Efficient Inference for Flow Matching via Unified Path CFG
Kosuke Ukita, Tsuyoshi Okita
The 30th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2026)
CV
Education
MSc in Creative Informatics
| Apr. 2024 - Mar. 2026 (expected)
Kyushu Institute of Technology, Graduate School of Computer Science and Systems Engineering
GPA: 3.6 / 4.0
BSc in Artificial Intelligence
| Apr. 2020 - Mar. 2024
Kyushu Institute of Technology, Computer Science and Systems Engineering
GPA: 3.7 / 4.0
High School Diploma
| Apr. 2017 - Mar. 2020
Kanonji Daiichi High School, Science and Mathematics Course
GPA: 4.9 / 5.0
Work Experience
Research Assistant in Okita Laboratory
| Dec. 2023 - Present
Superviser: Tsuyoshi Okita
Developed and optimized foundation models
Teaching Assistant
| Apr. 2024 - Jan. 2026
Teacher: Tsuyoshi Okita
Deep Learning, Deep Learning Project, etc.
OPTiM Corporation
| Oct. 2023 - Nov. 2023
Research Intern / Part-time Research Assistant
Engaged in research and developed AI technologies for agricultural DX
Publications
High-Performance Self-Supervised Learning by Joint Training of Flow Matching
Kosuke Ukita, Tsuyoshi Okita
The 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026)
Foundation Models to Tackle Activity Recognition in Unknown Domain: Sussex-Huawei Locomotion Challenge 2025 Task 2
Tsuyoshi Okita, Kosuke Ukita, Asahi Miyazaki, Daichi Kubota, Jukichi Ota, Naoki Kagiyama, Asahi Nishikawa, Nagayasu Daichi, Syunya Tomitaka, Daisuke Nozaki, Yuki Odo, Raku Yamashita, Xiaolong Ye, Huayu Gao, Kazuki Okahashi, Koki Matsuishi, Masaharu Kagiyama, Kodai Hirata, Haruki Kai, Lin Wang, Hristijan Gjoreski, Mathias Ciliberto, Paula Lago, Kazuya Murao, Daniel Roggen
Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp Companion '25), pp. 983–991
October 2025 Espoo, Finland
OralRefeered
Multimodal Foundation Model for Cross-Modal Retrieval and Activity Recognition Tasks
Koki Matsuishi, Kosuke Ukita, Tsuyoshi Okita
International Journal of Activity and Behavior Computing (IJABC), Care XDX Center, Kyushu Institute of Technology, Vol. 2025, No. 3, pp. 1-25
Energy-Efficient High-Performance Represen-tation Learning for Sensor Data via Flow Matching
Kosuke Ukita, Tsuyoshi Okita
The 7th International Symposium on Neuromorphic AI Hardware, Paper No. P-19
October 2025 Kitakyushu, Japan
PosterNon-refeered
Image Classification Using a Diffusion Model as a PreTraining Model
Kosuke Ukita, Xiaolong Ye, Tsuyoshi Okita
arXiv preprint arXiv:2505.06890
May 2025
PreprintNon-refeered
AURA-MFM: 詳細な行動理解のためのCLIPを用いたマルチモーダル基盤モデルの構築
松石康希, 浮田嵩祐, 大北剛
情報処理学会研究報告(IPSJ SIG Technical Report), Vol. 2025-UBI-85, No. 8
Improving Human Activity Recognition through Diffusion Models
Kosuke Ukita, Tsuyoshi Okita
The International Symposium on Applied Engineering and Sciences (SAES2024), No. p0052
November 2024 Kitakyushu, Japan
OralNon-refeered
Ensemble Learning of Models for Human Activity Recognition
Asahi Miyazaki, Kosuke Ukita, Tsuyoshi Okita
The International Symposium on Applied Engineering and Sciences (SAES2024), No. p0053
November 2024 Kitakyushu, Japan
OralNon-refeered
Analysis of Human Activity Recognition by Diffusion Models
Kosuke Ukita, Tsuyoshi Okita
Companion of the 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '24), pp. 458–463
October 2024 Melbourne, Australia
OralRefeered
表現条件付き潜在拡散モデルと表現学習
浮田嵩祐, Ye Xiaolong, 大北剛
火の国情報シンポジウム 2024, No. A4-4
March 2024 Kagoshima, Japan
OralNon-refeered
Towards LLMs for Sensor Data: Multi-Task Self-Supervised Learning
Tsuyoshi Okita, Kosuke Ukita, Koki Matsuishi, Masaharu Kagiyama, Kodai Hirata, Asahi Miyazaki
Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing (UbiComp/ISWC '23 Adjunct), pp. 499–504
Awards
Spotlight Presentation (Top 3%)
The 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS 2026)May 2026
Incentive Award (奨励賞)
IPSJ Kyushu Branch (情報処理学会九州支部)March 2024
Highest Award (最優秀賞)
The 8th Sports Data Analysis CompetitionMay 2019
Others
Research Interests
Generative AIFlow MatchingFoundation ModelsMultimodal LearningDiffusion ModelsMachine Learning
Languages
PythonC++CJavaJavaScriptTypeScriptGoSQLR
Frameworks & Tools
PyTorchTensorFlowHugging FaceJupyterABCIDockerGit
Other Skills
Deep LearningNeural NetworksModel TrainingData ProcessingAPI DevelopmentLinux