Zaiying Zhao / 趙 在瀛
1st-year PhD student at Yamasaki Lab, The University of Tokyo.
My interest lies in computer vision, particularly in fairness of multimodal AI models.
News
Jul 2026 – A paper has been accepted to COLM.
May 2026 – A paper has won an oral spot at MIRU 2026.
Feb 2026 – A paper has been accepted to TMLR.
May 2025 – A paper has won an oral spot at MIRU 2025 (largest CV conference in Japan).
Apr 2025 – A paper has been accepted to CVPR ReGenAI 2025.
Apr 2025 – Launched this personal website.
Publications
*: Equal Contributions; †: My Advisee
Journal Paper
-
Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper
Atsuyuki Miyai*, Mashiro Toyooka*, Takashi Otonari, Zaiying Zhao, Kiyoharu Aizawa
TMLR 2026
Conference Paper (International)
-
WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira, Atsuki Sato, Tatsumi Sunada, Shota Onohara, Hiromasa Yamanishi, Mashiro Toyooka, Kunato Nishina, Ryoma Maeda, Kiyoharu Aizawa, Toshihiko Yamasaki
COLM 2026 -
Exploring Fairness Across Fine-Grained Attributes in Large Vision-Language Models
Zaiying Zhao, Toshihiko Yamasaki
CVPR ReGenAI 2025 -
Self-examination Mechanism: Improving Standard Accuracy in Adversarial Purification
Sora Suegami*, Yutaro Oguri*, Zaiying Zhao*, Yu Kagaya*, Toshihiko Yamasaki
IVSP 2024
Preprint
-
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
Atsuyuki Miyai, Mashiro Toyooka*, Zaiying Zhao*, Kenta Watanabe*, Toshihiko Yamasaki, Kiyoharu Aizawa
arXiv, 2026 -
Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA
Zaiying Zhao, Toshihiko Yamasaki
arXiv, 2025 -
Language-guided Detection and Mitigation of Unknown Dataset Bias
Zaiying Zhao, Soichiro Kumano, Toshihiko Yamasaki
arXiv, 2024
Conference Paper (Domestic)
-
Beyond Demographics: Counterfactual VQA for Auditing Fairness in Black-Box LVLMs
Zaiying Zhao, Toshihiko Yamasaki
MIRU 2026, Oral (selected) -
Large Vision-Language Modelの多様な属性に対する公平性の検証
趙 在瀛, 山崎 俊彦
MIRU 2025, Oral (selected) -
Vision-Languageモデルを利用した画像分類におけるバイアスの言語的抽出と緩和
趙 在瀛, 熊野 創一郎, 山崎 俊彦
MIRU 2024, Oral (selected)
Awards / Scholarship
Apr 2026 - Present – SPRING GX, The University of Tokyo
Aug 2025 – Promising Student Award, MIRU2025
Apr 2025 - Present – Research Assistant (WINGS-RA), The University of Tokyo
Aug 2024 – Promising Student Award, MIRU2024
Mar 2024 – Best Presentation Award, IVSP 2024
Education
-
Ph.D. in Information Science and Technology Apr 2026 – PresentGraduate School of Information Science and Technology, The University of Tokyo, JapanSupervisor: Prof. Toshihiko Yamasaki -
M.S. in Information Science and Technology Apr 2024 – Mar 2026Graduate School of Information Science and Technology, The University of Tokyo, JapanSupervisor: Prof. Toshihiko Yamasaki -
B.S. in Engineering Apr 2020 – Mar 2024Department of Information and Communication Engineering, Faculty of Engineering, The University of Tokyo, JapanSupervisor: Prof. Toshihiko Yamasaki
Work Experience
-
The University of Tokyo Apr 2026 – PresentSPRING GX Program Participant -
The University of Tokyo Apr 2025 – PresentWINGS RA (卓越RA)Research Assistant in the WINGS-CFS program. -
DeNA Aug 2024 – Oct 2024AI Specialist (Intern)Internship focused on AI research and development.
Internship report: Creating Ball Tracking Data from Basketball Game Videos -
Nagase Co., Ltd. Aug 2022 – Mar 2025Software Engineer -
Fixstars Corporation Aug 2022 – Sep 2022Software Engineer (Intern)
Contact
Email: zhao[at]cvm.t.u-tokyo.ac.jp