Session Details
[3Yin-A]Poster 5
Wed. Jun 10, 2026 9:30 AM - 11:00 AM JST
Wed. Jun 10, 2026 12:30 AM - 2:00 AM UTC
Wed. Jun 10, 2026 12:30 AM - 2:00 AM UTC
Room Y(Exhibition hall AB 1)
[3Yin-A-01]Visibility-Gated State Estimation for Assembly State Transitions
〇Wataru Fujita1, Toshiyuki Hatta1,2, Yasuaki Susumu1 (1. Mitsubishi Electric Corporation, 2. The University of Electro-Communications)
[3Yin-A-02]Affordance-Aware Hierarchical Multimodal Retrieval-Augmented Generation for Mobile Manipulation
〇Ryosuke Korekata1,2,3, Quanting Xie3, Yonatan Bisk3, Komei Sugiura1,2 (1. Keio University, 2. Keio AI Research Center, 3. Carnegie Mellon University)
[3Yin-A-03]Designing AI-Mediated Facilitation for Visual Thinking Strategies:Exploring the Tension Between Neutrality and EmpathyAn Exploratory Study of Neutrality and Empathy in AI-Mediated Dialogue
〇Asuka Saito1,2 (1. SMFL, 2. TOKYO CITY UNIVERSITY)
[3Yin-A-04]Four-Layer External Structuring for LLM InteractionsA Zero-Infrastructure Dialogue Control Architecture
〇nobuaki hori1 (1. Independent Researcher)
[3Yin-A-05]Table-Aware Text Segmentation for Masking Sensitive Information in Document Images
〇Takuto Yamamoto1, Hibiki Miyatake2, Shogo Sakaue1, Yamato Okamoto1 (1. CyberAgent, Inc., 2. WEDDING PARK CO., LTD.)
[3Yin-A-06]Evaluating Accuracy and Efficiency in Lightweight Image Classification via Knowledge Distillation from Large Foundation Models
〇Yuki Wada1, Yoshitaka Koike1, Masaaki Hayashida1, Yasushi Iwata1 (1. NS Solutions Corporation)
[3Yin-A-07]Multi-label Supervised Contrastive Learning for Medical Image Classification
〇Eichi Takaya1, Ryusei Inamori1 (1. Tohoku University Graduate School of Medicine)
[3Yin-A-08]Improving Accuracy of VLM-based Elemental Motion Recognition using Therblig Motion Transitions
〇Toshiki Kotani1, Ryo Sakai1, Taiki Fuji1, Kentaro Yoshimura1 (1. Hitachi, Ltd.)
[3Yin-A-09]Emotional Time Series Analysis of Movie Scripts Using LLM-Based Mixed Emotions Extraction
〇Mao Takaha1, Keita Nishimoto1, Kimitaka Asatani1, Ichiro Sakata1 (1. The University of Tokyo)
[3Yin-A-10]LLM-jp Chatbot Arena: Building a Dialogue Evaluation Platform for Japanese LLMs
〇Hirokazu Kiyomaru1, Hiroaki Sugiyama2, Hiroshi Tokoyo3, Takahiro Kubo3, Naoaki Okazaki4,1 (1. National Institute of Informatics, 2. NTT, 3. Amazon Web Services Japan, 4. Institute of Science Tokyo)
[3Yin-A-11]DiffNator: Generating Structured Explanations of Time-Series Differences
〇Kota Dohi1, Tomoya Nishida1, Harsh Purohit1, Takashi Endo1, Yohei Kawaguchi1 (1. Hitachi, Ltd.)
