Publications — Kazuki Kawamura 河村和紀

Publications

PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows
Kazuki Kawamura, Satoshi Waki, Kei Tateno — ACL 26, 2026

Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies
Koichi Tanaka, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Yuki Sasamoto, Kei Tateno, Takuma Udagawa, Wei-Wei Du, Yuta Saito — ICLR 26, 2026

ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy
Kazuki Kawamura, Kengo Nakai, Jun Rekimoto — ICCVW 25, 2025

Guiding well-matched users to target content via optimized promotional content
Kazuki Kawamura, Kei Tateno, Takuma Udagawa, Masahiro Yoshida — U.S. Patent App. 18/868,877, 2025

Off-Policy Evaluation and Learning for the Future under Non-Stationarity
Tatsuhiro Shimizu, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Kei Tateno, Takuma Udagawa, Yuta Saito — KDD 25, 2025

Counterfactual Reciprocal Recommender Systems for User-to-User Matching
Kazuki Kawamura, Takuma Udagawa, Kei Tateno — KDD 25, 2025

Offline Contextual Bandits in the Presence of New Actions
Ren Kishimoto, Tatsuhiro Shimizu, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Yuki Sasamoto, Kei Tateno, Takuma Udagawa, Yuta Saito — KDD 25, 2025

SakugaFlow: A Stagewise Illustration Framework Emulating the Human Drawing Process and Providing Interactive Tutoring for Novice Drawing Skills
Kazuki Kawamura, Jun Rekimoto — CHI 25, 2025

Forecasting music trends and finding new artists based on music features
Kazuki Kawamura — U.S. Patent App. 18/712,717, 2025

Parallel and Mini-Batch Stable Matching for Large-Scale Reciprocal Recommender Systems
Kento Nakada, Kazuki Kawamura, Ryosuke Furukawa — RecSys 24, 2024

Skill-learning support that highlights where a learner differs from a reference performance
Kazuki Kawamura, Jun Rekimoto, Kojiro Kashiwa — U.S. Patent App. 18/261,139, 2024

FastPerson: Enhancing Video-Based Learning through Video Summarization that Preserves Linguistic and Visual Contexts
Kazuki Kawamura, Jun Rekimoto — AHs 24, CHI 24, 2024

Generating Summary Videos from User Questions to Support Video-Based Learning
Kazuki Kawamura, Jun Rekimoto — CHI 23, 2023

AIxSpeed: Playback Speed Optimization Using Listening Comprehension of Speech Recognition Models
Kazuki Kawamura, Jun Rekimoto — UIST 22, AHs 23, 2023

DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech
Kazuki Kawamura, Jun Rekimoto — ICMLA 22, 2022

HTML-LSTM: information extraction from html tables in web pages using tree-structured LSTM
Kazuki Kawamura, Akihiro Yamamoto — DS 21, 2021

Deep state-space model for noise tolerant skeleton-based action recognition
Kazuki Kawamura, Takashi Matsubara, Kuniaki Uehara — IEICE Trans. Inf. Syst. 20, 2020

Full-text PDFs (hosted on casp.jp)

PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows (ACL 26)

Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies (ICLR 26)

ManzaiSet: A Multimodal Dataset of Viewer Responses to Japanese Manzai Comedy (ICCVW 25)

Off-Policy Evaluation and Learning for the Future under Non-Stationarity (KDD 25)

Counterfactual Reciprocal Recommender Systems for User-to-User Matching (KDD 25)

Offline Contextual Bandits in the Presence of New Actions (KDD 25)

SakugaFlow: A Stagewise Illustration Framework Emulating the Human Drawing Process and Providing Interactive Tutoring for Novice Drawing Skills (CHI 25)

Forecasting music trends and finding new artists based on music features (U.S. Patent App. 18/712,717, 2025)

Parallel and Mini-Batch Stable Matching for Large-Scale Reciprocal Recommender Systems (RecSys 24)

FastPerson: Enhancing Video-Based Learning through Video Summarization that Preserves Linguistic and Visual Contexts (AHs 24 / CHI 24)

AIxSpeed: Playback Speed Optimization Using Listening Comprehension of Speech Recognition Models (UIST 22 / AHs 23)

DDSupport: Language Learning Support System that Displays Differences and Distances from Model Speech (ICMLA 22)

HTML-LSTM: information extraction from html tables in web pages using tree-structured LSTM (DS 21)

Deep state-space model for noise tolerant skeleton-based action recognition (IEICE Trans. Inf. Syst. 20)