Yankun Wu

Computer Vision
Fairness in Generative AI
Instance-level Retrieval
Medical Imaging

Hello!👋 I am Yankun. I am a postdoc at Premium Research Institute for Human Metaverse Medicine (PRIMe) and D3 center, The University of Osaka. I finished my PhD in Computer Science at The University of Osaka in September 2025, supervised by Prof. Noa Garcia and Prof. Yuta Nakashima.

I work on computer vision, including fairness, instance-level recognition, image generation, art analysis, segmentation, and medical imaging. I hope to do research that is good for society :-)

🍰publications

full publications on Google Scholar
TMLR · 2026

Instance-Level Generation for Representation Learning

Yankun Wu, Zakaria Laskar, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias

Code
FAccT · 2026

Context matters: Auditing gender bias in T2I generation through risk-tiered use-case profiles

Jose Luna*, Yankun Wu*, Xiaofei Xie, Noa Garcia

AIES · 2025

Privacy in image datasets: A case study on pregnancy ultrasounds

Rawisara Lohanimit, Yankun Wu, Amelia Katirai, Yuta Nakashima, Noa Garcia

AIES · 2024

Stable diffusion exposed: Gender bias from prompt to image

Yankun Wu, Yuta Nakashima, Noa Garcia

ICMR · 2023

Not only generative art: Stable diffusion for content-style disentanglement in art analysis

Yankun Wu, Yuta Nakashima, Noa Garcia

Code
CVPR (Highlight) · 2023

Uncurated image-text datasets: Shedding light on demographic bias

Noa Garcia, Yusuke Hirota, Yankun Wu, Yuta Nakashima

Code

𝄞recent

2026.06
A special session Multimodal Computer Vision in Medicine: Bridging Data Modalities for Clinical Impact was accepted at MMM 2027. The accepted papers will be included in the proceeding. Submit here and select the special session. Deadline is Aug 16, 2026.
2026.06
One paper accepted at TMLR 2026. Huge thanks to my amazing collaborators Zakaria Laskar, Giorgos Kordopatis-Zilos, Noa Garcia, and Giorgos Tolias for their continuous support and effort!
2026.05
Won the PRIMe Joint Research Grant for Junior Investigators. Thanks to amazing co-PIs Jovana Panic and Rodolfo Allendes!
2026.04
One paper accepted at FAccT 2026. Big thanks to Jose Luna and Noa for their effort!
2026.04
Instance-Level Recognition and Generation (ILR+G) Workshop was accepted at ECCV 2026. We have financial support and student grant this year! Submit here.