稲積研修生、Kruengkrai研究員、吉野チームディレクターら知識獲得・対話研究チームの研究をACLをはじめとするトップ会議で発表しました。

知識獲得・対話研究チームの研究成果が2025年にACL、Interspeech、ICASSP、IROSなど多くのTop tier会議で発表されました。合計18本の査読付き国際会議論文となっています。

詳細は以下になります．

• Takuma Sato, Seiya Kawano, Koichiro Yoshino. "Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs" In Proceedings of International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL), Mumbai, India, December 2025.
• Shusuke Komatsu, Kazuyo Onishi, Koki Tanaka, Dohyun Kim, Koichiro Yoshino. "Efficient ASR Domain Adaptation with Long Noun Phrases: Harnessing the Linguistic Characteristics of Japanese" In Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Honolulu, Hawaii, USA, December 2025.
• Shiki Sato, Jun Baba, Asahi Hentona, Shinji Iwata, Akifumi Yoshimoto, Koichiro Yoshino. "Proactive User Information Acquisition via Chats on User-Favored Topics" In Findings of The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), Suzhou, China, November 2025.
• Jesse Atuhurra, Hidetaka Kamigaito, Taro Watanabe, and Koichiro Yoshino. "J-ORA: A Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception" In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, October 2025.
• Konosuke Yamasaki, Shohei Tanaka, Akishige Yuguchi, Seiya Kawano, Koichiro Yoshino. "Multi-step or Direct: A Proactive Home-Assistant System Based on Commonsense Reasoning" In Proceedings of The 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Avignon, France, August 2025.
• Kazuyo Onishi, Hien Ohnaka, Koichiro Yoshino. "Modeling Turn-Taking Speed and Speaker Characteristics" In Proceedings of The 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Avignon, France, August 2025.
• Muhammad Yeza Baihaqi, Angel Fernando Garcia Contreras, Seiya Kawano, Koichiro Yoshino. "LLM-Driven Approach for Motion Control in Human-Robot Dialogue for Elevating Engagement" In Proceedings of IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Eindhoven, Netherlands, August 2025.
• Kiyotada Mori, Seiya kawano, Chaoran Liu, Carlos Toshinori Ishi, Angel Fernando Garcia Contreras, Koichiro Yoshino. "What Do Humans Hear When Interacting? Experiments on Selective Listening for Evaluating ASR of Spoken Dialogue Systems" In Proceedings of INTERSPEECH, Rotterdam, Netherlands, August 2025.
• Kiyotada Mori, Seiya Kawano, Angel Fernando Garcia Contreras, Koichiro Yoshino. "Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model" In Proceedings of INTERSPEECH, Rotterdam, Netherlands, August 2025.
• Muhammad Yeza Baihaqi, Angel Fernando Garcia Contreras, Seiya Kawano, Koichiro Yoshino. "Rapport-Building Dialogue Strategies for Deeper Connection: Integrating Proactive Behavior, Personalization, and Aizuchi Backchannels" In Proceedings of INTERSPEECH, Rotterdam, Netherlands, August 2025.
• Muhammad Yeza Baihaqi, Angel Fernando Garcia Contreras, Seiya Kawano, Koichiro Yoshino. "Co-Speech Motion for Virtual Agents in Dialogue Using LLM-Driven Primitive Action Selection" In Proceedings of INTERSPEECH, Rotterdam, Netherlands, August 2025 (Show&Tell).
• Shun Inadumi, Nobuhiro Ueda, Koichiro Yoshino. "Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures" In Proceedings of The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, July 2025.
• Canasai Kruengkrai, Koichiro Yoshino. "Teaching Text Agents to Learn Sequential Decision Making from Failure" In Proceedings of The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, July 2025.
• Kai Yoshida, Masahiro Mizukami, Seiya Kawano, Canasai Kruenkrai, Hiroaki Sugiyama, Koichiro Yoshino. "Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression." In Proceedings of the 50th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hyderabad, India, April 2025.
• Takuma Miwa, Yusuke Oda, Seiya Kawano, Koichiro Yoshino. "Efficient Channel Generation for QCNN based on Multi-Pauli Matrices." In Proceedings of International Conference on Quantum Communications, Networking, and Computing (QCNC), Nara, Japan, March 2025.
• Daichi Yoshihara, Akishige Yuguchi, Seiya Kawano, Takamasa Iio, Koichiro Yoshino. "What Should Autonomous Robots Verbalize and What Should They Not?" In Proceedings of The 31st International Conference on MultiMedia Modeling (MMM), Nara, Japan, January 2025.
• Angel F. Garcia Contreras, Wen-Yu Chang, Seiya Kawano, Yun-Nung Chen, Koichiro Yoshino. "Using Language Models to Generate and Forget the Narrative Memories of an Assistive Robot." In Proceedings of The 31st International Conference on MultiMedia Modeling (MMM), Nara, Japan, January 2025.
• Yasutomo Kawanishi, Yutaka Nakamura, Taiken Shintani, Carlos Toshinori Ishi, Seiya Kawano, Koichiro Yoshino, Takashi Minato, Michihiko Minoh. "RoboDJ: Live Commentary Robots System Driven by Physical- and Cyber-world Observations." In Proceedings of The 31st International Conference on MultiMedia Modeling (MMM), Nara, Japan, January 2025, Best Demo Honorable Mention Award.