About me
This is Issey Sukeda. Currently, I am a PhD student under the supervision of Prof. Tomonari Sei and Prof. Takeru Matsuda. My interest covers statistics and operations research. My full publications can be accessed from Publication. Any collaboration, job offer, or discussion is welcome !
🔥 News
- Feb. 2026 🎉 Our paper was accepted in Neural Computation!
- Dec. 2025 🎉 Our paper was accepted in ACM Multimedia Asia 2025 Workshop!
- Oct. 2025 🎉 Two papers were accepted in IJCNLP-AACL 2025 Main conference!
- Aug. 2025 🎉 Our paper was accepted in SIGGRAPH 2025 Posters!
- Oct. 2024 🎉 Our paper was accepted in Statistical Papers!
- Oct. 2024 🎉 Our paper was accepted in Statistics & Probability Letters!
- Oct. 2024 🎉 My paper was accepted in NeurIPS Workshop 2024 AIM-FM!
- Sep. 2024 🎉 Our paper was accepted in ACM SenSys 2024!
- Apr. 2024 🎉 Our paper was accepted in Artificial Intelligence for Health.
- Dec. 2023 🎉 My research was accepted as KAKUSEI Project by AIST.
- Oct. 2023 🎉 Our paper was accepted in NeurIPS Workshop 2023 DGM4H ! See you in New Orleans !
- Jan. 2023 🎉 Our paper was accepted in European Journal of Operational Research !
- Nov. 2022 🎉 Our paper was accepted in ACM SenSys 2022 !
- Feb. 2022 💪 Founded EQUES Inc. as CTO !
💊 Medical/Pharma LLM Projects
- Foundation models × Healthcare network data is a collaborative research with Kyoto Univ. and EQUES Inc.
- JPharmatron-7B is the first Japanese pharmaceutical domain specific LLM, developed along with new benchamrks JPharmaBench. Accepted at IJCNLP-AACL 2025 Main. A work at EQUES Inc.
- Japanese Medical Language Model Evaluation Harness is the evaluation codes and leaderboard for medical LLMs. A work at AIST KAKUSEI.
- MedSwallow is the second Japanese medical LLM finetuned from Swallow-70b-instruct-hf. A work at UTokyo Hospital.
- JMedLoRA is the first Japanese medical LLM finetuned from Llama2. A work at UTokyo Hospital.
- awesome-latest-LLM is the curation of the latest and competent LLMs, including medical domain adaptation. Personal work.
🗒 Pure Statistics Projects
- Minimum information Markov model is a brand new Markov model that models the marginal stationary distribution and the dependence function seperately.
- Minimum Information Copula is the library that numerically calculates the density function of minimum information copula, the most natural copula under predetermined constraints.
- OGI (objective general index) implementation in Python is the Python implementation of Sei (2016).
🧠 Statistics x Neuroscience Projects
- A development of new methods for phase-amplitude coupling analysis is ongoing …
- Sparse Torus Graph introduces a high-dimensional circular model with regularization to estimate dependence structure behind EEG phase, i.e., phase-based connectivity.
🤖 Other AI Projects
- Lineart interpolation is a LoRA weight for Qwen Image Edit.
💰 Fundings & Grants
- RIKEN CBS Junior Research Associate [JPY 7.8M + 1.5M]
- JSPS DC2 (selected and declined due to CTO position)
- IST-RA, funded by UTokyo IST.
- AIST KAKUSEI, funded by AIST [JPY 3M]
- JEES Softbank AI scholarship [JPY 1M]
🏆 Awards
2025
- 🛩 ICSDS 2025 Student Award
- 🏆 KAKUSEI Award, AIST.
2024
- 🥇 1st Place, CBS Retreat 2024 - Poster Theory/Tech Award, RIKEN CBS
- 🏆 Best Presentation Award, Japan Society of Statistics
- 🥇 1st place, Sports Data Science Competition (MLB division), Japan Society of Statistics
2023
- 🏆 ISI Tokyo Memorial Award, Japan Society of Statistics
- 🥇 Student Best Presentation Award, Japan Society of Statistics
〜2021
- 🏆 Finalist, Fin SUM Business Contest 2021
- 🏆 Yahoo Prize, Civictech Challenge Cup 2021 U-22
- 🥇 1st place, AI/SUM Business Contest 2020
- 🥈 2nd place, UTokyo MDS Data Analysis Contest 2019
- 🥉 Bronze Award, Chemistry Grand Prix 2016
- 🥉 3rd place, All Japan Diabolo Competition 2015