Publications

Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model

NeurIPS2025

Machine Learning / Deep Learning

By : Kotaro Ikeda, Masanori Koyama, Jinzhe Zhang, Kohei Hayashi, Kenji Fukumizu

Creating a general-purpose generative model for healthcare data based on multiple clinical studies

PLOS Digital Health

Bioinformatics / Healthcare

By : Hiroshi Maruyama, Kotatsu Bito, Yuki Saito, Masanobu Hibi, Shun Katada, Aya Kawakami, Kenta Oono, Nontawat Charoenphakdee, Zhengyan Gao, Hideyoshi Igata, Masashi Yoshikawa, Yoshiaki Ota, Hiroki Okui, Kei Akita, Shoichiro Yamaguchi, Yohei Sugawara, Shin-ichi Maeda

Development of an AI-based Magnetic Resonance Imaging Reading Support Program (AMP) for Deep Endometriosis Diagnosis

Scientific Reports

Bioinformatics / Healthcare

Computer Vision

By : Rie Shiokawa, Junichiro Iwasawa, Yumiko Oishi Tanaka, Yuta Tokuoka, Yohei Sugawara, Yuichiro Hirano, Ryo Takaji, Yayoi Hayakawa, Keita Oda, Yasunori Kudo, Miho Li, Kazue Mizuno, Kazuhisa Ozeki, Ayako Nishimoto-Kakiuch, Kimio Terao

Efficient Universal Potential Distillation with Pre-trained Students in LightPFP

NeurIPS2025 AI4Mat

Chemoinformatics / Materials Science

By : Wenwen Li, Nontawat Charoenphakdee, Yong-Bin Zhuang, Yuta Tsuboi, Ryuhei Okuno, So Takamoto

P-DRUM: Post-hoc Descriptor-based Residual Uncertainty Modeling for Machine Learning Potentials

NeurIPS2025 ML4PS

Chemoinformatics / Materials Science

By : Shih-Peng Huang, Nontawat Charoenphakdee, Yuta Tsuboi, Yong-Bin Zhuang, Wenwen Li

Anatomical 3D Style Transfer Enabling Efficient Federated Learning with Extremely Low Communication Costs

NeurIPS2024 AIM-FM workshop

Bioinformatics / Healthcare

By : Yuto Shibata, Yasunori Kudo, Yohei Sugawara

Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization

The Second Workshop on GenAI for Health @ NeurIPS2025

Bioinformatics / Healthcare

By : Wataru Kawakami, Keita Suzuki, Junichiro Iwasawa,

Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models

5th Deep Generative Models Workshop @ MICCAI 2025

Bioinformatics / Healthcare

By : Xinkai Zhao, Yuta Tokuoka, Junichiro Iwasawa, Keita Oda,

Efficient Construction of Model Family through Progressive Training Using Model Expansion

COLM2025

Foundation model / LLM

By : Kazuki Yano, Sho Takase, Sosuke Kobayashi, Shun Kiyono, Jun Suzuki

Spike No More: Stabilizing the Pre-training of Large Language Models

COLM2025

Foundation model / LLM

By : Sho Takase, Shun Kiyono, Sosuke Kobayashi, Jun Suzuki

When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars

COLM2025

Foundation model / LLM

By : Rei Higuchi, Ryotaro Kawata, Naoki Nishikawa, Kazusato Oko, Shoichiro Yamaguchi, Sosuke Kobayashi, Seiya Tokui, Kohei Hayashi, Daisuke Okanohara, Taiji Suzuki

Flow matching achieves almost minimax optimal convergence

ICLR2025

Machine Learning / Deep Learning

By : Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama