing Fan
Adaptive Multimodal Sentiment Analysis with Stream-Based Active Learning for Spoken Dialogue Systems. Atsuto Ajichi, Takato Hayashi, Kazunori Komatani, Shogo Okada
20:00 🍽️🍷 Social Dinner
Sunday, March 1
8:30 - 9:00 Registration
9:00 - 10:00 [Session 9] Keynote: Giulio Jacucci
10:00 - 10:45 [Session 9] Industry Talk (Chair: Mahed Mousavi)
"AI in a real use case of TP Italy Group: results achieved and new challenges" Vincenzo Giliberti & Vincenzo Lanzolla, Teleperformance Italy.
"New Avenues in Dialog: Coding and Adversarial Security", Michael Johnston, Amazon
10:45 - 11:15 Coffee Break
11:15 - 12:45 [Session 10] Human-centered Interaction (Chair: Zoraida Callejas)
Predicting Turn-Taking in Child–Adult Conversations Using Voice Activity Projection. Youcef Brahimi, César Blanc, Abdellah Fourtassi
Supporting Human Operators during Customer Service Interactions with Agentic-RAG. Juan Barrionuevo-Valenzuela, Daniel Calderón-González, Zoraida Callejas, David Griol
Analysis of Child-Caregiver Interactions for Developing a Caregiver Spoken Dialogue System. Sanae Yamashita, Shota Mochizuki, Yuko Kuma, Ray Sakai, Ayaka Sasaki, Ryuichiro Higashinaka
Can code-switching improve the user experience with a dialogue system app for recording endangered languages?. Jacqueline Brixey, David Traum
Estimating Relationships between Participants in Multi-Party Chat Corpus. Akane Fukushige, Koji Inoue, Keiko Ochi, Tatsuya Kawahara, Sanae Yamashita, Ryuichiro Higashinaka
12:45 - 14:00 Lunch Break
14:00 - 15:15 [Session 11] Special Session: ConvAI in the Health Domain (Chair: Tatsuya Kawahara)
WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient-Facing Dialogue. Zachary Ellis, Jared Joselowitz, Yash Deo, Yajie He, Anna Kalygina, Aisling Higham, Mana Rahimzadeh, Yan Jia, Ibrahim Habli, Ernest Lim
ReflectOR: An LLM-Based Agent for Post-Operative Surgical Debriefing. Lorenzo Fumi, Marco Bombieri, Sara Allievi, Stefano Bonvini, Theodora Chaspari, Marco Zenati, Paolo Giorgini
Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialogue. Run Chen, Wen Liang, Ziwei Gong, Lin Ai, Julia Hirschberg
CoVaPh: A Vision-Language Multi-Agent Dialogue System for Tool-Augmented Pharmacogenetic Reasoning and Personalized Guidance. Shang-Chun Luke Lu, Hsin Yang, Hui-Hsin Xue, Ping Lin Tsai, Yu Jing Weng, Shiou-Chi Li, Jen-Wei Huang, Hui Hua Chang
15:15 - 16:15 [Session 11] Panel: ConvAI in the Health Domain
Panelists:
Tatsuya Kawahara, Kyoto University, Japan
Marco Zenati, Harvard Medical School, USA
Giuseppe Riccardi (Chair), University of Trento, Italy
Tommaso Ciulli, Secretary of the Italian Society of Digital Psychology, Italy
Arindam Ghosh, Oviva, Germany
16:15 - 16:45 Coffee Break
16:45 - 17:30 [Session 12] Paper Awards & Closing Remarks
Page updated
Report abuse