[3Yin-A-12]Comparative Evaluation of Evidence-Linked Structured Summaries for Administrative Long-Term Care Q&A
〇Seiichirou Yokoo1, Yoriko Yokoo1 (1. Terra Incognita LLC)
[3Yin-A-13]Japanese License Plate Recognition Using a Lightweight VLM Trained on Synthetic Data and Constrained Decoding
〇Kota Shinjo1, Shin Suyama1, Shintaro Yoshizawa1 (1. TOYOTA MOTOR CORPORATION)
[3Yin-A-14]Empathetic Response Prompt Optimization Using Reinforcement Learning with Emotional Information
〇Rong Cong1, Ichiro Kobayashi1 (1. Ochanomizu University)
[3Yin-A-15]Sycophancy in TRPG Game Master AI: Effects on Player Experience
〇Tensho Watanabe1, Kento Haneda1, Keisuke Sakaguchi1,2 (1. Tohoku University, 2. RIKEN)
[3Yin-A-16]Image Classification Using Anonymized Images with Reduced Communication Cost
〇Rai Takahahshi1,2, Hirokazu Nosato1, Yosuke Iijima2 (1. Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, 2. National Institute of Technology (KOSEN), Oyama College, Advanced Course)
[3Yin-A-17]DAGRI SubTask-1: Dataset Expansion for Information Extraction from Agricultural PDF Documents
〇rio kumakura1, Yasutomo Kimura1, Tsuyoshi Morioka2, akio Kobayashi3, Masahiro Otomo3, Junichi Ishihara3, Kenta Baba3, Tetsuo Katsuragi3 (1. Otaru university of commerce, 2. AIREV, Inc., 3. National Agriculture and Food Research Organization)
[3Yin-A-18]Autonomous Tunnel Inspection Robot Enabling Both Deliberate Planning and Real Time Execution via Bidirectional Collaboration between Cloud and Local VLMs
〇Ryosuke Yamanaka1, Yoshito Okada1, Satoshi Tadokoro1, Kazunori Ohno1 (1. Tohoku University)
[3Yin-A-19]Autoformulation Benchmark Suite of Black-Box Optimization Problems Described in Natural Language
〇Yutaro Yamada1, Kei Hiroshima1, Nozomu Yoshinari1, Kento Uchida1, Shinnichi Shirakawa1 (1. Yokohama National University)
[3Yin-A-20]Development of a Motion Recording System and Data Collection Experiments Toward Realizing MR-Based Medical Interview Examinations
〇Yusei Hashimoto1, Ryo Taguchi1, Satoshi Arakawa2, Shin Ishihara2 (1. Nagoya Institute of Technology, 2. Fujita Health University)
[3Yin-A-21]A Multi-Persona AI Music Critique System with Real-time Performance Analysis and RAG
〇Kiwamu Sato1 (1. Accenture Japan Ltd)
[3Yin-A-22]Multi-Label Sentiment Classification of Contemporary Tanka and Its Feature Analysis
〇Marin Kurokawa1, Daichi Mochihashi2,3, Ichiro Kobayashi1 (1. Ochanomizu University, 2. The Institute of Statistical Mathematics, 3. National Institute for Japanese Language and Linguistics)
[3Yin-A-23]Analyzing Image and Text Contributions to Social Bias in VLMs
〇Daiki Shirafuji1, Makoto Takenaka1, Tatsuhiko Saito1 (1. Mitsubishi Electric Corporation)
[3Yin-A-24]Consideration of automatic graphic recording system
〇Haruhito Zenio1, Koki Saito1, Makoto Enomoto1, Takayuki Hoshino1, Eiji Takahashi1 (1. BIPROGY Inc.)
[3Yin-A-25]Vehicle Tracking and Intersection Traffic Flow Analysis Using Camera View and Bird’s Eye View
〇Shin Suyama1, Kota Shinjo1, Shintaro Yoshizawa1, Kazuhiro Shintani1 (1. Toyota Motor Corporation)
[3Yin-A-26]Vision-Language-Action Models for Laboratory Automation: Challenges in Task Evaluation Metrics and Language Grounding
〇Kazuhide Shirai1 (1. CHUGAI PHARMACEUTICAL CO., LTD.)
[3Yin-A-27]Evaluation and Analysis of Language-Model Pretraining Configurations for Brain-State Prediction
〇Ai Hamada1, Yuki Taya1, Ichiro Kobayashi1 (1. Ochanomizu University)
[3Yin-A-28]Prototype of a Three-Dimensional Mandibular Motion Measurement System Using a Stereo Camera
〇Kodai Ichikawa1, Ryo Taguchi1, Satoru Aoyama2, Miyuki Yokoi2, Mitsuyoshi Yoshida2 (1. Nagoya Institute of Technology, 2. Fujita Health University)
[3Yin-A-29]A Predictive State Representation View of Large Language Model GenerationPossibilities of a dynamical dystems Interpretation of LLMs
〇Shinnosuke Mizuno1, Yohei Kobashi1 (1. The University of Tokyo)
[3Yin-A-30]Improving Knowledge Distillation Fidelity via Adaptive Reweighting Based on Loss Divergence
〇Masato Mita1 (1. Recruit Co.,Ltd.)
