Taishi Nakamura

PhD student, Institute of Science Tokyo

MS student, Institute of Science Tokyo

Joined

March 2024

Names

Taishi Nakamura (Preferred)

Emails

****@rio.gsic.titech.ac.jp (Confirmed)

****@rio.scrc.iir.isct.ac.jp (Confirmed)

****@sakana.ai (Confirmed)

Personal Links

Career & Education History

PhD student

Institute of Science Tokyo (isct.ac.jp)

2026 – 2029

MS student

Institute of Science Tokyo (isct.ac.jp)

2024 – 2026

Undergrad student

Tokyo Institute of Technology (titech.ac.jp)

2021 – 2024

Advisors, Relations & Conflicts

Coauthor

Jun Suzuki

2024 – Present

Coauthor

Takuya Akiba

2024 – Present

Advisor

Rio Yokota

2023 – Present

Expertise

No areas of expertise listed

Publications

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Huu Nguyen, Victor May, Harsh Raj, Marianna Nezhurina, Yishan Wang, Yanqi Luo, Vu Minh Chien, Taishi Nakamura, Ken Tsui, Van Khue Nguyen, David Salinas, Aleksandra Krasnodębska, Christoph Schuhmann, Mats Leon Richter, Xuan-Son Vu, Jenia Jitsev
- Accepted by TMLR
- Readers: Everyone
Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs
Koshiro Saito, Sakae Mizuki, Masanari Oi, Taishi Nakamura, Taihei Shiotani, Koki Maeda, Youmi Ma, Kakeru Hattori, Kazuki Fujii, Takumi Okamoto, Shigeki Ishida, Hiroya Takamura, Rio Yokota, Naoaki Okazaki
- 1st workshop on Multilingual and Equitable Language Technologies (MELT), COLM 2025
- Readers: Everyone
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Huu Nguyen, Victor May, Harsh Raj, Marianna Nezhurina, Yishan Wang, Yanqi Luo, Vu Minh Chien, Taishi Nakamura, Ken Tsui, Van Khue Nguyen, David Salinas, Aleksandra Krasnodębska, Christoph Schuhmann, Mats Leon Richter, Xuan-Son Vu, Jenia Jitsev
- ICLR 2026 Workshop DATA-FM
- Readers: Everyone
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
Kazuki Fujii, Yukito Tajima, Sakae Mizuki, Masaki Kawamura, Hinari Shimada, Taihei Shiotani, Koshiro Saito, Masanari Oi, Taishi Nakamura, Takumi Okamoto, Shigeki Ishida, Kakeru Hattori, Youmi Ma, Hiroya Takamura, Rio Yokota, Jun Sakuma, Naoaki Okazaki
- ICLR 2026 Poster
- Readers: Everyone
Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
Taishi Nakamura, Satoki Ishikawa, Masaki Kawamura, Takumi Okamoto, Daisuke Nohara, Jun Suzuki, Rio Yokota
- ICLR 2026 Oral
- Readers: Everyone
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive Text Sources
Huu Nguyen, Victor May, Harsh Raj, Marianna Nezhurina, Yishan Wang, Yanqi Luo, Vu Minh Chien, Taishi Nakamura, Ken Tsui, Van Khue Nguyen, David Salinas, Aleksandra Krasnodębska, Mats Leon Richter, Christoph Schuhmann, Xuan-Son Vu, Jenia Jitsev
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
Taishi Nakamura, Satoki Ishikawa, Masaki Kawamura, Takumi Okamoto, Daisuke Nohara, Jun Suzuki, Rio Yokota
- AI4Math@ICML25 Poster
- Readers: Everyone
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
Kazuki Fujii, Yukito Tajima, Sakae Mizuki, Hinari Shimada, Taihei Shiotani, Koshiro Saito, Masanari Ohi, Masaki Kawamura, Taishi Nakamura, Takumi Okamoto, Shigeki Ishida, Kakeru Hattori, Youmi Ma, Hiroya Takamura, Rio Yokota, Naoaki Okazaki
- Submitted to NeurIPS 2025 Datasets and Benchmarks Track
- Readers: Everyone
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search
Yuichi Inoue, Kou Misaki, Yuki Imajuku, So Kuroki, Taishi Nakamura, Takuya Akiba
- NeurIPS 2025 spotlight
- Readers: Everyone
Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models
Youmi Ma, Sakae Mizuki, Kazuki Fujii, Taishi Nakamura, Masanari Ohi, Hinari Shimada, Taihei Shiotani, Koshiro Saito, Koki Maeda, Kakeru Hattori, Takumi Okamoto, Shigeki Ishida, Rio Yokota, Hiroya Takamura, Naoaki Okazaki
- COLM 2025
- Readers: Everyone

View all 17 publications

Co-Authors

View all 46 co-authors