Yunqiao Yang Research Fellow, Nanyang Technological University (NTU) Email: hustyyq[at]gmail[dot]com [Google Scholar]

Biography

I am currently a Research Fellow at Nanyang Technological University (NTU), working under the supervision of Prof. Luke Ong. I received my Ph.D. in Computer Science from the City University of Hong Kong in 2025, under the supervision of Prof. Ying Wei and Prof. Kede Ma. I earned my M.Sc. and B.Sc. degrees from Huazhong University of Science and Technology (HUST) in 2021 and 2019, respectively, under the supervision of Prof. Xin Yang.

I am currently seeking postdoctoral and faculty positions. Please feel free to reach out.

Research Interests

My research centers on model adaptation and medical image analysis, with a particular emphasis on leveraging concept-level guidance to improve generalization, interpretability, and controllability of pre-trained models. I develop principled algorithms for efficient task adaptation and targeted behavior modification in modern deep learning systems.

• Concept-Guided Training: Integrating concept-level supervision into fine-tuning to enhance generalization and interpretability across downstream tasks.
• Model Editing: Identifying and editing a sparse, critical subset of model parameters to achieve localized behavior modification while preserving overall model functionality.

Research Experience

Machine Learning Center @ Tencent AI Lab, Shenzhen, China Research Intern: Model Adaptation Nov. 2021 – Oct. 2023 Supervised by Prof. Long-Kai Huang

Jarvis Research Center @ Tencent Youtu Lab, Shenzhen, China Research Intern: Medical Image Analysis May 2020 – Sept. 2020 Supervised by Prof. Yefeng Zheng

News

Selected Publications [Full List]

	Concept-Guided Tokenization: Closing the Gap Between Reconstruction and Generations Yunqiao Yang, Haokun Lin, Guanzhong Wu, Ying Wei International Conference on Machine Learning (ICML), 2026. [Paper] [Code]
	Learning Where to Edit Vision Transformers Yunqiao Yang, Long-Kai Huang, Shengzhuang Chen, Kede Ma, Ying Wei Conference on Neural Information Processing Systems (NeurIPS), 2024. [Paper] [Code]
	Concept-wise Fine-tuning Matters in Preventing Negative Transfer Yunqiao Yang, Long-Kai Huang, Ying Wei IEEE International Conference on Computer Vision (ICCV), 2023. [Paper] [Code]
	Hiding Images in Diffusion Models by Editing Learned Score Functions Haoyu Chen, Yunqiao Yang, Nan Zhong, Kede Ma IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [Paper] [Code]
	Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying Wei International Conference on Machine Learning (ICML), 2024. [Paper] [Code]

Selected Honors

• NeurIPS Scholar Award, 2024.
• First Place Award, MICCAI 2020 CADA Challenge.
• Second Place Award, MICCAI 2020 ADAM Challenge.
• Academic Scholarship, Huazhong University of Science and Technology, 2019, 2020.
• Outstanding Bachelor's Graduate, HUST, 2019.
• Excellent Study Scholarship, Huazhong University of Science and Technology, 2018.
• Second-Class Prize, Huazhong Mathematics Contest in Modeling, 2017.

Services

Conference Reviewer:

• IEEE International Conference on Computer Vision (ICCV), 2025
• Conference on Neural Information Processing Systems (NeurIPS), 2025
• International Conference on Learning Representations (ICLR), 2026
• International Conference on Machine Learning (ICML), 2026
• Association for the Advancement of Artificial Intelligence (AAAI), 2026

Journal Reviewer:

• IEEE Transactions on Medical Imaging (TMI)
• IEEE Transactions on Information Forensics and Security (TIFS)
• Transactions on Machine Learning Research (TMLR)
• Image and Vision Computing