[3Yin-A-31]Construction of a High-Difficulty Japanese QA Benchmark Based on Human-Oriented Quizzes
〇Toumi Sasaki1, Daisuke Kawahara1,2 (1. Waseda University, 2. National Institute of Informatics, LLMC)
[3Yin-A-32]Analysis of Animal Vocalization Transcription Using Inter-Species Phonetic Alphabet (ISPA)
〇Ren Yokoyama1, Katsuhito Sudoh1 (1. Nara Women's University)
[3Yin-A-33]Locomanipulation Planning for Probabilistic Completeness via Sampling-based Feasibility Check and Contact Graph Search
〇Takuma Hiraoka1, Naoki Hiraoka1, Kunio Kojima1, Kei Okada1 (1. The University of Tokyo)
[3Yin-A-34]Recognition of vowels in speech imagery EEG using LPA line spectra and Conformer
〇Ryota Matsumoto1, Shuji Shinohara1, Ryo Taguchi2, Yurie Iribe3, Tsuneo Nitta4 (1. TokyoDenki University, 2. Nagoya Institute of Technology, 3. Aichi Prefectural University, 4. Toyohashi University of Technology)
[3Yin-A-35]A Survey of the History of Research on Spontaneous and Autonomous Learning Agents
〇Naoto Yoshida1 (1. Kyoto University)
[3Yin-A-36]Hazard Estimation with Multimodal Large Language Models Using Synthetic Videos: Toward Smart Monitoring for Preschool Children
〇Tetsuya Yamamoto1, Fumihiko Ishida1 (1. National Institute of Technology, Toyama College)
[3Yin-A-37]Study on personal identification technology for visualizing work conditions in manufacturing sites
〇Takahiro Suzuki1, Ryota Matsutake1 (1. FUJI ELECTRIC CO., LTD)
[3Yin-A-38]A VR-Based Multimodal Interaction System for Studying Non-Verbal Communication Among International Students to Reduce the Illusion of Transparency
〇Mehedi Hassan Rico1, Yoshimasa Ohmoto1 (1. Shizuoka University)
[3Yin-A-39]Effectiveness Evaluation of Boiling Acoustic Signal Regression Using DAE in High-Noise Environments
〇Yuuki Honma1, Yoshitaka Ueki1 (1. Tokyo University of Science)
[3Yin-A-40]Comparing Bias in AI-Generated Anime-style and Realistic Illustrations
〇Ayano Ito1, Shoma Mizuno1, Keiichi Namikoshi1, Yuko Sakurai1, Satoshi Oyama2,3 (1. Nagoya Instiute of Technology, 2. Nagoya City University, 3. RIKEN API)
[3Yin-A-41]Spatial Reasoning for Lunar Rovers Using Vision-language model with Top-Down Terrain Maps
〇Takashi Kubo1, Naoya Takeishi1, Takehisa Yairi1 (1. University of Tokyo)
[3Yin-A-42]Evaluation of Blow Detection Performance in Yacht Racing Using Multimodal LLMs
Takumi Terauchi1, 〇Kotaro Nishimura1, Kensuke Ota1, Keiichi Namikoshi1, Yuko Sakurai1 (1. Nagoya Institute of Technology)
[3Yin-A-43]A Simulation Study of How Guidance Affects the Distribution of Time Spent in a Stadium Concourse
〇Anna Okui1, Hideki Fujii1 (1. The University of Tokyo)
[3Yin-A-44]An LLM-Based Method for Automated Correction of Terminology Inconsistency in Design Documents Using a Term Dictionary
〇Kazu Nishikawa1, Yuta Koreeda1, Yasuhide Mori1, Shun Oida1, Daisuke Fukui1 (1. Hitachi)
[3Yin-A-45]Gaze Generation Model Evaluation via Image Retrieval Tasks Using Gaze Behavior
〇Iwamoto Yuma1, Matsuno Shogo1 (1. The University of Electro-Communications)
[3Yin-A-46]Leadership Emergence in Personality Assigned LLM-based Multi-Agent Systems:Simulation and Evaluation via Automated Dialogue
〇Chie Yamanishi1, Yuki Nozaki2, Yoshinobu Kano1 (1. Shizuoka University, 2. Konan University)
[3Yin-A-47]Symbol Emergence Model with Dynamic Vocabulary Acquisition using Non-parametric Bayes
〇nao takesawa1, Yasuhiro Minami1 (1. The University of Electro-Communications)
[3Yin-A-48]Performance Evaluation of Anomaly Detection on Concrete Revetment Images Acquired under Varying Outdoor Imaging Conditions
〇Yukino Tsuzuki1, Tomoyasu Nanaumi1, Junichi Okubo1, Junichiro Fujii1 (1. Yachiyo Engineering Co., Ltd.)
