Jinya Sakurai

Email GitHub Google Scholar LinkedIn CV

About

I am a PhD student at College of Computing and Data Science, Nanyang Technological University under the supervision of Prof. Jaehong Yoon. I graduated from The University of Tokyo in March 2026. From November 2025 to May 2026, I was a visiting student at the Institute for Infocomm Research, A*STAR I2R, under the supervision of Dr. Xun Xu.

My research interests center on discrete and continuous diffusion models and their applications, including image generation, language modeling, 3D generation, and text-to-speech systems. More broadly, I am interested in generative modeling, computer vision, 3D world understanding, and statistical machine learning.

Outside research, I enjoy playing badminton. I have brought my badminton racket to every country I have visited, including Sweden, Saudi Arabia, Switzerland, and Singapore.

News

AUG2026

Our paper Test-Time Scaling for Safe Text-Guided Image Generation via Intermediate Clean Estimates appeared on arXiv.

AUG2026

I started my PhD at Nanyang Technological University under the supervision of Prof. Jaehong Yoon!

JUL2026

Our paper FairT2I was accepted to Transactions on Machine Learning Research (TMLR)! Proceedings

MAY2026

Our paper OmniDiMM: Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling appeared as a preprint. Project · Paper

MAR2026

I graduated from The University of Tokyo.

NOV2025

I started visiting the Institute for Infocomm Research, A*STAR I2R, under the supervision of Dr. Xun Xu.

FEB2025

Our paper FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing appeared on arXiv.

Research Experience

Institute for Infocomm Research, A*STAR I2R

Visiting Student with Dr. Xun Xu
Nov. 2025 – May 2026

  • Working on diffusion models.

EPFL

Summer@EPFL with Prof. Amir Zamir
Jul. 2024 – Nov. 2025

  • Developing a transformer pretrained model for 3D modalities using masked token prediction.
  • Training VQ-VAE-style tokenizers for LRM-triplane and Gaussian splatter images.

KAUST

Visiting Student Research Program with Prof. Bernard Ghanem
Sep. 2023 – Mar. 2024

  • Developed an efficient token-dropping method for VideoMAE using motion vectors from H.264 compression to reduce computation and GPU memory usage.

Albert Inc.

Research Intern
Aug. 2021 – Jul. 2022

  • Developed a surface reconstruction method for noisy point clouds using energy-based generative models to improve robustness.

Publications

My work spans generative modeling, responsible text-to-image generation, and 3D representation learning. See the dedicated page for papers, abstracts, and resource links.

View all publications

Education

Nanyang Technological University

PhD in Computer Science
Aug. 2026 – Present

The University of Tokyo

Master of Computer Science
Apr. 2024 – Mar. 2026

The University of Tokyo

Bachelor of Information Science
Apr. 2019 – Sep. 2023

Awards/Scholarships

Shin-nihon Scholarship Foundation Scholar Japan

Apr. 2024 – March. 2026

World-leading Innovative Graduate Study Program Co-designing Future Society Awardee

The University of Tokyo
Oct. 2024 – March. 2026

Languages

  • Japanese (Native)
  • English (C2)

Contact