Ziyi Zhang
GitHub
|
Google Scholar
|
ORCID
ziyizhang27@whu.edu.cn
I am currently a Ph.D. student with Sensing IntelliGence and MAchine learning lab (SIGMA) in the School of Computer Science, Wuhan University (WHU), supervised by Prof. Dr. Yong Luo.
Previously, I received my Master's degree from the School of Computer Science, Nanjing University of Posts and Telecommunications (NJUPT), where I was supervised by Professor Qun Li.
In addition to my academic experience, I was fortunate to have spent a productive internship at ByteDance - Pico in 2022.
My research interests currently focus on generative models (particularly diffusion models) and reinforcement learning from human feedback.
-
Aligning Text-to-Image Diffusion Models with Constrained Reinforcement Learning IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025[PDF] -
Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning arXiv preprint, 2025 -
Aligning Few-Step Diffusion Models with Dense Reward Difference Learning arXiv preprint, 2024 -
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases International Conference on Machine Learning (ICML), 2024 -
HRNeXt: High-Resolution Context Network for Crowd Pose Estimation IEEE Transactions on Multimedia (IEEE TMM), 2023 -
Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation International Joint Conference on Artificial Intelligence (IJCAI), 2022 -
Dynamic Context Modeling Based Lightweight High-Resolution Network for Dense Prediction Engineering Applications of Artificial Intelligence (EAAI), 2024
-
Dual-Branch Framework with Convolutional Attentive Block for Video Anomaly Detection Chinese Control Conference (CCC), 2023
-
Anomaly Detection in Surveillance Videos via Memory-augmented Frame Prediction International Joint Conference on Neural Networks (IJCNN), 2022
-
Triple Loss Based Framework for Generalized Zero-Shot Learning IEICE Transactions on Information and Systems, 2022
-
Video Summarization Based on Spacial-temporal Transform Network Journal of Software, 2022
Reviewer: NeurIPS 2025, IEEE TMM, Pattern Recognition, Machine Intelligence Research, ICPR 2024, ICDM 2024