[3Yin-A-49]Corporate Document QA Benchmark Requiring Multi-Hop Reasoning
〇TAISEI OZAkI1,2, MIKI OTA1, YUTA KAMBAYASHI1, KOKI NAGATANI1 (1. MATSUO INSTITUTE, INC, 2. Osaka Metropolitan University)
[3Yin-A-50]Staking-based Signaling Mechanism in Decentralized LLM Agent Markets: Theoretical Analysis and Verification via ABM
〇Risa Yamaguchi1 (1. Keio University)
[3Yin-A-51]Exploring Few-Step Predictive Generation in Diffusion World Models
〇Keito Sei1, Jouei Okada2, Kotaro Aoki3 (1. Tokyo City University, 2. Tokyo University of Science , 3. Nagoya University)
[3Yin-A-52]Comparison of Accuracies of LLMs for Slot Extraction in a Medical Interview Training System
〇Naoki Sakaguchi1, Chee Siang Leow1, Hiromitsu Nishizaki1, Takehito Utsuro2, Junichi Hoshino2, Kentaro Takagaki1,3, Kenichi Kawabata1, Shoji Suzuki1 (1. University of Yamanashi, 2. University of Tsukuba, 3. Institute of Science Tokyo)
[3Yin-A-53]Proposal of a Cognitive Model–Based Robot Integrating Associative Wordplay and Bodily Expression
〇Jumpei Nishikawa1 (1. Okayama prefectural university)
[3Yin-A-54]Automated Spring Boot Unit Test Generation Using Workflow-Based AI AgentsImplementation of an Iterative Test Completion System Using JaCoCo and GPT-5
〇Kotaro Okamoto1, Kohei Itaya1 (1. IBM Japan Systems Engineering Co.)
[3Yin-A-55]Balancing Shared Experiences and Autonomous Exploration Through the Integration of Generative AI and Fixed Scenarios
〇Genki Shintani1, Yoshimasa Ohmoto1 (1. Shizuoka University)
[3Yin-A-56]Scaling MARL-CPC: Achieving Decentralized Coordination in Multi-Agent Environments
〇Pyii Phyo Maung1, Naoto Yoshida1, Tadahiro Taniguchi1,2 (1. Kyoto University, 2. Ritsumeikan University)
[3Yin-A-57]Emergence of Energy-Efficient Formation Flight Using an Extended Boids Model Considering Wingtip Vortices
〇Ryoji Daiko1, Takuto Sakuma1, Wen Gu1, Shohei Kato1 (1. Nagoya Institute of Technology)
[3Yin-A-58]A Proposal for Hybrid Automation to Improve Semiconductor Fab Operations Using AI Agents and a Configuration Management PlatformA Human-in-the-Loop–Based Incremental Automation Architecture
〇Makoto Kogoh1, Chiaki Morita1, Shiho Onodera1, Tadayuki Yoshida1, Tomoaki Mori1, Toshio Nakamura1, Asako Iwai1, Michiaki Tatsubori1 (1. IBM Japan)
[3Yin-A-59]Design and Evaluation of Autonomous Distributed Control Method for the Piano Movers Problem Using Multiple Robots
〇Yuki Ichiba1, Chonho Lee1 (1. Okayama Univercity of Science)
[3Yin-A-60]A proposal-based tourist information system using Large Language Models
〇Ryosei Maeda1, Tetsuro Takahashi1 (1. Kagoshima University)
[3Yin-A-61]Analyzing the Impact of Supplementary Materials on Audience Comprehension in Academic Presentations
〇Yuto Takei1, Takamasa Iio1, Marie Katsurai1 (1. Doshisha University)
[3Yin-A-62]Speech-based Behavior Generation for Motivational Interviewing Agents
〇Takashi Yamamoto1, Fumio Nihei1, Yukiko Nakano1 (1. Seikei University)
[3Yin-A-63]Estimation of Five-Finger Isometric Flexion Forces Using CNN and LSTM from Forearm B-mode Ultrasound Images
〇Shunya Sasaki1, Noriki Mochizuki1 (1. Nippon Institute of Technology)
[3Yin-A-64]Analyzing User Simulators for Persuasion Dialogue with User Cognitive Styles
〇Yotaro Watanabe1, Kise Yoshida2, Yuka Saito2, Meguru Takasaki1, Shoji Moriya2, Reina Akama2,3, Jun Suzuki2 (1. PKSHA Technology Inc., 2. Tohoku University, 3. NINJAL)