Schedule (August 3)
- All oral sessions are are held at PAIS 290.
- All poster sessions are held in the PAIS main lobby.
- Blue names indicate the presenters.
Oral Session 1
- Time: 11:00 – 12:30
- Session Chair: TBD
Papers
- DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio
Wataru Nakata, Yuki Saito, Kazuki Yamauchi, Emiru Tsunoo and Hiroshi Saruwatari
- Rethinking Binary Evaluation of Turn-Taking under Inherent Ambiguity
Yunosuke Kubo, Kenta Yamamoto, Ryu Takeda and Kazunori Komatani
- Tinker Tales: A Tangible Dialogue System for Child–AI Co-Creative Storytelling
Nayoung Choi, Jiseung Hong, Peace Cyebukayire, Ikseon Choi and Jinho D. Choi
- Suppressing Unnecessary Clarification Requests for Unknown Word Acquisition in Spoken Dialogue Using Syllable-Based ASR Confidence
Takumi Furuta, Ryu Takeda and Kazunori Komatani
- Towards Conversational Patient History-Taking: Voice-Interactive AI Agents for Pre-visit Dementia Diagnostic Interviews
Andrew G. Breithaupt, Nayoung Choi, James D. Finch, Jeanne M. Powell, Arin L. Nelson, Oz A. Alon, Howard J. Rosen and Jinho D. Choi
Oral Session 2
- Time: 14:00 – 15:30
- Session Chair: TBD
Papers
- ClarVis: A Dataset of Clarification Requests and Grounding in Collaborative Data Visualization Dialogues
Abari Bhattacharya and Barbara Di Eugenio
- Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
Ali Pourghasemi Fatideh, Wilder Baldwin, Maria Dhakal, Collin McMillan and Sepideh Ghanavati
- ArgAssist: LLM-based Argument Synthesis for Insurance Disputes
Anubhav Sinha, Nitin Ramrakhiyani, Sachin Pawar, Isha Narang and Manoj Apte (virtual)
- Detecting Experiential Intertextuality Across Migration Routes: Beyond Surface Similarity in French Narratives
Sakayo Toadoum Sari, Nelly Robin, Sais Lakhdar, Véronique Petit, Marie VENIARD, Said Jabbour and Delorme Fabien
- Breaking the Script: Do Role-Playing Agents Maintain Goal Alignment under Distraction?
Dongxu Lu, Albert Gatt and Johan Jeuring
Poster Session 1
Papers
- Conversational Grounding in Large Language Models: Evaluation Methods, Challenges and Future Directions
Michelle Elizabeth, Gwénolé Lecorvé, Lina M. Rojas Barahona and Magalie Ochs
- Sensor-Augmented Voice Activity Projection for Enhancing Turn-Taking Prediction
Satoki Hamanaka, Yasue Kishino, Yuiko Tsunomori, Shin Mizutani, Yuya Chiba, Tadashi Okoshi and Jin Nakazawa
- A Dialogue System for Second Language Learning with Dynamic Adaptation to In-Dialogue Difficulty Changes
Taku Morioka, Junya Takayama and Tomoyuki Kajiwara
- SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series
Galann Pennec, Zhengyuan Liu, Nicholas Asher, Philippe Muller and Nancy Chen
- Ping-Ponder: Concurrent Dual-Agent Spoken Dialogue via Shared Belief State
Akiko Masaki-Kato and Gulzar Haris
- Rethinking Role-Playing Evaluation: Anonymous Benchmarking and A Systematic Study of Personality Effects
Ji-Lun Peng and Yun-Nung Chen
- I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System
Zi Haur Pang, Yahui Fu, Koji Inoue and Tatsuya Kawahara
- For What Reason? Interpreting Models’ Encoding of Causation and Antithesis
Abhidip Bhattacharyya and Shira Wein
- CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis (Demo)
Yash Raj Singh
- From Felt Sense to Words: Construction and Analysis of a Focusing Dialogue Dataset for Verbalization
Yuiko Tsunomori, Yuya Chiba and Yosuke Koshikawa
- Retrieving Responses Useful as References in Counseling via LLM-Generated Structurally Analogous Dialogues
Yu Nakagawa, Nozomu Ikeda, Kotaro Funakoshi and Manabu Okumura
- Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
Vardhan Dongre and Dilek Hakkani-Tur
- Strategic Dialogue Assessment: The Crooked Path to Innocence (D&D)
Anshun Asher Zheng, Junyi Jessy Li and David I. Beaver